mirror of
https://github.com/calibrain/shelfmark.git
synced 2026-09-24 22:05:20 +01:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
5b3df2a463 | ||
|
|
5247ec6124 | ||
|
|
bd21ec1257 | ||
|
|
7b9c416df8 | ||
|
|
646b531669 | ||
|
|
eafb965662 | ||
|
|
7193036626 | ||
|
|
12d554a92f | ||
|
|
fae6140c6a | ||
|
|
63133097e4 | ||
|
|
82aeee387e | ||
|
|
4cd1091d16 | ||
|
|
651096ed7b | ||
|
|
ebb833a82c | ||
|
|
b7093f4594 | ||
|
|
b656f019be | ||
|
|
6e96ead519 | ||
|
|
7345f6be1a | ||
|
|
2b8b35bb52 | ||
|
|
58a5b5ed27 | ||
|
|
52c1702419 | ||
|
|
3e2a7a48d5 | ||
|
|
a178541561 | ||
|
|
78e1f4daba | ||
|
|
eeea92280c | ||
|
|
0a5256ecbb | ||
|
|
6d2af0ac28 | ||
|
|
056ddd372a | ||
|
|
d0e008adde | ||
|
|
03e219eb43 | ||
|
|
0e8608c427 | ||
|
|
7f770f54fa | ||
|
|
0eb8b78dc7 | ||
|
|
eb98b6a816 | ||
|
|
29ce83e274 | ||
|
|
e320b7623d | ||
|
|
bb848f05bc | ||
|
|
cc1a95f965 | ||
|
|
dfcd7c9b00 | ||
|
|
bd9a22bd6c | ||
|
|
ba4f7fb5e6 | ||
|
|
f1de248ed5 | ||
|
|
78d5d0632a | ||
|
|
3c51b7cfaa | ||
|
|
3a9cff9816 | ||
|
|
453d1f2b56 | ||
|
|
db11da5bda | ||
|
|
0b22618d96 | ||
|
|
42f308bc89 | ||
|
|
e93fbd2a9b | ||
|
|
cdd156e142 | ||
|
|
21f2b6b95c | ||
|
|
10554444a9 | ||
|
|
ce026e2eb8 | ||
|
|
ff770940ca | ||
|
|
340853477f | ||
|
|
816a735cde | ||
|
|
d1cdaaeb5e | ||
|
|
a1367f431d | ||
|
|
a4086f5e06 | ||
|
|
0d02c6db47 | ||
|
|
7c457ff83e | ||
|
|
00f3fa565c | ||
|
|
7fdaf3f67d | ||
|
|
e9f3b9a3ad | ||
|
|
8eb9bd5c21 | ||
|
|
a4d587037d | ||
|
|
1747b3466e | ||
|
|
81a057c8a0 | ||
|
|
91b1064689 | ||
|
|
c9a2b5eccf | ||
|
|
28969ac828 | ||
|
|
2f5d3dde7d | ||
|
|
2d949d4e7c | ||
|
|
100e0dd9f8 | ||
|
|
ceaccfd29f | ||
|
|
6bab9989ab | ||
|
|
f8d3f990ca | ||
|
|
30d7f228be | ||
|
|
b291df5cc9 | ||
|
|
9b1d4322b7 | ||
|
|
d7a21ea248 | ||
|
|
c487c6c483 | ||
|
|
404e8cc5c5 | ||
|
|
40d6a179b7 | ||
|
|
02a45c1a12 | ||
|
|
4c78a2f3a0 | ||
|
|
8b4230ee9f | ||
|
|
b57925c39d | ||
|
|
b6efed95ab | ||
|
|
44a261e857 | ||
|
|
14bd50bfd1 | ||
|
|
4f123977ff | ||
|
|
e3b05d6030 | ||
|
|
995d8d6631 | ||
|
|
9a27334d9c | ||
|
|
76c55a488c | ||
|
|
08d0a04cf2 | ||
|
|
36f9a52987 | ||
|
|
1536b91a46 | ||
|
|
fea63269e3 | ||
|
|
7886ba7038 | ||
|
|
1c19326bd0 | ||
|
|
2f70ed36e4 | ||
|
|
8d54cff383 | ||
|
|
63fa6213da | ||
|
|
61b3eaf351 | ||
|
|
7158b79146 | ||
|
|
3c1b79989a | ||
|
|
e41c1d4e8e | ||
|
|
ec7e3482bb | ||
|
|
05cd384efc | ||
|
|
880cc4a299 |
+19
-3
@@ -46,9 +46,7 @@ updates:
|
||||
# pre-release filter is bypassed for *grouped* updates
|
||||
# (dependabot-core#9496), so a grouped python update proposes pre-release
|
||||
# tags like python:3.15.0b2 as if they were a normal stable minor bump.
|
||||
# Updated individually, python is filtered correctly: alpha/beta/rc tags
|
||||
# are skipped and only stable releases (e.g. 3.15.0 once final) are
|
||||
# proposed. node + uv stay grouped into a single digest PR.
|
||||
# node + uv stay grouped into a single digest PR.
|
||||
patterns: ["*"]
|
||||
exclude-patterns: ["python"]
|
||||
ignore:
|
||||
@@ -58,6 +56,24 @@ updates:
|
||||
- dependency-name: "node"
|
||||
update-types: ["version-update:semver-major"]
|
||||
|
||||
# Python: block minor/major bumps. Ungrouping python (above) is NOT enough
|
||||
# to keep pre-releases out — dependabot-core#13815 rewrote the Docker
|
||||
# pre-release heuristic to catch PEP 440 tags like 3.15.0a2 / 3.5.0b3, but
|
||||
# the suffixed real tag still slipped through as PR #1169
|
||||
# (python:3.14.6-slim -> python:3.15.0b3-slim). CPython spells
|
||||
# pre-releases without a separator, so tag parsing reads 3.15.0b3 as an
|
||||
# ordinary version that sorts above 3.14.6.
|
||||
#
|
||||
# A minor-version ignore blocks it regardless of spelling. Patch bumps
|
||||
# (3.14.6 -> 3.14.7) and same-tag digest refreshes still land automatically.
|
||||
# Moving the runtime to a new Python minor is a manual, deliberate change:
|
||||
# bump the tag here and confirm C-extension wheels (greenlet/gevent) exist
|
||||
# for it — a source build against a pre-release ABI boots an app that binds
|
||||
# its port but never serves, which wedges e2e for the full 6h job limit.
|
||||
- dependency-name: "python"
|
||||
update-types:
|
||||
["version-update:semver-major", "version-update:semver-minor"]
|
||||
|
||||
# GitHub Actions
|
||||
- package-ecosystem: "github-actions"
|
||||
directory: "/"
|
||||
|
||||
@@ -67,10 +67,10 @@ jobs:
|
||||
run: echo "date=$(date +'%Y-%m-%d')" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Log in to the Container registry
|
||||
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
|
||||
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
@@ -78,7 +78,13 @@ jobs:
|
||||
|
||||
- name: Extract metadata for ${{ matrix.target }} image
|
||||
id: meta
|
||||
uses: docker/metadata-action@80c7e94dd9b9319bd5eb7a0e0fe9291e23a2a2e9 # v6.1.0
|
||||
uses: docker/metadata-action@dc802804100637a589fabce1cb79ff13a1411302 # v6.2.0
|
||||
env:
|
||||
# Annotate both the per-platform manifests and the multi-arch image
|
||||
# index. The index level is what manifest-list consumers (Renovate's
|
||||
# minimumReleaseAge soak check, provenance/SBOM tooling) read for the
|
||||
# standard org.opencontainers.image.* annotations, including `created`.
|
||||
DOCKER_METADATA_ANNOTATIONS_LEVELS: index,manifest
|
||||
with:
|
||||
images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}${{ matrix.image_name_suffix }}
|
||||
tags: |
|
||||
@@ -90,11 +96,11 @@ jobs:
|
||||
type=ref,event=tag
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
|
||||
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
|
||||
- name: Build and push ${{ matrix.target }} Docker image
|
||||
id: push
|
||||
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
|
||||
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
|
||||
with:
|
||||
platforms: linux/amd64,linux/arm64
|
||||
context: .
|
||||
@@ -105,10 +111,11 @@ jobs:
|
||||
RELEASE_VERSION=${{ github.ref_name }}
|
||||
tags: ${{ steps.meta.outputs.tags }}
|
||||
labels: ${{ steps.meta.outputs.labels }}
|
||||
annotations: ${{ steps.meta.outputs.annotations }}
|
||||
|
||||
- name: Generate artifact attestation for ${{ matrix.target }} image
|
||||
if: github.event_name != 'pull_request'
|
||||
uses: actions/attest-build-provenance@a2bbfa25375fe432b6a289bc6b6cd05ecd0c4c32 # v4.1.0
|
||||
uses: actions/attest-build-provenance@4d101475d8b20a2381f78447822ac1eab6504dd8 # v4.2.2
|
||||
with:
|
||||
subject-name: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}${{ matrix.image_name_suffix }}
|
||||
subject-digest: ${{ steps.push.outputs.digest }}
|
||||
@@ -127,14 +134,14 @@ jobs:
|
||||
LEGACY_NAME: calibre-web-automated-book-downloader
|
||||
steps:
|
||||
- name: Log in to registry
|
||||
uses: docker/login-action@650006c6eb7dba73a995cc03b0b2d7f5ca915bee # v4.2.0
|
||||
uses: docker/login-action@dbcb813823bdd20940b903addbd779551569679f # v4.6.0
|
||||
with:
|
||||
registry: ${{ env.REGISTRY }}
|
||||
username: ${{ github.actor }}
|
||||
password: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
|
||||
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
|
||||
- name: Create legacy aliases
|
||||
run: |
|
||||
|
||||
+15
-15
@@ -13,10 +13,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Install uv and Python
|
||||
uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # v8.2.0
|
||||
uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
|
||||
with:
|
||||
version: "0.11.3"
|
||||
python-version: "3.14"
|
||||
@@ -39,10 +39,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Install uv and Python
|
||||
uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # v8.2.0
|
||||
uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
|
||||
with:
|
||||
version: "0.11.3"
|
||||
python-version: "3.14"
|
||||
@@ -59,10 +59,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Install uv and Python
|
||||
uses: astral-sh/setup-uv@fac544c07dec837d0ccb6301d7b5580bf5edae39 # v8.2.0
|
||||
uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
|
||||
with:
|
||||
version: "0.11.3"
|
||||
python-version: "3.14"
|
||||
@@ -78,13 +78,13 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Set up Docker Buildx
|
||||
uses: docker/setup-buildx-action@d7f5e7f509e45cec5c76c4d5afdd7de93d0b3df5 # v4.1.0
|
||||
uses: docker/setup-buildx-action@bb05f3f5519dd87d3ba754cc423b652a5edd6d2c # v4.2.0
|
||||
|
||||
- name: Build shelfmark-lite image
|
||||
uses: docker/build-push-action@f9f3042f7e2789586610d6e8b85c8f03e5195baf # v7.2.0
|
||||
uses: docker/build-push-action@53b7df96c91f9c12dcc8a07bcb9ccacbed38856a # v7.3.0
|
||||
with:
|
||||
context: .
|
||||
target: shelfmark-lite
|
||||
@@ -99,10 +99,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Set up Node
|
||||
uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||||
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
|
||||
with:
|
||||
node-version: 24
|
||||
cache: "npm"
|
||||
@@ -122,10 +122,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Set up Node
|
||||
uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||||
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
|
||||
with:
|
||||
node-version: 24
|
||||
cache: "npm"
|
||||
@@ -142,10 +142,10 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Set up Node
|
||||
uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
|
||||
uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
|
||||
with:
|
||||
node-version: 24
|
||||
cache: "npm"
|
||||
|
||||
@@ -22,17 +22,17 @@ jobs:
|
||||
language: [python, javascript-typescript]
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@df4cb1c069e1874edd31b4311f1884172cec0e10 # v6.0.3
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
|
||||
- name: Initialize CodeQL
|
||||
uses: github/codeql-action/init@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v3
|
||||
uses: github/codeql-action/init@5595ccaf912efad79be6eef63a5619ff05969be3 # v3
|
||||
with:
|
||||
languages: ${{ matrix.language }}
|
||||
|
||||
- name: Autobuild
|
||||
uses: github/codeql-action/autobuild@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v3
|
||||
uses: github/codeql-action/autobuild@5595ccaf912efad79be6eef63a5619ff05969be3 # v3
|
||||
|
||||
- name: Perform CodeQL Analysis
|
||||
uses: github/codeql-action/analyze@8aad20d150bbac5944a9f9d289da16a4b0d87c1e # v3
|
||||
uses: github/codeql-action/analyze@5595ccaf912efad79be6eef63a5619ff05969be3 # v3
|
||||
with:
|
||||
category: "/language:${{ matrix.language }}"
|
||||
|
||||
@@ -0,0 +1,135 @@
|
||||
name: E2E Platform
|
||||
|
||||
# Hermetic end-to-end matrix: boots the app under test against mock
|
||||
# Anna's Archive / Cloudflare / bypasser / DNS / proxy / Tor / real torrent
|
||||
# clients and runs the cluster suite under each config profile.
|
||||
#
|
||||
# On a PR that touches relevant code, this runs a fast core subset *and* the heavy
|
||||
# `full` profile (real Chrome solving Cloudflare + DoH + real qBittorrent). The
|
||||
# `e2e-required` job aggregates them into ONE status check — make that check a
|
||||
# required status check in branch protection to block merges on any e2e failure
|
||||
# (see tests/e2e/platform/README.md "Gating PRs").
|
||||
|
||||
on:
|
||||
pull_request:
|
||||
schedule:
|
||||
- cron: "0 4 * * *" # nightly full matrix
|
||||
workflow_dispatch:
|
||||
|
||||
concurrency:
|
||||
group: e2e-platform-${{ github.ref }}
|
||||
cancel-in-progress: true
|
||||
|
||||
jobs:
|
||||
# Detect whether anything that affects the e2e platform changed. This lets the
|
||||
# required check always report (never stuck "pending") while only spending CI on
|
||||
# PRs that can actually break the e2e stack.
|
||||
changes:
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
relevant: ${{ steps.filter.outputs.relevant }}
|
||||
steps:
|
||||
- uses: actions/checkout@v7
|
||||
- uses: dorny/paths-filter@v4.0.3
|
||||
id: filter
|
||||
with:
|
||||
filters: |
|
||||
relevant:
|
||||
- 'shelfmark/**'
|
||||
- 'entrypoint.sh'
|
||||
- 'tor.sh'
|
||||
- 'Dockerfile'
|
||||
- 'tests/e2e/platform/**'
|
||||
- '.github/workflows/e2e-platform.yml'
|
||||
|
||||
select-profiles:
|
||||
needs: changes
|
||||
if: needs.changes.outputs.relevant == 'true' || github.event_name != 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
outputs:
|
||||
profiles: ${{ steps.pick.outputs.profiles }}
|
||||
steps:
|
||||
- id: pick
|
||||
run: |
|
||||
if [ "${{ github.event_name }}" = "pull_request" ]; then
|
||||
echo 'profiles=["baseline","bypasser-external","dns-blocked"]' >> "$GITHUB_OUTPUT"
|
||||
else
|
||||
echo 'profiles=["baseline","bypasser-external","bypasser-disabled","dns-manual","dns-blocked","dns-doh","proxy-http","proxy-socks","tor","client-transmission","client-deluge","client-qbittorrent-delayed"]' >> "$GITHUB_OUTPUT"
|
||||
fi
|
||||
|
||||
e2e:
|
||||
needs: select-profiles
|
||||
runs-on: ubuntu-latest
|
||||
# A wedged app under test must not burn GitHub's 6h max job limit. A healthy
|
||||
# profile run finishes in ~3-5 min; anything past 25 is hung, not slow.
|
||||
timeout-minutes: 25
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
profile: ${{ fromJSON(needs.select-profiles.outputs.profiles) }}
|
||||
name: e2e (${{ matrix.profile }})
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v7
|
||||
- name: Install uv and Python
|
||||
uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
|
||||
with:
|
||||
python-version: "3.14"
|
||||
enable-cache: true
|
||||
- name: Sync dependencies
|
||||
run: make install-python-dev
|
||||
- name: Run e2e platform (${{ matrix.profile }})
|
||||
run: tests/e2e/platform/run-e2e.sh env/${{ matrix.profile }}.env
|
||||
- name: Dump shelfmark logs on failure
|
||||
if: failure()
|
||||
run: cat tests/e2e/platform/.state/shelfmark.${{ matrix.profile }}.log || true
|
||||
|
||||
# Heavy "everything real" job: real Chrome internal bypasser solving Cloudflare +
|
||||
# DoH + real qBittorrent webseed download. Runs on relevant PRs and nightly.
|
||||
e2e-full:
|
||||
needs: changes
|
||||
if: needs.changes.outputs.relevant == 'true' || github.event_name != 'pull_request'
|
||||
runs-on: ubuntu-latest
|
||||
# Real Chrome + qBittorrent is the slowest profile; still nowhere near 40 min.
|
||||
timeout-minutes: 40
|
||||
name: e2e (full — real Chrome + qBittorrent)
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@v7
|
||||
- name: Install uv and Python
|
||||
uses: astral-sh/setup-uv@c771a70e6277c0a99b617c7a806ffedaca235ff9 # v9.0.0
|
||||
with:
|
||||
python-version: "3.14"
|
||||
enable-cache: true
|
||||
- name: Sync dependencies
|
||||
run: make install-python-dev
|
||||
- name: Run full pipeline
|
||||
run: tests/e2e/platform/run-e2e.sh env/full.env
|
||||
- name: Dump logs on failure
|
||||
if: failure()
|
||||
run: |
|
||||
cat tests/e2e/platform/.state/shelfmark.full.log || true
|
||||
docker logs e2e-qbittorrent || true
|
||||
|
||||
# Single aggregated gate. ALWAYS runs (so a required check never hangs "pending"
|
||||
# on unrelated PRs) and FAILS if any e2e job failed/was cancelled. Make THIS the
|
||||
# required status check in branch protection.
|
||||
e2e-required:
|
||||
name: e2e required
|
||||
needs: [e2e, e2e-full]
|
||||
if: always()
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Aggregate e2e results
|
||||
run: |
|
||||
matrix='${{ needs.e2e.result }}'
|
||||
full='${{ needs.e2e-full.result }}'
|
||||
echo "e2e matrix=$matrix, e2e-full=$full"
|
||||
# success or skipped (unrelated PR) is OK; failure/cancelled blocks.
|
||||
for r in "$matrix" "$full"; do
|
||||
if [ "$r" = "failure" ] || [ "$r" = "cancelled" ]; then
|
||||
echo "::error::An e2e platform job did not pass — blocking."
|
||||
exit 1
|
||||
fi
|
||||
done
|
||||
echo "All e2e platform jobs passed (or were skipped as not relevant)."
|
||||
@@ -166,6 +166,10 @@ ENV/
|
||||
env.bak/
|
||||
venv.bak/
|
||||
|
||||
# ...but the e2e platform test profiles live in an env/ dir and must be tracked
|
||||
!tests/e2e/platform/env/
|
||||
!tests/e2e/platform/env/*.env
|
||||
|
||||
# Spyder project settings
|
||||
.spyderproject
|
||||
.spyproject
|
||||
|
||||
+62
-18
@@ -4,7 +4,7 @@ ARG BUILDPLATFORM
|
||||
ARG BUILDARCH
|
||||
|
||||
# Frontend build stage.
|
||||
FROM --platform=$BUILDPLATFORM node:24-alpine@sha256:fb71d01345f11b708a3553c66e7c74074f2d506400ea81973343d915cb64eef0 AS frontend-builder
|
||||
FROM --platform=$BUILDPLATFORM node:24-alpine@sha256:d32cdf619f63fe0471182d08996dd516c6275bb5fd31ae06e55a570bd9e1ad43 AS frontend-builder
|
||||
|
||||
# Helpful debug output to see what platforms BuildKit thinks it's using
|
||||
RUN echo "BUILDPLATFORM=$BUILDPLATFORM BUILDARCH=$BUILDARCH TARGETPLATFORM=$TARGETPLATFORM TARGETARCH=$TARGETARCH"
|
||||
@@ -24,10 +24,14 @@ COPY src/frontend/ ./
|
||||
# Build the frontend
|
||||
RUN npm run build
|
||||
|
||||
# Use python-slim as the base image
|
||||
FROM python:3.14.5-slim@sha256:c845af9399020c7e562969a13689e929074a10fd057acd1b1fad06a2fb068e97 AS base
|
||||
# uv is a build-time tool only, so it is mounted into the RUNs that need it rather
|
||||
# than copied into the image. A COPY here would land ~24 MB in a `base` layer that
|
||||
# every published image inherits, and a later `rm` cannot take it back out again --
|
||||
# a RUN adds a layer, it does not rewrite the one underneath.
|
||||
FROM ghcr.io/astral-sh/uv:0.11.3@sha256:90bbb3c16635e9627f49eec6539f956d70746c409209041800a0280b93152823 AS uv
|
||||
|
||||
COPY --from=ghcr.io/astral-sh/uv:0.11.3@sha256:90bbb3c16635e9627f49eec6539f956d70746c409209041800a0280b93152823 /uv /uvx /bin/
|
||||
# Use python-slim as the base image
|
||||
FROM python:3.14.7-slim@sha256:ce40764625a4ff50df3548277632e7f96c4e77fe75fa848aae9885476e7df5a4 AS base
|
||||
|
||||
# Add build argument for version
|
||||
ARG BUILD_VERSION
|
||||
@@ -59,6 +63,11 @@ ENV FLASK_PORT=8084
|
||||
# Configure locale, timezone, and perform initial cleanup in a single layer
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
# For building C-extensions (cffi, gevent, etc.)
|
||||
gcc \
|
||||
g++ \
|
||||
libffi-dev \
|
||||
python3-dev \
|
||||
# For locale
|
||||
locales tzdata \
|
||||
# For healthcheck
|
||||
@@ -72,7 +81,12 @@ RUN apt-get update && \
|
||||
# --- Tor support (activated via USING_TOR=true) ---
|
||||
tor \
|
||||
supervisor \
|
||||
iptables && \
|
||||
iptables \
|
||||
# --- WireGuard support (activated via USING_WIREGUARD=true) ---
|
||||
wireguard-tools \
|
||||
iproute2 \
|
||||
procps \
|
||||
ca-certificates && \
|
||||
# Configure iptables alternatives for tor.sh compatibility
|
||||
update-alternatives --set iptables /usr/sbin/iptables-legacy && \
|
||||
update-alternatives --set ip6tables /usr/sbin/ip6tables-legacy && \
|
||||
@@ -101,6 +115,7 @@ WORKDIR /app
|
||||
# Install core Python dependencies first for better layer caching
|
||||
COPY pyproject.toml uv.lock ./
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
--mount=from=uv,source=/uv,target=/usr/local/bin/uv \
|
||||
uv sync --locked --no-default-groups
|
||||
|
||||
# Runtime dependencies are installed into /app/.venv during the build. Remove the
|
||||
@@ -131,7 +146,7 @@ RUN mkdir -p \
|
||||
ln -s /tmp/shelfmark/seleniumbase/archived_files /app/archived_files && \
|
||||
chown -R 1000:1000 /config /books /home/shelfmark /tmp/shelfmark /var/log/shelfmark && \
|
||||
chmod -R a+rX /app && \
|
||||
chmod +x /app/entrypoint.sh /app/tor.sh /app/genDebug.sh
|
||||
chmod +x /app/entrypoint.sh /app/tor.sh /app/wireguard.sh /app/genDebug.sh
|
||||
|
||||
# Expose the application port
|
||||
EXPOSE ${FLASK_PORT}
|
||||
@@ -147,21 +162,39 @@ ENTRYPOINT ["/usr/bin/dumb-init", "--"]
|
||||
|
||||
FROM base AS shelfmark
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends \
|
||||
# --- Chromium (PINNED to 149.0.7827.196) ---
|
||||
# Debian's chromium 150.0.7871.46-1~deb13u1 security update (trixie-security,
|
||||
# 2026-07-05) no longer opens the DevTools remote-debugging TCP port at all
|
||||
# (no listener, no DevToolsActivePort file, even with a custom --user-data-dir;
|
||||
# the RemoteDebuggingAllowed policy does not restore it). The SeleniumBase
|
||||
# Pure-CDP driver connects through that port (/json/version), so with 150 every
|
||||
# internal bypass dies with "Pure CDP browser startup failed" and all
|
||||
# CF-gated downloads fail. Install the last working version from
|
||||
# snapshot.debian.org until the bypasser can talk to Chromium >= 150 (e.g.
|
||||
# pipe-based DevTools / UC mode) or seleniumbase ships a fix.
|
||||
# Chrome 144+ requires --enable-unsafe-swiftshader for WebGL in Docker.
|
||||
# This flag is set in internal_bypasser.py _get_browser_args()
|
||||
ARG CHROMIUM_VERSION=149.0.7827.196-1~deb13u1
|
||||
ARG CHROMIUM_SNAPSHOT=20260704T000000Z
|
||||
|
||||
RUN echo "deb [check-valid-until=no] https://snapshot.debian.org/archive/debian-security/${CHROMIUM_SNAPSHOT}/ trixie-security main" \
|
||||
> /etc/apt/sources.list.d/chromium-pin-snapshot.list && \
|
||||
apt-get update -o Acquire::Retries=5 && \
|
||||
apt-get install -y --no-install-recommends -o Acquire::Retries=5 \
|
||||
# For dumb display
|
||||
xvfb \
|
||||
# For screen recording
|
||||
ffmpeg \
|
||||
# --- Chromium (unpinned - uses latest from Debian repos) ---
|
||||
# Chrome 144+ requires --enable-unsafe-swiftshader for WebGL in Docker.
|
||||
# This flag is set in internal_bypasser.py _get_browser_args()
|
||||
chromium \
|
||||
chromium-common \
|
||||
chromium=${CHROMIUM_VERSION} \
|
||||
chromium-common=${CHROMIUM_VERSION} \
|
||||
# For tkinter (pyautogui)
|
||||
python3-tk \
|
||||
# For RAR extraction
|
||||
unrar-free && \
|
||||
# Keep apt from "upgrading" chromium past the pin inside derived images
|
||||
printf 'Package: chromium chromium-common\nPin: version %s\nPin-Priority: 1001\n' "${CHROMIUM_VERSION}" \
|
||||
> /etc/apt/preferences.d/chromium-pin && \
|
||||
rm /etc/apt/sources.list.d/chromium-pin-snapshot.list && \
|
||||
# Create symlink so rarfile library can find unrar
|
||||
ln -sf /usr/bin/unrar-free /usr/bin/unrar && \
|
||||
# Cleanup APT cache
|
||||
@@ -171,10 +204,24 @@ RUN apt-get update && \
|
||||
|
||||
# Install the browser automation stack used by the full image
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
--mount=from=uv,source=/uv,target=/usr/local/bin/uv \
|
||||
uv sync --locked --no-default-groups --extra browser
|
||||
|
||||
# uv is only needed while building the image.
|
||||
RUN rm -f /usr/bin/uv /usr/bin/uvx
|
||||
# Deterministically resolve the Xlib namespace collision.
|
||||
# pyautogui/mouseinfo pull the stale `python3-xlib` (0.15, 2014), while the
|
||||
# `--extra browser` set pulls `python-xlib` (0.33). Both packages install into
|
||||
# the same top-level `Xlib/` namespace, so whichever lands last wins. When the
|
||||
# 2014 build wins, `Xlib.X` is missing `FamilyServerInterpreted`, which the
|
||||
# SeleniumBase Pure-CDP driver requires at browser startup -> every bypass fails
|
||||
# with "module 'Xlib.X' has no attribute 'FamilyServerInterpreted'" and no
|
||||
# Cloudflare/DDoS-Guard protected download can complete. Drop the stale package
|
||||
# and force python-xlib 0.33 to own the namespace. pyautogui runs fine against
|
||||
# 0.33 (superset API).
|
||||
RUN --mount=type=cache,target=/root/.cache/uv \
|
||||
--mount=from=uv,source=/uv,target=/usr/local/bin/uv \
|
||||
uv pip uninstall --python /app/.venv/bin/python python3-xlib && \
|
||||
uv pip install --python /app/.venv/bin/python --reinstall python-xlib==0.33 && \
|
||||
/app/.venv/bin/python -c "import Xlib.X; assert hasattr(Xlib.X, 'FamilyServerInterpreted'), 'Xlib.X.FamilyServerInterpreted missing after fix'; print('Xlib namespace OK:', Xlib.__version__)"
|
||||
|
||||
# Keep SeleniumBase's bundled driver cache writable for the fixed non-root user.
|
||||
RUN SELENIUMBASE_DRIVERS_DIR=$(/app/.venv/bin/python -c "import pathlib, seleniumbase; print(pathlib.Path(seleniumbase.__file__).resolve().parent / 'drivers')") && \
|
||||
@@ -192,7 +239,4 @@ FROM base AS shelfmark-lite
|
||||
|
||||
ENV USING_EXTERNAL_BYPASSER=true
|
||||
|
||||
# uv is only needed while building the image.
|
||||
RUN rm -f /usr/bin/uv /usr/bin/uvx
|
||||
|
||||
CMD ["/app/entrypoint.sh"]
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
.PHONY: help install install-ci install-python-dev dev build preview frontend-typecheck frontend-lint frontend-format frontend-format-fix frontend-checks frontend-test clean up down docker-build refresh restart build-serve python-lint python-lint-fix python-format python-format-fix python-typecheck python-dead-code python-checks python-test python-test-cov checks fix
|
||||
.PHONY: help install install-ci install-python-dev dev build preview frontend-typecheck frontend-lint frontend-format frontend-format-fix frontend-checks frontend-test clean up down docker-build refresh restart build-serve python-lint python-lint-fix python-format python-format-fix python-typecheck python-dead-code python-checks python-test python-test-cov e2e-platform e2e-platform-profile e2e-platform-matrix e2e-platform-full e2e-platform-build checks fix
|
||||
|
||||
# Frontend directory
|
||||
FRONTEND_DIR := src/frontend
|
||||
@@ -38,6 +38,10 @@ help:
|
||||
@echo " python-checks - Run all Python static analysis checks"
|
||||
@echo " python-test - Run unit tests"
|
||||
@echo " python-test-cov - Run unit tests with coverage report"
|
||||
@echo " e2e-platform - Run e2e docker platform (baseline profile)"
|
||||
@echo " e2e-platform-profile PROFILE=<name> - Run e2e platform for one profile"
|
||||
@echo " e2e-platform-matrix - Run e2e platform across all config profiles"
|
||||
@echo " e2e-platform-full - Run heavy 'full' profile (real Chrome bypasser + DoH + real qBittorrent)"
|
||||
@echo " clean - Remove node_modules and build artifacts"
|
||||
@echo ""
|
||||
@echo "Backend (Docker):"
|
||||
@@ -127,6 +131,30 @@ python-test-cov:
|
||||
@echo "Running tests with coverage..."
|
||||
uv run pytest tests/ -x --tb=short -m "not integration and not e2e" --cov --cov-report=term-missing
|
||||
|
||||
# E2E docker platform: hermetic stack (mock AA/Cloudflare/bypasser/DNS/proxy/Tor)
|
||||
# exercised across config profiles. See tests/e2e/platform/README.md.
|
||||
E2E_PLATFORM_DIR := tests/e2e/platform
|
||||
|
||||
e2e-platform:
|
||||
@echo "Running e2e platform (baseline profile)..."
|
||||
cd $(E2E_PLATFORM_DIR) && ./run-e2e.sh env/baseline.env
|
||||
|
||||
e2e-platform-profile:
|
||||
@echo "Running e2e platform (profile=$(PROFILE))..."
|
||||
cd $(E2E_PLATFORM_DIR) && ./run-e2e.sh env/$(PROFILE).env
|
||||
|
||||
e2e-platform-matrix:
|
||||
@echo "Running e2e platform matrix (all profiles)..."
|
||||
cd $(E2E_PLATFORM_DIR) && ./run-matrix.sh
|
||||
|
||||
e2e-platform-build:
|
||||
@echo "Pre-building e2e platform images once (reused across profiles)..."
|
||||
cd $(E2E_PLATFORM_DIR) && ./build-images.sh
|
||||
|
||||
e2e-platform-full:
|
||||
@echo "Running e2e platform FULL profile (real Chrome bypasser + DoH + real qBittorrent)..."
|
||||
cd $(E2E_PLATFORM_DIR) && ./run-e2e.sh env/full.env
|
||||
|
||||
# Frontend linting
|
||||
frontend-lint:
|
||||
@echo "Running Oxlint..."
|
||||
|
||||
@@ -0,0 +1,43 @@
|
||||
# Routes all traffic through a WireGuard tunnel - requires root startup.
|
||||
#
|
||||
# Mount your wg-quick config at /config/wg0.conf (read-only is fine). All
|
||||
# non-LAN egress is forced through the tunnel by an iptables kill-switch, so if
|
||||
# the tunnel drops, external traffic fails closed. LAN ranges (WebUI + internal
|
||||
# download clients like Prowlarr / qBittorrent) stay reachable off-tunnel.
|
||||
services:
|
||||
shelfmark-wireguard:
|
||||
image: ghcr.io/calibrain/shelfmark:latest
|
||||
environment:
|
||||
FLASK_PORT: 8084
|
||||
# Quoted so it is passed as the literal string "true": entrypoint.sh compares
|
||||
# $USING_WIREGUARD against "true", and some Compose implementations stringify
|
||||
# a bare YAML boolean as "True", which would silently NOT enable WireGuard.
|
||||
USING_WIREGUARD: "true"
|
||||
# Path to the mounted wg-quick config (default shown).
|
||||
WIREGUARD_CONFIG: /config/wg0.conf
|
||||
# CIDRs kept OFF the tunnel so the WebUI and internal clients stay reachable.
|
||||
LAN_NETWORK: 127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16
|
||||
PUID: 1000
|
||||
PGID: 1000
|
||||
cap_add:
|
||||
- NET_ADMIN
|
||||
- NET_RAW
|
||||
# WireGuard needs the module/kernel routing; NET_ADMIN covers wg-quick.
|
||||
sysctls:
|
||||
- net.ipv4.conf.all.src_valid_mark=1
|
||||
# Disable IPv6 in the container so the kill-switch can guarantee no IPv6
|
||||
# leak path on kernels/containers without a usable ip6tables. wireguard.sh
|
||||
# fails closed if IPv6 is neither kill-switched nor disabled. If your host
|
||||
# DOES have a working ip6tables you may omit these (an ip6tables kill-switch
|
||||
# is installed instead); or set WIREGUARD_ALLOW_IPV6_LEAK=true only if the
|
||||
# container genuinely has no IPv6 connectivity.
|
||||
- net.ipv6.conf.all.disable_ipv6=1
|
||||
- net.ipv6.conf.default.disable_ipv6=1
|
||||
ports:
|
||||
- 8084:8084
|
||||
restart: unless-stopped
|
||||
volumes:
|
||||
- /path/to/books:/books # Default destination for book downloads
|
||||
- /path/to/config:/config # App configuration (put wg0.conf here)
|
||||
# Required for torrent / usenet - path must match your download client's volume exactly
|
||||
# - /path/to/downloads:/path/to/downloads
|
||||
+60
-53
@@ -1,72 +1,79 @@
|
||||
[
|
||||
{ "language": "English", "code": "en" },
|
||||
{ "language": "Chinese", "code": "zh" },
|
||||
{ "language": "Russian", "code": "ru" },
|
||||
{ "language": "Spanish", "code": "es" },
|
||||
{ "language": "French", "code": "fr" },
|
||||
{ "language": "German", "code": "de" },
|
||||
{ "language": "Italian", "code": "it" },
|
||||
{ "language": "Portuguese", "code": "pt" },
|
||||
{ "language": "Polish", "code": "pl" },
|
||||
{ "language": "Bulgarian", "code": "bg" },
|
||||
{ "language": "Dutch", "code": "nl" },
|
||||
{ "language": "Japanese", "code": "ja" },
|
||||
{ "language": "Arabic", "code": "ar" },
|
||||
{ "language": "Hebrew", "code": "he" },
|
||||
{ "language": "Turkish", "code": "tr" },
|
||||
{ "language": "Hungarian", "code": "hu" },
|
||||
{ "language": "Latin", "code": "la" },
|
||||
{ "language": "Czech", "code": "cs" },
|
||||
{ "language": "Korean", "code": "ko" },
|
||||
{ "language": "Ukrainian", "code": "uk" },
|
||||
{ "language": "Indonesian", "code": "id" },
|
||||
{ "language": "Romanian", "code": "ro" },
|
||||
{ "language": "Swedish", "code": "sv" },
|
||||
{ "language": "Greek", "code": "el" },
|
||||
{ "language": "Lithuanian", "code": "lt" },
|
||||
{ "language": "Bangla", "code": "bn" },
|
||||
{ "language": "Traditional Chinese", "code": "zh‑Hant" },
|
||||
{ "language": "Afrikaans", "code": "af" },
|
||||
{ "language": "Catalan", "code": "ca" },
|
||||
{ "language": "Danish", "code": "da" },
|
||||
{ "language": "Thai", "code": "th" },
|
||||
{ "language": "Hindi", "code": "hi" },
|
||||
{ "language": "Irish", "code": "ga" },
|
||||
{ "language": "Latvian", "code": "lv" },
|
||||
{ "language": "English", "code": "en", "aliases": ["eng"] },
|
||||
{ "language": "Chinese", "code": "zh", "aliases": ["chi", "zho"] },
|
||||
{ "language": "Russian", "code": "ru", "aliases": ["rus"] },
|
||||
{ "language": "Spanish", "code": "es", "aliases": ["spa"] },
|
||||
{ "language": "French", "code": "fr", "aliases": ["fra", "fre"] },
|
||||
{ "language": "German", "code": "de", "aliases": ["deu", "ger"] },
|
||||
{ "language": "Italian", "code": "it", "aliases": ["ita"] },
|
||||
{ "language": "Portuguese", "code": "pt", "aliases": ["por"] },
|
||||
{ "language": "Polish", "code": "pl", "aliases": ["pol"] },
|
||||
{ "language": "Bulgarian", "code": "bg", "aliases": ["bul"] },
|
||||
{ "language": "Dutch", "code": "nl", "aliases": ["dut", "nld"] },
|
||||
{ "language": "Japanese", "code": "ja", "aliases": ["jap", "jpn"] },
|
||||
{ "language": "Arabic", "code": "ar", "aliases": ["ara"] },
|
||||
{ "language": "Hebrew", "code": "he", "aliases": ["heb"] },
|
||||
{ "language": "Turkish", "code": "tr", "aliases": ["tur"] },
|
||||
{ "language": "Hungarian", "code": "hu", "aliases": ["hun"] },
|
||||
{ "language": "Latin", "code": "la", "aliases": ["lat"] },
|
||||
{ "language": "Czech", "code": "cs", "aliases": ["ces", "cze"] },
|
||||
{ "language": "Korean", "code": "ko", "aliases": ["kor"] },
|
||||
{ "language": "Ukrainian", "code": "uk", "aliases": ["ukr"] },
|
||||
{ "language": "Indonesian", "code": "id", "aliases": ["ind"] },
|
||||
{ "language": "Romanian", "code": "ro", "aliases": ["rom", "ron"] },
|
||||
{ "language": "Swedish", "code": "sv", "aliases": ["swe"] },
|
||||
{ "language": "Greek", "code": "el", "aliases": ["ell", "gre"] },
|
||||
{ "language": "Lithuanian", "code": "lt", "aliases": ["lit"] },
|
||||
{ "language": "Bangla", "code": "bn", "aliases": ["ben", "bengali"] },
|
||||
{ "language": "Traditional Chinese", "code": "zh-Hant", "aliases": ["zh‑Hant"] },
|
||||
{ "language": "Afrikaans", "code": "af", "aliases": ["afr"] },
|
||||
{ "language": "Catalan", "code": "ca", "aliases": ["cat"] },
|
||||
{ "language": "Danish", "code": "da", "aliases": ["dan"] },
|
||||
{ "language": "Thai", "code": "th", "aliases": ["tha"] },
|
||||
{ "language": "Hindi", "code": "hi", "aliases": ["hin"] },
|
||||
{ "language": "Irish", "code": "ga", "aliases": ["gle"] },
|
||||
{ "language": "Latvian", "code": "lv", "aliases": ["lav"] },
|
||||
{ "language": "Tibetan", "code": "bo" },
|
||||
{ "language": "Kannada", "code": "kn" },
|
||||
{ "language": "Serbian", "code": "sr" },
|
||||
{ "language": "Persian", "code": "fa" },
|
||||
{ "language": "Croatian", "code": "hr" },
|
||||
{ "language": "Kannada", "code": "kn", "aliases": ["kan"] },
|
||||
{ "language": "Serbian", "code": "sr", "aliases": ["srp"] },
|
||||
{ "language": "Persian", "code": "fa", "aliases": ["farsi", "fas", "per"] },
|
||||
{ "language": "Croatian", "code": "hr", "aliases": ["hrv"] },
|
||||
{ "language": "Slovak", "code": "sk" },
|
||||
{ "language": "Javanese", "code": "jv" },
|
||||
{ "language": "Vietnamese", "code": "vi" },
|
||||
{ "language": "Urdu", "code": "ur" },
|
||||
{ "language": "Finnish", "code": "fi" },
|
||||
{ "language": "Norwegian", "code": "no" },
|
||||
{ "language": "Javanese", "code": "jv", "aliases": ["jav"] },
|
||||
{ "language": "Vietnamese", "code": "vi", "aliases": ["vie"] },
|
||||
{ "language": "Urdu", "code": "ur", "aliases": ["urd"] },
|
||||
{ "language": "Finnish", "code": "fi", "aliases": ["fin"] },
|
||||
{ "language": "Norwegian", "code": "no", "aliases": ["nor"] },
|
||||
{ "language": "Kinyarwanda", "code": "rw" },
|
||||
{ "language": "Tamil", "code": "ta" },
|
||||
{ "language": "Tamil", "code": "ta", "aliases": ["tam"] },
|
||||
{ "language": "Belarusian", "code": "be" },
|
||||
{ "language": "Kazakh", "code": "kk" },
|
||||
{ "language": "Mongolian", "code": "mn" },
|
||||
{ "language": "Georgian", "code": "ka" },
|
||||
{ "language": "Slovenian", "code": "sl" },
|
||||
{ "language": "Slovenian", "code": "sl", "aliases": ["slv"] },
|
||||
{ "language": "Esperanto", "code": "eo" },
|
||||
{ "language": "Galician", "code": "gl" },
|
||||
{ "language": "Marathi", "code": "mr" },
|
||||
{ "language": "Filipino", "code": "fil" },
|
||||
{ "language": "Gujarati", "code": "gu" },
|
||||
{ "language": "Malayalam", "code": "ml" },
|
||||
{ "language": "Marathi", "code": "mr", "aliases": ["mar"] },
|
||||
{ "language": "Filipino", "code": "fil", "aliases": ["tagalog", "tgl"] },
|
||||
{ "language": "Gujarati", "code": "gu", "aliases": ["guj"] },
|
||||
{ "language": "Malayalam", "code": "ml", "aliases": ["mal"] },
|
||||
{ "language": "Kyrgyz", "code": "ky" },
|
||||
{ "language": "Azerbaijani", "code": "az" },
|
||||
{ "language": "Quechua", "code": "qu" },
|
||||
{ "language": "Swahili", "code": "sw" },
|
||||
{ "language": "Bashkir", "code": "ba" },
|
||||
{ "language": "Punjabi", "code": "pa" },
|
||||
{ "language": "Malay", "code": "ms" },
|
||||
{ "language": "Telugu", "code": "te" },
|
||||
{ "language": "Punjabi", "code": "pa", "aliases": ["pan"] },
|
||||
{ "language": "Malay", "code": "ms", "aliases": ["may", "msa"] },
|
||||
{ "language": "Telugu", "code": "te", "aliases": ["tel"] },
|
||||
{ "language": "Albanian", "code": "sq" },
|
||||
{ "language": "Uyghur", "code": "ug" },
|
||||
{ "language": "Armenian", "code": "hy" },
|
||||
{ "language": "Shan", "code": "shn" }
|
||||
{ "language": "Shan", "code": "shn" },
|
||||
{ "language": "Bosnian", "code": "bs", "aliases": ["bos"] },
|
||||
{ "language": "Burmese", "code": "my", "aliases": ["bur", "mya"] },
|
||||
{ "language": "Estonian", "code": "et", "aliases": ["est"] },
|
||||
{ "language": "Icelandic", "code": "is", "aliases": ["ice", "isl"] },
|
||||
{ "language": "Manx", "code": "gv", "aliases": ["glv"] },
|
||||
{ "language": "Scottish Gaelic", "code": "gd", "aliases": ["gla"] },
|
||||
{ "language": "Sanskrit", "code": "sa", "aliases": ["san"] }
|
||||
]
|
||||
|
||||
@@ -0,0 +1,25 @@
|
||||
# Local development - WireGuard variant
|
||||
services:
|
||||
shelfmark-wireguard-dev:
|
||||
extends:
|
||||
file: ./compose/docker-compose.wireguard.yml
|
||||
service: shelfmark-wireguard
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile
|
||||
target: shelfmark
|
||||
environment:
|
||||
# Quoted so they are passed as the literal string "true" (entrypoint.sh and
|
||||
# the app compare against "true"); a bare YAML boolean can be stringified as
|
||||
# "True" by some Compose variants, silently disabling the feature.
|
||||
DEBUG: "true"
|
||||
USING_WIREGUARD: "true"
|
||||
WIREGUARD_CONFIG: /config/wg0.conf
|
||||
volumes:
|
||||
- ./.local/config:/config
|
||||
- ./.local/books:/books
|
||||
- ./.local/log:/var/log/shelfmark
|
||||
- ./.local/tmp:/tmp/shelfmark
|
||||
# Place your wg-quick config at ./.local/config/wg0.conf
|
||||
# Required for torrent / usenet - path must match your download client's volume exactly
|
||||
# - /path/to/downloads:/path/to/downloads
|
||||
@@ -91,6 +91,10 @@ Example:
|
||||
- Shelfmark can see the same files at `/downloads/books/...`
|
||||
- Add a mapping from Remote Path `/data/torrents` to Local Path `/downloads`
|
||||
|
||||
If the files are copied or synced into Shelfmark on a delay, increase **Completed Path Wait (seconds)**
|
||||
in Settings -> Advanced. The default is 60 seconds; seedbox or remote-sync setups may need a value
|
||||
longer than the sync interval.
|
||||
|
||||
## File Processing Options
|
||||
|
||||
### Transfer Method (Torrent / Usenet Only)
|
||||
|
||||
+281
-22
@@ -7,6 +7,7 @@ This document lists all configuration options that can be set via environment va
|
||||
## Table of Contents
|
||||
|
||||
- [Bootstrap Configuration](#bootstrap-configuration)
|
||||
- [Egress / VPN Routing](#egress--vpn-routing)
|
||||
- [General](#general)
|
||||
- [Search Mode](#search-mode)
|
||||
- [Downloads](#downloads)
|
||||
@@ -22,6 +23,7 @@ This document lists all configuration options that can be set via environment va
|
||||
- [Hardcover](#metadata-providers-hardcover)
|
||||
- [Open Library](#metadata-providers-open-library)
|
||||
- [Google Books](#metadata-providers-google-books)
|
||||
- [Moly.hu](#metadata-providers-moly.hu)
|
||||
- [Direct Download](#direct-download)
|
||||
- [Download Sources](#direct-download-download-sources)
|
||||
- [Cloudflare Bypass](#direct-download-cloudflare-bypass)
|
||||
@@ -145,6 +147,98 @@ Show the onboarding wizard on first run. Set to false to skip (useful for epheme
|
||||
|
||||
</details>
|
||||
|
||||
## Egress / VPN Routing
|
||||
|
||||
These startup-only variables are consumed by `entrypoint.sh` / `wireguard.sh` to select and configure the WireGuard transparent-egress kill-switch. `USING_WIREGUARD` and [`USING_TOR`](#using_tor) (documented under Network) are mutually exclusive; both require root startup.
|
||||
|
||||
| Variable | Description | Type | Default |
|
||||
|----------|-------------|------|---------|
|
||||
| `USING_WIREGUARD` | Route all traffic through a WireGuard VPN tunnel with a fail-closed iptables kill-switch (non-tunnel egress is dropped). Requires root startup and NET_ADMIN (plus NET_RAW). Mutually exclusive with USING_TOR. | boolean | `false` |
|
||||
| `WIREGUARD_CONFIG` | Path to the mounted wg-quick configuration file. | string (path) | `/config/wg0.conf` |
|
||||
| `WIREGUARD_INTERFACE` | WireGuard interface name brought up by wg-quick. | string | `wg0` |
|
||||
| `LAN_NETWORK` | Comma-separated CIDRs kept off the tunnel so the WebUI and internal download clients (Prowlarr, qBittorrent) stay reachable. | string (comma-separated) | `127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16` |
|
||||
| `WIREGUARD_ENFORCE_DNS` | Pin the container's resolver so DNS cannot silently fall back to an off-tunnel path. The resolver used is WIREGUARD_DNS if set, else the tunnel config's DNS = line. This does NOT force queries through the tunnel: it is designed for a trusted LAN resolver kept reachable off-tunnel via LAN_NETWORK (the query leaves over the LAN; the resolver encrypts upstream while the download still egresses via the tunnel). Special case: when Docker's embedded resolver (nameserver 127.0.0.11) is present, it is PRESERVED so container-name resolution (e.g. prowlarr, qbittorrent) keeps working, and the embedded resolver's upstream must be pinned via the container's compose dns: list. Fails closed (refuses to start) only when no embedded resolver is present AND no resolver is defined, or /etc/resolv.conf is not writable. | boolean | `true` |
|
||||
| `WIREGUARD_DNS` | Explicit resolver(s) (comma/space separated) to pin when WIREGUARD_ENFORCE_DNS is true and Docker's embedded resolver is NOT in use. Use when the VPN's pushed DNS filters domains you need; point it at a resolver reachable via the tunnel or an allowed LAN resolver. NOTE: when the embedded resolver (127.0.0.11) is present it is preserved and this value cannot repoint its upstream from inside the container — set the container's compose dns: list to the trusted resolver instead. | string (comma-separated) | `unset (uses config DNS = line)` |
|
||||
| `WIREGUARD_DISABLE_IPV6` | Strip IPv6 Address/AllowedIPs/DNS from the tunnel config before wg-quick (many container kernels lack the ip6tables raw table wg-quick needs) and remove IPv6 as a leak surface. | boolean | `true` |
|
||||
| `WIREGUARD_ALLOW_IPV6_LEAK` | Escape hatch: continue startup even when an IPv6 kill-switch cannot be installed AND IPv6 cannot be disabled. Only set when the container has no IPv6 connectivity, as IPv6 egress may otherwise bypass the tunnel. | boolean | `false` |
|
||||
| `WIREGUARD_ALLOW_WEBUI_OFFTUNNEL` | When false (default) the kill-switch is strictly fail-closed: the only off-tunnel egress permitted is loopback, the tunnel device and the LAN allowlist. Set true only if a NON-LAN client (e.g. a public reverse proxy on a different segment) must reach the WebUI; it permits app-server REPLY packets (--sport FLASK_PORT, conntrack REPLY) to leave off-tunnel. Server replies only, never client-initiated egress, so it cannot leak outbound browsing/downloads or the real IP for outbound requests, but it is still an off-tunnel path while the tunnel is down, hence opt-in. LAN WebUI clients never need it (covered by LAN_NETWORK). | boolean | `false` |
|
||||
| `WIREGUARD_STALE_AFTER` | Seconds since the last WireGuard handshake before the healthcheck bounces the tunnel. | number | `180` |
|
||||
|
||||
<details>
|
||||
<summary>Detailed descriptions</summary>
|
||||
|
||||
#### `USING_WIREGUARD`
|
||||
|
||||
Route all traffic through a WireGuard VPN tunnel with a fail-closed iptables kill-switch (non-tunnel egress is dropped). Requires root startup and NET_ADMIN (plus NET_RAW). Mutually exclusive with USING_TOR.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `WIREGUARD_CONFIG`
|
||||
|
||||
Path to the mounted wg-quick configuration file.
|
||||
|
||||
- **Type:** string (path)
|
||||
- **Default:** `/config/wg0.conf`
|
||||
|
||||
#### `WIREGUARD_INTERFACE`
|
||||
|
||||
WireGuard interface name brought up by wg-quick.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `wg0`
|
||||
|
||||
#### `LAN_NETWORK`
|
||||
|
||||
Comma-separated CIDRs kept off the tunnel so the WebUI and internal download clients (Prowlarr, qBittorrent) stay reachable.
|
||||
|
||||
- **Type:** string (comma-separated)
|
||||
- **Default:** `127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16`
|
||||
|
||||
#### `WIREGUARD_ENFORCE_DNS`
|
||||
|
||||
Pin the container's resolver so DNS cannot silently fall back to an off-tunnel path. The resolver used is WIREGUARD_DNS if set, else the tunnel config's DNS = line. This does NOT force queries through the tunnel: it is designed for a trusted LAN resolver kept reachable off-tunnel via LAN_NETWORK (the query leaves over the LAN; the resolver encrypts upstream while the download still egresses via the tunnel). Special case: when Docker's embedded resolver (nameserver 127.0.0.11) is present, it is PRESERVED so container-name resolution (e.g. prowlarr, qbittorrent) keeps working, and the embedded resolver's upstream must be pinned via the container's compose dns: list. Fails closed (refuses to start) only when no embedded resolver is present AND no resolver is defined, or /etc/resolv.conf is not writable.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `true`
|
||||
|
||||
#### `WIREGUARD_DNS`
|
||||
|
||||
Explicit resolver(s) (comma/space separated) to pin when WIREGUARD_ENFORCE_DNS is true and Docker's embedded resolver is NOT in use. Use when the VPN's pushed DNS filters domains you need; point it at a resolver reachable via the tunnel or an allowed LAN resolver. NOTE: when the embedded resolver (127.0.0.11) is present it is preserved and this value cannot repoint its upstream from inside the container — set the container's compose dns: list to the trusted resolver instead.
|
||||
|
||||
- **Type:** string (comma-separated)
|
||||
- **Default:** `unset (uses config DNS = line)`
|
||||
|
||||
#### `WIREGUARD_DISABLE_IPV6`
|
||||
|
||||
Strip IPv6 Address/AllowedIPs/DNS from the tunnel config before wg-quick (many container kernels lack the ip6tables raw table wg-quick needs) and remove IPv6 as a leak surface.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `true`
|
||||
|
||||
#### `WIREGUARD_ALLOW_IPV6_LEAK`
|
||||
|
||||
Escape hatch: continue startup even when an IPv6 kill-switch cannot be installed AND IPv6 cannot be disabled. Only set when the container has no IPv6 connectivity, as IPv6 egress may otherwise bypass the tunnel.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `WIREGUARD_ALLOW_WEBUI_OFFTUNNEL`
|
||||
|
||||
When false (default) the kill-switch is strictly fail-closed: the only off-tunnel egress permitted is loopback, the tunnel device and the LAN allowlist. Set true only if a NON-LAN client (e.g. a public reverse proxy on a different segment) must reach the WebUI; it permits app-server REPLY packets (--sport FLASK_PORT, conntrack REPLY) to leave off-tunnel. Server replies only, never client-initiated egress, so it cannot leak outbound browsing/downloads or the real IP for outbound requests, but it is still an off-tunnel path while the tunnel is down, hence opt-in. LAN WebUI clients never need it (covered by LAN_NETWORK).
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `WIREGUARD_STALE_AFTER`
|
||||
|
||||
Seconds since the last WireGuard handshake before the healthcheck bounces the tunnel.
|
||||
|
||||
- **Type:** number
|
||||
- **Default:** `180`
|
||||
|
||||
</details>
|
||||
|
||||
## General
|
||||
|
||||
| Variable | Description | Type | Default |
|
||||
@@ -153,7 +247,7 @@ Show the onboarding wizard on first run. Set to false to skip (useful for epheme
|
||||
| `CALIBRE_WEB_URL` | Adds a navigation button to your book library (Calibre-Web Automated, Grimmory, etc). | string | _none_ |
|
||||
| `AUDIOBOOK_LIBRARY_URL` | Adds a separate navigation button for your audiobook library (Audiobookshelf, Plex, etc). When both URLs are set, icons are shown instead of text. | string | _none_ |
|
||||
| `SUPPORTED_FORMATS` | Book formats to include in search results. ZIP/RAR archives are extracted automatically and book files are used if found. | string (comma-separated) | `epub,mobi,azw3,fb2,djvu,cbz,cbr` |
|
||||
| `SUPPORTED_AUDIOBOOK_FORMATS` | Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found. | string (comma-separated) | `m4b,mp3` |
|
||||
| `SUPPORTED_AUDIOBOOK_FORMATS` | Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found. | string (comma-separated) | `m4b,mp3,m4a,flac,ogg,wma,aac,wav,opus,zip,rar` |
|
||||
| `BOOK_LANGUAGE` | Default language filter for searches. | string (comma-separated) | `en` |
|
||||
|
||||
<details>
|
||||
@@ -202,7 +296,7 @@ Book formats to include in search results. ZIP/RAR archives are extracted automa
|
||||
Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found.
|
||||
|
||||
- **Type:** string (comma-separated)
|
||||
- **Default:** `m4b,mp3`
|
||||
- **Default:** `m4b,mp3,m4a,flac,ogg,wma,aac,wav,opus,zip,rar`
|
||||
|
||||
#### `BOOK_LANGUAGE`
|
||||
|
||||
@@ -339,8 +433,8 @@ The release source tab to open by default in the release modal for audiobooks. U
|
||||
| `BOOKS_OUTPUT_MODE` | Choose where completed book files are sent. | string (choice) | `folder` |
|
||||
| `INGEST_DIR` | Directory where downloaded files are saved. Use {User} for per-user folders (e.g. /books/{User}). | string | `/books` |
|
||||
| `FILE_ORGANIZATION` | Choose how downloaded book files are named and organized. | string (choice) | `rename` |
|
||||
| `TEMPLATE_RENAME` | Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads. | string | `{Author} - {Title} ({Year})` |
|
||||
| `TEMPLATE_ORGANIZE` | Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. | string | `{Author}/{Title} ({Year})` |
|
||||
| `TEMPLATE_RENAME` | Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads. | string | `{Author} - {Title} ({Year})` |
|
||||
| `TEMPLATE_ORGANIZE` | Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. | string | `{Author}/{Title} ({Year})` |
|
||||
| `HARDLINK_TORRENTS` | Create hardlinks instead of copying. Preserves seeding but archives won't be extracted. Don't use if destination is a library ingest folder. | boolean | `false` |
|
||||
| `BOOKLORE_HOST` | Base URL of your Grimmory instance | string | _none_ |
|
||||
| `BOOKLORE_USERNAME` | Grimmory account username | string | _none_ |
|
||||
@@ -361,8 +455,8 @@ The release source tab to open by default in the release modal for audiobooks. U
|
||||
| `EMAIL_ALLOW_UNVERIFIED_TLS` | Disable TLS certificate verification (not recommended). | boolean | `false` |
|
||||
| `DESTINATION_AUDIOBOOK` | Directory where downloaded audiobook files are saved. Leave empty to use the Books destination. | string | _none_ |
|
||||
| `FILE_ORGANIZATION_AUDIOBOOK` | Choose how downloaded audiobook files are named and organized. | string (choice) | `rename` |
|
||||
| `TEMPLATE_AUDIOBOOK_RENAME` | Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads. | string | `{Author} - {Title}` |
|
||||
| `TEMPLATE_AUDIOBOOK_ORGANIZE` | Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. | string | `{Author}/{Title}/{Title}` |
|
||||
| `TEMPLATE_AUDIOBOOK_RENAME` | Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads. | string | `{Author} - {Title}` |
|
||||
| `TEMPLATE_AUDIOBOOK_ORGANIZE` | Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. | string | `{Author}/{Title}/{Title}` |
|
||||
| `HARDLINK_TORRENTS_AUDIOBOOK` | Create hardlinks instead of copying. Preserves seeding but archives won't be extracted. Don't use if destination is a library ingest folder. | boolean | `true` |
|
||||
| `AUTO_OPEN_DOWNLOADS_SIDEBAR` | Automatically open the downloads sidebar when a new download is queued. | boolean | `false` |
|
||||
| `DOWNLOAD_TO_BROWSER_CONTENT_TYPES` | Automatically download completed files to your browser for the selected content types. | string (comma-separated) | _empty list_ |
|
||||
@@ -406,7 +500,7 @@ Choose how downloaded book files are named and organized.
|
||||
|
||||
**Naming Template**
|
||||
|
||||
Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads.
|
||||
Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `{Author} - {Title} ({Year})`
|
||||
@@ -415,7 +509,7 @@ Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename wi
|
||||
|
||||
**Path Template**
|
||||
|
||||
Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty.
|
||||
Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension). Universal adds: {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `{Author}/{Title} ({Year})`
|
||||
@@ -616,7 +710,7 @@ Choose how downloaded audiobook files are named and organized.
|
||||
|
||||
**Naming Template**
|
||||
|
||||
Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads.
|
||||
Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. Rename templates are filename-only (no '/' or '\'); use Organize for folders. Applies to single-file downloads.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `{Author} - {Title}`
|
||||
@@ -625,7 +719,7 @@ Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename wi
|
||||
|
||||
**Path Template**
|
||||
|
||||
Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty.
|
||||
Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} (source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: {Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `{Author}/{Title}/{Title}`
|
||||
@@ -953,11 +1047,13 @@ Comma-separated hosts to bypass proxy (e.g., localhost,127.0.0.1,10.*,*.local)
|
||||
|----------|-------------|------|---------|
|
||||
| `URL_BASE` | Optional URL path prefix. Use a path like /shelfmark (no hostname). Leave blank for root. | string | _none_ |
|
||||
| `DEBUG` | Enable verbose logging to console and file. Not recommended for normal use. | boolean | `false` |
|
||||
| `LOG_LEVEL` | Lowest severity written to the console and log file. Ignored while Debug Mode is on, which forces Debug. | string (choice) | `INFO` |
|
||||
| `MAIN_LOOP_SLEEP_TIME` | How often the download queue is checked for new items. | number | `5` |
|
||||
| `DOWNLOAD_PROGRESS_UPDATE_INTERVAL` | How often download progress is broadcast to the UI. | number | `1` |
|
||||
| `CUSTOM_SCRIPT` | Path to a script to run after each successful download. Must be executable. | string | _none_ |
|
||||
| `CUSTOM_SCRIPT_PATH_MODE` | Pass the path to the custom script as an absolute path or relative to the destination folder. | string (choice) | `absolute` |
|
||||
| `CUSTOM_SCRIPT_JSON_PAYLOAD` | Send a JSON payload to the script via stdin. Useful for multi-file imports (audiobooks) or richer metadata without relying on path parsing. | boolean | `false` |
|
||||
| `DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT` | How long to wait after a torrent or usenet client reports completion for the completed file path to become visible to Shelfmark. Increase this for seedbox or remote-sync workflows. | number | `60` |
|
||||
| `COVERS_CACHE_ENABLED` | Cache book covers on the server for faster loading. | boolean | `true` |
|
||||
| `COVERS_CACHE_TTL` | How long to keep cached covers. Set to 0 to keep forever (recommended for static artwork). | number | `0` |
|
||||
| `COVERS_CACHE_MAX_SIZE_MB` | Maximum disk space for cached covers. Oldest images are removed when limit is reached. | number | `500` |
|
||||
@@ -988,6 +1084,17 @@ Enable verbose logging to console and file. Not recommended for normal use.
|
||||
- **Default:** `false`
|
||||
- **Requires restart:** Yes
|
||||
|
||||
#### `LOG_LEVEL`
|
||||
|
||||
**Log Level**
|
||||
|
||||
Lowest severity written to the console and log file. Ignored while Debug Mode is on, which forces Debug.
|
||||
|
||||
- **Type:** string (choice)
|
||||
- **Default:** `INFO`
|
||||
- **Requires restart:** Yes
|
||||
- **Options:** `DEBUG` (Debug), `INFO` (Info), `WARNING` (Warning), `ERROR` (Error), `CRITICAL` (Critical)
|
||||
|
||||
#### `MAIN_LOOP_SLEEP_TIME`
|
||||
|
||||
**Queue Check Interval (seconds)**
|
||||
@@ -1038,6 +1145,16 @@ Send a JSON payload to the script via stdin. Useful for multi-file imports (audi
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT`
|
||||
|
||||
**Completed Path Wait (seconds)**
|
||||
|
||||
How long to wait after a torrent or usenet client reports completion for the completed file path to become visible to Shelfmark. Increase this for seedbox or remote-sync workflows.
|
||||
|
||||
- **Type:** number
|
||||
- **Default:** `60`
|
||||
- **Constraints:** min: 0, max: 3600
|
||||
|
||||
#### `COVERS_CACHE_ENABLED`
|
||||
|
||||
**Enable Cover Cache**
|
||||
@@ -1107,6 +1224,7 @@ How long to cache individual book details. Default: 600 (10 minutes). Max: 60480
|
||||
| `PROWLARR_API_KEY` | Found in Prowlarr: Settings > General > API Key | string (secret) | _none_ |
|
||||
| `PROWLARR_INDEXERS` | Select which indexers to search. 📚 = has book categories. Leave empty to search all. | string (comma-separated) | _empty list_ |
|
||||
| `PROWLARR_AUTO_EXPAND` | Automatically retry search without category filtering if no results are found | boolean | `false` |
|
||||
| `PROWLARR_COLLAPSE_DUPLICATES` | Collapse a release that several indexer entries returned down to a single row, keeping the entry with the best Prowlarr priority. Turn this off to see every entry that carried it, which is what makes results from filter-specific entries (freeleech and the like) visible. | boolean | `true` |
|
||||
| `PROWLARR_USE_SEED_PREFERENCES` | Apply per-indexer seed time and ratio preferences from Prowlarr when sending torrents to the download client | boolean | `false` |
|
||||
|
||||
<details>
|
||||
@@ -1159,6 +1277,15 @@ Automatically retry search without category filtering if no results are found
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `PROWLARR_COLLAPSE_DUPLICATES`
|
||||
|
||||
**Show one row per release**
|
||||
|
||||
Collapse a release that several indexer entries returned down to a single row, keeping the entry with the best Prowlarr priority. Turn this off to see every entry that carried it, which is what makes results from filter-specific entries (freeleech and the like) visible.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `true`
|
||||
|
||||
#### `PROWLARR_USE_SEED_PREFERENCES`
|
||||
|
||||
**Use Prowlarr seed preferences**
|
||||
@@ -1177,6 +1304,8 @@ Apply per-indexer seed time and ratio preferences from Prowlarr when sending tor
|
||||
| `NEWZNAB_ENABLED` | Enable searching for books via a Newznab-compatible indexer | boolean | `false` |
|
||||
| `NEWZNAB_URL` | Base URL of your Newznab indexer or aggregator | string | _none_ |
|
||||
| `NEWZNAB_API_KEY` | Your Newznab API key (leave blank if not required) | string (secret) | _none_ |
|
||||
| `NEWZNAB_EBOOK_CATEGORIES` | Newznab category IDs searched for ebooks. Most indexers use the standard 7000, but some use custom IDs. Leave empty to use 7000. | string (comma-separated) | `7000` |
|
||||
| `NEWZNAB_AUDIOBOOK_CATEGORIES` | Newznab category IDs searched for audiobooks. Most indexers use the standard 3030, but some use custom IDs. Leave empty to use 3030. | string (comma-separated) | `3030` |
|
||||
| `NEWZNAB_AUTO_EXPAND` | Automatically retry search without category filtering if no results are found | boolean | `false` |
|
||||
|
||||
<details>
|
||||
@@ -1210,6 +1339,24 @@ Your Newznab API key (leave blank if not required)
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
|
||||
#### `NEWZNAB_EBOOK_CATEGORIES`
|
||||
|
||||
**Ebook Categories**
|
||||
|
||||
Newznab category IDs searched for ebooks. Most indexers use the standard 7000, but some use custom IDs. Leave empty to use 7000.
|
||||
|
||||
- **Type:** string (comma-separated)
|
||||
- **Default:** `7000`
|
||||
|
||||
#### `NEWZNAB_AUDIOBOOK_CATEGORIES`
|
||||
|
||||
**Audiobook Categories**
|
||||
|
||||
Newznab category IDs searched for audiobooks. Most indexers use the standard 3030, but some use custom IDs. Leave empty to use 3030.
|
||||
|
||||
- **Type:** string (comma-separated)
|
||||
- **Default:** `3030`
|
||||
|
||||
#### `NEWZNAB_AUTO_EXPAND`
|
||||
|
||||
**Auto-expand search on no results**
|
||||
@@ -1291,9 +1438,11 @@ Delay between requests in seconds to avoid rate limiting (0-10).
|
||||
| `IRC_SERVER` | IRC server hostname | string | _none_ |
|
||||
| `IRC_PORT` | IRC server port (usually 6697 for TLS, 6667 for plain) | number | `6697` |
|
||||
| `IRC_USE_TLS` | Enable TLS/SSL encryption for the IRC connection. Disable for servers that don't support TLS. | boolean | `true` |
|
||||
| `IRC_CHANNEL` | Channel name without the # prefix | string | _none_ |
|
||||
| `IRC_CHANNEL` | Channel name without the # prefix. Used for all searches unless a separate audiobook channel is configured below. | string | _none_ |
|
||||
| `IRC_NICK` | Your IRC nickname (required). Must be unique on the IRC network. | string | _none_ |
|
||||
| `IRC_SEARCH_BOT` | The search bot to address queries to (required). | string | _none_ |
|
||||
| `IRC_SEARCH_BOT` | The search bot to address queries to (required). Searches are sent as "@<bot> <query>". | string | _none_ |
|
||||
| `IRC_AUDIOBOOK_CHANNEL` | Optional. Channel name (without the # prefix) for networks that index audiobooks separately, such as Undernet's bookz. Leave blank (the usual setting) to search the main channel above for audiobooks too. | string | _none_ |
|
||||
| `IRC_AUDIOBOOK_SEARCH_BOT` | Optional. Search bot for the audiobook channel. Leave blank to reuse the main search bot above. Only used when an audiobook channel is set. | string | _none_ |
|
||||
| `IRC_CACHE_TTL` | How long to keep cached search results before they expire. | string (choice) | `2592000` |
|
||||
|
||||
<details>
|
||||
@@ -1331,7 +1480,7 @@ Enable TLS/SSL encryption for the IRC connection. Disable for servers that don't
|
||||
|
||||
**Channel**
|
||||
|
||||
Channel name without the # prefix
|
||||
Channel name without the # prefix. Used for all searches unless a separate audiobook channel is configured below.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _none_
|
||||
@@ -1351,12 +1500,30 @@ Your IRC nickname (required). Must be unique on the IRC network.
|
||||
|
||||
**Search bot**
|
||||
|
||||
The search bot to address queries to (required). Searches are sent as "@<bot> <query>". Without it, queries would be posted unaddressed to the channel.
|
||||
The search bot to address queries to (required). Searches are sent as "@<bot> <query>".
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _none_
|
||||
- **Required:** Yes
|
||||
|
||||
#### `IRC_AUDIOBOOK_CHANNEL`
|
||||
|
||||
**Audiobook channel**
|
||||
|
||||
Optional. Channel name (without the # prefix) for networks that index audiobooks separately, such as Undernet's bookz. Leave blank (the usual setting) to search the main channel above for audiobooks too.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _none_
|
||||
|
||||
#### `IRC_AUDIOBOOK_SEARCH_BOT`
|
||||
|
||||
**Audiobook search bot**
|
||||
|
||||
Optional. Search bot for the audiobook channel. Leave blank to reuse the main search bot above. Only used when an audiobook channel is set.
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _none_
|
||||
|
||||
#### `IRC_CACHE_TTL`
|
||||
|
||||
**Cache Duration**
|
||||
@@ -1374,9 +1541,12 @@ How long to keep cached search results before they expire.
|
||||
| Variable | Description | Type | Default |
|
||||
|----------|-------------|------|---------|
|
||||
| `PROWLARR_TORRENT_CLIENT` | Choose which torrent client to use | string (choice) | _empty string_ |
|
||||
| `ALLDEBRID_API_KEY` | AllDebrid API Key (apiv4) from your AllDebrid account settings | string (secret) | _none_ |
|
||||
| `REALDEBRID_API_KEY` | Real-Debrid API Key (Secret Token) from your Real-Debrid account settings | string (secret) | _none_ |
|
||||
| `QBITTORRENT_URL` | Web UI URL of your qBittorrent instance | string | _none_ |
|
||||
| `QBITTORRENT_USERNAME` | qBittorrent Web UI username | string | _none_ |
|
||||
| `QBITTORRENT_PASSWORD` | qBittorrent Web UI password | string (secret) | _none_ |
|
||||
| `QBITTORRENT_API_KEY` | Found in qBittorrent: Options > Web UI > API Key (qBittorrent 5.2.0+). Used instead of the username and password when set. | string (secret) | _none_ |
|
||||
| `QBITTORRENT_CATEGORY` | Category to assign to book downloads in qBittorrent | string | `books` |
|
||||
| `QBITTORRENT_CATEGORY_AUDIOBOOK` | Category for audiobook downloads. Leave empty to use the book category. | string | _empty string_ |
|
||||
| `QBITTORRENT_DOWNLOAD_DIR` | Server-side directory where torrents are downloaded (optional, uses qBittorrent default if not specified) | string | _none_ |
|
||||
@@ -1396,9 +1566,11 @@ How long to keep cached search results before they expire.
|
||||
| `RTORRENT_URL` | XML-RPC URL of your rTorrent instance | string | _none_ |
|
||||
| `RTORRENT_USERNAME` | HTTP Basic auth username (if authentication enabled) | string | _none_ |
|
||||
| `RTORRENT_PASSWORD` | HTTP Basic auth password | string (secret) | _none_ |
|
||||
| `RTORRENT_LABEL` | Label to assign to book downloads in rTorrent | string | `cwabd` |
|
||||
| `RTORRENT_LABEL` | Label to assign to ebook downloads in rTorrent | string | `cwabd` |
|
||||
| `RTORRENT_AUDIOBOOK_LABEL` | Label to assign to audiobook downloads in rTorrent (falls back to Book Label if not set) | string | _none_ |
|
||||
| `RTORRENT_DOWNLOAD_DIR` | Server-side directory where torrents are downloaded (optional, uses rTorrent default if not specified) | string | _none_ |
|
||||
| `PROWLARR_TORRENT_ACTION` | Remove deletes the torrent from your client immediately after import (stops seeding, files are kept); Keep leaves it in the client to continue seeding | string (choice) | `keep` |
|
||||
| `PROWLARR_TORRENT_ACTION` | Choose whether to keep, remove, or move the torrent to another category or label after import | string (choice) | `keep` |
|
||||
| `PROWLARR_TORRENT_POST_IMPORT_CATEGORY` | Category or label to assign after a successful import | string | _empty string_ |
|
||||
| `PROWLARR_USENET_CLIENT` | Choose which usenet client to use | string (choice) | _empty string_ |
|
||||
| `NZBGET_URL` | URL of your NZBGet instance | string | _none_ |
|
||||
| `NZBGET_USERNAME` | NZBGet control username | string | `nzbget` |
|
||||
@@ -1422,7 +1594,25 @@ Choose which torrent client to use
|
||||
|
||||
- **Type:** string (choice)
|
||||
- **Default:** _empty string_
|
||||
- **Options:** `""` (None), `qbittorrent` (qBittorrent), `transmission` (Transmission), `deluge` (Deluge), `rtorrent` (rTorrent)
|
||||
- **Options:** `""` (None), `alldebrid` (AllDebrid), `qbittorrent` (qBittorrent), `realdebrid` (Real-Debrid), `transmission` (Transmission), `deluge` (Deluge), `rtorrent` (rTorrent)
|
||||
|
||||
#### `ALLDEBRID_API_KEY`
|
||||
|
||||
**API Key**
|
||||
|
||||
AllDebrid API Key (apiv4) from your AllDebrid account settings
|
||||
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
|
||||
#### `REALDEBRID_API_KEY`
|
||||
|
||||
**API Key**
|
||||
|
||||
Real-Debrid API Key (Secret Token) from your Real-Debrid account settings
|
||||
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
|
||||
#### `QBITTORRENT_URL`
|
||||
|
||||
@@ -1451,6 +1641,15 @@ qBittorrent Web UI password
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
|
||||
#### `QBITTORRENT_API_KEY`
|
||||
|
||||
**API Key**
|
||||
|
||||
Found in qBittorrent: Options > Web UI > API Key (qBittorrent 5.2.0+). Used instead of the username and password when set.
|
||||
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
|
||||
#### `QBITTORRENT_CATEGORY`
|
||||
|
||||
**Book Category**
|
||||
@@ -1626,11 +1825,20 @@ HTTP Basic auth password
|
||||
|
||||
**Book Label**
|
||||
|
||||
Label to assign to book downloads in rTorrent
|
||||
Label to assign to ebook downloads in rTorrent
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** `cwabd`
|
||||
|
||||
#### `RTORRENT_AUDIOBOOK_LABEL`
|
||||
|
||||
**Audiobook Label**
|
||||
|
||||
Label to assign to audiobook downloads in rTorrent (falls back to Book Label if not set)
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _none_
|
||||
|
||||
#### `RTORRENT_DOWNLOAD_DIR`
|
||||
|
||||
**Download Directory**
|
||||
@@ -1644,11 +1852,20 @@ Server-side directory where torrents are downloaded (optional, uses rTorrent def
|
||||
|
||||
**Torrent Completion Action**
|
||||
|
||||
Remove deletes the torrent from your client immediately after import (stops seeding, files are kept); Keep leaves it in the client to continue seeding
|
||||
Choose whether to keep, remove, or move the torrent to another category or label after import
|
||||
|
||||
- **Type:** string (choice)
|
||||
- **Default:** `keep`
|
||||
- **Options:** `keep` (Keep), `remove` (Remove)
|
||||
- **Options:** `keep` (Keep), `remove` (Remove), `change_category` (Change Category)
|
||||
|
||||
#### `PROWLARR_TORRENT_POST_IMPORT_CATEGORY`
|
||||
|
||||
**Post-Import Category**
|
||||
|
||||
Category or label to assign after a successful import
|
||||
|
||||
- **Type:** string
|
||||
- **Default:** _empty string_
|
||||
|
||||
#### `PROWLARR_USENET_CLIENT`
|
||||
|
||||
@@ -1760,7 +1977,7 @@ Move deletes the job from your usenet client after import; Copy keeps it in the
|
||||
| Variable | Description | Type | Default |
|
||||
|----------|-------------|------|---------|
|
||||
| `HARDCOVER_ENABLED` | Enable Hardcover as a metadata provider for book searches | boolean | `false` |
|
||||
| `HARDCOVER_API_KEY` | Get your API key from hardcover.app/account/api | string (secret) | _none_ |
|
||||
| `HARDCOVER_API_KEY` | Get your API key from hardcover.app/account/api (starts with hc_pat_) | string (secret) | _none_ |
|
||||
| `HARDCOVER_DEFAULT_SORT` | Default sort order for Hardcover search results. | string (choice) | `relevance` |
|
||||
| `HARDCOVER_EXCLUDE_COMPILATIONS` | Filter out compilations, anthologies, and omnibus editions from search results | boolean | `false` |
|
||||
| `HARDCOVER_EXCLUDE_UNRELEASED` | Filter out books with a release year in the future | boolean | `false` |
|
||||
@@ -1782,7 +1999,7 @@ Enable Hardcover as a metadata provider for book searches
|
||||
|
||||
**API Key**
|
||||
|
||||
Get your API key from hardcover.app/account/api
|
||||
Get your API key from hardcover.app/account/api (starts with hc_pat_)
|
||||
|
||||
- **Type:** string (secret)
|
||||
- **Default:** _none_
|
||||
@@ -1900,6 +2117,26 @@ Default sort order for Google Books search results.
|
||||
|
||||
</details>
|
||||
|
||||
### Metadata Providers: Moly.hu
|
||||
|
||||
| Variable | Description | Type | Default |
|
||||
|----------|-------------|------|---------|
|
||||
| `MOLY_ENABLED` | Enable Moly.hu as a metadata provider for book searches | boolean | `false` |
|
||||
|
||||
<details>
|
||||
<summary>Detailed descriptions</summary>
|
||||
|
||||
#### `MOLY_ENABLED`
|
||||
|
||||
**Enable Moly.hu**
|
||||
|
||||
Enable Moly.hu as a metadata provider for book searches
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
</details>
|
||||
|
||||
## Direct Download
|
||||
|
||||
### Direct Download: Download Sources
|
||||
@@ -1907,6 +2144,7 @@ Default sort order for Google Books search results.
|
||||
| Variable | Description | Type | Default |
|
||||
|----------|-------------|------|---------|
|
||||
| `DIRECT_DOWNLOAD_ENABLED` | Show Direct Download in release-source lists and allow Direct mode searches. Add your own mirror URLs in the Mirrors tab before using it. | boolean | `false` |
|
||||
| `DIRECT_DOWNLOAD_LANGUAGE_FROM_PATH` | When language metadata is missing or unknown, parse the distant path (file path shown in search results) for language tags like [BD FR] or [En]. Also enables local language filtering so lgli files without AA language metadata are not excluded before the distant path can be checked. | boolean | `false` |
|
||||
| `AA_DONATOR_KEY` | Enables fast download access on AA. Get this from your donator account page. | string (secret) | _none_ |
|
||||
| `FAST_SOURCES_DISPLAY` | Always tried first, no waiting or bypass required. | JSON array | _see UI for defaults_ |
|
||||
| `SOURCE_PRIORITY` | Fallback sources, may have waiting. Requires bypasser. Drag to reorder. | JSON array | _see UI for defaults_ |
|
||||
@@ -1934,6 +2172,15 @@ Show Direct Download in release-source lists and allow Direct mode searches. Add
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `DIRECT_DOWNLOAD_LANGUAGE_FROM_PATH`
|
||||
|
||||
**Detect Language From Distant Path**
|
||||
|
||||
When language metadata is missing or unknown, parse the distant path (file path shown in search results) for language tags like [BD FR] or [En]. Also enables local language filtering so lgli files without AA language metadata are not excluded before the distant path can be checked.
|
||||
|
||||
- **Type:** boolean
|
||||
- **Default:** `false`
|
||||
|
||||
#### `AA_DONATOR_KEY`
|
||||
|
||||
**Account Donator Key**
|
||||
@@ -2057,6 +2304,7 @@ Override destination based on content type metadata.
|
||||
| `EXT_BYPASSER_URL` | URL of the external bypasser service (e.g., FlareSolverr). | string | `http://flaresolverr:8191` |
|
||||
| `EXT_BYPASSER_PATH` | API path for the external bypasser. | string | `/v1` |
|
||||
| `EXT_BYPASSER_TIMEOUT` | Timeout for external bypasser requests in milliseconds. | number | `60000` |
|
||||
| `BYPASS_BROWSER_IDLE_TIMEOUT` | How long the bypass helper process may sit unused before it is shut down. Higher keeps more searches fast, lower frees memory sooner. | number | `180` |
|
||||
|
||||
<details>
|
||||
<summary>Detailed descriptions</summary>
|
||||
@@ -2112,6 +2360,17 @@ Timeout for external bypasser requests in milliseconds.
|
||||
- **Requires restart:** Yes
|
||||
- **Constraints:** min: 10000, max: 300000
|
||||
|
||||
#### `BYPASS_BROWSER_IDLE_TIMEOUT`
|
||||
|
||||
**Bypasser Idle Timeout (seconds)**
|
||||
|
||||
How long the bypass helper process may sit unused before it is shut down. Higher keeps more searches fast, lower frees memory sooner.
|
||||
|
||||
- **Type:** number
|
||||
- **Default:** `180`
|
||||
- **Requires restart:** Yes
|
||||
- **Constraints:** min: 30, max: 3600
|
||||
|
||||
</details>
|
||||
|
||||
### Direct Download: Mirrors
|
||||
|
||||
+17
-3
@@ -12,7 +12,7 @@ With a subpath (`URL_BASE=/shelfmark/`):
|
||||
https://<your-shelfmark-domain>/shelfmark/api/auth/oidc/callback
|
||||
```
|
||||
|
||||
The callback URL is constructed from the incoming request, so your reverse proxy must forward `X-Forwarded-Proto` and `X-Forwarded-Host` correctly. PKCE (S256) is used automatically.
|
||||
The callback URL is constructed from the incoming request, so your reverse proxy must forward `X-Forwarded-Proto` and `X-Forwarded-Host` correctly, including the external port when it is not the protocol default. PKCE (S256) is used automatically.
|
||||
|
||||
## Settings
|
||||
|
||||
@@ -30,7 +30,19 @@ Configure in **Settings → Security → Authentication Method → OIDC**.
|
||||
| Auto-Provision Users | Create accounts on first login | `true` |
|
||||
| Login Button Label | Custom text for the sign-in button | — |
|
||||
|
||||
Use **Test Connection** to verify discovery and client configuration before attempting login.
|
||||
Use **Test Connection** to verify discovery, client configuration, and the provider's token signing keys (JWKS) before attempting login.
|
||||
|
||||
> **Authentik users:** make sure your provider has a **Signing Key** selected (e.g. the default self-signed certificate). Without one, Authentik serves an empty JWKS document and every login fails with an OIDC callback error, even though the discovery document looks healthy.
|
||||
|
||||
## Account Linking
|
||||
|
||||
On login, Shelfmark matches the OIDC identity to a user account in this order:
|
||||
|
||||
1. **OIDC subject** — a user who has logged in through this provider before.
|
||||
2. **Email** — a local account with the same (unique) email address. This only happens when the provider also asserts `email_verified: true` for the address; an unverified email would let anyone claim a local account by registering its address at the IdP.
|
||||
3. Otherwise, a new account is created when **Auto-Provision Users** is enabled (username conflicts get a numeric suffix), or the login is rejected with "Account not found" when it is disabled.
|
||||
|
||||
If the `email_verified` claim is missing or `false`, email linking is silently skipped — a common surprise when the address was never verified at the identity provider (e.g. Keycloak's **Email verified** toggle on the user, or Authentik accounts created without email verification). Make sure the `email` scope is requested and the address is marked verified in your IdP.
|
||||
|
||||
## Environment Variables
|
||||
|
||||
@@ -46,6 +58,8 @@ If `DISABLE_LOCAL_AUTH` and `OIDC_AUTO_REDIRECT` are both enabled, users are red
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
- **No token signing keys (empty JWKS)** — The provider's JWKS endpoint returned no keys, so ID tokens can't be verified. In Authentik this happens when the provider has no **Signing Key** selected; pick one (e.g. the default self-signed certificate) and try again.
|
||||
- **Issuer validation failed** — The issuer in the token doesn't match the discovery document. Check your provider's external URL / issuer configuration.
|
||||
- **Callback URL mismatch** — Reverse proxy isn't forwarding `X-Forwarded-Proto` or `X-Forwarded-Host`, so the constructed callback URL doesn't match what's registered in the provider.
|
||||
- **Account not found** — Auto-provision is disabled and the user hasn't been pre-created by an admin.
|
||||
- **Account not found** — Auto-provision is disabled and the user hasn't been pre-created by an admin. If you pre-created the account with a matching email, see [Account Linking](#account-linking): the provider must send `email_verified: true` for linking to happen.
|
||||
- **Login created a duplicate account instead of linking to my local one** — Email linking requires a verified email; see [Account Linking](#account-linking). With `DEBUG=true`, the log notes when linking is skipped because the address isn't verified.
|
||||
|
||||
@@ -23,10 +23,11 @@ server {
|
||||
location / {
|
||||
proxy_pass http://shelfmark:8084;
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header Host $http_host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $http_host;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection $connection_upgrade;
|
||||
}
|
||||
@@ -56,11 +57,11 @@ All Shelfmark paths (UI, API, assets, Socket.IO) are served under the base path.
|
||||
location /shelfmark/ {
|
||||
proxy_pass http://shelfmark:8084/shelfmark/;
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header Host $http_host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Host $http_host;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection $connection_upgrade;
|
||||
proxy_read_timeout 86400;
|
||||
@@ -136,11 +137,11 @@ location /shelfmark/ {
|
||||
|
||||
proxy_pass http://shelfmark:8084/shelfmark/;
|
||||
proxy_http_version 1.1;
|
||||
proxy_set_header Host $host;
|
||||
proxy_set_header Host $http_host;
|
||||
proxy_set_header X-Real-IP $remote_addr;
|
||||
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
||||
proxy_set_header X-Forwarded-Proto $scheme;
|
||||
proxy_set_header X-Forwarded-Host $host;
|
||||
proxy_set_header X-Forwarded-Host $http_host;
|
||||
proxy_set_header Upgrade $http_upgrade;
|
||||
proxy_set_header Connection $connection_upgrade;
|
||||
proxy_read_timeout 86400;
|
||||
@@ -158,6 +159,7 @@ If login, settings saves, or downloads appear to fail in the browser but the act
|
||||
- Do not force `Connection: upgrade` on every request. That can break normal `POST` and `PUT` responses while the backend still processes them.
|
||||
- If your proxy UI does not support conditional websocket headers, remove the forced websocket headers entirely and let Shelfmark fall back to polling.
|
||||
- Keep the standard forwarded headers: `Host`, `X-Forwarded-For`, `X-Forwarded-Proto`, and `X-Forwarded-Host` when using a subpath or OIDC.
|
||||
- Preserve the original port in `Host` and `X-Forwarded-Host` by using `$http_host` rather than `$host` when Shelfmark is exposed on a custom port.
|
||||
|
||||
This is especially relevant for Nginx Proxy Manager or custom advanced config snippets that add websocket headers globally.
|
||||
|
||||
|
||||
+45
-3
@@ -81,6 +81,13 @@ if is_truthy "$ENABLE_LOGGING_VALUE"; then
|
||||
fi
|
||||
fi
|
||||
|
||||
# Egress modes are mutually exclusive. Check this BEFORE starting either one so
|
||||
# we never run tor.sh and then abort, leaving a half-configured network stack.
|
||||
if [ "$USING_TOR" = "true" ] && [ "$USING_WIREGUARD" = "true" ]; then
|
||||
echo "USING_TOR and USING_WIREGUARD are mutually exclusive; enable only one egress mode." >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
if [ "$USING_TOR" = "true" ]; then
|
||||
if [ "$RUN_AS_NON_ROOT" = "true" ]; then
|
||||
echo "USING_TOR=true requires the container to start as root." >&2
|
||||
@@ -90,6 +97,15 @@ if [ "$USING_TOR" = "true" ]; then
|
||||
./tor.sh
|
||||
fi
|
||||
|
||||
if [ "$USING_WIREGUARD" = "true" ]; then
|
||||
if [ "$RUN_AS_NON_ROOT" = "true" ]; then
|
||||
echo "USING_WIREGUARD=true requires the container to start as root." >&2
|
||||
echo "Non-root mode skips the privileged network setup WireGuard depends on." >&2
|
||||
exit 1
|
||||
fi
|
||||
./wireguard.sh
|
||||
fi
|
||||
|
||||
if [ "$FILE_LOGGING_ENABLED" = "true" ]; then
|
||||
start_file_logging "$LOG_FILE"
|
||||
fi
|
||||
@@ -235,13 +251,22 @@ test_write() {
|
||||
return 1
|
||||
fi
|
||||
|
||||
if ! run_as_target_user sh -c 'echo 0123456789_TEST > "$1"' _ "$test_file"; then
|
||||
# This is a probe: a failure here is expected (e.g. a fresh root-owned bind
|
||||
# mount) and is recovered by the caller via change_ownership + re-probe. Hide
|
||||
# the shell's "Permission denied"/"Read-only file system" stderr so a handled
|
||||
# probe miss doesn't masquerade as a real boot failure in the logs.
|
||||
if ! run_as_target_user sh -c 'echo 0123456789_TEST 2>/dev/null > "$1"' _ "$test_file"; then
|
||||
echo "Failed to write test file in $folder as $USERNAME"
|
||||
return 1
|
||||
fi
|
||||
|
||||
FILE_CONTENT=$(cat "$test_file" 2>/dev/null || echo "")
|
||||
rm -f "$test_file"
|
||||
# A folder can be writable but not deletable (e.g. a Synology share without
|
||||
# "Delete subfolders and files"). That is not a boot failure - the app writes
|
||||
# files in place on such shares - so don't let a failed cleanup print an
|
||||
# alarming error or fail the probe.
|
||||
run_as_target_user rm -f "$test_file" 2>/dev/null || \
|
||||
echo "Note: could not remove test file in $folder (folder is writable but not deletable)"
|
||||
[ "$FILE_CONTENT" = "0123456789_TEST" ]
|
||||
result=$?
|
||||
if [ $result -eq 0 ]; then
|
||||
@@ -448,12 +473,29 @@ else
|
||||
if [ $config_ok -ne 0 ]; then
|
||||
fail_unwritable_config_dir "$CONFIG_PATH"
|
||||
fi
|
||||
|
||||
# The ingest/destination library (default /books) is user data and may be a
|
||||
# bind mount owned by another uid; downloads fail with "Destination not
|
||||
# writable" if the runtime user can't write there. Fix the top-level dir only
|
||||
# (root mode) so we don't recursively chown a potentially huge library.
|
||||
make_writable "${INGEST_DIR:-/books}" root
|
||||
fi
|
||||
|
||||
# Always run Gunicorn (even when DEBUG=true) to ensure Socket.IO WebSocket
|
||||
# upgrades work reliably on customer machines.
|
||||
# Map app LOG_LEVEL (often DEBUG/INFO/...) to gunicorn's --log-level (lowercase).
|
||||
gunicorn_loglevel=$([ "$DEBUG" = "true" ] && echo debug || echo "${LOG_LEVEL:-info}" | tr '[:upper:]' '[:lower:]')
|
||||
# Gunicorn rejects anything outside its own list, so normalize and fall back to
|
||||
# info rather than letting a typo stop the container from booting.
|
||||
if [ "$DEBUG" = "true" ]; then
|
||||
gunicorn_loglevel=debug
|
||||
else
|
||||
gunicorn_loglevel=$(echo "${LOG_LEVEL:-info}" | tr '[:upper:]' '[:lower:]')
|
||||
[ "$gunicorn_loglevel" = "warn" ] && gunicorn_loglevel=warning
|
||||
case "$gunicorn_loglevel" in
|
||||
debug|info|warning|error|critical) ;;
|
||||
*) gunicorn_loglevel=info ;;
|
||||
esac
|
||||
fi
|
||||
command="${GUNICORN_BIN} --log-level ${gunicorn_loglevel} --access-logfile - --error-logfile - --worker-class geventwebsocket.gunicorn.workers.GeventWebSocketWorker --workers 1 -t 300 -b ${FLASK_HOST:-0.0.0.0}:${FLASK_PORT:-8084} shelfmark.main:app"
|
||||
|
||||
# If DEBUG and not using an external bypass
|
||||
|
||||
+8
-5
@@ -19,28 +19,31 @@ dependencies = [
|
||||
"psutil",
|
||||
"emoji",
|
||||
"rarfile",
|
||||
"qbittorrent-api",
|
||||
"qbittorrent-api>=2026.8.1",
|
||||
"transmission-rpc",
|
||||
"authlib>=1.7.2,<1.8",
|
||||
"apprise>=1.11.0",
|
||||
"apprise>=1.12.0",
|
||||
# HTTP/2 client for RFC 8484 DoH: quad9 rejects HTTP/1.1 outright (505), which
|
||||
# requests cannot speak. See shelfmark/download/doh_wireformat.py.
|
||||
"httpx[http2]>=0.28.1",
|
||||
]
|
||||
|
||||
[project.optional-dependencies]
|
||||
browser = [
|
||||
"pyvirtualdisplay",
|
||||
"pyautogui",
|
||||
"seleniumbase==4.49.10",
|
||||
"seleniumbase==4.51.12",
|
||||
"python-xlib",
|
||||
]
|
||||
|
||||
[dependency-groups]
|
||||
dev = [
|
||||
"basedpyright>=1.39.7",
|
||||
"basedpyright>=1.39.10",
|
||||
"prek",
|
||||
"pytest",
|
||||
"pytest-cov",
|
||||
"pytest-xdist>=3.8.0",
|
||||
"ruff==0.15.17",
|
||||
"ruff==0.16.3",
|
||||
"vulture>=2.14",
|
||||
]
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
<img src="src/frontend/public/logo.png" alt="Shelfmark" width="200">
|
||||
|
||||
> [!NOTE]
|
||||
> This project is in a stable state as of May 2026 but is not under active maintenance.
|
||||
> Shelfmark is feature stable and maintained on a best-effort basis. Bug fixes, security updates, and small quality-of-life improvements are still shipped, and pull requests are reviewed — including new features. There is no roadmap for new features for now.
|
||||
|
||||
Shelfmark is a self-hosted web interface for searching and requesting books and audiobooks across multiple sources. Bring your own sources, metadata providers, and download clients to build a single hub for your digital library. Supports multiple users with a built-in request system, so you can share your instance with others and let them browse and request books on their own.
|
||||
|
||||
@@ -44,6 +44,7 @@ Works great alongside the following library tools, with support for automatic im
|
||||
### Prerequisites
|
||||
|
||||
- Docker & Docker Compose
|
||||
- At least 2 GB of RAM available to the container when using the standard image — see [Memory Requirements](#memory-requirements)
|
||||
|
||||
### Installation
|
||||
|
||||
@@ -94,6 +95,30 @@ volumes:
|
||||
- Aggregates releases from multiple configured sources
|
||||
- Full audiobook support
|
||||
|
||||
### Hardcover API Key
|
||||
|
||||
Hardcover powers metadata search in Universal mode. Create a token at
|
||||
[hardcover.app/account/api](https://hardcover.app/account/api) — current keys start with `hc_pat_`
|
||||
and are far shorter than the JWTs Hardcover issued before August 2026.
|
||||
|
||||
Tick these seven scopes on the token screen:
|
||||
|
||||
| Scope | Used for |
|
||||
|-------|----------|
|
||||
| `read:catalog` | Metadata search, plus book, edition, author and series lookups |
|
||||
| `read:library` | Your reading status and shelf counts |
|
||||
| `read:lists` | Your lists and the books on them |
|
||||
| `read:me:content` | Test Connection and the "Connected as" label |
|
||||
| `read:users` | Usernames shown alongside lists |
|
||||
| `write:library` | Setting a book's reading status from Shelfmark |
|
||||
| `write:lists` | Adding and removing books from lists, including auto-remove on download |
|
||||
|
||||
The two `write:` scopes matter only if you set reading status from Shelfmark or leave
|
||||
**Auto-Remove from List on Download** enabled (it is on by default) — without them those actions
|
||||
fail silently. Everything else Hardcover offers (journal, goals, reviews, prompts, notifications,
|
||||
account) can stay unticked. The `all` scope works too, but it grants full account access including
|
||||
deletion, so prefer the list above.
|
||||
|
||||
### Environment Variables
|
||||
|
||||
Environment variables work for initial setup and Docker deployments. They serve as defaults that can be overridden in the web interface.
|
||||
@@ -106,13 +131,23 @@ Environment variables work for initial setup and Docker deployments. They serve
|
||||
| `PUID` / `PGID` | Runtime user/group for the default root-startup flow (also supports legacy `UID`/`GID`) | `1000` / `1000` |
|
||||
| `SEARCH_MODE` | `direct` or `universal` | `universal` |
|
||||
| `USING_TOR` | Enable Tor routing (requires root startup) | `false` |
|
||||
| `USING_WIREGUARD` | Enable WireGuard VPN egress with kill-switch (requires root startup) | `false` |
|
||||
| `WIREGUARD_CONFIG` | Path to the mounted wg-quick config | `/config/wg0.conf` |
|
||||
| `WIREGUARD_INTERFACE` | WireGuard interface name | `wg0` |
|
||||
| `LAN_NETWORK` | Comma-separated CIDRs kept off the tunnel so the WebUI / internal clients stay reachable | `127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16` |
|
||||
| `WIREGUARD_ENFORCE_DNS` | Pin the resolver (via `WIREGUARD_DNS`, else the config's `DNS =`) so DNS can't silently fall back to an off-tunnel path. Designed for a trusted LAN resolver kept reachable via `LAN_NETWORK` (query leaves over the LAN; download still egresses via the tunnel) — it does **not** force queries through the tunnel. Docker's embedded resolver (`127.0.0.11`) is preserved when present so container-name resolution keeps working; pin its upstream via the container's `dns:` list. Fails closed if no resolver is available or `/etc/resolv.conf` is not writable. | `true` |
|
||||
| `WIREGUARD_DNS` | Explicit resolver(s) to pin (comma/space separated). Use when the VPN's pushed DNS filters domains you need; point at a resolver reachable via the tunnel or an allowed LAN resolver. | _(unset; uses config `DNS =`)_ |
|
||||
| `WIREGUARD_DISABLE_IPV6` | Strip IPv6 from the tunnel config (many container kernels lack the ip6tables `raw` table wg-quick needs) and remove IPv6 as a leak surface. | `true` |
|
||||
| `WIREGUARD_ALLOW_IPV6_LEAK` | Escape hatch: continue even when an IPv6 kill-switch can't be installed AND IPv6 can't be disabled. Only set if the container has no IPv6 connectivity. | `false` |
|
||||
| `WIREGUARD_ALLOW_WEBUI_OFFTUNNEL` | Opt-in off-tunnel WebUI reachability. Default (`false`) keeps the kill-switch strictly fail-closed: the only off-tunnel egress is loopback, the tunnel device and the LAN allowlist. Set `true` only if a **non-LAN** client (e.g. a public reverse proxy on another segment) must reach the WebUI; it permits app-server **replies** (`--sport FLASK_PORT`, conntrack REPLY) off-tunnel — server replies only, never client-initiated egress. LAN clients never need it (covered by `LAN_NETWORK`). | `false` |
|
||||
| `WIREGUARD_STALE_AFTER` | Seconds since the last handshake before the healthcheck bounces the tunnel. | `180` |
|
||||
|
||||
See the full [Environment Variables Reference](docs/environment-variables.md) for all available options.
|
||||
|
||||
Some of the additional options available in Settings:
|
||||
- **Prowlarr** - Configure indexers and download clients to download books and audiobooks
|
||||
- **Additional audiobook sources** - Configure additional sources for audiobook discovery
|
||||
- **IRC** - Add details for IRC book sources and download directly from the UI
|
||||
- **IRC** - Add details for IRC book sources and download directly from the UI. Most networks serve audiobooks from the same channel as ebooks (on `irc.irchighway.net` that's `#ebooks`, while `#bookz` is effectively inactive), so leave the separate audiobook channel blank unless your network actually indexes one. IRC audiobooks usually arrive as ZIP/RAR archives — keep those enabled under Supported Audiobook Formats or the releases are filtered out of results
|
||||
- **Library Link** - Add a link to your Calibre-Web or Grimmory instance in the UI header
|
||||
- **File processing** - Customiseable download paths, file renaming and directory creation with template-based renaming
|
||||
- **Network Settings** - Custom proxy support (SOCKS5 + HTTP/S) and configurable DNS
|
||||
@@ -128,6 +163,17 @@ docker compose up -d
|
||||
|
||||
The full-featured image with all network capabilities included.
|
||||
|
||||
#### Memory Requirements
|
||||
|
||||
The standard image ships a real Chromium browser, which it launches to solve Cloudflare challenges for Direct Download. Chromium needs room to run:
|
||||
|
||||
- **2 GB of RAM available to the container** is a safe minimum; 1 GB or less is where problems usually start
|
||||
- Only relevant if you use Direct Download. Prowlarr, IRC and audiobook sources don't start the browser
|
||||
|
||||
When the container is starved of memory, Chromium fails to start and every Direct Download fails with unrelated-looking errors — repeated `403 detected; switching to bypasser` followed by `No download URL found`, and downloads that never complete. If you're seeing that, check the container's memory limit and the host's free memory before suspecting your ISP or DNS.
|
||||
|
||||
If you can't spare the memory, use the [Lite](#lite) image with an external resolver (e.g. FlareSolverr) running elsewhere.
|
||||
|
||||
#### Tor Routing
|
||||
Optional Tor support for network privacy:
|
||||
```bash
|
||||
@@ -141,12 +187,31 @@ docker compose -f docker-compose.tor.yml up -d
|
||||
- Timezone is auto-detected from Tor exit node
|
||||
- Custom DNS/proxy settings are ignored when Tor is active
|
||||
|
||||
#### WireGuard VPN Routing
|
||||
Optional WireGuard support to route all external egress through a VPN tunnel with a fail-closed kill-switch:
|
||||
```bash
|
||||
curl -O https://raw.githubusercontent.com/calibrain/shelfmark/main/compose/docker-compose.wireguard.yml
|
||||
# place your wg-quick config where the compose mounts /config, as wg0.conf
|
||||
docker compose -f docker-compose.wireguard.yml up -d
|
||||
```
|
||||
|
||||
**Notes:**
|
||||
- Requires root startup
|
||||
- Requires `NET_ADMIN` and `NET_RAW` capabilities
|
||||
- Mount a standard wg-quick config at `WIREGUARD_CONFIG` (default `/config/wg0.conf`)
|
||||
- All non-LAN egress is forced through the tunnel; if the tunnel drops, external traffic **fails closed** while LAN ranges (WebUI, Prowlarr, qBittorrent) stay reachable
|
||||
- IPv4 and IPv6 both fail closed. On kernels without a usable `ip6tables`, disable IPv6 for the container (`sysctls: net.ipv6.conf.all.disable_ipv6=1`, as in the compose example) or the container refuses to start rather than risk an IPv6 leak
|
||||
- A supervised healthcheck bounces the tunnel if the handshake goes stale, and refreshes the endpoint allow rules so a roaming/rotated peer endpoint can reconnect
|
||||
- Mutually exclusive with `USING_TOR`
|
||||
- **DNS trust:** `WIREGUARD_DNS` must be a resolver you trust on a trusted network segment. When it is a LAN resolver (kept reachable off-tunnel by `LAN_NETWORK`), the query to that resolver leaves as plaintext UDP/53 on the LAN — the resolver is responsible for encrypting upstream. Two resolver paths exist: (1) when Docker's embedded resolver (`127.0.0.11`) is present it is **preserved** so container names (Prowlarr, qBittorrent) resolve — you MUST pin its upstream to a trusted resolver via the container's compose `dns:` list, since `WIREGUARD_DNS` cannot repoint the embedded resolver from inside the container; (2) otherwise `WIREGUARD_DNS`/the config `DNS =` line is written to `/etc/resolv.conf`. Setting `WIREGUARD_ENFORCE_DNS=false` is a **foot-gun**: with no embedded resolver present the container then uses its inherited resolver, which forwards to the Docker daemon's upstream **off-tunnel**, leaking your DNS. Leave enforcement on unless you have pinned the resolver another way.
|
||||
|
||||
### Lite
|
||||
A lighter image without the built-in browser automation. Ideal for:
|
||||
|
||||
- **External services** - Already running FlareSolverr or similar for other applications
|
||||
- **Alternative sources** - Using Prowlarr, IRC, or other configured sources
|
||||
- **Audiobooks** - Using Shelfmark primarily for audiobooks
|
||||
- **Constrained hosts** - No bundled browser, so it runs comfortably below the standard image's [memory requirements](#memory-requirements)
|
||||
|
||||
```bash
|
||||
curl -O https://raw.githubusercontent.com/calibrain/shelfmark/main/compose/docker-compose.lite.yml
|
||||
@@ -197,9 +262,11 @@ These are non-goals, not missing features.
|
||||
|
||||
## Contributing
|
||||
|
||||
Shelfmark's core feature set is complete. Development focuses on stability, bug fixes, quality-of-life improvements, and refining the search experience. Contributions in these areas are welcome, please file issues or submit pull requests on GitHub.
|
||||
Shelfmark's core feature set is complete.
|
||||
|
||||
Feature requests that fall outside the project scope (library integration, automation, collection management) will be closed. If you're unsure whether something fits, open a discussion first.
|
||||
Pull requests are welcome and all of them get reviewed, new features included. If you want a feature, the fastest path is to send a PR for it rather than to file a request.
|
||||
|
||||
Feature requests that fall outside the project scope (library integration, automation, collection management) will be closed, and PRs implementing them won't be merged. If you're unsure whether something fits, open a discussion first.
|
||||
|
||||
## Health Monitoring
|
||||
|
||||
@@ -219,7 +286,10 @@ Logs are available via:
|
||||
- `docker logs <container-name>`
|
||||
- `/var/log/shelfmark/` inside the container (when `ENABLE_LOGGING=true`)
|
||||
|
||||
Log level is configurable via Settings or `LOG_LEVEL` environment variable.
|
||||
Log level is configurable under Settings → Advanced or via the `LOG_LEVEL` environment
|
||||
variable (`DEBUG`, `INFO`, `WARNING`, `ERROR`, `CRITICAL`; case-insensitive, defaults to
|
||||
`INFO`). The environment variable wins over the setting, and `DEBUG=true` forces `DEBUG`
|
||||
regardless of either. Changes take effect on restart.
|
||||
|
||||
## Development
|
||||
|
||||
|
||||
@@ -238,6 +238,113 @@ def _generate_bootstrap_env_docs() -> list[str]:
|
||||
return lines
|
||||
|
||||
|
||||
def _generate_egress_env_docs() -> list[str]:
|
||||
"""Generate documentation for VPN/Tor egress environment variables.
|
||||
|
||||
These are startup-only variables consumed by entrypoint.sh / wireguard.sh
|
||||
(before and outside the settings registry) to select and configure the
|
||||
transparent-egress kill-switch. `USING_TOR` has a registry-backed entry
|
||||
under Network and is cross-referenced rather than repeated here so the two
|
||||
mutually exclusive egress modes are discoverable side by side without
|
||||
emitting a duplicate `#### USING_TOR` anchor.
|
||||
"""
|
||||
egress_vars = [
|
||||
{
|
||||
"name": "USING_WIREGUARD",
|
||||
"description": "Route all traffic through a WireGuard VPN tunnel with a fail-closed iptables kill-switch (non-tunnel egress is dropped). Requires root startup and NET_ADMIN (plus NET_RAW). Mutually exclusive with USING_TOR.",
|
||||
"type": "boolean",
|
||||
"default": "false",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_CONFIG",
|
||||
"description": "Path to the mounted wg-quick configuration file.",
|
||||
"type": "string (path)",
|
||||
"default": "/config/wg0.conf",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_INTERFACE",
|
||||
"description": "WireGuard interface name brought up by wg-quick.",
|
||||
"type": "string",
|
||||
"default": "wg0",
|
||||
},
|
||||
{
|
||||
"name": "LAN_NETWORK",
|
||||
"description": "Comma-separated CIDRs kept off the tunnel so the WebUI and internal download clients (Prowlarr, qBittorrent) stay reachable.",
|
||||
"type": "string (comma-separated)",
|
||||
"default": "127.0.0.0/8,10.0.0.0/8,172.16.0.0/12,192.168.0.0/16",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_ENFORCE_DNS",
|
||||
"description": "Pin the container's resolver so DNS cannot silently fall back to an off-tunnel path. The resolver used is WIREGUARD_DNS if set, else the tunnel config's DNS = line. This does NOT force queries through the tunnel: it is designed for a trusted LAN resolver kept reachable off-tunnel via LAN_NETWORK (the query leaves over the LAN; the resolver encrypts upstream while the download still egresses via the tunnel). Special case: when Docker's embedded resolver (nameserver 127.0.0.11) is present, it is PRESERVED so container-name resolution (e.g. prowlarr, qbittorrent) keeps working, and the embedded resolver's upstream must be pinned via the container's compose dns: list. Fails closed (refuses to start) only when no embedded resolver is present AND no resolver is defined, or /etc/resolv.conf is not writable.",
|
||||
"type": "boolean",
|
||||
"default": "true",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_DNS",
|
||||
"description": "Explicit resolver(s) (comma/space separated) to pin when WIREGUARD_ENFORCE_DNS is true and Docker's embedded resolver is NOT in use. Use when the VPN's pushed DNS filters domains you need; point it at a resolver reachable via the tunnel or an allowed LAN resolver. NOTE: when the embedded resolver (127.0.0.11) is present it is preserved and this value cannot repoint its upstream from inside the container — set the container's compose dns: list to the trusted resolver instead.",
|
||||
"type": "string (comma-separated)",
|
||||
"default": "unset (uses config DNS = line)",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_DISABLE_IPV6",
|
||||
"description": "Strip IPv6 Address/AllowedIPs/DNS from the tunnel config before wg-quick (many container kernels lack the ip6tables raw table wg-quick needs) and remove IPv6 as a leak surface.",
|
||||
"type": "boolean",
|
||||
"default": "true",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_ALLOW_IPV6_LEAK",
|
||||
"description": "Escape hatch: continue startup even when an IPv6 kill-switch cannot be installed AND IPv6 cannot be disabled. Only set when the container has no IPv6 connectivity, as IPv6 egress may otherwise bypass the tunnel.",
|
||||
"type": "boolean",
|
||||
"default": "false",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_ALLOW_WEBUI_OFFTUNNEL",
|
||||
"description": "When false (default) the kill-switch is strictly fail-closed: the only off-tunnel egress permitted is loopback, the tunnel device and the LAN allowlist. Set true only if a NON-LAN client (e.g. a public reverse proxy on a different segment) must reach the WebUI; it permits app-server REPLY packets (--sport FLASK_PORT, conntrack REPLY) to leave off-tunnel. Server replies only, never client-initiated egress, so it cannot leak outbound browsing/downloads or the real IP for outbound requests, but it is still an off-tunnel path while the tunnel is down, hence opt-in. LAN WebUI clients never need it (covered by LAN_NETWORK).",
|
||||
"type": "boolean",
|
||||
"default": "false",
|
||||
},
|
||||
{
|
||||
"name": "WIREGUARD_STALE_AFTER",
|
||||
"description": "Seconds since the last WireGuard handshake before the healthcheck bounces the tunnel.",
|
||||
"type": "number",
|
||||
"default": "180",
|
||||
},
|
||||
]
|
||||
|
||||
lines = [
|
||||
"## Egress / VPN Routing",
|
||||
"",
|
||||
"These startup-only variables are consumed by `entrypoint.sh` / `wireguard.sh` to select and configure the WireGuard transparent-egress kill-switch. `USING_WIREGUARD` and [`USING_TOR`](#using_tor) (documented under Network) are mutually exclusive; both require root startup.",
|
||||
"",
|
||||
"| Variable | Description | Type | Default |",
|
||||
"|----------|-------------|------|---------|",
|
||||
]
|
||||
|
||||
lines.extend(
|
||||
f"| `{var['name']}` | {var['description']} | {var['type']} | `{var['default']}` |"
|
||||
for var in egress_vars
|
||||
)
|
||||
|
||||
lines.append("")
|
||||
lines.append("<details>")
|
||||
lines.append("<summary>Detailed descriptions</summary>")
|
||||
lines.append("")
|
||||
|
||||
for var in egress_vars:
|
||||
lines.append(f"#### `{var['name']}`")
|
||||
lines.append("")
|
||||
lines.append(var["description"])
|
||||
lines.append("")
|
||||
lines.append(f"- **Type:** {var['type']}")
|
||||
lines.append(f"- **Default:** `{var['default']}`")
|
||||
lines.append("")
|
||||
|
||||
lines.append("</details>")
|
||||
lines.append("")
|
||||
|
||||
return lines
|
||||
|
||||
|
||||
def generate_env_docs() -> str:
|
||||
"""Generate markdown documentation for all environment variables."""
|
||||
# Import settings modules to ensure all settings are registered
|
||||
@@ -282,6 +389,7 @@ def generate_env_docs() -> str:
|
||||
# Generate TOC
|
||||
toc_entries = [
|
||||
"- [Bootstrap Configuration](#bootstrap-configuration)",
|
||||
"- [Egress / VPN Routing](#egress--vpn-routing)",
|
||||
]
|
||||
|
||||
# Ungrouped tabs first
|
||||
@@ -307,6 +415,9 @@ def generate_env_docs() -> str:
|
||||
# Add bootstrap environment variables documentation
|
||||
lines.extend(_generate_bootstrap_env_docs())
|
||||
|
||||
# Add egress / VPN routing (startup-only, shell-driven) documentation
|
||||
lines.extend(_generate_egress_env_docs())
|
||||
|
||||
# Generate documentation for ungrouped tabs
|
||||
for tab in grouped_tabs.get(None, []):
|
||||
lines.extend(_generate_tab_docs(tab))
|
||||
|
||||
@@ -0,0 +1,52 @@
|
||||
"""Challenge-page detection shared by the bypassers and the HTTP retry path.
|
||||
|
||||
Kept out of `internal_bypasser` so the HTTP layer can recognise an interstitial
|
||||
without importing SeleniumBase: that module is imported lazily precisely because its
|
||||
browser dependencies are optional, and external-bypasser setups run without them.
|
||||
"""
|
||||
|
||||
# Matched against lowercased text, so every entry must be lowercase.
|
||||
CLOUDFLARE_INDICATORS = [
|
||||
"just a moment",
|
||||
"verify you are human",
|
||||
"verifying you are human",
|
||||
"cloudflare.com/products/turnstile",
|
||||
]
|
||||
|
||||
DDOS_GUARD_INDICATORS = [
|
||||
"ddos-guard",
|
||||
"ddos guard",
|
||||
"checking your browser before accessing",
|
||||
"complete the manual check to continue",
|
||||
"could not verify your browser automatically",
|
||||
]
|
||||
|
||||
# Markers that exist only in raw markup: the bypassers scan rendered innerText, where
|
||||
# a script src or a <title> never appears. The title match is scoped to the tag on
|
||||
# purpose - hosts word the rest of that sentence differently, and matching "checking
|
||||
# your browser" as free text would trip on any page that merely discusses a challenge.
|
||||
_RAW_HTML_MARKERS = (
|
||||
"<title>checking your browser",
|
||||
"/cdn-cgi/challenge-platform",
|
||||
"/.well-known/ddos-guard/",
|
||||
)
|
||||
|
||||
# An interstitial is a few KB of markup. Past that it is a real page that happens to
|
||||
# mention a marker - a protected site links its own DDoS-Guard endpoints on every page.
|
||||
MAX_CHALLENGE_HTML_CHARS = 64 * 1024
|
||||
|
||||
|
||||
def challenge_marker(html: str) -> str | None:
|
||||
"""Return the marker proving `html` is an unsolved challenge page, or None.
|
||||
|
||||
Only meaningful for a response that already carries a challenge status: the
|
||||
markers appear on protected sites' real pages too, so the status is what
|
||||
separates "blocked" from "served".
|
||||
"""
|
||||
if not html or len(html) > MAX_CHALLENGE_HTML_CHARS:
|
||||
return None
|
||||
lowered = html.lower()
|
||||
for marker in (*_RAW_HTML_MARKERS, *DDOS_GUARD_INDICATORS, *CLOUDFLARE_INDICATORS):
|
||||
if marker in lowered:
|
||||
return marker
|
||||
return None
|
||||
@@ -0,0 +1,260 @@
|
||||
"""Clearance cookies won by a bypass, shared by every bypasser implementation.
|
||||
|
||||
Kept in its own module rather than inside a bypasser because both of them feed it and
|
||||
both read from it. The internal bypasser cannot host it: it imports seleniumbase at
|
||||
module scope, which is exactly the dependency an external-bypasser deployment is
|
||||
entitled not to have installed.
|
||||
"""
|
||||
|
||||
import threading
|
||||
import time
|
||||
from collections.abc import Mapping
|
||||
from typing import Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from shelfmark.core.logger import setup_logger
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# Cookie storage - shared with requests library for Cloudflare bypass
|
||||
# Nested mapping of domain to cookie name to cookie metadata.
|
||||
_cf_cookies: dict[str, dict] = {}
|
||||
_cf_cookies_lock = threading.Lock()
|
||||
|
||||
# User-Agent storage - Cloudflare ties cf_clearance to the UA that solved the challenge
|
||||
_cf_user_agents: dict[str, str] = {}
|
||||
|
||||
# Protection cookie names we care about (Cloudflare and DDoS-Guard)
|
||||
CF_COOKIE_NAMES = {"cf_clearance", "__cf_bm", "cf_chl_2", "cf_chl_prog"}
|
||||
DDG_COOKIE_NAMES = {
|
||||
"__ddg1_",
|
||||
"__ddg2_",
|
||||
"__ddg5_",
|
||||
"__ddg8_",
|
||||
"__ddg9_",
|
||||
"__ddg10_",
|
||||
"__ddgid_",
|
||||
"__ddgmark_",
|
||||
"ddg_last_challenge",
|
||||
}
|
||||
|
||||
# DDoS-Guard cookies that describe *one* check rather than granting clearance, and so
|
||||
# must never be replayed on a later request. Observed live on Anna's Archive:
|
||||
#
|
||||
# __ddg9_ the client IP address
|
||||
# __ddg10_ the unix timestamp the check was issued
|
||||
# __ddg8_ an opaque token issued with them, same ~40 minute expiry
|
||||
#
|
||||
# Clearance itself lives in __ddg1_/__ddg2_/__ddgid_ (roughly a year) and __ddg5_.
|
||||
# Replaying the trio is actively harmful: once the timestamp ages out - or the egress
|
||||
# IP changes, which happens routinely behind a VPN - the values no longer describe the
|
||||
# caller, DDoS-Guard re-arms its check and answers every request with a ?check=1
|
||||
# redirect. That is the redirect loop, and it is self-inflicted. Dropping them simply
|
||||
# lets DDoS-Guard issue a fresh set, exactly as it does for a browser.
|
||||
DDG_EPHEMERAL_COOKIE_NAMES = {
|
||||
"__ddg8_",
|
||||
"__ddg9_",
|
||||
"__ddg10_",
|
||||
"ddg_last_challenge",
|
||||
}
|
||||
|
||||
|
||||
def _get_base_domain(domain: str) -> str:
|
||||
"""Extract base domain from hostname (e.g., 'www.example.com' -> 'example.com')."""
|
||||
return ".".join(domain.split(".")[-2:]) if "." in domain else domain
|
||||
|
||||
|
||||
def _get_full_cookie_domains() -> set[str]:
|
||||
"""Return mirror domains that need full-session cookie extraction."""
|
||||
from shelfmark.core.mirrors import get_zlib_cookie_domains
|
||||
|
||||
return {_get_base_domain(domain) for domain in get_zlib_cookie_domains()}
|
||||
|
||||
|
||||
def _should_extract_cookie(name: str, *, extract_all: bool) -> bool:
|
||||
"""Determine if a cookie should be extracted based on its name."""
|
||||
# Checked before extract_all: a per-check token is wrong to replay for every
|
||||
# domain, including the full-session ones.
|
||||
if name in DDG_EPHEMERAL_COOKIE_NAMES:
|
||||
return False
|
||||
if extract_all:
|
||||
return True
|
||||
is_cf = name in CF_COOKIE_NAMES or name.startswith("cf_")
|
||||
is_ddg = name in DDG_COOKIE_NAMES or name.startswith("__ddg")
|
||||
return is_cf or is_ddg
|
||||
|
||||
|
||||
def _cookie_field(cookie: Any, name: str) -> Any:
|
||||
"""Read one field from a cookie in either shape we are handed.
|
||||
|
||||
The internal bypasser extracts CDP cookie objects; an external bypasser returns
|
||||
the same fields as JSON objects, so the difference is attribute versus key access.
|
||||
"""
|
||||
if isinstance(cookie, Mapping):
|
||||
return cookie.get(name)
|
||||
return getattr(cookie, name, None)
|
||||
|
||||
|
||||
def _cookie_expiry(cookie: Any) -> float | None:
|
||||
"""A cookie's absolute expiry, or None when it is a session cookie.
|
||||
|
||||
The two spellings are not interchangeable and both reach this store. CDP and
|
||||
Playwright cookies carry `expires`; the WebDriver cookie object - what a
|
||||
Selenium-based solver such as FlareSolverr returns - carries `expiry`. Reading
|
||||
only one silently turns every cookie from the other into a never-expiring one,
|
||||
which is exactly how dead clearance ends up replayed forever (see
|
||||
get_cf_cookies_for_domain).
|
||||
|
||||
The value is coerced rather than trusted: it arrives as JSON from a service we
|
||||
do not control, and a string here used to raise straight out of the store.
|
||||
"""
|
||||
for field in ("expires", "expiry"):
|
||||
raw = _cookie_field(cookie, field)
|
||||
if raw is None:
|
||||
continue
|
||||
try:
|
||||
expiry = float(raw)
|
||||
except TypeError, ValueError:
|
||||
logger.debug("Unreadable cookie expiry %r; treating as a session cookie", raw)
|
||||
return None
|
||||
# <= 0 is how both shapes spell "session cookie", not "expired in 1970".
|
||||
return expiry if expiry > 0 else None
|
||||
return None
|
||||
|
||||
|
||||
def store_extracted_cookies(
|
||||
*,
|
||||
url: str,
|
||||
cookies: list[Any],
|
||||
user_agent: str | None = None,
|
||||
) -> None:
|
||||
"""Store filtered bypass cookies (and optional UA) for a URL domain."""
|
||||
parsed = urlparse(url)
|
||||
domain = parsed.hostname or ""
|
||||
if not domain:
|
||||
return
|
||||
|
||||
base_domain = _get_base_domain(domain)
|
||||
extract_all = base_domain in _get_full_cookie_domains()
|
||||
|
||||
cookies_found: dict[str, dict[str, Any]] = {}
|
||||
for cookie in cookies:
|
||||
name = _cookie_field(cookie, "name") or ""
|
||||
if not _should_extract_cookie(name, extract_all=extract_all):
|
||||
continue
|
||||
secure = _cookie_field(cookie, "secure")
|
||||
cookies_found[name] = {
|
||||
"value": _cookie_field(cookie, "value") or "",
|
||||
"domain": _cookie_field(cookie, "domain") or domain,
|
||||
"path": _cookie_field(cookie, "path") or "/",
|
||||
"expiry": _cookie_expiry(cookie),
|
||||
"secure": True if secure is None else bool(secure),
|
||||
"httpOnly": True,
|
||||
}
|
||||
|
||||
if not cookies_found:
|
||||
return
|
||||
|
||||
with _cf_cookies_lock:
|
||||
_cf_cookies[base_domain] = cookies_found
|
||||
if user_agent:
|
||||
_cf_user_agents[base_domain] = user_agent
|
||||
logger.debug("Stored UA for %s: %s...", base_domain, str(user_agent)[:60])
|
||||
else:
|
||||
logger.debug("No UA captured for %s", base_domain)
|
||||
|
||||
cookie_type = "all" if extract_all else "protection"
|
||||
logger.debug("Extracted %s %s cookies for %s", len(cookies_found), cookie_type, base_domain)
|
||||
|
||||
|
||||
def _is_cookie_expired(cookie: dict[str, Any]) -> bool:
|
||||
"""Whether a stored cookie's expiry has passed. Session cookies never expire here."""
|
||||
expiry = cookie.get("expiry")
|
||||
if expiry is None:
|
||||
expiry = cookie.get("expires")
|
||||
if not expiry or expiry <= 0:
|
||||
return False
|
||||
return time.time() > expiry
|
||||
|
||||
|
||||
def get_cf_cookies_for_domain(domain: str) -> dict[str, str]:
|
||||
"""Get stored cookies for a domain. Returns empty dict if none available."""
|
||||
if not domain:
|
||||
return {}
|
||||
|
||||
base_domain = _get_base_domain(domain)
|
||||
|
||||
with _cf_cookies_lock:
|
||||
cookies = _cf_cookies.get(base_domain, {})
|
||||
if not cookies:
|
||||
return {}
|
||||
|
||||
cf_clearance = cookies.get("cf_clearance", {})
|
||||
if cf_clearance and _is_cookie_expired(cf_clearance):
|
||||
logger.debug("CF cookies expired for %s", base_domain)
|
||||
_cf_cookies.pop(base_domain, None)
|
||||
return {}
|
||||
|
||||
# Expiry applies to every cookie, not just Cloudflare's. DDoS-Guard domains
|
||||
# have no cf_clearance, so the check above never fired for them and dead
|
||||
# cookies were replayed indefinitely - the server answers those with a
|
||||
# challenge, which is indistinguishable from having sent nothing at all.
|
||||
live = {name: c for name, c in cookies.items() if not _is_cookie_expired(c)}
|
||||
if len(live) != len(cookies):
|
||||
expired = sorted(set(cookies) - set(live))
|
||||
logger.debug("Dropping expired cookies for %s: %s", base_domain, expired)
|
||||
if live:
|
||||
_cf_cookies[base_domain] = live
|
||||
else:
|
||||
_cf_cookies.pop(base_domain, None)
|
||||
|
||||
return {name: c["value"] for name, c in live.items()}
|
||||
|
||||
|
||||
def has_valid_cf_cookies(domain: str) -> bool:
|
||||
"""Check if we have valid Cloudflare cookies for a domain."""
|
||||
return bool(get_cf_cookies_for_domain(domain))
|
||||
|
||||
|
||||
def get_cf_user_agent_for_domain(domain: str) -> str | None:
|
||||
"""Get the User-Agent that was used during bypass for a domain."""
|
||||
if not domain:
|
||||
return None
|
||||
with _cf_cookies_lock:
|
||||
return _cf_user_agents.get(_get_base_domain(domain))
|
||||
|
||||
|
||||
def export_store() -> tuple[dict[str, dict], dict[str, str]]:
|
||||
"""Snapshot the whole store, for handing to another process.
|
||||
|
||||
The internal bypasser's Docker helper solves in a subprocess, so the clearance it
|
||||
wins has to be serialized back to the parent or the solve is lost with the child.
|
||||
"""
|
||||
with _cf_cookies_lock:
|
||||
return (
|
||||
{domain: dict(cookies) for domain, cookies in _cf_cookies.items()},
|
||||
dict(_cf_user_agents),
|
||||
)
|
||||
|
||||
|
||||
def import_store(cookies: object, user_agents: object) -> None:
|
||||
"""Merge a snapshot produced by :func:`export_store` into this process's store."""
|
||||
with _cf_cookies_lock:
|
||||
if isinstance(cookies, dict):
|
||||
_cf_cookies.update(cookies)
|
||||
if isinstance(user_agents, dict):
|
||||
_cf_user_agents.update(
|
||||
{str(domain): str(agent) for domain, agent in user_agents.items()}
|
||||
)
|
||||
|
||||
|
||||
def clear_cf_cookies(domain: str | None = None) -> None:
|
||||
"""Clear stored Cloudflare cookies and User-Agent. If domain is None, clear all."""
|
||||
with _cf_cookies_lock:
|
||||
if domain:
|
||||
base_domain = _get_base_domain(domain)
|
||||
_cf_cookies.pop(base_domain, None)
|
||||
_cf_user_agents.pop(base_domain, None)
|
||||
else:
|
||||
_cf_cookies.clear()
|
||||
_cf_user_agents.clear()
|
||||
@@ -2,17 +2,19 @@
|
||||
|
||||
import random
|
||||
import time
|
||||
from typing import TYPE_CHECKING
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
import requests
|
||||
|
||||
from shelfmark.bypass import BypassCancelledError
|
||||
from shelfmark.bypass.cookie_store import store_extracted_cookies
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.utils import normalize_http_url
|
||||
from shelfmark.download.network import get_ssl_verify
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Mapping
|
||||
from threading import Event
|
||||
|
||||
from shelfmark.download import network
|
||||
@@ -47,6 +49,47 @@ def _coerce_timeout_ms(value: object, default: int) -> int:
|
||||
return default
|
||||
|
||||
|
||||
def max_duration_seconds() -> float:
|
||||
"""Upper bound on how long get_bypassed_page() can take for one URL.
|
||||
|
||||
MAX_RETRY attempts at the configured read timeout, plus the exponential backoff waited
|
||||
between them (jitter is < 1s per gap, counted as a full second to stay conservative).
|
||||
Callers use this to declare a stall-detection grace; see shelfmark.download.activity.
|
||||
"""
|
||||
bypasser_timeout = _coerce_timeout_ms(config.get("EXT_BYPASSER_TIMEOUT", 60000), 60000)
|
||||
read_timeout = min((bypasser_timeout / 1000) + READ_TIMEOUT_BUFFER, MAX_READ_TIMEOUT)
|
||||
backoff_total = sum(
|
||||
min(BACKOFF_CAP, BACKOFF_BASE * (2 ** (attempt - 1))) + 1.0
|
||||
for attempt in range(1, MAX_RETRY)
|
||||
)
|
||||
return MAX_RETRY * read_timeout + backoff_total
|
||||
|
||||
|
||||
def _store_solution_clearance(target_url: str, solution: Mapping[str, Any]) -> None:
|
||||
"""Keep the clearance the solver won, so later requests do not re-solve.
|
||||
|
||||
A solve is the expensive part of an external bypass - tens of seconds of real
|
||||
browser - and FlareSolverr-compatible services hand back the cookies and the
|
||||
User-Agent that earned it. Dropping them meant every single request paid a 403
|
||||
plus a full solve, and a file download (which the solver cannot proxy, being
|
||||
binary) never presented clearance at all.
|
||||
|
||||
The UA matters as much as the cookies: Cloudflare ties cf_clearance to the UA
|
||||
that solved the challenge, so replaying the cookie under our own UA is rejected.
|
||||
"""
|
||||
cookies = solution.get("cookies") or []
|
||||
if not isinstance(cookies, list):
|
||||
logger.debug("External bypasser returned no usable cookie list for '%s'", target_url)
|
||||
return
|
||||
|
||||
user_agent = solution.get("userAgent")
|
||||
store_extracted_cookies(
|
||||
url=target_url,
|
||||
cookies=cookies,
|
||||
user_agent=user_agent if isinstance(user_agent, str) else None,
|
||||
)
|
||||
|
||||
|
||||
def _fetch_via_bypasser(target_url: str) -> str | None:
|
||||
"""Make a single request to the external bypasser service. Returns HTML or None."""
|
||||
raw_bypasser_url = _coerce_config_str(
|
||||
@@ -100,6 +143,15 @@ def _fetch_via_bypasser(target_url: str) -> str | None:
|
||||
logger.warning("External bypasser returned empty response for '%s'", target_url)
|
||||
return None
|
||||
|
||||
try:
|
||||
_store_solution_clearance(target_url, solution)
|
||||
except AttributeError, KeyError, TypeError, ValueError:
|
||||
# Storing clearance is an optimisation; the page is the product. The
|
||||
# solution JSON comes from a service we do not control, so a surprise in
|
||||
# its cookie shape must not discard HTML that already cost a ~30s solve
|
||||
# and send the caller round for up to MAX_RETRY more of them.
|
||||
logger.debug("Could not store bypass clearance for '%s'", target_url, exc_info=True)
|
||||
|
||||
except requests.exceptions.Timeout:
|
||||
logger.warning(
|
||||
"External bypasser timed out for '%s' (connect: %ss, read: %.0fs)",
|
||||
|
||||
@@ -5,7 +5,6 @@ import asyncio
|
||||
import json
|
||||
import os
|
||||
import random
|
||||
import shutil
|
||||
import signal
|
||||
import socket
|
||||
import stat
|
||||
@@ -28,6 +27,15 @@ from seleniumbase import cdp_driver
|
||||
from seleniumbase.undetected.cdp_driver.connection import ProtocolException
|
||||
|
||||
from shelfmark.bypass import BypassCancelledError
|
||||
from shelfmark.bypass.challenge import CLOUDFLARE_INDICATORS, DDOS_GUARD_INDICATORS
|
||||
from shelfmark.bypass.cookie_store import (
|
||||
clear_cf_cookies,
|
||||
export_store,
|
||||
get_cf_cookies_for_domain,
|
||||
get_cf_user_agent_for_domain,
|
||||
import_store,
|
||||
store_extracted_cookies,
|
||||
)
|
||||
from shelfmark.bypass.fingerprint import get_screen_size
|
||||
from shelfmark.config import env
|
||||
from shelfmark.config.env import LOG_DIR
|
||||
@@ -50,23 +58,31 @@ _LOADING_BODY_LENGTH_MAX = 50
|
||||
_PAGE_BODY_PREVIEW_CHARS = 500
|
||||
_BROWSER_START_TIMEOUT_SECONDS = 45.0
|
||||
_BYPASS_SUBPROCESS_TIMEOUT_SECONDS = 420.0
|
||||
# How long a cancelled bypass may take to close its browser before the calling thread
|
||||
# stops waiting for it. Counted on top of the bypass deadline, so every budget below is
|
||||
# set to leave room for it.
|
||||
_CDP_UNWIND_GRACE_SECONDS = 15.0
|
||||
# Same wall-clock budget as the Docker helper process, applied to the in-process CDP path
|
||||
# so both branches of get() are bounded the same way: the deadline plus the unwind grace
|
||||
# comes to _BYPASS_SUBPROCESS_TIMEOUT_SECONDS either way.
|
||||
_IN_PROCESS_BYPASS_TIMEOUT_SECONDS = _BYPASS_SUBPROCESS_TIMEOUT_SECONDS - _CDP_UNWIND_GRACE_SECONDS
|
||||
_BYPASS_CHILD_ENV = "SHELFMARK_INTERNAL_BYPASSER_CHILD"
|
||||
|
||||
# Challenge detection indicators
|
||||
CLOUDFLARE_INDICATORS = [
|
||||
"just a moment",
|
||||
"verify you are human",
|
||||
"verifying you are human",
|
||||
"cloudflare.com/products/turnstile",
|
||||
]
|
||||
|
||||
DDOS_GUARD_INDICATORS = [
|
||||
"ddos-guard",
|
||||
"ddos guard",
|
||||
"checking your browser before accessing",
|
||||
"complete the manual check to continue",
|
||||
"could not verify your browser automatically",
|
||||
]
|
||||
# The helper bounds each bypass below the parent's deadline, so it is the side that gives
|
||||
# up first: it still gets to report the timeout and close its browser, and stays available
|
||||
# for the next request. A parent that hit its deadline first could only kill the helper,
|
||||
# throwing away a process the next request would have to start again. The 30s covers the
|
||||
# unwind grace as well, so a helper that times out and closes its browser as slowly as it
|
||||
# is allowed to still answers with 15s to spare.
|
||||
_CHILD_BYPASS_TIMEOUT_SECONDS = _BYPASS_SUBPROCESS_TIMEOUT_SECONDS - 30.0
|
||||
# The helper publishes its answer by writing the result file the request named, so the
|
||||
# parent waits by watching for that file rather than by reading a stream it would have to
|
||||
# demultiplex from the helper's log output.
|
||||
_HELPER_RESULT_POLL_SECONDS = 0.05
|
||||
# Closing the helper's stdin asks it to shut down; this is how long it may take to finish
|
||||
# what it is doing and exit before its session is killed instead.
|
||||
_HELPER_SHUTDOWN_GRACE_SECONDS = 15.0
|
||||
_HELPER_IDLE_TIMEOUT_DEFAULT = 180.0
|
||||
_PARENT_WATCHDOG_INTERVAL_SECONDS = 5.0
|
||||
|
||||
|
||||
class _DisplayState(TypedDict):
|
||||
@@ -87,8 +103,8 @@ DISPLAY: _DisplayState = {
|
||||
"ffmpeg_output": None,
|
||||
}
|
||||
LOCKED = threading.Lock()
|
||||
_PGREP_PATH = shutil.which("pgrep")
|
||||
_PKILL_PATH = shutil.which("pkill")
|
||||
_PROC_ROOT = Path("/proc")
|
||||
_BROWSER_PROCESS_PATTERNS = ("chrome", "chromium", "Xvfb", "ffmpeg")
|
||||
_RNG = random.SystemRandom()
|
||||
|
||||
_CDP_OPERATION_ERRORS = (
|
||||
@@ -211,107 +227,42 @@ class _CdpWorker:
|
||||
msg = "CDP worker loop failed to start"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
@staticmethod
|
||||
async def _bounded(coro: Any, timeout: float | None) -> Any:
|
||||
"""Run the coroutine under its deadline, on the loop that owns it.
|
||||
|
||||
The deadline has to be enforced from inside the loop rather than by the calling
|
||||
thread: asyncio.wait_for() cancels the bypass and then *waits for it to unwind*,
|
||||
so `finally: await _close_cdp_driver(driver)` has finished by the time this
|
||||
raises. Cancelling from outside returns the moment the cancellation is scheduled,
|
||||
which in a helper serving many requests let the abandoned bypass close its browser
|
||||
while the next one was already opening its own - on the same loop, sharing the
|
||||
DISPLAY globals and one process group.
|
||||
"""
|
||||
if timeout is None:
|
||||
return await coro
|
||||
return await asyncio.wait_for(coro, timeout)
|
||||
|
||||
def run(self, coro: Any, timeout: float | None = None) -> Any:
|
||||
self.start()
|
||||
if not self._loop or self._loop.is_closed():
|
||||
msg = "CDP worker loop not available"
|
||||
raise RuntimeError(msg)
|
||||
future = asyncio.run_coroutine_threadsafe(coro, self._loop)
|
||||
return future.result(timeout=timeout)
|
||||
future = asyncio.run_coroutine_threadsafe(self._bounded(coro, timeout), self._loop)
|
||||
# Backstop for an unwind that wedges too: _close_cdp_driver awaits websockets that
|
||||
# a dead browser may never answer, and _bounded cannot outlive its own cleanup.
|
||||
wait_for = None if timeout is None else timeout + _CDP_UNWIND_GRACE_SECONDS
|
||||
try:
|
||||
return future.result(timeout=wait_for)
|
||||
except TimeoutError:
|
||||
# Otherwise the coroutine keeps running in the worker loop after we stop
|
||||
# waiting, holding the browser and racing the next bypass.
|
||||
future.cancel()
|
||||
raise
|
||||
|
||||
|
||||
_CDP_WORKER = _CdpWorker()
|
||||
|
||||
# Cookie storage - shared with requests library for Cloudflare bypass
|
||||
# Nested mapping of domain to cookie name to cookie metadata.
|
||||
_cf_cookies: dict[str, dict] = {}
|
||||
_cf_cookies_lock = threading.Lock()
|
||||
|
||||
# User-Agent storage - Cloudflare ties cf_clearance to the UA that solved the challenge
|
||||
_cf_user_agents: dict[str, str] = {}
|
||||
|
||||
# Protection cookie names we care about (Cloudflare and DDoS-Guard)
|
||||
CF_COOKIE_NAMES = {"cf_clearance", "__cf_bm", "cf_chl_2", "cf_chl_prog"}
|
||||
DDG_COOKIE_NAMES = {
|
||||
"__ddg1_",
|
||||
"__ddg2_",
|
||||
"__ddg5_",
|
||||
"__ddg8_",
|
||||
"__ddg9_",
|
||||
"__ddg10_",
|
||||
"__ddgid_",
|
||||
"__ddgmark_",
|
||||
"ddg_last_challenge",
|
||||
}
|
||||
|
||||
|
||||
def _get_base_domain(domain: str) -> str:
|
||||
"""Extract base domain from hostname (e.g., 'www.example.com' -> 'example.com')."""
|
||||
return ".".join(domain.split(".")[-2:]) if "." in domain else domain
|
||||
|
||||
|
||||
def _get_full_cookie_domains() -> set[str]:
|
||||
"""Return mirror domains that need full-session cookie extraction."""
|
||||
from shelfmark.core.mirrors import get_zlib_cookie_domains
|
||||
|
||||
return {_get_base_domain(domain) for domain in get_zlib_cookie_domains()}
|
||||
|
||||
|
||||
def _should_extract_cookie(name: str, *, extract_all: bool) -> bool:
|
||||
"""Determine if a cookie should be extracted based on its name."""
|
||||
if extract_all:
|
||||
return True
|
||||
is_cf = name in CF_COOKIE_NAMES or name.startswith("cf_")
|
||||
is_ddg = name in DDG_COOKIE_NAMES or name.startswith("__ddg")
|
||||
return is_cf or is_ddg
|
||||
|
||||
|
||||
def _store_extracted_cookies(
|
||||
*,
|
||||
url: str,
|
||||
cookies: list[Any],
|
||||
user_agent: str | None = None,
|
||||
) -> None:
|
||||
"""Store filtered bypass cookies (and optional UA) for a URL domain."""
|
||||
parsed = urlparse(url)
|
||||
domain = parsed.hostname or ""
|
||||
if not domain:
|
||||
return
|
||||
|
||||
base_domain = _get_base_domain(domain)
|
||||
extract_all = base_domain in _get_full_cookie_domains()
|
||||
|
||||
cookies_found: dict[str, dict[str, Any]] = {}
|
||||
for cookie in cookies:
|
||||
name = getattr(cookie, "name", "") or ""
|
||||
if not _should_extract_cookie(name, extract_all=extract_all):
|
||||
continue
|
||||
expires = getattr(cookie, "expires", None)
|
||||
if expires is not None and expires <= 0:
|
||||
expires = None
|
||||
cookies_found[name] = {
|
||||
"value": getattr(cookie, "value", ""),
|
||||
"domain": getattr(cookie, "domain", None) or domain,
|
||||
"path": getattr(cookie, "path", None) or "/",
|
||||
"expiry": expires,
|
||||
"secure": bool(getattr(cookie, "secure", True)),
|
||||
"httpOnly": True,
|
||||
}
|
||||
|
||||
if not cookies_found:
|
||||
return
|
||||
|
||||
with _cf_cookies_lock:
|
||||
_cf_cookies[base_domain] = cookies_found
|
||||
if user_agent:
|
||||
_cf_user_agents[base_domain] = user_agent
|
||||
logger.debug("Stored UA for %s: %s...", base_domain, str(user_agent)[:60])
|
||||
else:
|
||||
logger.debug("No UA captured for %s", base_domain)
|
||||
|
||||
cookie_type = "all" if extract_all else "protection"
|
||||
logger.debug("Extracted %s %s cookies for %s", len(cookies_found), cookie_type, base_domain)
|
||||
|
||||
|
||||
async def _extract_cookies_from_cdp(driver: Any, page: Any, url: str) -> None:
|
||||
"""Extract cookies from a CDP browser after successful bypass."""
|
||||
@@ -327,117 +278,116 @@ async def _extract_cookies_from_cdp(driver: Any, page: Any, url: str) -> None:
|
||||
except _CDP_OPERATION_ERRORS:
|
||||
user_agent = None
|
||||
|
||||
_store_extracted_cookies(url=url, cookies=all_cookies, user_agent=user_agent)
|
||||
store_extracted_cookies(url=url, cookies=all_cookies, user_agent=user_agent)
|
||||
|
||||
except _CDP_OPERATION_ERRORS as e:
|
||||
logger.debug("Failed to extract cookies: %s", e)
|
||||
|
||||
|
||||
def get_cf_cookies_for_domain(domain: str) -> dict[str, str]:
|
||||
"""Get stored cookies for a domain. Returns empty dict if none available."""
|
||||
if not domain:
|
||||
return {}
|
||||
|
||||
base_domain = _get_base_domain(domain)
|
||||
|
||||
with _cf_cookies_lock:
|
||||
cookies = _cf_cookies.get(base_domain, {})
|
||||
if not cookies:
|
||||
return {}
|
||||
|
||||
cf_clearance = cookies.get("cf_clearance", {})
|
||||
if cf_clearance:
|
||||
expiry = cf_clearance.get("expiry")
|
||||
if expiry is None:
|
||||
expiry = cf_clearance.get("expires")
|
||||
if expiry and expiry > 0 and time.time() > expiry:
|
||||
logger.debug("CF cookies expired for %s", base_domain)
|
||||
_cf_cookies.pop(base_domain, None)
|
||||
return {}
|
||||
|
||||
return {name: c["value"] for name, c in cookies.items()}
|
||||
def _read_process_cmdline(proc_dir: Path) -> str:
|
||||
"""Return a process's full command line, or "" when it cannot be read."""
|
||||
try:
|
||||
raw = (proc_dir / "cmdline").read_bytes()
|
||||
except OSError:
|
||||
return ""
|
||||
return raw.replace(b"\x00", b" ").decode("utf-8", "replace").strip()
|
||||
|
||||
|
||||
def has_valid_cf_cookies(domain: str) -> bool:
|
||||
"""Check if we have valid Cloudflare cookies for a domain."""
|
||||
return bool(get_cf_cookies_for_domain(domain))
|
||||
|
||||
|
||||
def get_cf_user_agent_for_domain(domain: str) -> str | None:
|
||||
"""Get the User-Agent that was used during bypass for a domain."""
|
||||
if not domain:
|
||||
def _read_process_pgid(proc_dir: Path) -> int | None:
|
||||
"""Return a process's group id from /proc/<pid>/stat, or None when unreadable."""
|
||||
try:
|
||||
stat_line = (proc_dir / "stat").read_text(encoding="utf-8", errors="replace")
|
||||
except OSError:
|
||||
return None
|
||||
# Field 2 (comm) is parenthesised and may itself contain spaces and parens, so the
|
||||
# fields are only unambiguous after the last ')': state, ppid, pgrp, ...
|
||||
fields = stat_line.rpartition(")")[2].split()
|
||||
pgrp_index = 2
|
||||
if len(fields) <= pgrp_index:
|
||||
return None
|
||||
try:
|
||||
return int(fields[pgrp_index])
|
||||
except ValueError:
|
||||
return None
|
||||
with _cf_cookies_lock:
|
||||
return _cf_user_agents.get(_get_base_domain(domain))
|
||||
|
||||
|
||||
def clear_cf_cookies(domain: str | None = None) -> None:
|
||||
"""Clear stored Cloudflare cookies and User-Agent. If domain is None, clear all."""
|
||||
with _cf_cookies_lock:
|
||||
if domain:
|
||||
base_domain = _get_base_domain(domain)
|
||||
_cf_cookies.pop(base_domain, None)
|
||||
_cf_user_agents.pop(base_domain, None)
|
||||
else:
|
||||
_cf_cookies.clear()
|
||||
_cf_user_agents.clear()
|
||||
def _find_browser_processes() -> list[tuple[int, int, str]]:
|
||||
"""Return (pid, pgid, cmdline) for every browser-ish process visible in /proc."""
|
||||
found: list[tuple[int, int, str]] = []
|
||||
try:
|
||||
entries = list(_PROC_ROOT.iterdir())
|
||||
except OSError as e:
|
||||
logger.debug("Could not list %s: %s", _PROC_ROOT, e)
|
||||
return found
|
||||
|
||||
for entry in entries:
|
||||
if not entry.name.isdigit():
|
||||
continue
|
||||
cmdline = _read_process_cmdline(entry)
|
||||
if not cmdline or not any(name in cmdline for name in _BROWSER_PROCESS_PATTERNS):
|
||||
continue
|
||||
pgid = _read_process_pgid(entry)
|
||||
if pgid is None:
|
||||
continue
|
||||
found.append((int(entry.name), pgid, cmdline))
|
||||
return found
|
||||
|
||||
|
||||
def _kill_process(pid: int, cmdline: str) -> bool:
|
||||
"""SIGKILL one process, reporting whether it was actually signalled."""
|
||||
try:
|
||||
os.kill(pid, signal.SIGKILL)
|
||||
except ProcessLookupError:
|
||||
return False
|
||||
except OSError as e:
|
||||
logger.warning("Failed to kill pid %s: %s", pid, e)
|
||||
return False
|
||||
logger.debug("Killed leftover process %s: %s", pid, cmdline[:120])
|
||||
return True
|
||||
|
||||
|
||||
def _cleanup_orphan_processes() -> int:
|
||||
"""Kill orphan Chrome/Xvfb/ffmpeg processes. Only runs in Docker mode."""
|
||||
"""Kill leftover Chrome/Xvfb/ffmpeg processes. Only runs in Docker mode.
|
||||
|
||||
Scoped to this bypass session's process group plus groups whose leader has died.
|
||||
A container-wide sweep (the old `pkill -9 -f chrome`) also matched the browsers a
|
||||
concurrently running bypass was still driving, so with MAX_CONCURRENT_DOWNLOADS > 1
|
||||
every worker that started a solve killed the others' browsers (#1231).
|
||||
"""
|
||||
if not env.DOCKERMODE:
|
||||
return 0
|
||||
|
||||
_stop_ffmpeg_recording()
|
||||
|
||||
processes_to_kill = ["chrome", "chromium", "Xvfb", "ffmpeg"]
|
||||
total_killed = 0
|
||||
|
||||
logger.debug("Checking for orphan processes...")
|
||||
logger.debug("Checking for leftover browser processes...")
|
||||
logger.log_resource_usage()
|
||||
|
||||
if _PGREP_PATH is None or _PKILL_PATH is None:
|
||||
logger.warning("Skipping orphan-process cleanup because pgrep/pkill are unavailable")
|
||||
if not _PROC_ROOT.is_dir():
|
||||
logger.warning("Skipping browser-process cleanup because %s is unavailable", _PROC_ROOT)
|
||||
return 0
|
||||
|
||||
for proc_name in processes_to_kill:
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[_PGREP_PATH, "-f", proc_name],
|
||||
capture_output=True,
|
||||
check=False,
|
||||
text=True,
|
||||
timeout=5,
|
||||
)
|
||||
if result.returncode != 0 or not result.stdout.strip():
|
||||
continue
|
||||
own_pid = os.getpid()
|
||||
own_pgid = os.getpgrp()
|
||||
total_killed = 0
|
||||
|
||||
pids = result.stdout.strip().split("\n")
|
||||
count = len(pids)
|
||||
logger.info("Found %s orphan %s process(es), killing...", count, proc_name)
|
||||
|
||||
kill_result = subprocess.run(
|
||||
[_PKILL_PATH, "-9", "-f", proc_name],
|
||||
capture_output=True,
|
||||
check=False,
|
||||
timeout=5,
|
||||
)
|
||||
if kill_result.returncode == 0:
|
||||
total_killed += count
|
||||
else:
|
||||
logger.warning("pkill for %s returned %s", proc_name, kill_result.returncode)
|
||||
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.warning("Timeout while checking for %s processes", proc_name)
|
||||
except _SUBPROCESS_OPERATION_ERRORS as e:
|
||||
logger.debug("Error checking for %s processes: %s", proc_name, e)
|
||||
for pid, pgid, cmdline in _find_browser_processes():
|
||||
if pid == own_pid:
|
||||
continue
|
||||
# Another live process group means another bypass session: its browsers are in
|
||||
# use, not orphans. Only our own group and groups whose leader is gone (a helper
|
||||
# that died or was killed, leaving its browser behind) are ours to clean up.
|
||||
if pgid != own_pgid and (_PROC_ROOT / str(pgid)).exists():
|
||||
logger.debug("Leaving pid %s to its live bypass session (pgid %s)", pid, pgid)
|
||||
continue
|
||||
if _kill_process(pid, cmdline):
|
||||
total_killed += 1
|
||||
|
||||
if total_killed > 0:
|
||||
time.sleep(1)
|
||||
logger.info("Cleaned up %s orphan process(es)", total_killed)
|
||||
logger.info("Cleaned up %s leftover browser process(es)", total_killed)
|
||||
logger.log_resource_usage()
|
||||
else:
|
||||
logger.debug("No orphan processes found")
|
||||
logger.debug("No leftover browser processes found")
|
||||
|
||||
return total_killed
|
||||
|
||||
@@ -894,23 +844,25 @@ def _run_bypass_in_current_process(url: str, retry: int, cancel_flag: Event | No
|
||||
if driver:
|
||||
await _close_cdp_driver(driver)
|
||||
|
||||
if os.environ.get(_BYPASS_CHILD_ENV) == "1":
|
||||
return asyncio.run(_run_bypass())
|
||||
return _CDP_WORKER.run(_run_bypass())
|
||||
# Bound the wait: this holds the module-wide LOCKED for its whole duration, and neither
|
||||
# page.get() nor page.wait() has a timeout of its own. Without a deadline here a single
|
||||
# wedged CDP session blocks every subsequent bypass in the process forever.
|
||||
#
|
||||
# The helper goes through the worker too, rather than asyncio.run: that owns a loop for
|
||||
# one call and closes it on the way out, so a helper serving many requests would build
|
||||
# and tear down a loop per bypass and would carry no deadline of its own. The worker's
|
||||
# loop lives in a thread, outlives any single bypass, and cancels the coroutine when the
|
||||
# deadline passes.
|
||||
timeout = (
|
||||
_CHILD_BYPASS_TIMEOUT_SECONDS
|
||||
if os.environ.get(_BYPASS_CHILD_ENV) == "1"
|
||||
else _IN_PROCESS_BYPASS_TIMEOUT_SECONDS
|
||||
)
|
||||
return _CDP_WORKER.run(_run_bypass(), timeout=timeout)
|
||||
|
||||
|
||||
def _store_child_bypass_state(payload: dict[str, Any]) -> None:
|
||||
cookies = payload.get("cookies")
|
||||
if isinstance(cookies, dict):
|
||||
with _cf_cookies_lock:
|
||||
_cf_cookies.update(cookies)
|
||||
|
||||
user_agents = payload.get("user_agents")
|
||||
if isinstance(user_agents, dict):
|
||||
with _cf_cookies_lock:
|
||||
_cf_user_agents.update(
|
||||
{str(domain): str(agent) for domain, agent in user_agents.items()}
|
||||
)
|
||||
import_store(payload.get("cookies"), payload.get("user_agents"))
|
||||
|
||||
|
||||
def _prepare_child_browser_env(env_vars: dict[str, str]) -> dict[str, str]:
|
||||
@@ -933,39 +885,247 @@ def _prepare_child_browser_env(env_vars: dict[str, str]) -> dict[str, str]:
|
||||
return env_vars
|
||||
|
||||
|
||||
def _terminate_helper_session(proc: subprocess.Popen[str]) -> None:
|
||||
"""Kill the bypass helper and every process it spawned.
|
||||
|
||||
start_new_session makes the helper a session leader, so its pid doubles as the
|
||||
process-group id of the browser tree underneath it and one killpg reaches all of it.
|
||||
"""
|
||||
if hasattr(os, "killpg"):
|
||||
with suppress(OSError):
|
||||
os.killpg(proc.pid, signal.SIGKILL)
|
||||
with suppress(OSError):
|
||||
proc.kill()
|
||||
with suppress(OSError, subprocess.SubprocessError):
|
||||
proc.wait(timeout=5)
|
||||
|
||||
|
||||
def _part_path(result_path: Path) -> Path:
|
||||
"""Where the helper stages a result before renaming it into place."""
|
||||
return result_path.with_name(result_path.name + ".part")
|
||||
|
||||
|
||||
class _BypassHelper:
|
||||
"""The helper subprocess that runs the bypasses, kept alive across them.
|
||||
|
||||
Spawning it costs about 4.5 seconds of interpreter start and imports before any work
|
||||
begins, paid on every protected request - and a single search issues several. What it
|
||||
keeps is the process, not the browser: each bypass still starts and closes its own
|
||||
Chrome, so nothing accumulates between requests.
|
||||
|
||||
Protocol: one JSON request per line on stdin, answered by writing the result file that
|
||||
request named. stdout and stderr stay attached to the parent's, so helper logs keep
|
||||
showing up in `docker logs` as before.
|
||||
|
||||
Only one request is ever in flight - get() serializes every bypass behind LOCKED. The
|
||||
lock here is for the idle reaper, which runs on a timer thread.
|
||||
"""
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._lock = threading.RLock()
|
||||
self._proc: subprocess.Popen[str] | None = None
|
||||
self._last_used = 0.0
|
||||
self._idle_timer: threading.Timer | None = None
|
||||
|
||||
def _idle_timeout(self) -> float:
|
||||
return _coerce_non_negative_float(
|
||||
app_config.get("BYPASS_BROWSER_IDLE_TIMEOUT", _HELPER_IDLE_TIMEOUT_DEFAULT),
|
||||
_HELPER_IDLE_TIMEOUT_DEFAULT,
|
||||
)
|
||||
|
||||
def _spawn(self) -> subprocess.Popen[str]:
|
||||
env_vars = os.environ.copy()
|
||||
env_vars[_BYPASS_CHILD_ENV] = "1"
|
||||
env_vars = _prepare_child_browser_env(env_vars)
|
||||
return subprocess.Popen(
|
||||
[sys.executable, "-m", "shelfmark.bypass.internal_bypasser"],
|
||||
stdin=subprocess.PIPE,
|
||||
text=True,
|
||||
env=env_vars,
|
||||
# Give the helper its own session: Chrome, Xvfb and ffmpeg inherit its process
|
||||
# group, which is what lets the cleanup sweep tell this helper's browsers apart
|
||||
# from a concurrent worker's (#1231) and lets us kill the whole tree below.
|
||||
start_new_session=True,
|
||||
)
|
||||
|
||||
def _running(self) -> subprocess.Popen[str] | None:
|
||||
proc = self._proc
|
||||
if proc is None:
|
||||
return None
|
||||
if proc.poll() is not None or proc.stdin is None or proc.stdin.closed:
|
||||
return None
|
||||
return proc
|
||||
|
||||
def _ensure_running(self) -> subprocess.Popen[str]:
|
||||
proc = self._running()
|
||||
if proc is not None:
|
||||
return proc
|
||||
if self._proc is not None:
|
||||
logger.info("Bypass helper exited (code %s), starting a new one", self._proc.returncode)
|
||||
self._discard()
|
||||
self._proc = self._spawn()
|
||||
return self._proc
|
||||
|
||||
def _discard(self, *, wait_for_exit: bool = True) -> None:
|
||||
"""Stop the helper and forget it.
|
||||
|
||||
`wait_for_exit` belongs to a helper that could still act on the closed pipe: an
|
||||
idle one is sitting in its stdin read, notices EOF and exits on its own. A helper
|
||||
dropped mid-bypass is blocked inside the solve and will not return to that read,
|
||||
so the grace cannot end in anything but the kill below - and the caller waiting it
|
||||
out is a user cancelling a download, holding LOCKED while every other bypass in
|
||||
the worker queues behind them.
|
||||
"""
|
||||
proc = self._proc
|
||||
self._proc = None
|
||||
if proc is None:
|
||||
return
|
||||
|
||||
# Closing stdin ends the helper's request loop, so an idle helper gets to exit on
|
||||
# its own. One mid-bypass cannot answer, and is killed below.
|
||||
with suppress(OSError):
|
||||
if proc.stdin is not None and not proc.stdin.closed:
|
||||
proc.stdin.close()
|
||||
if wait_for_exit:
|
||||
try:
|
||||
proc.wait(timeout=_HELPER_SHUTDOWN_GRACE_SECONDS)
|
||||
except subprocess.TimeoutExpired:
|
||||
logger.warning("Bypass helper did not exit on request, killing its session")
|
||||
|
||||
# Tear the session down either way: a helper killed mid-bypass leaves its Chrome
|
||||
# and Xvfb running, and those leftovers are what made the next worker's browser
|
||||
# fail to start. Harmless once it has already exited.
|
||||
_terminate_helper_session(proc)
|
||||
|
||||
def _cancel_idle_timer(self) -> None:
|
||||
if self._idle_timer is not None:
|
||||
self._idle_timer.cancel()
|
||||
self._idle_timer = None
|
||||
|
||||
def _arm_idle_timer(self) -> None:
|
||||
self._cancel_idle_timer()
|
||||
timeout = self._idle_timeout()
|
||||
if self._proc is None or timeout <= 0:
|
||||
return
|
||||
timer = threading.Timer(timeout, self._reap_if_idle)
|
||||
timer.daemon = True
|
||||
self._idle_timer = timer
|
||||
timer.start()
|
||||
|
||||
def _reap_if_idle(self) -> None:
|
||||
with self._lock:
|
||||
if self._proc is None:
|
||||
return
|
||||
idle_for = time.monotonic() - self._last_used
|
||||
timeout = self._idle_timeout()
|
||||
if idle_for < timeout:
|
||||
# A bypass started while this timer was waiting for the lock.
|
||||
self._arm_idle_timer()
|
||||
return
|
||||
logger.info("Closing idle bypass helper after %.0fs without work", idle_for)
|
||||
self._discard()
|
||||
|
||||
def run(
|
||||
self,
|
||||
payload: dict[str, Any],
|
||||
timeout: float,
|
||||
cancel_flag: Event | None,
|
||||
) -> dict[str, Any]:
|
||||
with self._lock:
|
||||
self._cancel_idle_timer()
|
||||
try:
|
||||
return self._exchange(payload, timeout, cancel_flag)
|
||||
finally:
|
||||
self._last_used = time.monotonic()
|
||||
self._arm_idle_timer()
|
||||
|
||||
def _exchange(
|
||||
self,
|
||||
payload: dict[str, Any],
|
||||
timeout: float,
|
||||
cancel_flag: Event | None,
|
||||
) -> dict[str, Any]:
|
||||
request_line = json.dumps(payload) + "\n"
|
||||
proc = self._ensure_running()
|
||||
try:
|
||||
self._write(proc, request_line)
|
||||
except OSError as exc:
|
||||
# A live helper can die between the liveness check and the write, so one retry
|
||||
# on a fresh process. A fresh one failing here is a real failure.
|
||||
logger.info("Bypass helper closed its pipe (%s), retrying on a new one", exc)
|
||||
# Nothing to ask of a helper we cannot write to: its read end is already gone.
|
||||
self._discard(wait_for_exit=False)
|
||||
proc = self._ensure_running()
|
||||
self._write(proc, request_line)
|
||||
|
||||
return self._await_result(proc, Path(str(payload["result_path"])), timeout, cancel_flag)
|
||||
|
||||
def _write(self, proc: subprocess.Popen[str], request_line: str) -> None:
|
||||
if proc.stdin is None:
|
||||
msg = "Bypass helper has no stdin pipe"
|
||||
raise OSError(msg)
|
||||
proc.stdin.write(request_line)
|
||||
proc.stdin.flush()
|
||||
|
||||
def _await_result(
|
||||
self,
|
||||
proc: subprocess.Popen[str],
|
||||
result_path: Path,
|
||||
timeout: float,
|
||||
cancel_flag: Event | None,
|
||||
) -> dict[str, Any]:
|
||||
deadline = time.monotonic() + timeout
|
||||
try:
|
||||
while not result_path.exists():
|
||||
if proc.poll() is not None:
|
||||
returncode = proc.returncode
|
||||
self._discard(wait_for_exit=False)
|
||||
msg = f"Internal bypasser helper exited without a result (code {returncode})"
|
||||
raise RuntimeError(msg)
|
||||
if cancel_flag is not None and cancel_flag.is_set():
|
||||
# The helper is mid-bypass and cannot be told to stop, so it goes.
|
||||
self._discard(wait_for_exit=False)
|
||||
_check_cancellation(cancel_flag, "Bypass cancelled while waiting for helper")
|
||||
if time.monotonic() >= deadline:
|
||||
self._discard(wait_for_exit=False)
|
||||
msg = "Internal bypasser helper process timed out"
|
||||
raise TimeoutError(msg)
|
||||
time.sleep(_HELPER_RESULT_POLL_SECONDS)
|
||||
|
||||
return json.loads(result_path.read_text(encoding="utf-8"))
|
||||
finally:
|
||||
# Every way out of here is final for this request: either the answer has been
|
||||
# read, or the helper that would have written it has just been killed. Nothing
|
||||
# will write these paths afterwards and nothing will come looking for them, so
|
||||
# they are cleaned on the failure paths too - otherwise every cancelled
|
||||
# download and every wedged solve leaves one behind for the container's life.
|
||||
for path in (result_path, _part_path(result_path)):
|
||||
with suppress(OSError):
|
||||
path.unlink()
|
||||
|
||||
|
||||
_BYPASS_HELPER = _BypassHelper()
|
||||
|
||||
|
||||
def _get_via_subprocess(url: str, retry: int, cancel_flag: Event | None = None) -> str:
|
||||
"""Run the browser bypass in a helper process isolated from gunicorn/gevent."""
|
||||
_check_cancellation(cancel_flag, "Bypass cancelled before helper process")
|
||||
result_path = (
|
||||
Path(tempfile.gettempdir()) / f"shelfmark-bypass-{os.getpid()}-{time.time_ns()}.json"
|
||||
)
|
||||
payload = {"url": url, "retry": retry, "result_path": str(result_path)}
|
||||
env_vars = os.environ.copy()
|
||||
env_vars[_BYPASS_CHILD_ENV] = "1"
|
||||
env_vars = _prepare_child_browser_env(env_vars)
|
||||
|
||||
proc = subprocess.Popen(
|
||||
[sys.executable, "-m", "shelfmark.bypass.internal_bypasser"],
|
||||
stdin=subprocess.PIPE,
|
||||
text=True,
|
||||
env=env_vars,
|
||||
)
|
||||
try:
|
||||
proc.communicate(json.dumps(payload), timeout=_BYPASS_SUBPROCESS_TIMEOUT_SECONDS)
|
||||
except subprocess.TimeoutExpired:
|
||||
proc.kill()
|
||||
proc.wait()
|
||||
msg = "Internal bypasser helper process timed out"
|
||||
raise TimeoutError(msg) from None
|
||||
|
||||
try:
|
||||
result = json.loads(result_path.read_text())
|
||||
except FileNotFoundError as exc:
|
||||
msg = f"Internal bypasser helper exited without a result (code {proc.returncode})"
|
||||
raise RuntimeError(msg) from exc
|
||||
finally:
|
||||
with suppress(OSError):
|
||||
result_path.unlink()
|
||||
# DNS provider state lives only in the parent's memory (no disk persistence), so the
|
||||
# freshly spawned helper would otherwise pre-resolve AA hostnames against the system
|
||||
# resolver - which may be blocked or hijacked by the user's ISP. Pass the parent's
|
||||
# active DNS config so the helper mirrors it (e.g. DoH) when building Chrome's host
|
||||
# resolver rules. Sent with every request, not just at spawn, because a helper outlives
|
||||
# changes the parent makes to its DNS provider.
|
||||
payload = {
|
||||
"url": url,
|
||||
"retry": retry,
|
||||
"result_path": str(result_path),
|
||||
"dns_config": network.get_dns_config(),
|
||||
}
|
||||
result = _BYPASS_HELPER.run(payload, _BYPASS_SUBPROCESS_TIMEOUT_SECONDS, cancel_flag)
|
||||
|
||||
if not isinstance(result, dict):
|
||||
msg = "Internal bypasser helper returned an invalid result"
|
||||
@@ -1240,12 +1400,36 @@ def _try_with_cached_cookies(url: str, hostname: str) -> str | None:
|
||||
if response.status_code == HTTPStatus.OK:
|
||||
logger.debug("Cached cookies worked, skipped Chrome bypass")
|
||||
return response.text
|
||||
logger.debug(
|
||||
"Cached cookies rejected (%s) for %s; discarding them",
|
||||
response.status_code,
|
||||
url,
|
||||
)
|
||||
except _REQUEST_OPERATION_ERRORS as exc:
|
||||
# A redirect loop lands here too: DDoS-Guard answers a dead clearance cookie
|
||||
# with an endless ?check=1 bounce rather than a status we can read.
|
||||
logger.debug("Cached cookie retry failed for %s: %s", url, exc)
|
||||
|
||||
# Reached only when the cached cookies did not produce a page, so they are no
|
||||
# longer clearance. Dropping them now means the imminent Chrome solve starts from
|
||||
# a clean slate and later requests cannot re-present the same rejected cookie.
|
||||
# Guarded because clear_cf_cookies("") means "every host", which would wipe
|
||||
# clearance for sites that are working fine.
|
||||
if hostname:
|
||||
clear_cf_cookies(hostname)
|
||||
return None
|
||||
|
||||
|
||||
def max_duration_seconds() -> float:
|
||||
"""Upper bound on how long get_bypassed_page() can take for one URL.
|
||||
|
||||
Both branches of get() are capped at _BYPASS_SUBPROCESS_TIMEOUT_SECONDS, and
|
||||
get_bypassed_page() may call it twice (once, then again after a mirror/DNS rotation).
|
||||
Callers use this to declare a stall-detection grace; see shelfmark.download.activity.
|
||||
"""
|
||||
return 2 * _BYPASS_SUBPROCESS_TIMEOUT_SECONDS
|
||||
|
||||
|
||||
def get_bypassed_page(
|
||||
url: str, selector: network.AAMirrorSelector | None = None, cancel_flag: Event | None = None
|
||||
) -> str | None:
|
||||
@@ -1278,24 +1462,117 @@ def get_bypassed_page(
|
||||
return response_html
|
||||
|
||||
|
||||
def _run_child_process() -> int:
|
||||
"""CLI entrypoint used by the Docker helper subprocess."""
|
||||
request = json.loads(sys.stdin.read() or "{}")
|
||||
def _dns_fingerprint(dns_config: dict[str, Any]) -> tuple[str, tuple[str, ...], bool]:
|
||||
"""Reduce a DNS config to what has to match for two of them to be the same one."""
|
||||
provider = str(dns_config.get("provider") or "").strip().lower()
|
||||
servers = dns_config.get("servers") if provider == "manual" else None
|
||||
server_list = tuple(str(server) for server in servers) if isinstance(servers, list) else ()
|
||||
return (provider, server_list, bool(dns_config.get("doh_enabled")))
|
||||
|
||||
|
||||
def _apply_parent_dns_config(dns_config: dict[str, Any]) -> None:
|
||||
"""Mirror the parent process's active DNS provider in this helper subprocess.
|
||||
|
||||
DNS state is in-memory only, so a helper left to itself would pre-resolve AA hostnames
|
||||
(for Chrome's --host-resolver-rules) against a resolver that may be blocked or
|
||||
hijacked. Re-applying the parent's provider keeps the helper on the same DoH/custom
|
||||
resolver the parent already validated.
|
||||
|
||||
Compared against what this process is *actually* resolving through, rather than
|
||||
against the last config it happened to be handed. The helper now outlives the request,
|
||||
so it has to be able to travel back to auto as well as away from it - which a user
|
||||
flipping CUSTOM_DNS in settings does live, without a restart - and asking the network
|
||||
module what it is doing beats keeping a second, drifting copy of that answer here.
|
||||
"""
|
||||
wanted = _dns_fingerprint(dns_config)
|
||||
provider, servers, use_doh = wanted
|
||||
if not provider:
|
||||
return
|
||||
# set_dns_provider() rebuilds the resolvers, so it is worth doing only on a real change.
|
||||
if wanted == _dns_fingerprint(network.get_dns_config()):
|
||||
return
|
||||
|
||||
try:
|
||||
network.set_dns_provider(provider, list(servers) or None, use_doh=use_doh)
|
||||
except (OSError, RuntimeError, ValueError) as exc:
|
||||
logger.warning("Could not apply parent DNS config (%s): %s", provider, exc)
|
||||
|
||||
|
||||
def _terminate_own_session() -> None:
|
||||
"""SIGKILL this process and every process it spawned, browser included."""
|
||||
if hasattr(os, "killpg") and os.getpgrp() == os.getpid():
|
||||
with suppress(OSError):
|
||||
os.killpg(os.getpgrp(), signal.SIGKILL)
|
||||
# A thread cannot end the process any other way; sys.exit would only end itself.
|
||||
os._exit(1)
|
||||
|
||||
|
||||
def _watch_parent_process(original_ppid: int, interval: float) -> None:
|
||||
"""Take the browser down with us once the app process that spawned us is gone.
|
||||
|
||||
Cleanup only reclaims process groups whose leader has died, so a helper that outlives
|
||||
its parent (worker restart, OOM kill) would sit there holding a browser that no later
|
||||
bypass is allowed to touch.
|
||||
"""
|
||||
while os.getppid() == original_ppid:
|
||||
time.sleep(interval)
|
||||
logger.warning("Bypass helper lost its parent process; taking the browser down")
|
||||
_terminate_own_session()
|
||||
|
||||
|
||||
def _start_parent_watchdog() -> None:
|
||||
"""Watch the spawning process in the background for the life of this helper."""
|
||||
threading.Thread(
|
||||
target=_watch_parent_process,
|
||||
args=(os.getppid(), _PARENT_WATCHDOG_INTERVAL_SECONDS),
|
||||
daemon=True,
|
||||
name="BypassParentWatchdog",
|
||||
).start()
|
||||
|
||||
|
||||
def _publish_result(result_path: Path, payload: dict[str, Any]) -> None:
|
||||
"""Write the result file atomically.
|
||||
|
||||
The parent decides the request is answered the moment this path exists, so it must
|
||||
never observe a half-written file. Rename within the same directory is atomic.
|
||||
"""
|
||||
tmp_path = _part_path(result_path)
|
||||
tmp_path.write_text(json.dumps(payload), encoding="utf-8")
|
||||
tmp_path.replace(result_path)
|
||||
|
||||
|
||||
def _handle_child_request(request_line: str) -> int:
|
||||
"""Answer one request from the parent."""
|
||||
request = json.loads(request_line or "{}")
|
||||
result_path = Path(str(request["result_path"]))
|
||||
url = str(request["url"])
|
||||
retry = _coerce_positive_int(
|
||||
request.get("retry"), _coerce_positive_int(app_config.MAX_RETRY, 10)
|
||||
)
|
||||
|
||||
dns_config = request.get("dns_config")
|
||||
if isinstance(dns_config, dict):
|
||||
_apply_parent_dns_config(dns_config)
|
||||
|
||||
# The parent owns the cookie store; this process only solves. Starting each request
|
||||
# from an empty store is what a helper spawned per request gave for free, and losing
|
||||
# it is what let clearance the parent had deliberately purged for some *other* host
|
||||
# survive here and get merged back over the parent's copy by the export below - the
|
||||
# dead-cookie resurrection that http.py's _redirect_loop_handoff purges to avoid.
|
||||
# Nothing is lost by dropping it: get() below re-checks cached cookies, and the
|
||||
# parent already ran that same check against a store that is a superset of this one.
|
||||
clear_cf_cookies()
|
||||
|
||||
try:
|
||||
html = get(url, retry=retry)
|
||||
cookies, user_agents = export_store()
|
||||
payload = {
|
||||
"ok": True,
|
||||
"html": html,
|
||||
"cookies": _cf_cookies,
|
||||
"user_agents": _cf_user_agents,
|
||||
"cookies": cookies,
|
||||
"user_agents": user_agents,
|
||||
}
|
||||
result_path.write_text(json.dumps(payload), encoding="utf-8")
|
||||
_publish_result(result_path, payload)
|
||||
except Exception as exc: # noqa: BLE001 - helper boundary must serialize failures.
|
||||
payload = {
|
||||
"ok": False,
|
||||
@@ -1303,10 +1580,30 @@ def _run_child_process() -> int:
|
||||
"error": str(exc),
|
||||
"traceback": traceback.format_exc(),
|
||||
}
|
||||
result_path.write_text(json.dumps(payload), encoding="utf-8")
|
||||
_publish_result(result_path, payload)
|
||||
return 1
|
||||
return 0
|
||||
|
||||
|
||||
def _run_child_process() -> int:
|
||||
"""CLI entrypoint used by the Docker helper subprocess.
|
||||
|
||||
Serves one request per line of stdin until the parent closes the pipe, so a burst of
|
||||
protected requests - a single search is several - pays the interpreter start and imports
|
||||
once instead of per request. Each bypass still gets its own browser, closed before the
|
||||
answer is published.
|
||||
"""
|
||||
exit_code = 0
|
||||
for line in sys.stdin:
|
||||
request_line = line.strip()
|
||||
if not request_line:
|
||||
continue
|
||||
exit_code = _handle_child_request(request_line)
|
||||
return exit_code
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Started here rather than in _run_child_process() so it only ever watches a real
|
||||
# spawned helper, never a test or an embedded call.
|
||||
_start_parent_watchdog()
|
||||
raise SystemExit(_run_child_process())
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
from typing import Any
|
||||
|
||||
from shelfmark.core.config import config
|
||||
@@ -23,7 +24,7 @@ _BOOKLORE_OPTIONS_CACHE: dict[str, Any] = {
|
||||
|
||||
|
||||
def _get_booklore_cache_key(base_url: str, username: str, password: str) -> str:
|
||||
return f"{base_url}|{username}|{hash(password)}"
|
||||
return f"{base_url}|{username}|{hashlib.sha256(password.encode()).hexdigest()}"
|
||||
|
||||
|
||||
def _get_booklore_select_options(
|
||||
|
||||
+57
-13
@@ -6,34 +6,78 @@ import shutil
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
LOG_LEVELS = ("DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL")
|
||||
|
||||
|
||||
def string_to_bool(s: str) -> bool:
|
||||
"""Convert string to boolean."""
|
||||
return s.lower() in ["true", "yes", "1", "y"]
|
||||
|
||||
|
||||
def _read_advanced_config(key: str) -> object | None:
|
||||
"""Read a key from the advanced settings file (import-time safe)."""
|
||||
config_dir = Path(os.getenv("CONFIG_DIR", "/config"))
|
||||
config_file = config_dir / "plugins" / "advanced.json"
|
||||
|
||||
if config_file.exists():
|
||||
try:
|
||||
with config_file.open() as f:
|
||||
config = json.load(f)
|
||||
if key in config:
|
||||
return config[key]
|
||||
except json.JSONDecodeError, OSError:
|
||||
pass
|
||||
|
||||
return None
|
||||
|
||||
|
||||
def _read_debug_from_config() -> bool:
|
||||
"""Read DEBUG from env var or config file (import-time safe)."""
|
||||
env_debug = os.environ.get("DEBUG")
|
||||
if env_debug is not None:
|
||||
return string_to_bool(env_debug)
|
||||
|
||||
# Try to read from config file
|
||||
config_dir = Path(os.getenv("CONFIG_DIR", "/config"))
|
||||
config_file = config_dir / "plugins" / "advanced.json"
|
||||
|
||||
if config_file.exists():
|
||||
try:
|
||||
with config_file.open() as f:
|
||||
config = json.load(f)
|
||||
if "DEBUG" in config:
|
||||
return bool(config["DEBUG"])
|
||||
except json.JSONDecodeError, OSError:
|
||||
pass
|
||||
value = _read_advanced_config("DEBUG")
|
||||
if value is not None:
|
||||
return bool(value)
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def normalize_log_level(raw: str | None) -> str:
|
||||
"""Normalize a log level name, falling back to INFO when unrecognized."""
|
||||
if raw is None:
|
||||
return "INFO"
|
||||
|
||||
normalized = raw.strip().upper()
|
||||
# "WARN" is a logging alias, but gunicorn only accepts "warning".
|
||||
if normalized == "WARN":
|
||||
normalized = "WARNING"
|
||||
|
||||
if normalized not in LOG_LEVELS:
|
||||
return "INFO"
|
||||
|
||||
return normalized
|
||||
|
||||
|
||||
def _read_log_level_from_config(debug: bool) -> str:
|
||||
"""Resolve the app log level from DEBUG, env var, or config file.
|
||||
|
||||
DEBUG wins when enabled, mirroring how entrypoint.sh picks gunicorn's level.
|
||||
Otherwise LOG_LEVEL is read from the env var, then the settings file, and
|
||||
falls back to INFO when unset or unrecognized.
|
||||
"""
|
||||
if debug:
|
||||
return "DEBUG"
|
||||
|
||||
raw = os.environ.get("LOG_LEVEL")
|
||||
if raw is None:
|
||||
value = _read_advanced_config("LOG_LEVEL")
|
||||
raw = value if isinstance(value, str) else None
|
||||
|
||||
return normalize_log_level(raw)
|
||||
|
||||
|
||||
def _is_sqlite_file(path: Path) -> bool:
|
||||
"""Check if a file is a valid SQLite database by reading magic bytes."""
|
||||
try:
|
||||
@@ -101,7 +145,7 @@ INGEST_DIR = Path(os.getenv("INGEST_DIR", "/books"))
|
||||
# =============================================================================
|
||||
|
||||
DEBUG = _read_debug_from_config()
|
||||
LOG_LEVEL = "DEBUG" if DEBUG else "INFO"
|
||||
LOG_LEVEL = _read_log_level_from_config(DEBUG)
|
||||
ENABLE_LOGGING = string_to_bool(os.getenv("ENABLE_LOGGING", "true"))
|
||||
|
||||
|
||||
|
||||
@@ -7,7 +7,7 @@ from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Any, Protocol
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
from collections.abc import Callable, Sequence
|
||||
from os import PathLike
|
||||
|
||||
_DEPRECATED_SETTINGS_RESTRICTION_KEYS = (
|
||||
@@ -16,6 +16,13 @@ _DEPRECATED_SETTINGS_RESTRICTION_KEYS = (
|
||||
"RESTRICT_SETTINGS_TO_ADMIN",
|
||||
)
|
||||
|
||||
# The audiobook format list shipped as the default until the format sets were unified.
|
||||
# It only covered m4b/mp3, so FLAC/OPUS/OGG/M4A releases were dropped from search results
|
||||
# and rejected after download - and the wider default alone would never reach existing
|
||||
# installs, because initialize_default_configs() only writes defaults when the config
|
||||
# file does not exist yet.
|
||||
_LEGACY_AUDIOBOOK_FORMATS_DEFAULT = ("m4b", "mp3")
|
||||
|
||||
|
||||
class MigrationLogger(Protocol):
|
||||
"""Logger surface used by config migration helpers."""
|
||||
@@ -57,6 +64,54 @@ def _pick_legacy_settings_restriction(config: dict[str, Any]) -> bool | None:
|
||||
return None
|
||||
|
||||
|
||||
def migrate_audiobook_formats(
|
||||
*,
|
||||
load_general_config: Callable[[], dict[str, Any]],
|
||||
# `object` rather than `None`: the result is discarded, and savers that report
|
||||
# success (settings_registry.save_config_file returns bool) are not assignable to a
|
||||
# `-> None` callable.
|
||||
save_general_config: Callable[[dict[str, Any]], object],
|
||||
widened_formats: Sequence[str],
|
||||
logger: MigrationLogger,
|
||||
) -> None:
|
||||
"""Widen an untouched audiobook format list to the current, fuller default.
|
||||
|
||||
Only a list that still matches the old default exactly is rewritten. Any other value
|
||||
means someone chose it deliberately, and a migration that "helpfully" re-enabled
|
||||
formats a user had turned off would be worse than leaving them on the narrow list.
|
||||
"""
|
||||
try:
|
||||
config = load_general_config()
|
||||
|
||||
if "SUPPORTED_AUDIOBOOK_FORMATS" not in config:
|
||||
# Nothing persisted, so the field default already applies.
|
||||
logger.debug("No persisted audiobook formats - the current default applies")
|
||||
return
|
||||
|
||||
current = config.get("SUPPORTED_AUDIOBOOK_FORMATS")
|
||||
if not isinstance(current, list):
|
||||
return
|
||||
|
||||
normalized = {str(fmt).strip().lower() for fmt in current if str(fmt).strip()}
|
||||
if normalized != set(_LEGACY_AUDIOBOOK_FORMATS_DEFAULT):
|
||||
logger.debug(
|
||||
"Audiobook formats were customized (%s) - left unchanged", sorted(normalized)
|
||||
)
|
||||
return
|
||||
|
||||
save_general_config({"SUPPORTED_AUDIOBOOK_FORMATS": list(widened_formats)})
|
||||
logger.info(
|
||||
"Widened audiobook formats from the legacy default %s to %s",
|
||||
list(_LEGACY_AUDIOBOOK_FORMATS_DEFAULT),
|
||||
list(widened_formats),
|
||||
)
|
||||
|
||||
except FileNotFoundError:
|
||||
logger.debug("No existing general config file found - nothing to migrate")
|
||||
except Exception:
|
||||
logger.exception("Failed to migrate audiobook formats")
|
||||
|
||||
|
||||
def migrate_security_settings(
|
||||
*,
|
||||
load_security_config: Callable[[], dict[str, Any]],
|
||||
|
||||
@@ -115,7 +115,7 @@ def check_oidc_connection(
|
||||
response.raise_for_status()
|
||||
document = response.json()
|
||||
|
||||
required_fields = ["issuer", "authorization_endpoint", "token_endpoint"]
|
||||
required_fields = ["issuer", "authorization_endpoint", "token_endpoint", "jwks_uri"]
|
||||
missing_fields = [field for field in required_fields if field not in document]
|
||||
if missing_fields:
|
||||
return {
|
||||
@@ -123,6 +123,24 @@ def check_oidc_connection(
|
||||
"message": f"Discovery document missing fields: {', '.join(missing_fields)}",
|
||||
}
|
||||
|
||||
# Logins verify the ID token against the provider's JWKS, so an empty key
|
||||
# set (e.g. an Authentik provider with no Signing Key selected) means every
|
||||
# login will fail even though discovery looks healthy.
|
||||
jwks_uri = str(document["jwks_uri"])
|
||||
jwks_response = requests.get(jwks_uri, timeout=10, verify=get_ssl_verify(jwks_uri))
|
||||
jwks_response.raise_for_status()
|
||||
jwks_document = jwks_response.json()
|
||||
jwks_keys = jwks_document.get("keys") if isinstance(jwks_document, dict) else None
|
||||
if not jwks_keys:
|
||||
return {
|
||||
"success": False,
|
||||
"message": (
|
||||
"Discovery document is valid, but the provider returned no token "
|
||||
"signing keys (empty JWKS), so logins will fail. If you use "
|
||||
"Authentik, select a Signing Key in the provider settings."
|
||||
),
|
||||
}
|
||||
|
||||
return {"success": True, "message": f"Connected to {document['issuer']}"}
|
||||
except Exception as exc:
|
||||
logger.exception("OIDC connection test failed")
|
||||
|
||||
+104
-16
@@ -1,6 +1,5 @@
|
||||
"""Core settings registration and derived configuration values."""
|
||||
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
@@ -15,6 +14,8 @@ from shelfmark.config.download_settings_handlers import (
|
||||
check_books_destination,
|
||||
)
|
||||
from shelfmark.config.email_settings import check_email_connection
|
||||
from shelfmark.config.migrations import migrate_audiobook_formats
|
||||
from shelfmark.core.languages import supported_book_languages
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.settings_registry import (
|
||||
ActionButton,
|
||||
@@ -35,6 +36,10 @@ from shelfmark.core.settings_registry import (
|
||||
register_on_save,
|
||||
register_settings,
|
||||
)
|
||||
from shelfmark.core.utils import ARCHIVE_FORMATS, AUDIOBOOK_FORMATS
|
||||
|
||||
_DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_DEFAULT = 60
|
||||
_DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_MAX = 3600
|
||||
|
||||
|
||||
def _on_save_advanced(values: dict[str, Any]) -> dict[str, Any]:
|
||||
@@ -43,6 +48,40 @@ def _on_save_advanced(values: dict[str, Any]) -> dict[str, Any]:
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
timeout_key = "DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT"
|
||||
if timeout_key in values:
|
||||
raw_timeout = values.get(timeout_key)
|
||||
if isinstance(raw_timeout, bool):
|
||||
return {
|
||||
"error": True,
|
||||
"message": "Completed Path Wait must be a number of seconds",
|
||||
"values": values,
|
||||
}
|
||||
if raw_timeout is None:
|
||||
return {
|
||||
"error": True,
|
||||
"message": "Completed Path Wait must be a number of seconds",
|
||||
"values": values,
|
||||
}
|
||||
try:
|
||||
timeout_seconds = int(raw_timeout)
|
||||
except TypeError, ValueError:
|
||||
return {
|
||||
"error": True,
|
||||
"message": "Completed Path Wait must be a number of seconds",
|
||||
"values": values,
|
||||
}
|
||||
if timeout_seconds < 0 or timeout_seconds > _DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_MAX:
|
||||
return {
|
||||
"error": True,
|
||||
"message": (
|
||||
"Completed Path Wait must be between 0 and "
|
||||
f"{_DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_MAX} seconds"
|
||||
),
|
||||
"values": values,
|
||||
}
|
||||
values[timeout_key] = timeout_seconds
|
||||
|
||||
mappings = values.get("PROWLARR_REMOTE_PATH_MAPPINGS")
|
||||
if mappings is None:
|
||||
return {"error": False, "values": values}
|
||||
@@ -97,6 +136,20 @@ def _on_save_advanced(values: dict[str, Any]) -> dict[str, Any]:
|
||||
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
|
||||
def migrate_audiobook_format_settings() -> None:
|
||||
"""Bring installs created before the audiobook format sets were unified up to date."""
|
||||
from shelfmark.core.settings_registry import load_config_file, save_config_file
|
||||
|
||||
migrate_audiobook_formats(
|
||||
load_general_config=lambda: load_config_file("general"),
|
||||
save_general_config=lambda values: save_config_file("general", values),
|
||||
widened_formats=[*AUDIOBOOK_FORMATS, *ARCHIVE_FORMATS],
|
||||
logger=logger,
|
||||
)
|
||||
|
||||
|
||||
_SMTP_PORT_MAX = 65535
|
||||
_EMAIL_ATTACHMENT_LIMIT_MB_MAX = 600
|
||||
|
||||
@@ -106,11 +159,8 @@ for key in ["CONFIG_DIR", "LOG_DIR", "TMP_DIR", "INGEST_DIR", "DEBUG", "DOCKERMO
|
||||
if hasattr(env, key):
|
||||
logger.debug(" %s: %s", key, getattr(env, key))
|
||||
|
||||
# Load supported book languages from data file
|
||||
# Path is relative to the package root, not this file
|
||||
_DATA_DIR = Path(__file__).resolve().parent.parent.parent / "data"
|
||||
with (_DATA_DIR / "book-languages.json").open() as file:
|
||||
_SUPPORTED_BOOK_LANGUAGE = json.load(file)
|
||||
# Selectable book languages, without the resolution aliases clients do not need.
|
||||
_SUPPORTED_BOOK_LANGUAGE = supported_book_languages()
|
||||
|
||||
# Directory settings
|
||||
BASE_DIR = Path(__file__).resolve().parent.parent.parent
|
||||
@@ -181,11 +231,7 @@ _FORMAT_OPTIONS = [
|
||||
]
|
||||
|
||||
_AUDIOBOOK_FORMAT_OPTIONS = [
|
||||
{"value": "m4b", "label": "M4B"},
|
||||
{"value": "mp3", "label": "MP3"},
|
||||
{"value": "m4a", "label": "M4A"},
|
||||
{"value": "zip", "label": "ZIP"},
|
||||
{"value": "rar", "label": "RAR"},
|
||||
{"value": fmt, "label": fmt.upper()} for fmt in (*AUDIOBOOK_FORMATS, *ARCHIVE_FORMATS)
|
||||
]
|
||||
|
||||
_DOWNLOAD_TO_BROWSER_CONTENT_TYPE_OPTIONS = [
|
||||
@@ -382,7 +428,7 @@ def general_settings() -> list[SettingsField]:
|
||||
label="Supported Audiobook Formats",
|
||||
description="Audiobook formats to include in search results. ZIP/RAR archives are extracted automatically and audiobook files are used if found.",
|
||||
options=_AUDIOBOOK_FORMAT_OPTIONS,
|
||||
default=["m4b", "mp3"],
|
||||
default=[*AUDIOBOOK_FORMATS, *ARCHIVE_FORMATS],
|
||||
),
|
||||
MultiSelectField(
|
||||
key="BOOK_LANGUAGE",
|
||||
@@ -975,7 +1021,7 @@ def download_settings() -> list[SettingsField]:
|
||||
key="TEMPLATE_RENAME",
|
||||
label="Naming Template",
|
||||
description=(
|
||||
"Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} "
|
||||
"Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} "
|
||||
"(source filename without extension). Universal adds: {Series}, "
|
||||
"{SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: "
|
||||
"{Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. "
|
||||
@@ -994,7 +1040,7 @@ def download_settings() -> list[SettingsField]:
|
||||
key="TEMPLATE_ORGANIZE",
|
||||
label="Path Template",
|
||||
description=(
|
||||
"Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, "
|
||||
"Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, "
|
||||
"{OriginalName} (source filename without extension). Universal adds: {Series}, "
|
||||
"{SeriesPosition}, {Subtitle}, {PrimaryTitle}. Use arbitrary prefix/suffix: "
|
||||
"{Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty."
|
||||
@@ -1257,7 +1303,7 @@ def download_settings() -> list[SettingsField]:
|
||||
key="TEMPLATE_AUDIOBOOK_RENAME",
|
||||
label="Naming Template",
|
||||
description=(
|
||||
"Variables: {Author}, {Title}, {Year}, {User}, {OriginalName} "
|
||||
"Variables: {Author}, {Title}, {Year}, {Language}, {User}, {OriginalName} "
|
||||
"(source filename without extension), {Series}, {SeriesPosition}, {Subtitle}, "
|
||||
"{PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: "
|
||||
"{Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty. "
|
||||
@@ -1274,7 +1320,7 @@ def download_settings() -> list[SettingsField]:
|
||||
key="TEMPLATE_AUDIOBOOK_ORGANIZE",
|
||||
label="Path Template",
|
||||
description=(
|
||||
"Use / to create folders. Variables: {Author}, {Title}, {Year}, {User}, "
|
||||
"Use / to create folders. Variables: {Author}, {Title}, {Year}, {Language}, {User}, "
|
||||
"{OriginalName} (source filename without extension), {Series}, {SeriesPosition}, "
|
||||
"{Subtitle}, {PrimaryTitle}, {PartNumber}. Use arbitrary prefix/suffix: "
|
||||
"{Vol. SeriesPosition - } outputs 'Vol. 2 - ' when set, nothing when empty."
|
||||
@@ -1609,6 +1655,19 @@ def cloudflare_bypass_settings() -> list[SettingsField]:
|
||||
requires_restart=True,
|
||||
show_when={"field": "USING_EXTERNAL_BYPASSER", "value": True},
|
||||
),
|
||||
NumberField(
|
||||
key="BYPASS_BROWSER_IDLE_TIMEOUT",
|
||||
label="Bypasser Idle Timeout (seconds)",
|
||||
description=(
|
||||
"How long the bypass helper process may sit unused before it is shut down. "
|
||||
"Higher keeps more searches fast, lower frees memory sooner."
|
||||
),
|
||||
default=180,
|
||||
min_value=30,
|
||||
max_value=3600,
|
||||
requires_restart=True,
|
||||
show_when={"field": "USING_EXTERNAL_BYPASSER", "value": False},
|
||||
),
|
||||
]
|
||||
|
||||
|
||||
@@ -1727,6 +1786,23 @@ def advanced_settings() -> list[SettingsField]:
|
||||
default=False,
|
||||
requires_restart=True,
|
||||
),
|
||||
SelectField(
|
||||
key="LOG_LEVEL",
|
||||
label="Log Level",
|
||||
description=(
|
||||
"Lowest severity written to the console and log file. "
|
||||
"Ignored while Debug Mode is on, which forces Debug."
|
||||
),
|
||||
options=[
|
||||
{"value": "DEBUG", "label": "Debug", "description": "Everything, very noisy."},
|
||||
{"value": "INFO", "label": "Info", "description": "Normal activity (default)."},
|
||||
{"value": "WARNING", "label": "Warning", "description": "Warnings and problems."},
|
||||
{"value": "ERROR", "label": "Error", "description": "Failures only."},
|
||||
{"value": "CRITICAL", "label": "Critical", "description": "Fatal errors only."},
|
||||
],
|
||||
default="INFO",
|
||||
requires_restart=True,
|
||||
),
|
||||
NumberField(
|
||||
key="MAIN_LOOP_SLEEP_TIME",
|
||||
label="Queue Check Interval (seconds)",
|
||||
@@ -1780,6 +1856,18 @@ def advanced_settings() -> list[SettingsField]:
|
||||
title="Remote Path Mappings",
|
||||
description="Map download client paths to paths inside Shelfmark. Needed when volume mounts differ between containers.",
|
||||
),
|
||||
NumberField(
|
||||
key="DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT",
|
||||
label="Completed Path Wait (seconds)",
|
||||
description=(
|
||||
"How long to wait after a torrent or usenet client reports completion "
|
||||
"for the completed file path to become visible to Shelfmark. Increase "
|
||||
"this for seedbox or remote-sync workflows."
|
||||
),
|
||||
default=_DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_DEFAULT,
|
||||
min_value=0,
|
||||
max_value=_DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT_MAX,
|
||||
),
|
||||
TableField(
|
||||
key="PROWLARR_REMOTE_PATH_MAPPINGS",
|
||||
label="Path Mappings",
|
||||
|
||||
@@ -39,6 +39,7 @@ def upsert_cwa_user(
|
||||
email=normalized_email,
|
||||
role=role,
|
||||
allow_email_link=True,
|
||||
sync_username=True,
|
||||
collision_strategy=collision_strategy,
|
||||
alias_suffix=_CWA_ALIAS_SUFFIX,
|
||||
context=context,
|
||||
|
||||
@@ -108,6 +108,7 @@ def _build_updates(
|
||||
auth_source: str,
|
||||
role: str,
|
||||
sync_role: bool,
|
||||
username: str | object,
|
||||
email: str | None | object,
|
||||
display_name: str | None | object,
|
||||
subject_field: str | None,
|
||||
@@ -116,6 +117,8 @@ def _build_updates(
|
||||
updates: dict[str, Any] = {"auth_source": auth_source}
|
||||
if sync_role:
|
||||
updates["role"] = _normalize_role(role)
|
||||
if username is not UNSET:
|
||||
updates["username"] = _normalize_username(username)
|
||||
if email is not UNSET:
|
||||
updates["email"] = _normalize_email(email)
|
||||
if display_name is not UNSET:
|
||||
@@ -125,10 +128,17 @@ def _build_updates(
|
||||
return updates
|
||||
|
||||
|
||||
def _next_suffix_username(user_db: UserDB, base_username: str) -> str:
|
||||
def _next_suffix_username(
|
||||
user_db: UserDB,
|
||||
base_username: str,
|
||||
*,
|
||||
exclude_user_id: int | None = None,
|
||||
) -> str:
|
||||
candidate = base_username
|
||||
suffix = 1
|
||||
while user_db.get_user(username=candidate):
|
||||
while existing := user_db.get_user(username=candidate):
|
||||
if exclude_user_id is not None and int(existing.get("id") or 0) == exclude_user_id:
|
||||
return candidate
|
||||
candidate = f"{base_username}_{suffix}"
|
||||
suffix += 1
|
||||
return candidate
|
||||
@@ -149,7 +159,7 @@ def _find_existing_alias_user(
|
||||
]
|
||||
if not candidates:
|
||||
return None
|
||||
return sorted(candidates, key=lambda user: int(user.get("id") or 0))[0]
|
||||
return min(candidates, key=lambda user: int(user.get("id") or 0), default=None)
|
||||
|
||||
|
||||
def _resolve_create_username(
|
||||
@@ -185,6 +195,38 @@ def _resolve_create_username(
|
||||
return _next_suffix_username(user_db, alias_base), None, "username_collision_alias"
|
||||
|
||||
|
||||
def _resolve_update_username(
|
||||
user_db: UserDB,
|
||||
*,
|
||||
current_user: dict[str, Any],
|
||||
requested_username: str,
|
||||
strategy: CollisionStrategy,
|
||||
alias_suffix: str,
|
||||
) -> str:
|
||||
current_user_id = int(current_user["id"])
|
||||
existing = user_db.get_user(username=requested_username)
|
||||
if existing is None or int(existing.get("id") or 0) == current_user_id:
|
||||
return requested_username
|
||||
|
||||
if strategy == "suffix":
|
||||
return _next_suffix_username(
|
||||
user_db,
|
||||
requested_username,
|
||||
exclude_user_id=current_user_id,
|
||||
)
|
||||
if strategy == "alias":
|
||||
return _next_suffix_username(
|
||||
user_db,
|
||||
f"{requested_username}{alias_suffix}",
|
||||
exclude_user_id=current_user_id,
|
||||
)
|
||||
|
||||
# `takeover` can select an existing row during creation, but once an
|
||||
# identity is already matched it must never replace a different username
|
||||
# owner. Preserve the matched row's current collision-free name instead.
|
||||
return str(current_user["username"])
|
||||
|
||||
|
||||
def upsert_external_user(
|
||||
user_db: UserDB,
|
||||
*,
|
||||
@@ -197,6 +239,7 @@ def upsert_external_user(
|
||||
subject: str | None = None,
|
||||
allow_email_link: bool = False,
|
||||
sync_role: bool = True,
|
||||
sync_username: bool = False,
|
||||
allow_create: bool = True,
|
||||
collision_strategy: CollisionStrategy = "takeover",
|
||||
alias_suffix: str | None = None,
|
||||
@@ -229,10 +272,26 @@ def upsert_external_user(
|
||||
subject=subject,
|
||||
allow_email_link=allow_email_link,
|
||||
)
|
||||
resolved_alias_suffix = alias_suffix or f"__{auth_source}"
|
||||
update_username: str | object = UNSET
|
||||
if (
|
||||
matched is not None
|
||||
and sync_username
|
||||
and normalize_auth_source(matched.get("auth_source"), matched.get("oidc_subject"))
|
||||
== auth_source
|
||||
):
|
||||
update_username = _resolve_update_username(
|
||||
user_db,
|
||||
current_user=matched,
|
||||
requested_username=normalized_username,
|
||||
strategy=collision_strategy,
|
||||
alias_suffix=resolved_alias_suffix,
|
||||
)
|
||||
updates = _build_updates(
|
||||
auth_source=auth_source,
|
||||
role=normalized_role,
|
||||
sync_role=sync_role,
|
||||
username=update_username,
|
||||
email=normalized_email if email is not UNSET else UNSET,
|
||||
display_name=normalized_display_name if display_name is not UNSET else UNSET,
|
||||
subject_field=subject_field,
|
||||
@@ -261,7 +320,6 @@ def upsert_external_user(
|
||||
)
|
||||
return None, "not_found"
|
||||
|
||||
resolved_alias_suffix = alias_suffix or f"__{auth_source}"
|
||||
create_username, takeover_target, create_reason = _resolve_create_username(
|
||||
user_db,
|
||||
auth_source=auth_source,
|
||||
|
||||
@@ -0,0 +1,138 @@
|
||||
"""Canonical language resolution shared by every release source.
|
||||
|
||||
Release sources report a language in whatever shape their upstream uses: a
|
||||
two-letter code, an ISO 639-2 three-letter code in either the bibliographic or
|
||||
terminological form, or an English name. They all need the same ISO 639-1 code
|
||||
out the other side, so the aliases live in one place (``data/book-languages.json``)
|
||||
and adding a language means editing one file.
|
||||
"""
|
||||
|
||||
import json
|
||||
import threading
|
||||
import unicodedata
|
||||
from pathlib import Path
|
||||
|
||||
from shelfmark.core.logger import setup_logger
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
LANGUAGE_DATA_PATH = Path(__file__).resolve().parents[1].parent / "data" / "book-languages.json"
|
||||
|
||||
# Values a source uses to mean "we could not tell".
|
||||
LANGUAGE_PLACEHOLDERS = frozenset({"", "-", "--", "unknown", "unk", "n/a", "na", "none", "null"})
|
||||
|
||||
_ALIAS_TO_CODE: dict[str, str] | None = None
|
||||
_CODE_TO_NAME: dict[str, str] | None = None
|
||||
_LOCK = threading.Lock()
|
||||
|
||||
|
||||
# Separators that stand in for the hyphen in a subtag. The dashes turn up in
|
||||
# codes copied from web pages -- "zh‑Hant" used U+2011, which renders close
|
||||
# enough to both a hyphen and an underscore to go unnoticed -- and the
|
||||
# underscore is the spelling Direct Download accepted before this module existed.
|
||||
_SUBTAG_SEPARATORS = dict.fromkeys(map(ord, "‐‑‒–—―−﹘﹣-_"), "-")
|
||||
|
||||
|
||||
def _fold(value: str) -> str:
|
||||
"""Casefold, strip accents, and normalize subtag separators, so 'Español'
|
||||
and 'espanol', or 'zh-Hant', 'zh‑Hant' and 'zh_Hant', all match."""
|
||||
decomposed = unicodedata.normalize("NFKD", value).translate(_SUBTAG_SEPARATORS)
|
||||
stripped = "".join(ch for ch in decomposed if not unicodedata.combining(ch))
|
||||
return " ".join(stripped.split()).casefold()
|
||||
|
||||
|
||||
def _load() -> tuple[dict[str, str], dict[str, str]]:
|
||||
global _ALIAS_TO_CODE, _CODE_TO_NAME
|
||||
|
||||
if _ALIAS_TO_CODE is not None and _CODE_TO_NAME is not None:
|
||||
return _ALIAS_TO_CODE, _CODE_TO_NAME
|
||||
|
||||
with _LOCK:
|
||||
if _ALIAS_TO_CODE is not None and _CODE_TO_NAME is not None:
|
||||
return _ALIAS_TO_CODE, _CODE_TO_NAME
|
||||
|
||||
alias_to_code: dict[str, str] = {}
|
||||
code_to_name: dict[str, str] = {}
|
||||
|
||||
try:
|
||||
raw = json.loads(LANGUAGE_DATA_PATH.read_text(encoding="utf-8"))
|
||||
except OSError, ValueError:
|
||||
logger.exception("Failed to load language data from %s", LANGUAGE_DATA_PATH)
|
||||
raw = []
|
||||
|
||||
if not isinstance(raw, list):
|
||||
logger.warning("Language data at %s is not a list", LANGUAGE_DATA_PATH)
|
||||
raw = []
|
||||
|
||||
for item in raw:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
code = str(item.get("code") or "").strip()
|
||||
name = str(item.get("language") or "").strip()
|
||||
if not code:
|
||||
continue
|
||||
|
||||
code_to_name.setdefault(code, name or code)
|
||||
|
||||
for candidate in (code, name, *(item.get("aliases") or [])):
|
||||
folded = _fold(str(candidate))
|
||||
if folded and folded not in LANGUAGE_PLACEHOLDERS:
|
||||
alias_to_code.setdefault(folded, code)
|
||||
|
||||
_ALIAS_TO_CODE = alias_to_code
|
||||
_CODE_TO_NAME = code_to_name
|
||||
return alias_to_code, code_to_name
|
||||
|
||||
|
||||
def normalize_language(value: object) -> str | None:
|
||||
"""Resolve any known spelling of a language to its ISO 639-1 code.
|
||||
|
||||
Accepts a two-letter code, an ISO 639-2 three-letter code in either the
|
||||
bibliographic or terminological form, or an English name. Returns None for
|
||||
anything unrecognised or for the placeholders a source uses to say it does
|
||||
not know, so callers can treat "no language" uniformly.
|
||||
"""
|
||||
if value is None:
|
||||
return None
|
||||
|
||||
folded = _fold(str(value))
|
||||
if not folded or folded in LANGUAGE_PLACEHOLDERS:
|
||||
return None
|
||||
|
||||
alias_to_code, _ = _load()
|
||||
return alias_to_code.get(folded)
|
||||
|
||||
|
||||
def language_name(code: str | None) -> str | None:
|
||||
"""Return the English name for a language code, or None if unknown."""
|
||||
if not code:
|
||||
return None
|
||||
|
||||
_, code_to_name = _load()
|
||||
return code_to_name.get(str(code).strip())
|
||||
|
||||
|
||||
def language_alias_map() -> dict[str, str]:
|
||||
"""Every known alias mapped to its code, for callers doing their own matching.
|
||||
|
||||
Direct Download scans free-text paths and needs the whole alias set up front
|
||||
to look for, rather than resolving one candidate at a time.
|
||||
"""
|
||||
alias_to_code, _ = _load()
|
||||
return dict(alias_to_code)
|
||||
|
||||
|
||||
def supported_book_languages() -> list[dict[str, str]]:
|
||||
"""The selectable languages, as ``{"language": ..., "code": ...}``.
|
||||
|
||||
Aliases are an implementation detail of resolution, so they are left out of
|
||||
what the settings dropdown and the API hand to clients.
|
||||
"""
|
||||
_, code_to_name = _load()
|
||||
return [{"language": name, "code": code} for code, name in code_to_name.items()]
|
||||
|
||||
|
||||
def known_language_codes() -> frozenset[str]:
|
||||
"""Every ISO 639-1 code the bundled language data defines."""
|
||||
_, code_to_name = _load()
|
||||
return frozenset(code_to_name)
|
||||
@@ -108,6 +108,9 @@ class DownloadTask:
|
||||
retry_expected_hash: str | None = None # Optional torrent hash used to match client downloads
|
||||
retry_ratio_limit: float | None = None # Optional post-download seeding ratio
|
||||
retry_seeding_time_limit_minutes: int | None = None # Optional post-download seeding time limit
|
||||
retry_source_context: dict[str, Any] = field(
|
||||
default_factory=dict
|
||||
) # Source-private context for retry/re-resolution
|
||||
can_retry_without_staged_source: bool = (
|
||||
True # Whether the source can restart without a preserved staged file
|
||||
)
|
||||
@@ -116,6 +119,7 @@ class DownloadTask:
|
||||
series_name: str | None = None
|
||||
series_position: float | None = None # Float for novellas (e.g., 1.5)
|
||||
subtitle: str | None = None # Book subtitle for naming templates
|
||||
language: str | None = None # Release language code for the {Language} template variable
|
||||
|
||||
# Hardlinking support
|
||||
original_download_path: str | None = None # Path in download client (for hardlinking)
|
||||
|
||||
@@ -4,6 +4,7 @@ import re
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from shelfmark.core.languages import LANGUAGE_PLACEHOLDERS, normalize_language
|
||||
from shelfmark.core.logger import setup_logger
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -19,6 +20,7 @@ KNOWN_TOKENS = [
|
||||
"primarytitle",
|
||||
"originalname",
|
||||
"partnumber",
|
||||
"language",
|
||||
"subtitle",
|
||||
"author",
|
||||
"series",
|
||||
@@ -66,6 +68,33 @@ def format_series_position(position: str | float | None) -> str:
|
||||
return str(position)
|
||||
|
||||
|
||||
def normalize_language_code(language: str | None) -> str:
|
||||
"""Resolve a release language to the single spelling used in a path.
|
||||
|
||||
Sources report the same language in different shapes: "en", "eng", "English".
|
||||
All of them have to collapse to one code, or the editions they identify end
|
||||
up in separate folders, which is the collision this token exists to prevent.
|
||||
Placeholder values render empty so `{ (Language)}` disappears entirely
|
||||
rather than labelling a folder "(unknown)".
|
||||
|
||||
A language the bundled data does not know is kept, casefolded, rather than
|
||||
dropped: it still separates editions, and it cannot collide with a resolved
|
||||
code precisely because nothing resolves it.
|
||||
"""
|
||||
if not language:
|
||||
return ""
|
||||
|
||||
resolved = normalize_language(language)
|
||||
if resolved is not None:
|
||||
return resolved
|
||||
|
||||
normalized = " ".join(str(language).split()).strip().casefold()
|
||||
if normalized in LANGUAGE_PLACEHOLDERS:
|
||||
return ""
|
||||
|
||||
return normalized
|
||||
|
||||
|
||||
def derive_primary_title(title: str | None, subtitle: str | None) -> str:
|
||||
"""Return the title without an explicit subtitle suffix when possible."""
|
||||
title_value = " ".join(str(title or "").split()).strip()
|
||||
@@ -91,8 +120,7 @@ PAD_NUMBERS_PATTERN = re.compile(r"\d+")
|
||||
|
||||
def natural_sort_key(path: str | Path) -> str:
|
||||
"""Generate a sort key with padded numbers for natural sorting."""
|
||||
filename = Path(path).name.lower()
|
||||
return PAD_NUMBERS_PATTERN.sub(lambda m: m.group().zfill(9), filename)
|
||||
return PAD_NUMBERS_PATTERN.sub(lambda m: m.group().zfill(9), str(path).lower())
|
||||
|
||||
|
||||
def assign_part_numbers(
|
||||
|
||||
@@ -33,6 +33,11 @@ logger = setup_logger(__name__)
|
||||
oauth = OAuth()
|
||||
_RETURN_TO_SESSION_KEY = "oidc_return_to"
|
||||
_OIDC_CLIENT_ERRORS = (OAuthError, OSError, RuntimeError, TypeError, ValueError)
|
||||
_EMPTY_JWKS_MESSAGE = (
|
||||
"Authentication failed: the identity provider returned no token signing keys "
|
||||
"(empty JWKS). If you use Authentik, select a Signing Key in the provider "
|
||||
"settings and try again."
|
||||
)
|
||||
|
||||
|
||||
class _ClaimsMappingLike(Protocol):
|
||||
@@ -121,6 +126,17 @@ def _normalize_return_to(raw_return_to: object) -> str | None:
|
||||
return urlunsplit(("", "", path, parsed.query, parsed.fragment))
|
||||
|
||||
|
||||
def _idp_jwks_has_no_keys(client: Any) -> bool:
|
||||
"""Return True when the IdP's JWKS document verifiably contains no signing keys."""
|
||||
try:
|
||||
jwk_set = client.fetch_jwk_set(force=True)
|
||||
except (*_OIDC_CLIENT_ERRORS, KeyError):
|
||||
return False
|
||||
if not isinstance(jwk_set, Mapping):
|
||||
return False
|
||||
return not jwk_set.get("keys")
|
||||
|
||||
|
||||
def _get_pending_return_to(*, clear: bool = False) -> str | None:
|
||||
"""Read the pending post-login target from the session."""
|
||||
raw_return_to = (
|
||||
@@ -274,6 +290,17 @@ def register_oidc_routes(app: Flask, user_db: UserDB) -> None:
|
||||
return redirect(
|
||||
_login_error_url(f"OIDC token claim validation failed: {claim_name}")
|
||||
)
|
||||
except KeyError, ValueError:
|
||||
# An IdP serving an empty JWKS document (e.g. an Authentik provider
|
||||
# with no Signing Key selected) surfaces as KeyError('keys') while
|
||||
# importing the key set. Test Connection only validates discovery,
|
||||
# so this is the first place the misconfiguration becomes visible.
|
||||
if _idp_jwks_has_no_keys(client):
|
||||
logger.exception(
|
||||
"OIDC callback failed: the IdP JWKS document contains no signing keys"
|
||||
)
|
||||
return redirect(_login_error_url(_EMPTY_JWKS_MESSAGE))
|
||||
raise
|
||||
claims = _normalize_claims(token.get("userinfo"))
|
||||
|
||||
# If userinfo is missing or claims are too sparse, request it explicitly.
|
||||
@@ -306,6 +333,12 @@ def register_oidc_routes(app: Flask, user_db: UserDB) -> None:
|
||||
is_admin = admin_group in groups
|
||||
|
||||
allow_email_link = bool(user_info.get("email")) and _is_email_verified(claims)
|
||||
if user_info.get("email") and not allow_email_link:
|
||||
logger.debug(
|
||||
"OIDC email %s is not marked verified by the IdP; skipping "
|
||||
"email-based account linking",
|
||||
user_info["email"],
|
||||
)
|
||||
user = provision_oidc_user(
|
||||
user_db,
|
||||
user_info,
|
||||
|
||||
@@ -9,6 +9,7 @@ from typing import TYPE_CHECKING, Any
|
||||
|
||||
from werkzeug.utils import secure_filename
|
||||
|
||||
from shelfmark.config.env import normalize_log_level
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.request_helpers import coerce_bool, normalize_optional_text
|
||||
|
||||
@@ -898,6 +899,9 @@ def _get_env_value_for_field(field: FieldBase) -> tuple[bool, object | None]:
|
||||
"WELIB_MIRROR_URLS",
|
||||
} and isinstance(parsed, list):
|
||||
parsed = _normalize_mirror_env_urls(parsed)
|
||||
if field.key == "LOG_LEVEL" and isinstance(parsed, str):
|
||||
# LOG_LEVEL is commonly set lowercase; the field options are uppercase.
|
||||
parsed = normalize_log_level(parsed)
|
||||
return True, parsed
|
||||
|
||||
if field.key == "AA_MIRROR_URLS":
|
||||
|
||||
@@ -344,6 +344,7 @@ class UserDB:
|
||||
|
||||
_ALLOWED_UPDATE_COLUMNS: ClassVar[frozenset[str]] = frozenset(
|
||||
{
|
||||
"username",
|
||||
"email",
|
||||
"display_name",
|
||||
"password_hash",
|
||||
@@ -353,6 +354,7 @@ class UserDB:
|
||||
}
|
||||
)
|
||||
_USER_UPDATE_STATEMENTS: ClassVar[dict[str, str]] = {
|
||||
"username": "UPDATE users SET username = ? WHERE id = ?",
|
||||
"email": "UPDATE users SET email = ? WHERE id = ?",
|
||||
"display_name": "UPDATE users SET display_name = ? WHERE id = ?",
|
||||
"password_hash": "UPDATE users SET password_hash = ? WHERE id = ?",
|
||||
|
||||
@@ -115,6 +115,21 @@ def is_audiobook(content_type: str | None) -> bool:
|
||||
return bool(content_type and "audiobook" in content_type.lower())
|
||||
|
||||
|
||||
# Every audio format an audiobook can legitimately arrive in, and the single source of
|
||||
# truth for that list. The settings UI, release-source parsing, archive extraction and
|
||||
# post-download scanning all derive from it, so a format added here becomes selectable,
|
||||
# searchable AND downloadable at once. These used to be four hand-maintained copies that
|
||||
# had drifted apart: the settings UI only offered m4b/mp3/m4a, which meant a FLAC
|
||||
# audiobook could never be enabled, was silently dropped from every search result, and
|
||||
# was rejected after download as "format not supported".
|
||||
AUDIOBOOK_FORMATS = ("m4b", "mp3", "m4a", "flac", "ogg", "wma", "aac", "wav", "opus")
|
||||
|
||||
# Multi-file audiobooks are almost always distributed as an archive. These are containers
|
||||
# rather than formats: they are what a *release* looks like, and the formats above are
|
||||
# what comes out of one after extraction.
|
||||
ARCHIVE_FORMATS = ("zip", "rar")
|
||||
|
||||
|
||||
CONTENT_TYPES = [
|
||||
"book (fiction)",
|
||||
"book (non-fiction)",
|
||||
|
||||
@@ -0,0 +1,81 @@
|
||||
"""Stall-detection grace signalling for long single-shot download operations.
|
||||
|
||||
The orchestrator cancels a download after `STALL_TIMEOUT` seconds without activity, where
|
||||
"activity" means a *changed* status event or a *changed* progress value. That de-duplication
|
||||
is deliberate - a keep-alive that repeats the same payload on a timer proves nothing about
|
||||
whether the operation is still making progress, so letting it refresh the stall clock would
|
||||
make a genuinely wedged download immortal.
|
||||
|
||||
Operations that legitimately take longer than `STALL_TIMEOUT` but cannot report incremental
|
||||
progress therefore declare an explicit upper bound up front instead:
|
||||
|
||||
request_activity_grace(status_callback, my_worst_case_seconds)
|
||||
try:
|
||||
...one long blocking call...
|
||||
finally:
|
||||
release_activity_grace(status_callback)
|
||||
|
||||
The grace is a single absolute deadline. It is never extended, so the operation still dies
|
||||
if it overruns its own declared budget - just at *its* bound rather than at a global 300s.
|
||||
|
||||
The signal rides on the existing `status_callback` channel using a sentinel status, which
|
||||
avoids threading a new parameter through every handler, post-processor and output module.
|
||||
`shelfmark.download.orchestrator`'s per-task `status_callback` closure intercepts the
|
||||
sentinel and never forwards it to `update_download_status`.
|
||||
|
||||
Adopters should be operations that yield to the gevent hub while blocking (`requests`,
|
||||
patched `subprocess`). An operation that blocks the hub outright - `shutil.copy2`, sqlite -
|
||||
will still be killed by the gunicorn worker timeout regardless of any grace, and must go
|
||||
through `shelfmark.download.fs.run_blocking_io` first.
|
||||
|
||||
Current adopters: `shelfmark.download.http.html_get_page` (protection bypass).
|
||||
Candidates: `download.clients.base_handler._wait_for_completed_path`, archive extraction in
|
||||
`download.postprocess.scan`, large-file copies in `download.outputs.folder`, email/BookLore
|
||||
uploads, and the Anna's Archive countdown in `release_sources.direct_download` (which today
|
||||
refreshes the stall clock on every tick of a loop that proves nothing about the remote).
|
||||
"""
|
||||
|
||||
from collections.abc import Callable
|
||||
|
||||
# Not a QueueStatus value, so `update_download_status` would reject it anyway; the
|
||||
# orchestrator's status_callback intercepts it before that point.
|
||||
ACTIVITY_GRACE_STATUS = "__activity_grace__"
|
||||
|
||||
StatusCallback = Callable[[str, str | None], None]
|
||||
|
||||
# A status_callback is caller-supplied and may raise; a failed liveness hint must never
|
||||
# break the operation it was protecting. Mirrors http._STATUS_CALLBACK_ERRORS.
|
||||
_CALLBACK_ERRORS = (AttributeError, KeyError, OSError, RuntimeError, TypeError, ValueError)
|
||||
|
||||
|
||||
def request_activity_grace(status_callback: StatusCallback | None, seconds: float) -> None:
|
||||
"""Ask the orchestrator to suppress stall detection for up to `seconds` from now."""
|
||||
_emit(status_callback, seconds)
|
||||
|
||||
|
||||
def release_activity_grace(status_callback: StatusCallback | None) -> None:
|
||||
"""Drop any outstanding grace and count now as activity."""
|
||||
_emit(status_callback, 0)
|
||||
|
||||
|
||||
def parse_activity_grace(status: str, message: str | None) -> float | None:
|
||||
"""Return the requested grace in seconds, or None if this is not a grace event.
|
||||
|
||||
Never raises: a malformed sentinel is treated as "not a grace event" so a bad emitter
|
||||
cannot take down the status pipeline.
|
||||
"""
|
||||
if status != ACTIVITY_GRACE_STATUS:
|
||||
return None
|
||||
try:
|
||||
return max(float(message or 0), 0.0)
|
||||
except TypeError, ValueError:
|
||||
return 0.0
|
||||
|
||||
|
||||
def _emit(status_callback: StatusCallback | None, seconds: float) -> None:
|
||||
if status_callback is None:
|
||||
return
|
||||
try:
|
||||
status_callback(ACTIVITY_GRACE_STATUS, str(float(seconds)))
|
||||
except _CALLBACK_ERRORS:
|
||||
return
|
||||
@@ -7,6 +7,7 @@ from pathlib import Path
|
||||
from typing import TYPE_CHECKING, cast
|
||||
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.utils import AUDIOBOOK_FORMATS
|
||||
from shelfmark.core.utils import is_audiobook as check_audiobook
|
||||
from shelfmark.download.fs import atomic_move
|
||||
from shelfmark.download.postprocess.policy import (
|
||||
@@ -98,7 +99,7 @@ ALL_EBOOK_EXTENSIONS = {
|
||||
}
|
||||
|
||||
# All known audio extensions (superset of what user might enable for audiobooks)
|
||||
ALL_AUDIO_EXTENSIONS = {".m4b", ".mp3", ".m4a", ".aac", ".flac", ".ogg", ".wma", ".wav", ".opus"}
|
||||
ALL_AUDIO_EXTENSIONS = {f".{fmt}" for fmt in AUDIOBOOK_FORMATS}
|
||||
|
||||
|
||||
def _filter_files(
|
||||
|
||||
@@ -325,6 +325,19 @@ class DownloadClient(ABC):
|
||||
|
||||
"""
|
||||
|
||||
def set_category(self, download_id: str, category: str) -> bool:
|
||||
"""Update a download's category or label when supported by the client.
|
||||
|
||||
Args:
|
||||
download_id: The client-specific download ID.
|
||||
category: Category or label to assign.
|
||||
|
||||
Returns:
|
||||
True if the category was updated, otherwise False.
|
||||
|
||||
"""
|
||||
return False
|
||||
|
||||
@abstractmethod
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Get the path where files were downloaded.
|
||||
@@ -359,10 +372,13 @@ class DownloadClient(ABC):
|
||||
|
||||
# Client registry: protocol -> list of client classes
|
||||
_CLIENTS: dict[str, list[type[DownloadClient]]] = {}
|
||||
ClientType = TypeVar("ClientType", bound=DownloadClient)
|
||||
_BUILTIN_CLIENT_MODULES = (
|
||||
"shelfmark.download.clients.alldebrid",
|
||||
"shelfmark.download.clients.deluge",
|
||||
"shelfmark.download.clients.nzbget",
|
||||
"shelfmark.download.clients.qbittorrent",
|
||||
"shelfmark.download.clients.realdebrid",
|
||||
"shelfmark.download.clients.rtorrent",
|
||||
"shelfmark.download.clients.sabnzbd",
|
||||
"shelfmark.download.clients.transmission",
|
||||
@@ -383,7 +399,7 @@ def _ensure_builtin_clients_registered() -> None:
|
||||
|
||||
def register_client(
|
||||
protocol: str,
|
||||
) -> Callable[[type[DownloadClient]], type[DownloadClient]]:
|
||||
) -> Callable[[type[ClientType]], type[ClientType]]:
|
||||
"""Register a download client for a protocol.
|
||||
|
||||
Multiple clients can be registered for the same protocol.
|
||||
@@ -399,7 +415,7 @@ def register_client(
|
||||
|
||||
"""
|
||||
|
||||
def decorator(cls: type[DownloadClient]) -> type[DownloadClient]:
|
||||
def decorator(cls: type[ClientType]) -> type[ClientType]:
|
||||
if protocol not in _CLIENTS:
|
||||
_CLIENTS[protocol] = []
|
||||
_CLIENTS[protocol].append(cls)
|
||||
|
||||
@@ -0,0 +1,681 @@
|
||||
"""AllDebrid debrid service client for Shelfmark.
|
||||
|
||||
Routes magnet links through the AllDebrid API (v4/v4.1) to download
|
||||
torrent content via AllDebrid's CDN infrastructure.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
import threading
|
||||
import time
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, ClassVar, NoReturn
|
||||
from urllib.parse import quote
|
||||
|
||||
import requests
|
||||
|
||||
from shelfmark.config.env import TMP_DIR
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.download.clients import (
|
||||
DownloadClient,
|
||||
DownloadState,
|
||||
DownloadStatus,
|
||||
register_client,
|
||||
)
|
||||
from shelfmark.download.clients._coercion import config_text
|
||||
from shelfmark.download.http import download_url
|
||||
from shelfmark.download.network import get_ssl_verify
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
_API_BASE = "https://api.alldebrid.com/v4"
|
||||
_AGENT = "shelfmark"
|
||||
|
||||
_ALLDEBRID_CLIENT_ERRORS = (
|
||||
AttributeError,
|
||||
OSError,
|
||||
requests.exceptions.RequestException,
|
||||
RuntimeError,
|
||||
TypeError,
|
||||
ValueError,
|
||||
)
|
||||
|
||||
# AllDebrid magnet status codes (from API v4.1 documentation).
|
||||
_STATUS_DOWNLOADING = frozenset({0, 1, 2, 3})
|
||||
_STATUS_READY = 4
|
||||
|
||||
# Timeouts and retry limits for API calls.
|
||||
_API_TIMEOUT = 30
|
||||
_STATUS_TIMEOUT = 15
|
||||
_DELAYED_POLL_INTERVAL = 5
|
||||
_DELAYED_POLL_MAX_ATTEMPTS = 12
|
||||
|
||||
# File extensions recognised as book or audiobook content.
|
||||
_BOOK_EXTENSIONS = (
|
||||
".aac",
|
||||
".azw",
|
||||
".azw3",
|
||||
".cbr",
|
||||
".cbz",
|
||||
".djvu",
|
||||
".doc",
|
||||
".docx",
|
||||
".epub",
|
||||
".fb2",
|
||||
".flac",
|
||||
".lit",
|
||||
".m4a",
|
||||
".m4b",
|
||||
".mobi",
|
||||
".mp3",
|
||||
".ogg",
|
||||
".opus",
|
||||
".pdf",
|
||||
".rtf",
|
||||
".txt",
|
||||
".wma",
|
||||
)
|
||||
|
||||
|
||||
def _flatten_magnet_files(
|
||||
entries: list[dict[str, Any]],
|
||||
prefix: str = "",
|
||||
) -> list[dict[str, Any]]:
|
||||
"""Flatten AllDebrid's nested file tree into a list of file dicts.
|
||||
|
||||
AllDebrid returns files with ``"n"`` (name), ``"s"`` (size),
|
||||
``"l"`` (link), and ``"e"`` (children) keys. Directories use
|
||||
``"e"`` to nest their contents.
|
||||
|
||||
Returns:
|
||||
List of ``{"filename": ..., "size": ..., "link": ...}`` dicts.
|
||||
|
||||
"""
|
||||
flat: list[dict[str, Any]] = []
|
||||
for entry in entries:
|
||||
name = entry.get("n", "")
|
||||
if "e" in entry:
|
||||
flat.extend(
|
||||
_flatten_magnet_files(entry["e"], prefix=f"{prefix}{name}/"),
|
||||
)
|
||||
elif entry.get("l"):
|
||||
flat.append(
|
||||
{
|
||||
"filename": f"{prefix}{name}",
|
||||
"size": entry.get("s", 0),
|
||||
"link": entry["l"],
|
||||
}
|
||||
)
|
||||
return flat
|
||||
|
||||
|
||||
def _raise_runtime_error(message: str) -> NoReturn:
|
||||
raise RuntimeError(message)
|
||||
|
||||
|
||||
@dataclass
|
||||
class _DownloadState:
|
||||
"""Internal mutable state for an in-progress AllDebrid download."""
|
||||
|
||||
magnet_id: str
|
||||
name: str
|
||||
target_dir: Path
|
||||
phase: str = "uploading"
|
||||
error_message: str | None = None
|
||||
progress: float = 0.0
|
||||
download_thread: threading.Thread | None = None
|
||||
lock: threading.Lock = field(default_factory=threading.Lock)
|
||||
|
||||
|
||||
@register_client("torrent")
|
||||
class AllDebridClient(DownloadClient):
|
||||
"""AllDebrid debrid service client.
|
||||
|
||||
Downloads torrent content by uploading magnet links to AllDebrid,
|
||||
waiting for the torrent to complete on their servers, then fetching
|
||||
the resulting files via direct HTTP download from AllDebrid's CDN.
|
||||
|
||||
API documentation: https://docs.alldebrid.com/
|
||||
"""
|
||||
|
||||
protocol = "torrent"
|
||||
name = "alldebrid"
|
||||
|
||||
_downloads: ClassVar[dict[str, _DownloadState]] = {}
|
||||
_downloads_lock = threading.Lock()
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._api_key = config_text(config.get("ALLDEBRID_API_KEY", ""))
|
||||
|
||||
def _auth_headers(self) -> dict[str, str]:
|
||||
"""Return Authorization header dict for API requests."""
|
||||
return {"Authorization": f"Bearer {self._api_key}"}
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# DownloadClient interface
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@staticmethod
|
||||
def is_configured() -> bool:
|
||||
"""Return True when AllDebrid is selected and an API key exists."""
|
||||
client = config_text(config.get("PROWLARR_TORRENT_CLIENT", ""))
|
||||
api_key = config_text(config.get("ALLDEBRID_API_KEY", ""))
|
||||
return client == "alldebrid" and bool(api_key)
|
||||
|
||||
def test_connection(self) -> tuple[bool, str]:
|
||||
"""Validate the API key and check Premium subscription status."""
|
||||
if not self._api_key:
|
||||
return False, "AllDebrid API Key is required"
|
||||
try:
|
||||
url = f"{_API_BASE}/user"
|
||||
resp = requests.get(
|
||||
url,
|
||||
headers=self._auth_headers(),
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
if data.get("status") != "success":
|
||||
err = data.get("error", {}).get("message", "API error")
|
||||
return False, f"AllDebrid error: {err}"
|
||||
user = data.get("data", {}).get("user", {})
|
||||
username = user.get("username", "Unknown")
|
||||
if not user.get("isPremium", False):
|
||||
return (
|
||||
False,
|
||||
f"AllDebrid user '{username}' does not have a Premium subscription",
|
||||
)
|
||||
except _ALLDEBRID_CLIENT_ERRORS as e:
|
||||
return False, f"Connection failed: {e}"
|
||||
else:
|
||||
return True, f"Connected to AllDebrid as '{username}' (Premium)"
|
||||
|
||||
def add_download(
|
||||
self,
|
||||
url: str,
|
||||
name: str,
|
||||
category: str | None = None,
|
||||
expected_hash: str | None = None,
|
||||
**kwargs: object,
|
||||
) -> str:
|
||||
"""Upload a magnet link to AllDebrid and return the magnet ID."""
|
||||
if not self._api_key:
|
||||
msg = "AllDebrid API key is not configured"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
magnet_link = url
|
||||
if not magnet_link.startswith("magnet:") and expected_hash:
|
||||
magnet_link = f"magnet:?xt=urn:btih:{expected_hash}"
|
||||
|
||||
api_url = f"{_API_BASE}/magnet/upload"
|
||||
try:
|
||||
resp = requests.post(
|
||||
api_url,
|
||||
headers=self._auth_headers(),
|
||||
data={"magnets[]": magnet_link},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(api_url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
if data.get("status") != "success":
|
||||
code = data.get("error", {}).get("code", "UNKNOWN")
|
||||
msg = f"AllDebrid upload failed: {code}"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
magnets = data.get("data", {}).get("magnets", [])
|
||||
if not magnets:
|
||||
msg = "No magnet returned from AllDebrid"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
info = magnets[0]
|
||||
if info.get("error"):
|
||||
code = info["error"].get("code", "UNKNOWN")
|
||||
msg = f"AllDebrid magnet error: {code}"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
magnet_id = str(info.get("id", ""))
|
||||
if not magnet_id:
|
||||
msg = "No magnet ID returned from AllDebrid"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
target_dir = TMP_DIR / f"alldebrid_{magnet_id}"
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
state = _DownloadState(
|
||||
magnet_id=magnet_id,
|
||||
name=name,
|
||||
target_dir=target_dir,
|
||||
phase="waiting_ad",
|
||||
)
|
||||
with self._downloads_lock:
|
||||
self._downloads[magnet_id] = state
|
||||
|
||||
logger.info(
|
||||
"Added torrent to AllDebrid: ID %s (%s)",
|
||||
magnet_id,
|
||||
name,
|
||||
)
|
||||
|
||||
except Exception:
|
||||
logger.exception("Failed to upload magnet to AllDebrid")
|
||||
raise
|
||||
|
||||
else:
|
||||
return magnet_id
|
||||
|
||||
def get_status(self, download_id: str) -> DownloadStatus:
|
||||
"""Poll AllDebrid for magnet status and drive the download."""
|
||||
state = self._ensure_state(download_id)
|
||||
|
||||
# Return cached terminal / in-flight states immediately.
|
||||
with state.lock:
|
||||
if state.phase == "error":
|
||||
return DownloadStatus.error(
|
||||
state.error_message or "AllDebrid error",
|
||||
)
|
||||
if state.phase == "complete":
|
||||
return DownloadStatus(
|
||||
progress=100.0,
|
||||
state=DownloadState.COMPLETE,
|
||||
message="Complete",
|
||||
complete=True,
|
||||
file_path=str(state.target_dir),
|
||||
)
|
||||
if state.phase == "downloading_http":
|
||||
return DownloadStatus(
|
||||
progress=state.progress,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message="Downloading files via HTTP...",
|
||||
complete=False,
|
||||
file_path=None,
|
||||
)
|
||||
|
||||
# Ask AllDebrid for the current magnet status.
|
||||
try:
|
||||
status_url = f"{_API_BASE.replace('/v4', '/v4.1')}/magnet/status"
|
||||
resp = requests.post(
|
||||
status_url,
|
||||
headers=self._auth_headers(),
|
||||
data={"id": download_id},
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(status_url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
if data.get("status") != "success":
|
||||
err = data.get("error", {}).get("message", "Status failed")
|
||||
return DownloadStatus.error(
|
||||
f"AllDebrid status error: {err}",
|
||||
)
|
||||
|
||||
mag = self._extract_magnet_info(data)
|
||||
return self._handle_magnet_status(mag, state)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(
|
||||
"Error checking AllDebrid status for %s",
|
||||
download_id,
|
||||
)
|
||||
return DownloadStatus.error(str(e))
|
||||
|
||||
def remove(
|
||||
self,
|
||||
download_id: str,
|
||||
*,
|
||||
delete_files: bool = False,
|
||||
) -> bool:
|
||||
"""Delete the magnet from AllDebrid and clean up local files."""
|
||||
try:
|
||||
url = f"{_API_BASE}/magnet/delete"
|
||||
requests.post(
|
||||
url,
|
||||
headers=self._auth_headers(),
|
||||
data={"id": download_id},
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
except _ALLDEBRID_CLIENT_ERRORS as e:
|
||||
logger.warning("Failed to delete magnet from AllDebrid: %s", e)
|
||||
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.pop(download_id, None)
|
||||
|
||||
if state and state.target_dir.exists():
|
||||
shutil.rmtree(state.target_dir, ignore_errors=True)
|
||||
return True
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Return the local directory containing downloaded files."""
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.get(download_id)
|
||||
if state and state.phase == "complete":
|
||||
return str(state.target_dir)
|
||||
target_dir = TMP_DIR / f"alldebrid_{download_id}"
|
||||
if target_dir.exists():
|
||||
return str(target_dir)
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Internal helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _ensure_state(self, download_id: str) -> _DownloadState:
|
||||
"""Get or create download state for the given magnet ID."""
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.get(download_id)
|
||||
if state:
|
||||
return state
|
||||
|
||||
target_dir = TMP_DIR / f"alldebrid_{download_id}"
|
||||
state = _DownloadState(
|
||||
magnet_id=download_id,
|
||||
name=f"Download {download_id}",
|
||||
target_dir=target_dir,
|
||||
phase="waiting_ad",
|
||||
)
|
||||
with self._downloads_lock:
|
||||
self._downloads[download_id] = state
|
||||
return state
|
||||
|
||||
@staticmethod
|
||||
def _extract_magnet_info(data: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Extract magnet info dict from a status API response."""
|
||||
mag_data = data.get("data", {}).get("magnets", {})
|
||||
if isinstance(mag_data, list) and mag_data:
|
||||
return mag_data[0]
|
||||
if isinstance(mag_data, dict):
|
||||
return mag_data
|
||||
return {}
|
||||
|
||||
def _handle_magnet_status(
|
||||
self,
|
||||
mag: dict[str, Any],
|
||||
state: _DownloadState,
|
||||
) -> DownloadStatus:
|
||||
"""Map AllDebrid magnet status to a DownloadStatus."""
|
||||
status_code = mag.get("statusCode")
|
||||
|
||||
if status_code in _STATUS_DOWNLOADING:
|
||||
size = mag.get("size", 0)
|
||||
downloaded = mag.get("downloaded", 0)
|
||||
pct = (downloaded / size * 100.0) if size > 0 else 0.0
|
||||
return DownloadStatus(
|
||||
progress=pct * 0.5,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message=(f"AllDebrid downloading torrent ({mag.get('filename', state.name)})"),
|
||||
complete=False,
|
||||
file_path=None,
|
||||
download_speed=mag.get("downloadSpeed", 0),
|
||||
)
|
||||
|
||||
if status_code == _STATUS_READY or mag.get("ready", False):
|
||||
self._maybe_start_download_thread(state)
|
||||
return DownloadStatus(
|
||||
progress=50.0,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message="AllDebrid ready, retrieving files...",
|
||||
complete=False,
|
||||
file_path=None,
|
||||
)
|
||||
|
||||
# Terminal error from AllDebrid.
|
||||
error_txt = mag.get("error", {}).get("message") or f"AllDebrid status code {status_code}"
|
||||
with state.lock:
|
||||
state.phase = "error"
|
||||
state.error_message = error_txt
|
||||
return DownloadStatus.error(error_txt)
|
||||
|
||||
def _maybe_start_download_thread(self, state: _DownloadState) -> None:
|
||||
"""Spawn a background thread to unlock and download files."""
|
||||
with state.lock:
|
||||
already_running = state.phase in (
|
||||
"unlocking",
|
||||
"downloading_http",
|
||||
"complete",
|
||||
)
|
||||
thread_alive = state.download_thread is not None and state.download_thread.is_alive()
|
||||
if already_running or thread_alive:
|
||||
return
|
||||
state.phase = "unlocking"
|
||||
t = threading.Thread(
|
||||
target=self._process_and_download,
|
||||
args=(state,),
|
||||
daemon=True,
|
||||
)
|
||||
state.download_thread = t
|
||||
t.start()
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Link unlocking
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _unlock_file_link(self, link: str) -> str:
|
||||
"""Resolve an AllDebrid file link to a direct CDN download URL.
|
||||
|
||||
AllDebrid's ``/v4/magnet/files`` endpoint returns virtual links
|
||||
(``alldebrid.com/f/...``) that must be converted to direct CDN
|
||||
URLs via ``/v4/link/unlock``.
|
||||
|
||||
Strategy:
|
||||
1. If the link is already a CDN URL (``/dl/``), return it.
|
||||
2. ``POST /v4/link/unlock`` with Bearer auth (primary).
|
||||
3. ``GET /v4/link/unlock`` with query parameters (fallback).
|
||||
4. Append ``apikey=`` to ``alldebrid.com/f/`` links
|
||||
(last-resort fallback for ghost-cached torrents).
|
||||
|
||||
"""
|
||||
# 1. Already a direct CDN link.
|
||||
if "/dl/" in link:
|
||||
return link
|
||||
|
||||
headers = self._auth_headers()
|
||||
unlock_url = f"{_API_BASE}/link/unlock"
|
||||
err_msg = "Unknown unlock error"
|
||||
|
||||
# 2. POST unlock (primary method).
|
||||
try:
|
||||
resp = requests.post(
|
||||
unlock_url,
|
||||
headers=headers,
|
||||
data={"link": link},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(unlock_url),
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
body = resp.json()
|
||||
if body.get("status") == "success":
|
||||
direct = self._resolve_unlock_data(
|
||||
body.get("data", {}),
|
||||
headers,
|
||||
)
|
||||
if direct:
|
||||
return direct
|
||||
err_msg = body.get("error", {}).get(
|
||||
"message",
|
||||
"Unlock failed",
|
||||
)
|
||||
except _ALLDEBRID_CLIENT_ERRORS as e:
|
||||
logger.debug("POST unlock exception: %s", e)
|
||||
|
||||
# 3. GET unlock fallback with URL-encoded link.
|
||||
try:
|
||||
encoded = quote(link, safe="")
|
||||
get_url = (
|
||||
f"{_API_BASE}/link/unlock?agent={_AGENT}&apikey={self._api_key}&link={encoded}"
|
||||
)
|
||||
resp = requests.get(
|
||||
get_url,
|
||||
headers=headers,
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(get_url),
|
||||
)
|
||||
if resp.status_code == 200:
|
||||
body = resp.json()
|
||||
if body.get("status") == "success":
|
||||
direct = body.get("data", {}).get("link")
|
||||
if direct:
|
||||
return direct
|
||||
err_msg = body.get("error", {}).get("message", err_msg)
|
||||
except _ALLDEBRID_CLIENT_ERRORS as e:
|
||||
logger.debug("GET unlock exception: %s", e)
|
||||
|
||||
# 4. Last-resort: append apikey to alldebrid.com/f/ links.
|
||||
if "alldebrid.com/f/" in link:
|
||||
logger.info(
|
||||
"Using apikey fallback for AllDebrid file link: %s",
|
||||
link,
|
||||
)
|
||||
if "apikey=" not in link:
|
||||
sep = "&" if "?" in link else "?"
|
||||
return f"{link}{sep}apikey={self._api_key}"
|
||||
return link
|
||||
|
||||
logger.error(
|
||||
"AllDebrid unlock failed for '%s': %s",
|
||||
link,
|
||||
err_msg,
|
||||
)
|
||||
msg = f"AllDebrid unlock failed: {err_msg}"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
def _resolve_unlock_data(
|
||||
self,
|
||||
data: dict[str, Any],
|
||||
headers: dict[str, str],
|
||||
) -> str | None:
|
||||
"""Extract the direct link from unlock response data.
|
||||
|
||||
Handles the *delayed link* flow where AllDebrid returns a
|
||||
``delayed`` ID instead of an immediate download link.
|
||||
"""
|
||||
# Delayed link: poll until the CDN file is ready.
|
||||
if "delayed" in data:
|
||||
delayed_id = data["delayed"]
|
||||
logger.info(
|
||||
"AllDebrid link delayed (ID %s), polling...",
|
||||
delayed_id,
|
||||
)
|
||||
delayed_url = f"{_API_BASE}/link/delayed"
|
||||
for _ in range(_DELAYED_POLL_MAX_ATTEMPTS):
|
||||
time.sleep(_DELAYED_POLL_INTERVAL)
|
||||
try:
|
||||
resp = requests.post(
|
||||
delayed_url,
|
||||
headers=headers,
|
||||
data={"id": delayed_id},
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(delayed_url),
|
||||
)
|
||||
if resp.status_code != 200:
|
||||
continue
|
||||
body = resp.json()
|
||||
d = body.get("data", {})
|
||||
if body.get("status") == "success" and d.get("status") == 2 and d.get("link"):
|
||||
return d["link"]
|
||||
except _ALLDEBRID_CLIENT_ERRORS as e:
|
||||
logger.debug("Delayed poll exception: %s", e)
|
||||
|
||||
return data.get("link")
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# File download pipeline
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _process_and_download(self, state: _DownloadState) -> None:
|
||||
"""Fetch the file list, unlock links, and download via HTTP.
|
||||
|
||||
Runs in a background thread spawned by ``_maybe_start_download_thread``.
|
||||
"""
|
||||
try:
|
||||
files = self._fetch_file_list(state.magnet_id)
|
||||
relevant = [f for f in files if f["filename"].lower().endswith(_BOOK_EXTENSIONS)]
|
||||
if not relevant:
|
||||
relevant = files
|
||||
|
||||
with state.lock:
|
||||
state.phase = "downloading_http"
|
||||
|
||||
total = len(relevant)
|
||||
for idx, file_info in enumerate(relevant):
|
||||
direct_link = self._unlock_file_link(file_info["link"])
|
||||
|
||||
rel_path = Path(file_info["filename"])
|
||||
dest = state.target_dir / rel_path
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
logger.info(
|
||||
"Downloading AllDebrid file %d/%d: %s",
|
||||
idx + 1,
|
||||
total,
|
||||
rel_path,
|
||||
)
|
||||
|
||||
buf = download_url(
|
||||
direct_link,
|
||||
referer="https://alldebrid.com/",
|
||||
)
|
||||
if not buf:
|
||||
msg = f"Failed to download from {direct_link}"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
with dest.open("wb") as fh:
|
||||
fh.write(buf.getvalue())
|
||||
|
||||
with state.lock:
|
||||
state.progress = 50.0 + (idx + 1) / total * 50.0
|
||||
|
||||
with state.lock:
|
||||
state.phase = "complete"
|
||||
state.progress = 100.0
|
||||
|
||||
logger.info(
|
||||
"AllDebrid download complete for ID %s at %s",
|
||||
state.magnet_id,
|
||||
state.target_dir,
|
||||
)
|
||||
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Error in AllDebrid download for ID %s",
|
||||
state.magnet_id,
|
||||
)
|
||||
with state.lock:
|
||||
state.phase = "error"
|
||||
state.error_message = str(
|
||||
state.error_message or "Download failed",
|
||||
)
|
||||
|
||||
def _fetch_file_list(
|
||||
self,
|
||||
magnet_id: str,
|
||||
) -> list[dict[str, Any]]:
|
||||
"""Retrieve and flatten the file tree for a magnet."""
|
||||
url = f"{_API_BASE}/magnet/files"
|
||||
resp = requests.post(
|
||||
url,
|
||||
headers=self._auth_headers(),
|
||||
data={"id[]": magnet_id},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
if data.get("status") != "success":
|
||||
msg = f"Failed to list magnet files: {data.get('error')}"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
magnets = data.get("data", {}).get("magnets", [])
|
||||
if not magnets:
|
||||
msg = "No magnet files returned"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
files = _flatten_magnet_files(magnets[0].get("files", []))
|
||||
if not files:
|
||||
msg = "No files found in torrent"
|
||||
raise RuntimeError(msg)
|
||||
return files
|
||||
@@ -3,6 +3,7 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import errno
|
||||
import math
|
||||
import shutil
|
||||
import time
|
||||
from abc import ABC, abstractmethod
|
||||
@@ -55,6 +56,19 @@ SECONDS_PER_HOUR = 3600
|
||||
# How long to wait for completed files to appear (seconds)
|
||||
COMPLETED_PATH_RETRY_INTERVAL = 5
|
||||
COMPLETED_PATH_MAX_ATTEMPTS = 12 # 12 attempts * 5s = 60s grace period
|
||||
COMPLETED_PATH_TIMEOUT_SETTING = "DOWNLOAD_CLIENT_COMPLETED_PATH_TIMEOUT"
|
||||
COMPLETED_PATH_TIMEOUT_MAX_SECONDS = 3600
|
||||
_RETRYABLE_COMPLETED_PATH_ERRNOS = frozenset(
|
||||
code
|
||||
for code in (
|
||||
errno.ENOENT,
|
||||
getattr(errno, "ESTALE", None),
|
||||
getattr(errno, "EAGAIN", None),
|
||||
getattr(errno, "EBUSY", None),
|
||||
getattr(errno, "ETIMEDOUT", None),
|
||||
)
|
||||
if code is not None
|
||||
)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
@@ -69,6 +83,39 @@ class DownloadRequest:
|
||||
ratio_limit: float | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class _CompletedPathResolution:
|
||||
path: Path | None
|
||||
error: str | None
|
||||
retryable: bool
|
||||
|
||||
|
||||
def _coerce_completed_path_timeout_seconds(value: object, default: float) -> float:
|
||||
if isinstance(value, bool) or value is None:
|
||||
return default
|
||||
if isinstance(value, (int, float)):
|
||||
parsed = float(value)
|
||||
elif isinstance(value, str):
|
||||
try:
|
||||
parsed = float(value.strip())
|
||||
except ValueError:
|
||||
return default
|
||||
else:
|
||||
return default
|
||||
|
||||
if not math.isfinite(parsed) or parsed < 0:
|
||||
return default
|
||||
return min(parsed, float(COMPLETED_PATH_TIMEOUT_MAX_SECONDS))
|
||||
|
||||
|
||||
def _is_retryable_completed_path_probe(error: OSError | None) -> bool:
|
||||
return error is not None and error.errno in _RETRYABLE_COMPLETED_PATH_ERRNOS
|
||||
|
||||
|
||||
def _path_needs_mapping(path: str) -> bool:
|
||||
return (len(path) >= WINDOWS_DRIVE_PREFIX_LENGTH and path[1] == ":") or "\\" in path
|
||||
|
||||
|
||||
def _diagnose_path_issue(path: str) -> str:
|
||||
"""Analyze a path and return diagnostic hints for common issues.
|
||||
|
||||
@@ -167,6 +214,23 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
"""Maximum attempts when waiting for completed files."""
|
||||
return COMPLETED_PATH_MAX_ATTEMPTS
|
||||
|
||||
def _completed_path_timeout_seconds(self) -> float:
|
||||
"""Total time to wait for completed files to appear on disk."""
|
||||
fallback = self._completed_path_retry_interval() * self._completed_path_max_attempts()
|
||||
configured = config.get(COMPLETED_PATH_TIMEOUT_SETTING, fallback)
|
||||
return _coerce_completed_path_timeout_seconds(configured, fallback)
|
||||
|
||||
def _refresh_download_request_after_add_failure(
|
||||
self,
|
||||
*,
|
||||
task: DownloadTask,
|
||||
request: DownloadRequest,
|
||||
error: Exception,
|
||||
status_callback: Callable[[str, str | None], None],
|
||||
) -> DownloadRequest | None:
|
||||
"""Give source handlers one chance to refresh stale resolved download data."""
|
||||
return None
|
||||
|
||||
def _get_category_for_task(self, client: DownloadClient, task: DownloadTask) -> str | None:
|
||||
"""Get audiobook category if configured and applicable, else None for default."""
|
||||
if not is_audiobook(task.content_type):
|
||||
@@ -220,17 +284,47 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
)
|
||||
|
||||
elif protocol == "torrent":
|
||||
if config.get("PROWLARR_TORRENT_ACTION", "keep") != "remove":
|
||||
torrent_action = config.get("PROWLARR_TORRENT_ACTION", "keep")
|
||||
if torrent_action == "remove":
|
||||
try:
|
||||
client.remove(download_id, delete_files=False)
|
||||
except _CLIENT_CLEANUP_ERRORS as e:
|
||||
logger.warning(
|
||||
"Failed to remove torrent %s from %s: %s",
|
||||
download_id,
|
||||
getattr(client, "name", "client"),
|
||||
e,
|
||||
)
|
||||
return
|
||||
|
||||
if torrent_action != "change_category":
|
||||
return
|
||||
|
||||
post_import_category = normalize_optional_text(
|
||||
config.get("PROWLARR_TORRENT_POST_IMPORT_CATEGORY", "")
|
||||
)
|
||||
if post_import_category is None:
|
||||
return
|
||||
|
||||
try:
|
||||
client.remove(download_id, delete_files=False)
|
||||
category_updated = client.set_category(download_id, post_import_category)
|
||||
except _CLIENT_CLEANUP_ERRORS as e:
|
||||
logger.warning(
|
||||
"Failed to remove torrent %s from %s: %s",
|
||||
"Failed to set post-import category for torrent %s in %s: %s",
|
||||
download_id,
|
||||
getattr(client, "name", "client"),
|
||||
e,
|
||||
)
|
||||
return
|
||||
|
||||
if not category_updated:
|
||||
# Clients that cannot label torrents (debrid services) return False here,
|
||||
# and the ones that can already log the specific failure themselves.
|
||||
logger.debug(
|
||||
"Post-import category not applied to torrent %s in %s",
|
||||
download_id,
|
||||
getattr(client, "name", "client"),
|
||||
)
|
||||
|
||||
def _remove_usenet_download(
|
||||
self,
|
||||
@@ -387,6 +481,21 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
log_details: bool,
|
||||
) -> tuple[Path | None, str | None]:
|
||||
"""Resolve and validate the completed download path once."""
|
||||
result = self._resolve_download_path_once_detailed(
|
||||
client,
|
||||
download_id,
|
||||
log_details=log_details,
|
||||
)
|
||||
return result.path, result.error
|
||||
|
||||
def _resolve_download_path_once_detailed(
|
||||
self,
|
||||
client: DownloadClient,
|
||||
download_id: str,
|
||||
*,
|
||||
log_details: bool,
|
||||
) -> _CompletedPathResolution:
|
||||
"""Resolve and validate a completed path, including retryability."""
|
||||
try:
|
||||
raw_path = client.get_download_path(download_id)
|
||||
except Exception as e:
|
||||
@@ -402,7 +511,7 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
logger.debug(
|
||||
"Failed to resolve download path for %s %s: %s", client.name, download_id, e
|
||||
)
|
||||
return None, message
|
||||
return _CompletedPathResolution(None, message, retryable=False)
|
||||
|
||||
if not raw_path:
|
||||
message = (
|
||||
@@ -417,7 +526,7 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
logger.debug(
|
||||
"Download client returned empty path for %s %s", client.name, download_id
|
||||
)
|
||||
return None, message
|
||||
return _CompletedPathResolution(None, message, retryable=False)
|
||||
|
||||
from shelfmark.core.path_mappings import (
|
||||
get_client_host_identifier,
|
||||
@@ -457,7 +566,7 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
logger.error(failure_log, *failure_args)
|
||||
else:
|
||||
logger.debug(failure_log, *failure_args)
|
||||
return None, message
|
||||
return _CompletedPathResolution(None, message, retryable=False)
|
||||
|
||||
remapped_exists, remapped_error = _probe_completed_path(remapped)
|
||||
|
||||
@@ -480,7 +589,7 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
source_path_obj,
|
||||
remapped,
|
||||
)
|
||||
return remapped, None
|
||||
return _CompletedPathResolution(remapped, None, retryable=False)
|
||||
|
||||
message = (
|
||||
f"Remapped path '{remapped}' does not exist. "
|
||||
@@ -499,7 +608,11 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
logger.error(failure_log, *failure_args)
|
||||
else:
|
||||
logger.debug(failure_log, *failure_args)
|
||||
return None, message
|
||||
return _CompletedPathResolution(
|
||||
None,
|
||||
message,
|
||||
retryable=_is_retryable_completed_path_probe(remapped_error),
|
||||
)
|
||||
|
||||
source_exists, source_error = _probe_completed_path(source_path_obj)
|
||||
|
||||
@@ -522,7 +635,7 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
download_id,
|
||||
source_path_obj,
|
||||
)
|
||||
return source_path_obj, None
|
||||
return _CompletedPathResolution(source_path_obj, None, retryable=False)
|
||||
|
||||
hint = _diagnose_path_issue(raw_path)
|
||||
if mappings:
|
||||
@@ -555,7 +668,12 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
logger.error(failure_log, *failure_args)
|
||||
else:
|
||||
logger.debug(failure_log, *failure_args)
|
||||
return None, message
|
||||
return _CompletedPathResolution(
|
||||
None,
|
||||
message,
|
||||
retryable=not _path_needs_mapping(raw_path)
|
||||
and _is_retryable_completed_path_probe(source_error),
|
||||
)
|
||||
|
||||
def _wait_for_completed_path(
|
||||
self,
|
||||
@@ -567,23 +685,37 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
) -> tuple[Path | None, str | None]:
|
||||
"""Wait briefly for completed files to appear on disk."""
|
||||
last_error: str | None = None
|
||||
max_attempts = self._completed_path_max_attempts()
|
||||
retry_interval = self._completed_path_retry_interval()
|
||||
timeout_seconds = self._completed_path_timeout_seconds()
|
||||
if retry_interval <= 0 or timeout_seconds <= 0:
|
||||
max_attempts = 1
|
||||
else:
|
||||
max_attempts = int(math.ceil(timeout_seconds / retry_interval)) + 1
|
||||
|
||||
for attempt in range(1, max_attempts + 1):
|
||||
if cancel_flag and cancel_flag.is_set():
|
||||
return None, last_error
|
||||
|
||||
log_details = attempt == max_attempts
|
||||
resolved_path, error = self._resolve_download_path_once(
|
||||
result = self._resolve_download_path_once_detailed(
|
||||
client,
|
||||
download_id,
|
||||
log_details=log_details,
|
||||
)
|
||||
if resolved_path:
|
||||
return resolved_path, None
|
||||
if result.path:
|
||||
return result.path, None
|
||||
|
||||
last_error = error
|
||||
last_error = result.error
|
||||
|
||||
if not result.retryable:
|
||||
if not log_details:
|
||||
logger.error(
|
||||
"Completed path resolution is not retryable for %s (%s): %s",
|
||||
client.name,
|
||||
download_id,
|
||||
last_error,
|
||||
)
|
||||
return None, last_error
|
||||
|
||||
if attempt < max_attempts:
|
||||
status_callback("locating", "Waiting for completed files...")
|
||||
@@ -700,20 +832,41 @@ class ExternalClientHandler(DownloadHandler, ABC):
|
||||
status_callback("downloading", "Resuming existing download")
|
||||
else:
|
||||
# No existing download - add new
|
||||
status_callback("resolving", f"Sending to {client.name}")
|
||||
try:
|
||||
download_id = client.add_download(
|
||||
url=request.url,
|
||||
name=request.release_name,
|
||||
category=category,
|
||||
expected_hash=request.expected_hash,
|
||||
seeding_time_limit=request.seeding_time_limit,
|
||||
ratio_limit=request.ratio_limit,
|
||||
)
|
||||
except Exception as e:
|
||||
logger.exception("Failed to add to %s", client.name)
|
||||
status_callback("error", f"Failed to add to {client.name}: {e}")
|
||||
return None
|
||||
refresh_attempted = False
|
||||
while True:
|
||||
status_callback("resolving", f"Sending to {client.name}")
|
||||
try:
|
||||
download_id = client.add_download(
|
||||
url=request.url,
|
||||
name=request.release_name,
|
||||
category=category,
|
||||
expected_hash=request.expected_hash,
|
||||
seeding_time_limit=request.seeding_time_limit,
|
||||
ratio_limit=request.ratio_limit,
|
||||
# rTorrent has no category concept, so its audiobook label
|
||||
# can only be chosen from the content type (#1235).
|
||||
content_type=task.content_type,
|
||||
)
|
||||
except Exception as e:
|
||||
if not refresh_attempted:
|
||||
refresh_attempted = True
|
||||
refreshed_request = self._refresh_download_request_after_add_failure(
|
||||
task=task,
|
||||
request=request,
|
||||
error=e,
|
||||
status_callback=status_callback,
|
||||
)
|
||||
if (
|
||||
refreshed_request is not None
|
||||
and refreshed_request.protocol == request.protocol
|
||||
):
|
||||
request = refreshed_request
|
||||
continue
|
||||
|
||||
logger.exception("Failed to add to %s", client.name)
|
||||
status_callback("error", f"Failed to add to {client.name}: {e}")
|
||||
return None
|
||||
break
|
||||
|
||||
logger.info(
|
||||
"Added to %s: %s for '%s'", client.name, download_id, request.release_name
|
||||
|
||||
@@ -227,10 +227,10 @@ class DelugeClient(DownloadClient):
|
||||
|
||||
return self._rpc_call("daemon.info")
|
||||
|
||||
def _try_set_label(self, torrent_id: str, label: str) -> None:
|
||||
def _try_set_label(self, torrent_id: str, label: str) -> bool:
|
||||
"""Best-effort label assignment (requires Deluge Label plugin)."""
|
||||
if not label:
|
||||
return
|
||||
return False
|
||||
|
||||
try:
|
||||
# label.add will error if the plugin is unavailable or the label exists.
|
||||
@@ -240,6 +240,9 @@ class DelugeClient(DownloadClient):
|
||||
self._rpc_call("label.set_torrent", torrent_id, label)
|
||||
except _DELUGE_CLIENT_ERRORS as e:
|
||||
logger.debug("Could not set Deluge label '%s' for %s: %s", label, torrent_id, e)
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def is_configured() -> bool:
|
||||
@@ -277,7 +280,10 @@ class DelugeClient(DownloadClient):
|
||||
|
||||
torrent_info = extract_torrent_info(url, expected_hash=expected_hash)
|
||||
if not torrent_info.is_magnet and not torrent_info.torrent_data:
|
||||
_raise_runtime_error("Failed to fetch torrent file")
|
||||
message = "Failed to fetch torrent file"
|
||||
if torrent_info.fetch_error:
|
||||
message = f"{message}: {torrent_info.fetch_error}"
|
||||
_raise_runtime_error(message)
|
||||
|
||||
options: dict[str, Any] = {}
|
||||
if self._download_dir:
|
||||
@@ -419,6 +425,15 @@ class DelugeClient(DownloadClient):
|
||||
else:
|
||||
return False
|
||||
|
||||
def set_category(self, download_id: str, category: str) -> bool:
|
||||
"""Assign a label to a torrent using Deluge's Label plugin."""
|
||||
try:
|
||||
self._ensure_connected()
|
||||
return self._try_set_label(download_id, category)
|
||||
except _DELUGE_CLIENT_ERRORS as e:
|
||||
self._log_error("set_category", e)
|
||||
return False
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Return the resolved download path for a Deluge torrent."""
|
||||
try:
|
||||
|
||||
@@ -44,6 +44,7 @@ _HASH_LENGTH_40 = 40
|
||||
_HASH_LENGTH_ED2K = 32
|
||||
_HTTP_STATUS_FORBIDDEN = HTTPStatus.FORBIDDEN
|
||||
_HTTP_STATUS_NOT_FOUND = HTTPStatus.NOT_FOUND
|
||||
_METADATA_DOWNLOAD_STATES = {"forcedMetaDL", "metaDL"}
|
||||
_ONE_WEEK_IN_SECONDS = 604800
|
||||
|
||||
|
||||
@@ -94,6 +95,25 @@ def _hashes_match(hash1: str, hash2: str) -> bool:
|
||||
return False
|
||||
|
||||
|
||||
def _torrent_matches_download_id(torrent: object, download_id: str) -> bool:
|
||||
"""Match an ID against every identity qBittorrent exposes.
|
||||
|
||||
For hybrid torrents, qBittorrent's primary `hash` can change from the v1
|
||||
hash to the truncated v2 hash after metadata resolution. The full
|
||||
`infohash_v1` and `infohash_v2` fields preserve the torrent's identities.
|
||||
"""
|
||||
identifiers = (
|
||||
getattr(torrent, "hash", None),
|
||||
getattr(torrent, "infohash_v1", None),
|
||||
getattr(torrent, "infohash_v2", None),
|
||||
)
|
||||
|
||||
return any(
|
||||
isinstance(identifier, str) and identifier and _hashes_match(identifier, download_id)
|
||||
for identifier in identifiers
|
||||
)
|
||||
|
||||
|
||||
def _raise_runtime_error(message: str) -> NoReturn:
|
||||
raise RuntimeError(message)
|
||||
|
||||
@@ -166,63 +186,6 @@ def _build_qbittorrent_child_path(base_path: object, child_path: object) -> str
|
||||
class QBittorrentClient(DownloadClient):
|
||||
"""qBittorrent download client."""
|
||||
|
||||
def _is_torrent_loaded(self, torrent_hash: str) -> tuple[bool, str | None]:
|
||||
"""Check whether qBittorrent has registered a torrent yet.
|
||||
|
||||
Uses `/api/v2/torrents/properties?hash=<hash>`.
|
||||
|
||||
Returns:
|
||||
(loaded, error_message)
|
||||
|
||||
Notes:
|
||||
A false result with no error means "not loaded yet".
|
||||
|
||||
"""
|
||||
url = f"{self._base_url}/api/v2/torrents/properties"
|
||||
params = {"hash": torrent_hash}
|
||||
|
||||
try:
|
||||
self._client.auth_log_in()
|
||||
response = self._client._session.get(url, params=params, timeout=10)
|
||||
|
||||
# Re-authenticate and retry once on 403
|
||||
if response.status_code == _HTTP_STATUS_FORBIDDEN:
|
||||
logger.debug(
|
||||
"qBittorrent returned 403 for properties; re-authenticating and retrying"
|
||||
)
|
||||
self._client.auth_log_in()
|
||||
response = self._client._session.get(url, params=params, timeout=10)
|
||||
|
||||
if response.status_code == _HTTP_STATUS_FORBIDDEN:
|
||||
return False, "qBittorrent authentication failed (HTTP 403)"
|
||||
|
||||
# qBittorrent returns 404/409-ish responses depending on version when missing.
|
||||
if response.status_code == _HTTP_STATUS_NOT_FOUND:
|
||||
return False, None
|
||||
|
||||
response.raise_for_status()
|
||||
except requests.exceptions.HTTPError as e:
|
||||
status = getattr(getattr(e, "response", None), "status_code", None)
|
||||
if status == _HTTP_STATUS_NOT_FOUND:
|
||||
return False, None
|
||||
if status:
|
||||
return False, f"qBittorrent API request failed (HTTP {status})"
|
||||
return False, "qBittorrent API request failed"
|
||||
except requests.exceptions.ConnectionError:
|
||||
return False, f"Cannot connect to qBittorrent at {self._base_url}"
|
||||
except requests.exceptions.Timeout:
|
||||
return False, f"qBittorrent request timed out at {self._base_url}"
|
||||
except requests.exceptions.InvalidSchema:
|
||||
return (
|
||||
False,
|
||||
"qBittorrent URL is invalid (missing http:// or https://). "
|
||||
f"Configured: {self._base_url}",
|
||||
)
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
return False, f"qBittorrent API error: {type(e).__name__}: {e}"
|
||||
else:
|
||||
return True, None
|
||||
|
||||
protocol = "torrent"
|
||||
name = "qbittorrent"
|
||||
|
||||
@@ -244,6 +207,7 @@ class QBittorrentClient(DownloadClient):
|
||||
|
||||
username = config_text(config.get("QBITTORRENT_USERNAME", ""))
|
||||
password = config_text(config.get("QBITTORRENT_PASSWORD", ""))
|
||||
self._api_key = config_text(config.get("QBITTORRENT_API_KEY", ""))
|
||||
|
||||
# qbittorrent-api accepts either a full URL or host:port; prefer the normalized URL
|
||||
# for consistency.
|
||||
@@ -251,43 +215,40 @@ class QBittorrentClient(DownloadClient):
|
||||
host=self._base_url,
|
||||
username=username,
|
||||
password=password,
|
||||
api_key=self._api_key or None,
|
||||
VERIFY_WEBUI_CERTIFICATE=get_ssl_verify(self._base_url),
|
||||
)
|
||||
self._category = config_text(config.get("QBITTORRENT_CATEGORY", "books"))
|
||||
self._download_dir = config_text(config.get("QBITTORRENT_DOWNLOAD_DIR", ""))
|
||||
self._tags = _normalize_tags(config.get("QBITTORRENT_TAG", []))
|
||||
|
||||
def _get_torrents_info(
|
||||
self, torrent_hash: str | None = None
|
||||
) -> tuple[list[SimpleNamespace], str | None]:
|
||||
"""Get torrent info using GET.
|
||||
@property
|
||||
def _can_reauthenticate(self) -> bool:
|
||||
"""Whether a 403 is worth retrying; a bearer token cannot be refreshed like a session."""
|
||||
return not self._api_key
|
||||
|
||||
Behaviors:
|
||||
- Retry once on HTTP 403 by re-authenticating.
|
||||
- Keep "API/auth/connect" errors distinct from "torrent missing".
|
||||
- If a hash-specific query returns empty, fall back to listing by category
|
||||
and matching locally.
|
||||
|
||||
Returns:
|
||||
(torrents, error_message)
|
||||
def _ensure_authenticated(self) -> None:
|
||||
"""Authenticate the underlying HTTP session before it is used directly.
|
||||
|
||||
API keys (qBittorrent 5.2.0+) are sent as a bearer header on every request and
|
||||
have no login endpoint, so there is no session to establish up front.
|
||||
"""
|
||||
if self._api_key:
|
||||
return
|
||||
self._client.auth_log_in()
|
||||
|
||||
def _request_torrent_info_records(
|
||||
self, params: dict[str, str]
|
||||
) -> tuple[list[SimpleNamespace], str | None]:
|
||||
"""Request torrent info records from qBittorrent."""
|
||||
url = f"{self._base_url}/api/v2/torrents/info"
|
||||
|
||||
def do_request(params: dict[str, str]) -> requests.Response:
|
||||
# Ensure session is authenticated before using it directly
|
||||
self._client.auth_log_in()
|
||||
return self._client._session.get(url, params=params, timeout=10)
|
||||
|
||||
def parse_response(
|
||||
response: requests.Response,
|
||||
*,
|
||||
request_params: dict[str, str],
|
||||
) -> tuple[list[SimpleNamespace], str | None]:
|
||||
if response.status_code == _HTTP_STATUS_FORBIDDEN:
|
||||
try:
|
||||
self._ensure_authenticated()
|
||||
response = self._client._session.get(url, params=params, timeout=10)
|
||||
if response.status_code == _HTTP_STATUS_FORBIDDEN and self._can_reauthenticate:
|
||||
logger.debug("qBittorrent returned 403; re-authenticating and retrying")
|
||||
self._client.auth_log_in()
|
||||
response = self._client._session.get(url, params=request_params, timeout=10)
|
||||
self._ensure_authenticated()
|
||||
response = self._client._session.get(url, params=params, timeout=10)
|
||||
|
||||
if response.status_code == _HTTP_STATUS_FORBIDDEN:
|
||||
logger.warning("qBittorrent authentication failed (HTTP 403)")
|
||||
@@ -296,41 +257,6 @@ class QBittorrentClient(DownloadClient):
|
||||
response.raise_for_status()
|
||||
torrents = response.json()
|
||||
return [SimpleNamespace(**t) for t in torrents], None
|
||||
|
||||
try:
|
||||
primary_params: dict[str, str] = {}
|
||||
if torrent_hash:
|
||||
primary_params["hashes"] = torrent_hash
|
||||
|
||||
response = do_request(primary_params)
|
||||
torrents, error = parse_response(response, request_params=primary_params)
|
||||
if error:
|
||||
return [], error
|
||||
|
||||
if torrent_hash and not torrents:
|
||||
# Fallback 1: list by configured category
|
||||
category_params: dict[str, str] = {}
|
||||
if self._category:
|
||||
category_params["category"] = self._category
|
||||
|
||||
category_response = do_request(category_params)
|
||||
category_torrents, category_error = parse_response(
|
||||
category_response, request_params=category_params
|
||||
)
|
||||
if category_error:
|
||||
return [], category_error
|
||||
|
||||
if category_torrents:
|
||||
return category_torrents, None
|
||||
|
||||
# Fallback 2: list everything (handles per-task categories like audiobooks)
|
||||
all_response = do_request({})
|
||||
all_torrents, all_error = parse_response(all_response, request_params={})
|
||||
if all_error:
|
||||
return [], all_error
|
||||
|
||||
return all_torrents, None
|
||||
|
||||
except requests.exceptions.HTTPError as e:
|
||||
status = getattr(getattr(e, "response", None), "status_code", None)
|
||||
if status:
|
||||
@@ -355,8 +281,100 @@ class QBittorrentClient(DownloadClient):
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
logger.debug("Failed to get torrents info: %s", e)
|
||||
return [], f"qBittorrent API error: {type(e).__name__}: {e}"
|
||||
else:
|
||||
return torrents, None
|
||||
|
||||
def _get_torrent_info(self, download_id: str) -> tuple[SimpleNamespace | None, str | None]:
|
||||
"""Get one torrent by its current qBittorrent hash."""
|
||||
torrents, error = self._request_torrent_info_records({"hashes": download_id})
|
||||
if error or not torrents:
|
||||
return None, error
|
||||
return (
|
||||
next(
|
||||
(
|
||||
torrent
|
||||
for torrent in torrents
|
||||
if isinstance(getattr(torrent, "hash", None), str)
|
||||
and _hashes_match(torrent.hash, download_id)
|
||||
),
|
||||
None,
|
||||
),
|
||||
None,
|
||||
)
|
||||
|
||||
def _list_torrents_by_category(
|
||||
self, category: str | None
|
||||
) -> tuple[list[SimpleNamespace], str | None]:
|
||||
"""List torrent records in a category, or all records when unset."""
|
||||
params = {"category": category} if category else {}
|
||||
return self._request_torrent_info_records(params)
|
||||
|
||||
def _resolve_torrent(
|
||||
self, download_id: str, category: str | None = None
|
||||
) -> tuple[SimpleNamespace | None, str | None]:
|
||||
"""Resolve any known torrent identity to its current qBittorrent record."""
|
||||
torrent, error = self._get_torrent_info(download_id)
|
||||
if error or torrent:
|
||||
return torrent, error
|
||||
|
||||
categories = [candidate for candidate in (category, self._category) if candidate]
|
||||
for candidate in dict.fromkeys(categories):
|
||||
torrents, error = self._list_torrents_by_category(candidate)
|
||||
if error:
|
||||
return None, error
|
||||
torrent = next(
|
||||
(item for item in torrents if _torrent_matches_download_id(item, download_id)),
|
||||
None,
|
||||
)
|
||||
if torrent:
|
||||
return torrent, None
|
||||
|
||||
torrents, error = self._list_torrents_by_category(None)
|
||||
if error:
|
||||
return None, error
|
||||
return (
|
||||
next(
|
||||
(item for item in torrents if _torrent_matches_download_id(item, download_id)),
|
||||
None,
|
||||
),
|
||||
None,
|
||||
)
|
||||
|
||||
def _list_category_hashes(self, category: str | None) -> set[str] | None:
|
||||
"""Snapshot the hashes qBittorrent currently reports for a category."""
|
||||
torrents, error = self._list_torrents_by_category(category)
|
||||
if error:
|
||||
logger.debug("Could not snapshot qBittorrent torrents: %s", error)
|
||||
return None
|
||||
return {str(torrent.hash).lower() for torrent in torrents if getattr(torrent, "hash", None)}
|
||||
|
||||
def _discover_added_torrent_hash(
|
||||
self,
|
||||
name: str,
|
||||
category: str | None,
|
||||
known_hashes: set[str] | None,
|
||||
) -> str | None:
|
||||
"""Recover the hash of a torrent that was added without a known info_hash.
|
||||
|
||||
A `known_hashes` of None means the pre-add snapshot failed, so only a
|
||||
torrent matching the requested rename can identify the new arrival.
|
||||
"""
|
||||
for _ in range(20):
|
||||
torrents, error = self._list_torrents_by_category(category)
|
||||
if error:
|
||||
logger.debug("qBittorrent hash discovery: %s", error)
|
||||
else:
|
||||
new_torrents = [
|
||||
torrent
|
||||
for torrent in torrents
|
||||
if getattr(torrent, "hash", None)
|
||||
and (known_hashes is None or str(torrent.hash).lower() not in known_hashes)
|
||||
]
|
||||
for torrent in new_torrents:
|
||||
if getattr(torrent, "name", None) == name:
|
||||
return str(torrent.hash).lower()
|
||||
if known_hashes is not None and len(new_torrents) == 1:
|
||||
return str(new_torrents[0].hash).lower()
|
||||
time.sleep(0.5)
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def is_configured() -> bool:
|
||||
@@ -368,7 +386,7 @@ class QBittorrentClient(DownloadClient):
|
||||
def test_connection(self) -> tuple[bool, str]:
|
||||
"""Test connection to qBittorrent."""
|
||||
try:
|
||||
self._client.auth_log_in()
|
||||
self._ensure_authenticated()
|
||||
api_version = self._client.app.web_api_version
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
return False, f"Connection failed: {e!s}"
|
||||
@@ -425,6 +443,10 @@ class QBittorrentClient(DownloadClient):
|
||||
expected_hash = torrent_info.info_hash
|
||||
torrent_data = torrent_info.torrent_data
|
||||
|
||||
known_hashes: set[str] | None = None
|
||||
if not expected_hash:
|
||||
known_hashes = self._list_category_hashes(category)
|
||||
|
||||
# Per-torrent seeding limits from indexer
|
||||
seeding_time_limit_value = kwargs.get("seeding_time_limit")
|
||||
seeding_time_limit = coerce_optional_int(seeding_time_limit_value)
|
||||
@@ -459,27 +481,36 @@ class QBittorrentClient(DownloadClient):
|
||||
result_text = _normalize_add_result(result)
|
||||
logger.debug("qBittorrent add result: %s", result_text)
|
||||
|
||||
if not expected_hash:
|
||||
_raise_runtime_error("Could not determine torrent hash from URL")
|
||||
|
||||
if _is_explicit_add_failure(result):
|
||||
_raise_runtime_error(f"Failed to add torrent: {result_text}")
|
||||
|
||||
# Some qBittorrent-compatible clients return HTTP 200 with an empty body
|
||||
# instead of qBittorrent's literal "Ok." response. Prefer verifying that
|
||||
# the torrent becomes visible over trusting the response body alone.
|
||||
for _ in range(10):
|
||||
loaded, error = self._is_torrent_loaded(expected_hash)
|
||||
if not expected_hash:
|
||||
# qBittorrent fetches .torrent URLs itself, so the add can succeed
|
||||
# even when no hash could be extracted up front. Recover it by
|
||||
# watching for the new torrent to appear.
|
||||
expected_hash = self._discover_added_torrent_hash(name, category, known_hashes)
|
||||
if not expected_hash:
|
||||
message = "Could not determine torrent hash from URL"
|
||||
if torrent_info.fetch_error:
|
||||
message = f"{message} (torrent file fetch failed: {torrent_info.fetch_error})"
|
||||
_raise_runtime_error(message)
|
||||
|
||||
# Wait until qBittorrent has resolved magnet metadata so the returned
|
||||
# hash is its stable primary torrent ID, which may differ from the v1 hash.
|
||||
for _ in range(20):
|
||||
torrent, error = self._resolve_torrent(expected_hash, category)
|
||||
if error:
|
||||
logger.debug("qBittorrent add_download: %s", error)
|
||||
if loaded:
|
||||
logger.info("Added torrent: %s", expected_hash)
|
||||
return expected_hash.lower()
|
||||
elif torrent and getattr(torrent, "state", None) not in _METADATA_DOWNLOAD_STATES:
|
||||
torrent_hash = getattr(torrent, "hash", None)
|
||||
if isinstance(torrent_hash, str) and torrent_hash:
|
||||
logger.info("Added torrent: %s", torrent_hash)
|
||||
return torrent_hash.lower()
|
||||
time.sleep(0.5)
|
||||
|
||||
logger.warning(
|
||||
"Torrent add was not confirmed within the visibility grace period (response=%s), returning expected hash",
|
||||
result_text,
|
||||
_raise_runtime_error(
|
||||
"Torrent metadata resolution was not confirmed within the visibility grace period "
|
||||
f"(response={result_text})"
|
||||
)
|
||||
except _QBITTORRENT_CLIENT_ERRORS:
|
||||
logger.exception("qBittorrent add failed")
|
||||
@@ -498,19 +529,9 @@ class QBittorrentClient(DownloadClient):
|
||||
|
||||
"""
|
||||
try:
|
||||
torrents, error = self._get_torrents_info(download_id)
|
||||
torrent, error = self._get_torrent_info(download_id)
|
||||
if error:
|
||||
return DownloadStatus.error(error)
|
||||
|
||||
torrent = next(
|
||||
(
|
||||
t
|
||||
for t in torrents
|
||||
if isinstance(getattr(t, "hash", None), str)
|
||||
and _hashes_match(t.hash, download_id)
|
||||
),
|
||||
None,
|
||||
)
|
||||
if not torrent:
|
||||
return DownloadStatus.error("Torrent not found in qBittorrent")
|
||||
|
||||
@@ -604,6 +625,26 @@ class QBittorrentClient(DownloadClient):
|
||||
else:
|
||||
return True
|
||||
|
||||
def set_category(self, download_id: str, category: str) -> bool:
|
||||
"""Assign a category to a torrent in qBittorrent."""
|
||||
try:
|
||||
try:
|
||||
self._client.torrents_create_category(name=category)
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
if "Conflict" not in type(e).__name__ and "409" not in str(e):
|
||||
logger.debug("Could not create category '%s': %s", category, e)
|
||||
|
||||
self._client.torrents_set_category(
|
||||
torrent_hashes=download_id,
|
||||
category=category,
|
||||
)
|
||||
logger.info("Set qBittorrent category for %s to '%s'", download_id, category)
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
self._log_error("set_category", e)
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Get the path where torrent files are located.
|
||||
|
||||
@@ -616,20 +657,10 @@ class QBittorrentClient(DownloadClient):
|
||||
- join `save_path` with the torrent's top-level directory
|
||||
"""
|
||||
try:
|
||||
torrents, error = self._get_torrents_info(download_id)
|
||||
torrent, error = self._get_torrent_info(download_id)
|
||||
if error:
|
||||
logger.debug("qBittorrent get_download_path: %s", error)
|
||||
return None
|
||||
|
||||
torrent = next(
|
||||
(
|
||||
t
|
||||
for t in torrents
|
||||
if isinstance(getattr(t, "hash", None), str)
|
||||
and _hashes_match(t.hash, download_id)
|
||||
),
|
||||
None,
|
||||
)
|
||||
if not torrent:
|
||||
return None
|
||||
|
||||
@@ -675,11 +706,11 @@ class QBittorrentClient(DownloadClient):
|
||||
import os
|
||||
|
||||
def get_with_auth(url: str, params: dict[str, str]) -> requests.Response:
|
||||
self._client.auth_log_in()
|
||||
self._ensure_authenticated()
|
||||
resp = self._client._session.get(url, params=params, timeout=10)
|
||||
if resp.status_code == _HTTP_STATUS_FORBIDDEN:
|
||||
if resp.status_code == _HTTP_STATUS_FORBIDDEN and self._can_reauthenticate:
|
||||
logger.debug("qBittorrent returned 403; re-authenticating and retrying")
|
||||
self._client.auth_log_in()
|
||||
self._ensure_authenticated()
|
||||
resp = self._client._session.get(url, params=params, timeout=10)
|
||||
return resp
|
||||
|
||||
@@ -736,23 +767,19 @@ class QBittorrentClient(DownloadClient):
|
||||
if not torrent_info.info_hash:
|
||||
return None
|
||||
|
||||
torrents, error = self._get_torrents_info(torrent_info.info_hash)
|
||||
if error:
|
||||
logger.debug("qBittorrent find_existing: %s", error)
|
||||
return None
|
||||
|
||||
torrent = next(
|
||||
(
|
||||
t
|
||||
for t in torrents
|
||||
if isinstance(getattr(t, "hash", None), str)
|
||||
and _hashes_match(t.hash, torrent_info.info_hash)
|
||||
),
|
||||
None,
|
||||
)
|
||||
if torrent and isinstance(getattr(torrent, "hash", None), str):
|
||||
torrent_hash = torrent.hash
|
||||
return (torrent_hash.lower(), self.get_status(torrent_hash.lower()))
|
||||
for _ in range(20):
|
||||
torrent, error = self._resolve_torrent(torrent_info.info_hash, category)
|
||||
if error:
|
||||
logger.debug("qBittorrent find_existing: %s", error)
|
||||
return None
|
||||
if not torrent:
|
||||
return None
|
||||
if getattr(torrent, "state", None) not in _METADATA_DOWNLOAD_STATES:
|
||||
torrent_hash = getattr(torrent, "hash", None)
|
||||
if isinstance(torrent_hash, str) and torrent_hash:
|
||||
torrent_hash = torrent_hash.lower()
|
||||
return (torrent_hash, self.get_status(torrent_hash))
|
||||
time.sleep(0.5)
|
||||
except _QBITTORRENT_CLIENT_ERRORS as e:
|
||||
logger.debug("Error checking for existing torrent: %s", e)
|
||||
return None
|
||||
|
||||
@@ -0,0 +1,517 @@
|
||||
"""Real-Debrid debrid service client for Shelfmark.
|
||||
|
||||
Routes magnet links through the Real-Debrid REST API (v1.0) to download
|
||||
torrent content via Real-Debrid's CDN infrastructure.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import shutil
|
||||
import threading
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, ClassVar, NoReturn
|
||||
|
||||
import requests
|
||||
|
||||
from shelfmark.config.env import TMP_DIR
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.download.clients import (
|
||||
DownloadClient,
|
||||
DownloadState,
|
||||
DownloadStatus,
|
||||
register_client,
|
||||
)
|
||||
from shelfmark.download.clients._coercion import config_text
|
||||
from shelfmark.download.http import download_url
|
||||
from shelfmark.download.network import get_ssl_verify
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
_API_BASE = "https://api.real-debrid.com/rest/1.0"
|
||||
|
||||
_REALDEBRID_CLIENT_ERRORS = (
|
||||
AttributeError,
|
||||
OSError,
|
||||
requests.exceptions.RequestException,
|
||||
RuntimeError,
|
||||
TypeError,
|
||||
ValueError,
|
||||
)
|
||||
|
||||
# Real-Debrid torrent status values.
|
||||
_STATUS_DOWNLOADING = frozenset(
|
||||
{
|
||||
"magnet_conversion",
|
||||
"waiting_files_selection",
|
||||
"downloading",
|
||||
"compressing",
|
||||
"uploading",
|
||||
}
|
||||
)
|
||||
_STATUS_READY = "downloaded"
|
||||
_STATUS_ERROR = frozenset({"error", "virus", "dead"})
|
||||
|
||||
# Timeouts for API calls.
|
||||
_API_TIMEOUT = 30
|
||||
_STATUS_TIMEOUT = 15
|
||||
|
||||
# File extensions recognised as book or audiobook content.
|
||||
_BOOK_EXTENSIONS = (
|
||||
".aac",
|
||||
".azw",
|
||||
".azw3",
|
||||
".cbr",
|
||||
".cbz",
|
||||
".djvu",
|
||||
".doc",
|
||||
".docx",
|
||||
".epub",
|
||||
".fb2",
|
||||
".flac",
|
||||
".lit",
|
||||
".m4a",
|
||||
".m4b",
|
||||
".mobi",
|
||||
".mp3",
|
||||
".ogg",
|
||||
".opus",
|
||||
".pdf",
|
||||
".rtf",
|
||||
".txt",
|
||||
".wma",
|
||||
)
|
||||
|
||||
|
||||
def _raise_runtime_error(message: str) -> NoReturn:
|
||||
raise RuntimeError(message)
|
||||
|
||||
|
||||
@dataclass
|
||||
class _DownloadState:
|
||||
"""Internal mutable state for an in-progress Real-Debrid download."""
|
||||
|
||||
torrent_id: str
|
||||
name: str
|
||||
target_dir: Path
|
||||
phase: str = "uploading"
|
||||
error_message: str | None = None
|
||||
progress: float = 0.0
|
||||
download_thread: threading.Thread | None = None
|
||||
lock: threading.Lock = field(default_factory=threading.Lock)
|
||||
|
||||
|
||||
@register_client("torrent")
|
||||
class RealDebridClient(DownloadClient):
|
||||
"""Real-Debrid debrid service client.
|
||||
|
||||
Downloads torrent content by uploading magnet links to Real-Debrid,
|
||||
selecting all files for download on their servers, then unrestricting
|
||||
and fetching the resulting files via direct HTTP download from
|
||||
Real-Debrid's CDN.
|
||||
|
||||
API documentation: https://api.real-debrid.com/
|
||||
"""
|
||||
|
||||
protocol = "torrent"
|
||||
name = "realdebrid"
|
||||
|
||||
_downloads: ClassVar[dict[str, _DownloadState]] = {}
|
||||
_downloads_lock = threading.Lock()
|
||||
|
||||
def __init__(self) -> None:
|
||||
self._api_key = config_text(config.get("REALDEBRID_API_KEY", ""))
|
||||
|
||||
def _auth_headers(self) -> dict[str, str]:
|
||||
"""Return Authorization header dict for API requests."""
|
||||
return {"Authorization": f"Bearer {self._api_key}"}
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# DownloadClient interface
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
@staticmethod
|
||||
def is_configured() -> bool:
|
||||
"""Return True when Real-Debrid is selected and an API key exists."""
|
||||
client = config_text(config.get("PROWLARR_TORRENT_CLIENT", ""))
|
||||
api_key = config_text(config.get("REALDEBRID_API_KEY", ""))
|
||||
return client == "realdebrid" and bool(api_key)
|
||||
|
||||
def test_connection(self) -> tuple[bool, str]:
|
||||
"""Validate the API key and check Premium subscription status."""
|
||||
if not self._api_key:
|
||||
return False, "Real-Debrid API Key is required"
|
||||
try:
|
||||
url = f"{_API_BASE}/user"
|
||||
resp = requests.get(
|
||||
url,
|
||||
headers=self._auth_headers(),
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
user = resp.json()
|
||||
username = user.get("username", "Unknown")
|
||||
account_type = user.get("type", "free")
|
||||
if account_type != "premium":
|
||||
return (
|
||||
False,
|
||||
f"Real-Debrid user '{username}' does not have "
|
||||
f"a Premium subscription (type: {account_type})",
|
||||
)
|
||||
except _REALDEBRID_CLIENT_ERRORS as e:
|
||||
return False, f"Connection failed: {e}"
|
||||
else:
|
||||
return True, f"Connected to Real-Debrid as '{username}' (Premium)"
|
||||
|
||||
def add_download(
|
||||
self,
|
||||
url: str,
|
||||
name: str,
|
||||
category: str | None = None,
|
||||
expected_hash: str | None = None,
|
||||
**kwargs: object,
|
||||
) -> str:
|
||||
"""Upload a magnet link to Real-Debrid and select all files."""
|
||||
if not self._api_key:
|
||||
msg = "Real-Debrid API key is not configured"
|
||||
raise RuntimeError(msg)
|
||||
|
||||
magnet_link = url
|
||||
if not magnet_link.startswith("magnet:") and expected_hash:
|
||||
magnet_link = f"magnet:?xt=urn:btih:{expected_hash}"
|
||||
|
||||
add_url = f"{_API_BASE}/torrents/addMagnet"
|
||||
try:
|
||||
resp = requests.post(
|
||||
add_url,
|
||||
headers=self._auth_headers(),
|
||||
data={"magnet": magnet_link},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(add_url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
data = resp.json()
|
||||
|
||||
torrent_id = str(data.get("id", ""))
|
||||
if not torrent_id:
|
||||
msg = "No torrent ID returned from Real-Debrid"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
# Select all files so Real-Debrid starts downloading the torrent
|
||||
select_url = f"{_API_BASE}/torrents/selectFiles/{torrent_id}"
|
||||
sel_resp = requests.post(
|
||||
select_url,
|
||||
headers=self._auth_headers(),
|
||||
data={"files": "all"},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(select_url),
|
||||
)
|
||||
sel_resp.raise_for_status()
|
||||
|
||||
target_dir = TMP_DIR / f"realdebrid_{torrent_id}"
|
||||
target_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
state = _DownloadState(
|
||||
torrent_id=torrent_id,
|
||||
name=name,
|
||||
target_dir=target_dir,
|
||||
phase="waiting_rd",
|
||||
)
|
||||
with self._downloads_lock:
|
||||
self._downloads[torrent_id] = state
|
||||
|
||||
logger.info(
|
||||
"Added torrent to Real-Debrid: ID %s (%s)",
|
||||
torrent_id,
|
||||
name,
|
||||
)
|
||||
|
||||
except Exception:
|
||||
logger.exception("Failed to upload magnet to Real-Debrid")
|
||||
raise
|
||||
|
||||
else:
|
||||
return torrent_id
|
||||
|
||||
def get_status(self, download_id: str) -> DownloadStatus:
|
||||
"""Poll Real-Debrid for torrent status and drive the download."""
|
||||
state = self._ensure_state(download_id)
|
||||
|
||||
# Return cached terminal / in-flight states immediately.
|
||||
with state.lock:
|
||||
if state.phase == "error":
|
||||
return DownloadStatus.error(
|
||||
state.error_message or "Real-Debrid error",
|
||||
)
|
||||
if state.phase == "complete":
|
||||
return DownloadStatus(
|
||||
progress=100.0,
|
||||
state=DownloadState.COMPLETE,
|
||||
message="Complete",
|
||||
complete=True,
|
||||
file_path=str(state.target_dir),
|
||||
)
|
||||
if state.phase == "downloading_http":
|
||||
return DownloadStatus(
|
||||
progress=state.progress,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message="Downloading files via HTTP...",
|
||||
complete=False,
|
||||
file_path=None,
|
||||
)
|
||||
|
||||
# Query Real-Debrid for torrent info.
|
||||
try:
|
||||
info_url = f"{_API_BASE}/torrents/info/{download_id}"
|
||||
resp = requests.get(
|
||||
info_url,
|
||||
headers=self._auth_headers(),
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(info_url),
|
||||
)
|
||||
resp.raise_for_status()
|
||||
info = resp.json()
|
||||
return self._handle_torrent_info(info, state)
|
||||
|
||||
except Exception as e:
|
||||
logger.exception(
|
||||
"Error checking Real-Debrid status for %s",
|
||||
download_id,
|
||||
)
|
||||
return DownloadStatus.error(str(e))
|
||||
|
||||
def remove(
|
||||
self,
|
||||
download_id: str,
|
||||
*,
|
||||
delete_files: bool = False,
|
||||
) -> bool:
|
||||
"""Delete the torrent from Real-Debrid and clean up local files."""
|
||||
try:
|
||||
url = f"{_API_BASE}/torrents/delete/{download_id}"
|
||||
requests.delete(
|
||||
url,
|
||||
headers=self._auth_headers(),
|
||||
timeout=_STATUS_TIMEOUT,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
except _REALDEBRID_CLIENT_ERRORS as e:
|
||||
logger.warning("Failed to delete torrent from Real-Debrid: %s", e)
|
||||
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.pop(download_id, None)
|
||||
|
||||
if state and state.target_dir.exists():
|
||||
shutil.rmtree(state.target_dir, ignore_errors=True)
|
||||
return True
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Return the local directory containing downloaded files."""
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.get(download_id)
|
||||
if state and state.phase == "complete":
|
||||
return str(state.target_dir)
|
||||
target_dir = TMP_DIR / f"realdebrid_{download_id}"
|
||||
if target_dir.exists():
|
||||
return str(target_dir)
|
||||
return None
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Internal helpers
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _ensure_state(self, download_id: str) -> _DownloadState:
|
||||
"""Get or create download state for the given torrent ID."""
|
||||
with self._downloads_lock:
|
||||
state = self._downloads.get(download_id)
|
||||
if state:
|
||||
return state
|
||||
|
||||
target_dir = TMP_DIR / f"realdebrid_{download_id}"
|
||||
state = _DownloadState(
|
||||
torrent_id=download_id,
|
||||
name=f"Download {download_id}",
|
||||
target_dir=target_dir,
|
||||
phase="waiting_rd",
|
||||
)
|
||||
with self._downloads_lock:
|
||||
self._downloads[download_id] = state
|
||||
return state
|
||||
|
||||
def _handle_torrent_info(
|
||||
self,
|
||||
info: dict[str, Any],
|
||||
state: _DownloadState,
|
||||
) -> DownloadStatus:
|
||||
"""Map Real-Debrid torrent info to a DownloadStatus."""
|
||||
status = info.get("status", "")
|
||||
|
||||
if status in _STATUS_DOWNLOADING:
|
||||
progress = float(info.get("progress", 0.0))
|
||||
speed = int(info.get("speed", 0))
|
||||
filename = info.get("filename", state.name)
|
||||
return DownloadStatus(
|
||||
progress=progress * 0.5,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message=f"Real-Debrid downloading torrent ({filename})",
|
||||
complete=False,
|
||||
file_path=None,
|
||||
download_speed=speed,
|
||||
)
|
||||
|
||||
if status == _STATUS_READY:
|
||||
links = info.get("links", [])
|
||||
files = info.get("files", [])
|
||||
self._maybe_start_download_thread(state, links, files)
|
||||
return DownloadStatus(
|
||||
progress=50.0,
|
||||
state=DownloadState.DOWNLOADING,
|
||||
message="Real-Debrid ready, retrieving files...",
|
||||
complete=False,
|
||||
file_path=None,
|
||||
)
|
||||
|
||||
# Terminal error from Real-Debrid.
|
||||
error_txt = f"Real-Debrid status error: {status}"
|
||||
with state.lock:
|
||||
state.phase = "error"
|
||||
state.error_message = error_txt
|
||||
return DownloadStatus.error(error_txt)
|
||||
|
||||
def _maybe_start_download_thread(
|
||||
self,
|
||||
state: _DownloadState,
|
||||
links: list[str],
|
||||
files: list[dict[str, Any]],
|
||||
) -> None:
|
||||
"""Spawn a background thread to unrestrict and download files."""
|
||||
with state.lock:
|
||||
already_running = state.phase in (
|
||||
"unrestricting",
|
||||
"downloading_http",
|
||||
"complete",
|
||||
)
|
||||
thread_alive = state.download_thread is not None and state.download_thread.is_alive()
|
||||
if already_running or thread_alive:
|
||||
return
|
||||
state.phase = "unrestricting"
|
||||
t = threading.Thread(
|
||||
target=self._process_and_download,
|
||||
args=(state, links, files),
|
||||
daemon=True,
|
||||
)
|
||||
state.download_thread = t
|
||||
t.start()
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# File download pipeline
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _process_and_download(
|
||||
self,
|
||||
state: _DownloadState,
|
||||
links: list[str],
|
||||
files: list[dict[str, Any]],
|
||||
) -> None:
|
||||
"""Unrestrict links and download files via HTTP.
|
||||
|
||||
Runs in a background thread spawned by ``_maybe_start_download_thread``.
|
||||
"""
|
||||
try:
|
||||
if not links:
|
||||
msg = "No download links returned by Real-Debrid"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
# Match selected files with links
|
||||
selected_files = [f for f in files if f.get("selected") == 1]
|
||||
|
||||
# Filter relevant ebook / audiobook files
|
||||
relevant_indices: list[int] = []
|
||||
for i, f_info in enumerate(selected_files):
|
||||
path_str = f_info.get("path", "").lower()
|
||||
if path_str.endswith(_BOOK_EXTENSIONS):
|
||||
relevant_indices.append(i)
|
||||
|
||||
if not relevant_indices:
|
||||
relevant_indices = list(range(len(links)))
|
||||
|
||||
with state.lock:
|
||||
state.phase = "downloading_http"
|
||||
|
||||
total = len(relevant_indices)
|
||||
for idx, rel_idx in enumerate(relevant_indices):
|
||||
if rel_idx >= len(links):
|
||||
continue
|
||||
link = links[rel_idx]
|
||||
|
||||
# Unrestrict the Real-Debrid link to get direct CDN download URL
|
||||
unrestrict_url = f"{_API_BASE}/unrestrict/link"
|
||||
unl_resp = requests.post(
|
||||
unrestrict_url,
|
||||
headers=self._auth_headers(),
|
||||
data={"link": link},
|
||||
timeout=_API_TIMEOUT,
|
||||
verify=get_ssl_verify(unrestrict_url),
|
||||
)
|
||||
unl_resp.raise_for_status()
|
||||
unl_data = unl_resp.json()
|
||||
|
||||
direct_url = unl_data.get("download")
|
||||
filename = unl_data.get("filename")
|
||||
if not direct_url:
|
||||
msg = f"Failed to unrestrict Real-Debrid link: {link}"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
# Determine relative file path
|
||||
if rel_idx < len(selected_files):
|
||||
rel_path_str = selected_files[rel_idx].get("path", "").lstrip("/")
|
||||
rel_path = Path(rel_path_str)
|
||||
else:
|
||||
rel_path = Path(filename or f"file_{idx + 1}")
|
||||
|
||||
dest = state.target_dir / rel_path
|
||||
dest.parent.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
logger.info(
|
||||
"Downloading Real-Debrid file %d/%d: %s",
|
||||
idx + 1,
|
||||
total,
|
||||
rel_path,
|
||||
)
|
||||
|
||||
buf = download_url(
|
||||
direct_url,
|
||||
referer="https://real-debrid.com/",
|
||||
)
|
||||
if not buf:
|
||||
msg = f"Failed to download from {direct_url}"
|
||||
_raise_runtime_error(msg)
|
||||
|
||||
with dest.open("wb") as fh:
|
||||
fh.write(buf.getvalue())
|
||||
|
||||
with state.lock:
|
||||
state.progress = 50.0 + (idx + 1) / total * 50.0
|
||||
|
||||
with state.lock:
|
||||
state.phase = "complete"
|
||||
state.progress = 100.0
|
||||
|
||||
logger.info(
|
||||
"Real-Debrid download complete for ID %s at %s",
|
||||
state.torrent_id,
|
||||
state.target_dir,
|
||||
)
|
||||
|
||||
except Exception:
|
||||
logger.exception(
|
||||
"Error in Real-Debrid download for ID %s",
|
||||
state.torrent_id,
|
||||
)
|
||||
with state.lock:
|
||||
state.phase = "error"
|
||||
state.error_message = str(
|
||||
state.error_message or "Download failed",
|
||||
)
|
||||
@@ -4,13 +4,19 @@ Uses xmlrpc to communicate with rTorrent's RPC interface.
|
||||
"""
|
||||
|
||||
import ssl
|
||||
import time
|
||||
import xmlrpc.client as stdlib_xmlrpc_client
|
||||
from typing import Any, NoReturn, Protocol, cast
|
||||
from urllib.parse import urlparse
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.utils import get_hardened_xmlrpc_client
|
||||
from shelfmark.core.utils import (
|
||||
get_hardened_xmlrpc_client,
|
||||
)
|
||||
from shelfmark.core.utils import (
|
||||
is_audiobook as check_audiobook,
|
||||
)
|
||||
from shelfmark.download.clients import (
|
||||
DownloadClient,
|
||||
DownloadStatus,
|
||||
@@ -46,7 +52,13 @@ class _RTorrentLoadProtocol(Protocol):
|
||||
def start(self, target: str, url: str, commands: str) -> object: ...
|
||||
|
||||
|
||||
class _RTorrentCustom1Protocol(Protocol):
|
||||
def set(self, download_id: str, value: str) -> object: ...
|
||||
|
||||
|
||||
class _RTorrentDownloadProtocol(Protocol):
|
||||
custom1: _RTorrentCustom1Protocol
|
||||
|
||||
def multicall2(self, *args: object) -> list[list[Any]]: ...
|
||||
|
||||
def delete_tied(self, download_id: str) -> object: ...
|
||||
@@ -160,9 +172,14 @@ class RTorrentClient(DownloadClient):
|
||||
try:
|
||||
torrent_info = extract_torrent_info(url, expected_hash=expected_hash)
|
||||
|
||||
known_hashes: set[str] | None = None
|
||||
if not (torrent_info.info_hash or expected_hash):
|
||||
known_hashes = self._list_torrent_hashes()
|
||||
|
||||
commands = []
|
||||
|
||||
is_audiobook = kwargs.get("content_type") == "audiobook"
|
||||
content_type = kwargs.get("content_type")
|
||||
is_audiobook = check_audiobook(content_type if isinstance(content_type, str) else None)
|
||||
default_label = (
|
||||
self._audiobook_label if is_audiobook and self._audiobook_label else self._label
|
||||
)
|
||||
@@ -196,7 +213,15 @@ class RTorrentClient(DownloadClient):
|
||||
|
||||
torrent_hash = torrent_info.info_hash or expected_hash
|
||||
if not torrent_hash:
|
||||
_raise_runtime_error("Could not determine torrent hash from URL")
|
||||
# rTorrent fetches .torrent URLs itself, so the add can succeed
|
||||
# even when no hash could be extracted up front. Recover it by
|
||||
# watching for the new download to appear.
|
||||
torrent_hash = self._discover_added_torrent_hash(name, label, known_hashes)
|
||||
if not torrent_hash:
|
||||
message = "Could not determine torrent hash from URL"
|
||||
if torrent_info.fetch_error:
|
||||
message = f"{message} (torrent file fetch failed: {torrent_info.fetch_error})"
|
||||
_raise_runtime_error(message)
|
||||
|
||||
logger.debug("Added torrent to rTorrent: %s", torrent_hash)
|
||||
|
||||
@@ -319,12 +344,14 @@ class RTorrentClient(DownloadClient):
|
||||
|
||||
"""
|
||||
try:
|
||||
# rtorrent is somehow case sensitive and requires uppercase hashes for look
|
||||
torrent_hash = download_id.upper()
|
||||
if delete_files:
|
||||
self._rpc.d.delete_tied(download_id)
|
||||
self._rpc.d.erase(download_id)
|
||||
self._rpc.d.delete_tied(torrent_hash)
|
||||
self._rpc.d.erase(torrent_hash)
|
||||
else:
|
||||
self._rpc.d.stop(download_id)
|
||||
self._rpc.d.erase(download_id)
|
||||
self._rpc.d.stop(torrent_hash)
|
||||
self._rpc.d.erase(torrent_hash)
|
||||
|
||||
logger.info(
|
||||
"Removed torrent from rTorrent: %s%s",
|
||||
@@ -338,6 +365,19 @@ class RTorrentClient(DownloadClient):
|
||||
else:
|
||||
return True
|
||||
|
||||
def set_category(self, download_id: str, category: str) -> bool:
|
||||
"""Assign a label to a torrent using rTorrent's custom1 field."""
|
||||
try:
|
||||
# rtorrent is somehow case sensitive and requires uppercase hashes for look
|
||||
self._rpc.d.custom1.set(download_id.upper(), category)
|
||||
logger.info("Set rTorrent label for %s to '%s'", download_id, category)
|
||||
except _RTORRENT_CLIENT_ERRORS as e:
|
||||
error_type = type(e).__name__
|
||||
logger.exception("rTorrent set_category failed (%s)", error_type)
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Get the path where torrent files are located.
|
||||
|
||||
@@ -387,6 +427,56 @@ class RTorrentClient(DownloadClient):
|
||||
except _RTORRENT_CLIENT_ERRORS:
|
||||
return "/downloads"
|
||||
|
||||
def _list_torrent_hashes(self) -> set[str] | None:
|
||||
"""Snapshot the hashes rTorrent currently reports."""
|
||||
try:
|
||||
all_torrents = self._rpc.d.multicall2("", "", "d.hash=")
|
||||
except _RTORRENT_CLIENT_ERRORS as e:
|
||||
logger.debug("Could not snapshot rTorrent downloads: %s", e)
|
||||
return None
|
||||
return {str(row[0]).lower() for row in all_torrents if row and row[0]}
|
||||
|
||||
def _discover_added_torrent_hash(
|
||||
self,
|
||||
name: str,
|
||||
label: str,
|
||||
known_hashes: set[str] | None,
|
||||
) -> str | None:
|
||||
"""Recover the hash of a torrent that was added without a known info_hash.
|
||||
|
||||
rTorrent fetches .torrent URLs itself, so the add can succeed even when
|
||||
no hash could be extracted up front. A `known_hashes` of None means the
|
||||
pre-add snapshot failed, so only an exact name match can identify the
|
||||
new arrival.
|
||||
"""
|
||||
for _ in range(20):
|
||||
try:
|
||||
all_torrents = self._rpc.d.multicall2("", "", "d.hash=", "d.name=", "d.custom1=")
|
||||
except _RTORRENT_CLIENT_ERRORS as e:
|
||||
logger.debug("rTorrent hash discovery: %s", e)
|
||||
else:
|
||||
new_torrents = [
|
||||
row
|
||||
for row in all_torrents
|
||||
if row
|
||||
and row[0]
|
||||
and (known_hashes is None or str(row[0]).lower() not in known_hashes)
|
||||
]
|
||||
# The label set at add time distinguishes concurrent arrivals,
|
||||
# but rTorrent may not have applied it yet, so it only ever
|
||||
# narrows a non-empty candidate list.
|
||||
if label:
|
||||
labeled = [row for row in new_torrents if len(row) > 2 and row[2] == label]
|
||||
if labeled:
|
||||
new_torrents = labeled
|
||||
for row in new_torrents:
|
||||
if len(row) > 1 and row[1] == name:
|
||||
return str(row[0]).lower()
|
||||
if known_hashes is not None and len(new_torrents) == 1:
|
||||
return str(new_torrents[0][0]).lower()
|
||||
time.sleep(0.5)
|
||||
return None
|
||||
|
||||
def _get_torrent_path(self, download_id: str) -> str | None:
|
||||
"""Get the file path of a torrent by hash.
|
||||
|
||||
|
||||
@@ -159,6 +159,7 @@ def _test_qbittorrent_connection(current_values: dict[str, Any] | None = None) -
|
||||
raw_url = _resolve_string_setting(current_values, config.get, "QBITTORRENT_URL")
|
||||
username = _resolve_string_setting(current_values, config.get, "QBITTORRENT_USERNAME")
|
||||
password = _resolve_string_setting(current_values, config.get, "QBITTORRENT_PASSWORD")
|
||||
api_key = _resolve_string_setting(current_values, config.get, "QBITTORRENT_API_KEY")
|
||||
|
||||
if not raw_url:
|
||||
return {"success": False, "message": "qBittorrent URL is required"}
|
||||
@@ -174,6 +175,7 @@ def _test_qbittorrent_connection(current_values: dict[str, Any] | None = None) -
|
||||
host=url,
|
||||
username=username,
|
||||
password=password,
|
||||
api_key=api_key or None,
|
||||
VERIFY_WEBUI_CERTIFICATE=get_ssl_verify(url),
|
||||
)
|
||||
client.auth_log_in()
|
||||
@@ -181,9 +183,18 @@ def _test_qbittorrent_connection(current_values: dict[str, Any] | None = None) -
|
||||
except ImportError:
|
||||
return {"success": False, "message": "qbittorrent-api package not installed"}
|
||||
except _QBITTORRENT_SETTINGS_ERRORS as e:
|
||||
if isinstance(e, _QBittorrentLoginFailed):
|
||||
# LoginFailed carries no message of its own, so name the rejected credential.
|
||||
rejected = "API key" if api_key else "username or password"
|
||||
return {"success": False, "message": f"qBittorrent rejected the {rejected}"}
|
||||
return {"success": False, "message": f"Connection failed: {e!s}"}
|
||||
else:
|
||||
return {"success": True, "message": f"Connected to qBittorrent (API v{api_version})"}
|
||||
# Both credentials can be set at once, so name the one that actually authenticated.
|
||||
used = " using the API key" if api_key else ""
|
||||
return {
|
||||
"success": True,
|
||||
"message": f"Connected to qBittorrent (API v{api_version}){used}",
|
||||
}
|
||||
|
||||
|
||||
def _test_transmission_connection(current_values: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
@@ -520,6 +531,40 @@ def _test_sabnzbd_connection(current_values: dict[str, Any] | None = None) -> di
|
||||
return {"success": True, "message": f"Connected to SABnzbd {version}"}
|
||||
|
||||
|
||||
def _test_alldebrid_connection(current_values: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
"""Test the AllDebrid API connection using current form values."""
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.download.clients.alldebrid import AllDebridClient
|
||||
|
||||
current_values = current_values or {}
|
||||
api_key = _resolve_string_setting(current_values, config.get, "ALLDEBRID_API_KEY")
|
||||
|
||||
if not api_key:
|
||||
return {"success": False, "message": "AllDebrid API Key is required"}
|
||||
|
||||
client = AllDebridClient()
|
||||
client._api_key = api_key
|
||||
success, message = client.test_connection()
|
||||
return {"success": success, "message": message}
|
||||
|
||||
|
||||
def _test_realdebrid_connection(current_values: dict[str, Any] | None = None) -> dict[str, Any]:
|
||||
"""Test the Real-Debrid API connection using current form values."""
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.download.clients.realdebrid import RealDebridClient
|
||||
|
||||
current_values = current_values or {}
|
||||
api_key = _resolve_string_setting(current_values, config.get, "REALDEBRID_API_KEY")
|
||||
|
||||
if not api_key:
|
||||
return {"success": False, "message": "Real-Debrid API Key is required"}
|
||||
|
||||
client = RealDebridClient()
|
||||
client._api_key = api_key
|
||||
success, message = client.test_connection()
|
||||
return {"success": success, "message": message}
|
||||
|
||||
|
||||
# ==================== Download Clients Tab ====================
|
||||
|
||||
|
||||
@@ -544,13 +589,45 @@ def prowlarr_clients_settings() -> list[SettingsField]:
|
||||
description="Choose which torrent client to use",
|
||||
options=[
|
||||
{"value": "", "label": "None"},
|
||||
{"value": "alldebrid", "label": "AllDebrid"},
|
||||
{"value": "qbittorrent", "label": "qBittorrent"},
|
||||
{"value": "realdebrid", "label": "Real-Debrid"},
|
||||
{"value": "transmission", "label": "Transmission"},
|
||||
{"value": "deluge", "label": "Deluge"},
|
||||
{"value": "rtorrent", "label": "rTorrent"},
|
||||
],
|
||||
default="",
|
||||
),
|
||||
# --- AllDebrid Settings ---
|
||||
PasswordField(
|
||||
key="ALLDEBRID_API_KEY",
|
||||
label="API Key",
|
||||
description="AllDebrid API Key (apiv4) from your AllDebrid account settings",
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "alldebrid"},
|
||||
),
|
||||
ActionButton(
|
||||
key="test_alldebrid",
|
||||
label="Test Connection",
|
||||
description="Verify your AllDebrid configuration",
|
||||
style="primary",
|
||||
callback=_test_alldebrid_connection,
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "alldebrid"},
|
||||
),
|
||||
# --- Real-Debrid Settings ---
|
||||
PasswordField(
|
||||
key="REALDEBRID_API_KEY",
|
||||
label="API Key",
|
||||
description="Real-Debrid API Key (Secret Token) from your Real-Debrid account settings",
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "realdebrid"},
|
||||
),
|
||||
ActionButton(
|
||||
key="test_realdebrid",
|
||||
label="Test Connection",
|
||||
description="Verify your Real-Debrid configuration",
|
||||
style="primary",
|
||||
callback=_test_realdebrid_connection,
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "realdebrid"},
|
||||
),
|
||||
# --- qBittorrent Settings ---
|
||||
TextField(
|
||||
key="QBITTORRENT_URL",
|
||||
@@ -572,6 +649,12 @@ def prowlarr_clients_settings() -> list[SettingsField]:
|
||||
description="qBittorrent Web UI password",
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "qbittorrent"},
|
||||
),
|
||||
PasswordField(
|
||||
key="QBITTORRENT_API_KEY",
|
||||
label="API Key",
|
||||
description="Found in qBittorrent: Options > Web UI > API Key (qBittorrent 5.2.0+). Used instead of the username and password when set.",
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "value": "qbittorrent"},
|
||||
),
|
||||
ActionButton(
|
||||
key="test_qbittorrent",
|
||||
label="Test Connection",
|
||||
@@ -771,14 +854,23 @@ def prowlarr_clients_settings() -> list[SettingsField]:
|
||||
SelectField(
|
||||
key="PROWLARR_TORRENT_ACTION",
|
||||
label="Torrent Completion Action",
|
||||
description="Remove deletes the torrent from your client immediately after import (stops seeding, files are kept); Keep leaves it in the client to continue seeding",
|
||||
description="Choose whether to keep, remove, or move the torrent to another category or label after import",
|
||||
options=[
|
||||
{"value": "keep", "label": "Keep"},
|
||||
{"value": "remove", "label": "Remove"},
|
||||
{"value": "change_category", "label": "Change Category"},
|
||||
],
|
||||
default="keep",
|
||||
show_when={"field": "PROWLARR_TORRENT_CLIENT", "notEmpty": True},
|
||||
),
|
||||
TextField(
|
||||
key="PROWLARR_TORRENT_POST_IMPORT_CATEGORY",
|
||||
label="Post-Import Category",
|
||||
description="Category or label to assign after a successful import",
|
||||
placeholder="imported",
|
||||
default="",
|
||||
show_when={"field": "PROWLARR_TORRENT_ACTION", "value": "change_category"},
|
||||
),
|
||||
# --- Usenet Client Selection ---
|
||||
HeadingField(
|
||||
key="usenet_heading",
|
||||
|
||||
@@ -5,8 +5,10 @@ from __future__ import annotations
|
||||
import base64
|
||||
import hashlib
|
||||
import re
|
||||
import time
|
||||
from binascii import Error as BinasciiError
|
||||
from dataclasses import dataclass
|
||||
from threading import Lock
|
||||
from urllib.parse import ParseResult, parse_qs, urljoin, urlparse
|
||||
|
||||
import requests
|
||||
@@ -19,6 +21,7 @@ from shelfmark.download.network import get_ssl_verify
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
_MAGNET_RESPONSE_MAX_BYTES = 2000
|
||||
_TORRENT_FETCH_MAX_REDIRECTS = 5
|
||||
_BASE32_BTMH_TAG_BYTES = 34
|
||||
_BTIH_INFO_BYTE_HEX = 0x20
|
||||
_BTIH_PREFIX_BYTE = 0x12
|
||||
@@ -35,6 +38,15 @@ _TORRENT_FETCH_ERRORS = (
|
||||
_TORRENT_PARSE_ERRORS = (IndexError, KeyError, TypeError, ValueError)
|
||||
_TRUSTED_TORRENT_FETCH_URL_CONFIG_KEYS = ("PROWLARR_URL", "NEWZNAB_URL")
|
||||
|
||||
# Successful torrent fetches are reused for a short window so one add attempt
|
||||
# hits the download link only once. Tracker download links (e.g. private
|
||||
# trackers behind Prowlarr's proxy) can be slow, rate-limited, or single-use,
|
||||
# and both find_existing() and add_download() resolve the same URL (#1111).
|
||||
_TORRENT_FETCH_CACHE_TTL_SECONDS = 120.0
|
||||
_TORRENT_FETCH_CACHE_MAX_ENTRIES = 8
|
||||
_torrent_fetch_cache_lock = Lock()
|
||||
_torrent_fetch_cache: dict[str, tuple[float, TorrentInfo]] = {}
|
||||
|
||||
type BencodeValue = dict[str | bytes, BencodeValue] | list[BencodeValue] | int | bytes | str
|
||||
|
||||
|
||||
@@ -54,6 +66,9 @@ class TorrentInfo:
|
||||
magnet_url: str | None = None
|
||||
"""The actual magnet URL, if available."""
|
||||
|
||||
fetch_error: str | None = None
|
||||
"""Why fetching the .torrent URL failed, or None if it succeeded/was skipped."""
|
||||
|
||||
def with_info_hash(self, info_hash: str | None) -> TorrentInfo:
|
||||
"""Return a copy with the info_hash replaced when provided."""
|
||||
if info_hash:
|
||||
@@ -62,6 +77,7 @@ class TorrentInfo:
|
||||
torrent_data=self.torrent_data,
|
||||
is_magnet=self.is_magnet,
|
||||
magnet_url=self.magnet_url,
|
||||
fetch_error=self.fetch_error,
|
||||
)
|
||||
return self
|
||||
|
||||
@@ -96,21 +112,62 @@ def extract_torrent_info(
|
||||
if not fetch_torrent:
|
||||
return TorrentInfo(info_hash=expected_hash, torrent_data=None, is_magnet=False)
|
||||
|
||||
info = _get_cached_torrent_fetch(url)
|
||||
if info is None:
|
||||
info = _fetch_torrent_info(url)
|
||||
if info.fetch_error is None:
|
||||
_store_cached_torrent_fetch(url, info)
|
||||
|
||||
return info.with_info_hash(info.info_hash or expected_hash)
|
||||
|
||||
|
||||
def _get_cached_torrent_fetch(url: str) -> TorrentInfo | None:
|
||||
with _torrent_fetch_cache_lock:
|
||||
entry = _torrent_fetch_cache.get(url)
|
||||
if entry is None:
|
||||
return None
|
||||
fetched_at, info = entry
|
||||
if time.monotonic() - fetched_at > _TORRENT_FETCH_CACHE_TTL_SECONDS:
|
||||
del _torrent_fetch_cache[url]
|
||||
return None
|
||||
logger.debug("Reusing recently fetched torrent data for: %s...", url[:80])
|
||||
return info
|
||||
|
||||
|
||||
def _store_cached_torrent_fetch(url: str, info: TorrentInfo) -> None:
|
||||
with _torrent_fetch_cache_lock:
|
||||
_torrent_fetch_cache[url] = (time.monotonic(), info)
|
||||
while len(_torrent_fetch_cache) > _TORRENT_FETCH_CACHE_MAX_ENTRIES:
|
||||
oldest_url = min(_torrent_fetch_cache, key=lambda key: _torrent_fetch_cache[key][0])
|
||||
del _torrent_fetch_cache[oldest_url]
|
||||
|
||||
|
||||
def clear_torrent_fetch_cache() -> None:
|
||||
"""Drop all cached torrent fetches (used by tests)."""
|
||||
with _torrent_fetch_cache_lock:
|
||||
_torrent_fetch_cache.clear()
|
||||
|
||||
|
||||
def _fetch_torrent_info(url: str) -> TorrentInfo:
|
||||
"""Fetch a .torrent URL and parse out the info_hash and raw torrent data.
|
||||
|
||||
On failure, the returned TorrentInfo carries the reason in `fetch_error`
|
||||
so callers can surface it instead of a generic hash error.
|
||||
"""
|
||||
# A release source can legitimately hand us a download URL on a different
|
||||
# origin than the configured Prowlarr/Newznab endpoint (e.g. a direct
|
||||
# tracker link, or Prowlarr reached through a separate proxy). We still need
|
||||
# to fetch the .torrent to recover the info_hash when the source did not
|
||||
# provide one, so the prefetch runs regardless of origin. The Prowlarr API
|
||||
# key, however, is only ever sent to a trusted origin so it can never leak
|
||||
# to an arbitrary indexer/tracker host.
|
||||
trusted_origin = _is_trusted_torrent_fetch_url(url)
|
||||
|
||||
# tracker link, or Prowlarr reached through a separate proxy), and a trusted
|
||||
# Prowlarr download URL commonly redirects to the indexer's own download
|
||||
# link. We still need to fetch the .torrent to recover the info_hash when
|
||||
# the source did not provide one, so the prefetch runs regardless of origin
|
||||
# and follows cross-origin redirects. The Prowlarr API key, however, is
|
||||
# re-evaluated per hop and only ever sent to a trusted origin so it can
|
||||
# never leak to an arbitrary indexer/tracker host.
|
||||
headers: dict[str, str] = {"Accept": "application/x-bittorrent"}
|
||||
if trusted_origin:
|
||||
# TODO(shelfmark): Move this source-specific Prowlarr auth handling into a source hook.
|
||||
api_key = str(config.get("PROWLARR_API_KEY", "") or "").strip()
|
||||
if api_key:
|
||||
headers["X-Api-Key"] = api_key
|
||||
# TODO(shelfmark): Move this source-specific Prowlarr auth handling into a source hook.
|
||||
api_key = str(config.get("PROWLARR_API_KEY", "") or "").strip()
|
||||
if api_key:
|
||||
headers["X-Api-Key"] = api_key
|
||||
|
||||
def resolve_url(current: str, location: str) -> str:
|
||||
if not location:
|
||||
@@ -121,44 +178,47 @@ def extract_torrent_info(
|
||||
try:
|
||||
logger.debug("Fetching torrent file from: %s...", url[:80])
|
||||
|
||||
# Use allow_redirects=False to handle magnet link redirects manually
|
||||
# Some indexers redirect download URLs to magnet links
|
||||
resp = requests.get(
|
||||
url,
|
||||
timeout=30,
|
||||
allow_redirects=False,
|
||||
headers=headers,
|
||||
verify=get_ssl_verify(url),
|
||||
)
|
||||
# Redirects are followed manually: some indexers redirect download URLs
|
||||
# to magnet links, and each hop must decide anew whether it may see the
|
||||
# API key.
|
||||
current_url = url
|
||||
redirects_remaining = _TORRENT_FETCH_MAX_REDIRECTS
|
||||
while True:
|
||||
request_headers = dict(headers)
|
||||
if not _is_trusted_torrent_fetch_url(current_url):
|
||||
request_headers.pop("X-Api-Key", None)
|
||||
|
||||
# Check if this is a redirect to a magnet link
|
||||
if resp.status_code in (301, 302, 303, 307, 308):
|
||||
redirect_url = resolve_url(url, resp.headers.get("Location", ""))
|
||||
resp = requests.get(
|
||||
current_url,
|
||||
timeout=30,
|
||||
allow_redirects=False,
|
||||
headers=request_headers,
|
||||
verify=get_ssl_verify(current_url),
|
||||
)
|
||||
|
||||
if resp.status_code not in (301, 302, 303, 307, 308):
|
||||
break
|
||||
|
||||
redirect_url = resolve_url(current_url, resp.headers.get("Location", ""))
|
||||
if redirect_url.startswith("magnet:"):
|
||||
logger.debug("Download URL redirected to magnet link")
|
||||
info_hash = extract_hash_from_magnet(redirect_url)
|
||||
if not info_hash and expected_hash:
|
||||
info_hash = expected_hash
|
||||
return TorrentInfo(
|
||||
info_hash=info_hash,
|
||||
info_hash=extract_hash_from_magnet(redirect_url),
|
||||
torrent_data=None,
|
||||
is_magnet=True,
|
||||
magnet_url=redirect_url,
|
||||
)
|
||||
if not _is_trusted_torrent_fetch_url(redirect_url):
|
||||
logger.debug(
|
||||
"Skipping torrent prefetch redirect to untrusted URL: %s...",
|
||||
redirect_url[:80],
|
||||
if redirects_remaining <= 0:
|
||||
logger.warning("Too many redirects fetching torrent file: %s...", url[:80])
|
||||
return TorrentInfo(
|
||||
info_hash=None,
|
||||
torrent_data=None,
|
||||
is_magnet=False,
|
||||
fetch_error="too many redirects",
|
||||
)
|
||||
return TorrentInfo(info_hash=expected_hash, torrent_data=None, is_magnet=False)
|
||||
# Not a magnet redirect, follow it manually
|
||||
redirects_remaining -= 1
|
||||
logger.debug("Following redirect to: %s...", redirect_url[:80])
|
||||
resp = requests.get(
|
||||
redirect_url,
|
||||
timeout=30,
|
||||
headers=headers,
|
||||
verify=get_ssl_verify(redirect_url),
|
||||
)
|
||||
current_url = redirect_url
|
||||
|
||||
resp.raise_for_status()
|
||||
torrent_data = resp.content
|
||||
@@ -169,25 +229,22 @@ def extract_torrent_info(
|
||||
text_content = torrent_data.decode("utf-8", errors="ignore").strip()
|
||||
if text_content.startswith("magnet:"):
|
||||
logger.debug("Download URL returned magnet link as response body")
|
||||
info_hash = extract_hash_from_magnet(text_content)
|
||||
if not info_hash and expected_hash:
|
||||
info_hash = expected_hash
|
||||
return TorrentInfo(
|
||||
info_hash=info_hash,
|
||||
info_hash=extract_hash_from_magnet(text_content),
|
||||
torrent_data=None,
|
||||
is_magnet=True,
|
||||
magnet_url=text_content,
|
||||
)
|
||||
|
||||
info_hash = extract_info_hash_from_torrent(torrent_data) or expected_hash
|
||||
info_hash = extract_info_hash_from_torrent(torrent_data)
|
||||
if info_hash:
|
||||
logger.debug("Extracted hash from torrent file: %s", info_hash)
|
||||
else:
|
||||
logger.warning("Could not extract hash from torrent file")
|
||||
return TorrentInfo(info_hash=info_hash, torrent_data=torrent_data, is_magnet=False)
|
||||
except _TORRENT_FETCH_ERRORS as e:
|
||||
logger.debug("Could not fetch torrent file: %s", e)
|
||||
return TorrentInfo(info_hash=expected_hash, torrent_data=None, is_magnet=False)
|
||||
logger.warning("Could not fetch torrent file: %s", e)
|
||||
return TorrentInfo(info_hash=None, torrent_data=None, is_magnet=False, fetch_error=str(e))
|
||||
|
||||
|
||||
def _is_trusted_torrent_fetch_url(url: str) -> bool:
|
||||
|
||||
@@ -390,6 +390,30 @@ class TransmissionClient(DownloadClient):
|
||||
else:
|
||||
return True
|
||||
|
||||
def _get_torrent_labels(self, download_id: str) -> list[str]:
|
||||
"""Return a torrent's current labels, preserving their order."""
|
||||
torrent = self._client.get_torrent(download_id)
|
||||
raw_labels = getattr(torrent, "labels", None) or []
|
||||
return [str(label) for label in raw_labels if str(label)]
|
||||
|
||||
def set_category(self, download_id: str, category: str) -> bool:
|
||||
"""Add the post-import label to a torrent, keeping labels set elsewhere."""
|
||||
try:
|
||||
existing_labels = self._get_torrent_labels(download_id)
|
||||
if category in existing_labels:
|
||||
logger.debug(
|
||||
"Transmission torrent %s already has label '%s'", download_id, category
|
||||
)
|
||||
return True
|
||||
|
||||
self._client.change_torrent(ids=download_id, labels=[*existing_labels, category])
|
||||
logger.info("Added Transmission label '%s' to %s", category, download_id)
|
||||
except _TRANSMISSION_CLIENT_ERRORS as e:
|
||||
self._log_error("set_category", e)
|
||||
return False
|
||||
else:
|
||||
return True
|
||||
|
||||
def get_download_path(self, download_id: str) -> str | None:
|
||||
"""Get the path where torrent files are located.
|
||||
|
||||
|
||||
@@ -0,0 +1,158 @@
|
||||
"""RFC 8484 DNS wireformat encoding/decoding for DoH providers.
|
||||
|
||||
Providers split into two incompatible camps and the difference is not cosmetic:
|
||||
|
||||
* **JSON** (Cloudflare, Google) - ``?name=<host>&type=A`` returning a JSON body. A
|
||||
convention, not a standard, and the only one Shelfmark used to speak.
|
||||
* **Wireformat** (Quad9, OpenDNS) - RFC 8484 proper: a base64url-encoded DNS message
|
||||
in ``?dns=``, answered with ``application/dns-message``. Quad9 additionally
|
||||
*requires HTTP/2* per RFC 8484 section 5.2 and answers HTTP/1.1 with 505.
|
||||
|
||||
This module carries the codec only; the transport choice lives in the resolver.
|
||||
Encoding a query is a handful of bytes, and parsing an answer needs message
|
||||
compression support (RFC 1035 section 4.1.4) because answer names are almost always
|
||||
pointers back into the question.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import base64
|
||||
import secrets
|
||||
import struct
|
||||
|
||||
# Record types we resolve.
|
||||
TYPE_A = 1
|
||||
TYPE_AAAA = 28
|
||||
|
||||
_CLASS_IN = 1
|
||||
_HEADER = struct.Struct(">HHHHHH")
|
||||
_RR_FIXED = struct.Struct(">HHIH") # type, class, ttl, rdlength
|
||||
_FLAG_RECURSION_DESIRED = 0x0100
|
||||
_MAX_LABEL_JUMPS = 64 # cap pointer-following so a malicious answer cannot loop
|
||||
_MAX_NAME_LENGTH = 255
|
||||
|
||||
|
||||
class WireformatError(ValueError):
|
||||
"""Raised when a DNS wireformat message cannot be parsed."""
|
||||
|
||||
|
||||
def encode_query(hostname: str, record_type: int) -> bytes:
|
||||
"""Build a DNS query message for ``hostname``.
|
||||
|
||||
The ID is zero because RFC 8484 section 4.1 requires it for cacheability, but the
|
||||
caller may randomise it when not using a cache.
|
||||
"""
|
||||
if not hostname:
|
||||
msg = "hostname must not be empty"
|
||||
raise WireformatError(msg)
|
||||
|
||||
question = bytearray()
|
||||
for label in hostname.rstrip(".").split("."):
|
||||
encoded = label.encode("idna") if not label.isascii() else label.encode("ascii")
|
||||
if not encoded or len(encoded) > 63:
|
||||
msg = f"invalid DNS label in {hostname!r}"
|
||||
raise WireformatError(msg)
|
||||
question.append(len(encoded))
|
||||
question.extend(encoded)
|
||||
question.append(0)
|
||||
question.extend(struct.pack(">HH", record_type, _CLASS_IN))
|
||||
|
||||
header = _HEADER.pack(0, _FLAG_RECURSION_DESIRED, 1, 0, 0, 0)
|
||||
return header + bytes(question)
|
||||
|
||||
|
||||
def encode_query_param(hostname: str, record_type: int) -> str:
|
||||
"""Return the base64url ``dns=`` parameter value for a query (padding stripped)."""
|
||||
return base64.urlsafe_b64encode(encode_query(hostname, record_type)).rstrip(b"=").decode()
|
||||
|
||||
|
||||
def _read_name(message: bytes, offset: int) -> int:
|
||||
"""Skip over a (possibly compressed) name, returning the offset after it."""
|
||||
jumps = 0
|
||||
length = 0
|
||||
while True:
|
||||
if offset >= len(message):
|
||||
msg = "truncated DNS name"
|
||||
raise WireformatError(msg)
|
||||
label_len = message[offset]
|
||||
if label_len == 0:
|
||||
return offset + 1
|
||||
if label_len & 0xC0 == 0xC0:
|
||||
# A pointer ends this name; the rest of the record follows the 2 bytes.
|
||||
if offset + 1 >= len(message):
|
||||
msg = "truncated DNS name pointer"
|
||||
raise WireformatError(msg)
|
||||
return offset + 2
|
||||
offset += 1 + label_len
|
||||
length += 1 + label_len
|
||||
jumps += 1
|
||||
if jumps > _MAX_LABEL_JUMPS or length > _MAX_NAME_LENGTH:
|
||||
msg = "malformed DNS name"
|
||||
raise WireformatError(msg)
|
||||
|
||||
|
||||
def decode_answer(message: bytes, record_type: int) -> list[str]:
|
||||
"""Extract the IP addresses of ``record_type`` from a DNS response message.
|
||||
|
||||
Returns an empty list for a well-formed response that carries no matching record
|
||||
(NXDOMAIN, or only CNAMEs), and raises WireformatError for a malformed one - the
|
||||
caller treats those differently.
|
||||
"""
|
||||
if len(message) < _HEADER.size:
|
||||
msg = "DNS response shorter than its header"
|
||||
raise WireformatError(msg)
|
||||
|
||||
_id, _flags, qdcount, ancount, _ns, _ar = _HEADER.unpack_from(message, 0)
|
||||
offset = _HEADER.size
|
||||
|
||||
for _ in range(qdcount):
|
||||
offset = _read_name(message, offset)
|
||||
offset += 4 # QTYPE + QCLASS
|
||||
|
||||
results: list[str] = []
|
||||
for _ in range(ancount):
|
||||
offset = _read_name(message, offset)
|
||||
if offset + _RR_FIXED.size > len(message):
|
||||
msg = "truncated resource record"
|
||||
raise WireformatError(msg)
|
||||
rtype, rclass, _ttl, rdlength = _RR_FIXED.unpack_from(message, offset)
|
||||
offset += _RR_FIXED.size
|
||||
rdata = message[offset : offset + rdlength]
|
||||
if len(rdata) != rdlength:
|
||||
msg = "truncated record data"
|
||||
raise WireformatError(msg)
|
||||
offset += rdlength
|
||||
|
||||
if rclass != _CLASS_IN or rtype != record_type:
|
||||
continue
|
||||
if rtype == TYPE_A and rdlength == 4:
|
||||
results.append(".".join(str(b) for b in rdata))
|
||||
elif rtype == TYPE_AAAA and rdlength == 16:
|
||||
groups = struct.unpack(">8H", rdata)
|
||||
results.append(_compress_ipv6(groups))
|
||||
|
||||
return results
|
||||
|
||||
|
||||
def _compress_ipv6(groups: tuple[int, ...]) -> str:
|
||||
"""Render an IPv6 address with the longest zero run collapsed to '::'."""
|
||||
best_start = best_len = -1
|
||||
run_start = -1
|
||||
for i, group in enumerate([*list(groups), 1]): # sentinel closes a trailing run
|
||||
if group == 0 and i < len(groups):
|
||||
if run_start < 0:
|
||||
run_start = i
|
||||
elif run_start >= 0:
|
||||
if i - run_start > best_len:
|
||||
best_start, best_len = run_start, i - run_start
|
||||
run_start = -1
|
||||
|
||||
parts = [format(g, "x") for g in groups]
|
||||
if best_len > 1:
|
||||
return ":".join(parts[:best_start]) + "::" + ":".join(parts[best_start + best_len :])
|
||||
return ":".join(parts)
|
||||
|
||||
|
||||
def random_query_id() -> int:
|
||||
"""A random DNS message ID, for callers that do not want the RFC 8484 zero."""
|
||||
return secrets.randbelow(0x10000)
|
||||
+153
-6
@@ -4,6 +4,7 @@ These utilities handle file collisions atomically, avoiding TOCTOU race conditio
|
||||
when multiple workers may try to write to the same path simultaneously.
|
||||
"""
|
||||
|
||||
import contextlib
|
||||
import errno
|
||||
import os
|
||||
import shutil
|
||||
@@ -104,6 +105,57 @@ _PUBLISH_VERIFY_RETRY_SECONDS = 0.25
|
||||
_TEMPFILE_PREFIX = ".shelfmark."
|
||||
_TEMPFILE_SUFFIX = ".tmp"
|
||||
|
||||
# Destinations that accept writes but reject unlink/rename, e.g. a Synology share
|
||||
# with "Delete subfolders and files" unticked. Publishing a temp file into place
|
||||
# removes a directory entry, so those paths must be written in place instead.
|
||||
_DELETE_DENIED_DIRS: set[str] = set()
|
||||
|
||||
|
||||
class _PublishDeniedError(Exception):
|
||||
"""A fully-written temp file could not be renamed onto its final path."""
|
||||
|
||||
|
||||
def _is_delete_denied_error(error: Exception) -> bool:
|
||||
return isinstance(error, OSError) and error.errno in {errno.EACCES, errno.EPERM}
|
||||
|
||||
|
||||
def mark_delete_denied(directory: Path) -> None:
|
||||
"""Record that `directory` rejects deletes so later writes skip the temp file."""
|
||||
key = str(directory)
|
||||
if key in _DELETE_DENIED_DIRS:
|
||||
return
|
||||
_DELETE_DENIED_DIRS.add(key)
|
||||
logger.warning(
|
||||
"Destination %s rejects delete/rename; writing files in place instead of "
|
||||
"publishing atomically. Grant delete permission to restore atomic writes.",
|
||||
directory,
|
||||
)
|
||||
|
||||
|
||||
def clear_delete_denied(directory: Path) -> None:
|
||||
"""Forget recorded denials for `directory` and anything beneath it.
|
||||
|
||||
Subdirectories get marked independently (an `organize` layout publishes into
|
||||
per-author folders), so clearing only the exact key would leave a fixed
|
||||
destination writing in place until restart.
|
||||
"""
|
||||
if not _DELETE_DENIED_DIRS:
|
||||
return
|
||||
key = str(directory)
|
||||
prefix = f"{key}{os.sep}"
|
||||
_DELETE_DENIED_DIRS.difference_update(
|
||||
{marked for marked in _DELETE_DENIED_DIRS if marked == key or marked.startswith(prefix)}
|
||||
)
|
||||
|
||||
|
||||
def is_delete_denied(directory: Path) -> bool:
|
||||
"""True if `directory` or one of its ancestors is known to reject deletes."""
|
||||
if not _DELETE_DENIED_DIRS:
|
||||
return False
|
||||
if str(directory) in _DELETE_DENIED_DIRS:
|
||||
return True
|
||||
return any(str(parent) in _DELETE_DENIED_DIRS for parent in directory.parents)
|
||||
|
||||
|
||||
def _verify_transfer_size(
|
||||
dest: Path,
|
||||
@@ -361,10 +413,40 @@ def _create_temp_path(dest_path: Path) -> Path:
|
||||
return Path(temp_path)
|
||||
|
||||
|
||||
def _discard_path(path: Path) -> None:
|
||||
"""Best-effort unlink that tolerates destinations which reject deletes."""
|
||||
try:
|
||||
run_blocking_io(path.unlink, missing_ok=True)
|
||||
except OSError as exc:
|
||||
logger.warning("Could not remove %s: %s", path, exc)
|
||||
|
||||
|
||||
def _copy_into_claimed(source_path: Path, dest_path: Path, expected_size: int) -> None:
|
||||
"""Copy content straight into an already-claimed destination path.
|
||||
|
||||
Used when the destination rejects rename/unlink: there is no temp file to
|
||||
publish, so the final name is written in place. This is not atomic - a
|
||||
watcher can observe a partial file - but it is the only way to deliver on
|
||||
such a share. `copyfile` (not `copy2`) because metadata copying needs chmod,
|
||||
which those shares also tend to refuse.
|
||||
"""
|
||||
try:
|
||||
run_blocking_io(shutil.copyfile, str(source_path), str(dest_path))
|
||||
_verify_transfer_size(dest_path, expected_size, "copy")
|
||||
except Exception:
|
||||
with contextlib.suppress(OSError):
|
||||
run_blocking_io(dest_path.unlink, missing_ok=True)
|
||||
raise
|
||||
|
||||
|
||||
def _publish_temp_file(temp_path: Path, dest_path: Path) -> bool:
|
||||
"""Publish a temp file to its final path without overwriting existing files.
|
||||
|
||||
Returns True on success, False if the destination already exists.
|
||||
|
||||
Raises `_PublishDeniedError` when the rename is refused for lack of delete
|
||||
permission. The claimed destination is left in place so the caller can write
|
||||
into it directly instead.
|
||||
"""
|
||||
claimed = _claim_destination(dest_path)
|
||||
if not claimed:
|
||||
@@ -374,7 +456,19 @@ def _publish_temp_file(temp_path: Path, dest_path: Path) -> bool:
|
||||
# Publish by renaming the fully-written temp file into place. This gives
|
||||
# watchers an IN_MOVED_TO-style event on the final path instead of relying
|
||||
# on hardlink support in the destination filesystem.
|
||||
run_blocking_io(os.replace, str(temp_path), str(dest_path))
|
||||
try:
|
||||
run_blocking_io(os.replace, str(temp_path), str(dest_path))
|
||||
except OSError as e:
|
||||
if _is_delete_denied_error(e):
|
||||
log_transfer_permission_context(
|
||||
"publish_replace",
|
||||
source=temp_path,
|
||||
dest=dest_path,
|
||||
error=e,
|
||||
)
|
||||
mark_delete_denied(dest_path.parent)
|
||||
raise _PublishDeniedError(str(e)) from e
|
||||
raise
|
||||
|
||||
# Best-effort nudge for watchers that only react to close-write on the
|
||||
# final filename rather than rename/move events.
|
||||
@@ -383,6 +477,8 @@ def _publish_temp_file(temp_path: Path, dest_path: Path) -> bool:
|
||||
run_blocking_io(os.close, fd)
|
||||
except OSError:
|
||||
pass
|
||||
except _PublishDeniedError:
|
||||
raise
|
||||
except Exception as e:
|
||||
if _is_permission_error(e):
|
||||
log_transfer_permission_context(
|
||||
@@ -391,12 +487,23 @@ def _publish_temp_file(temp_path: Path, dest_path: Path) -> bool:
|
||||
dest=dest_path,
|
||||
error=e,
|
||||
)
|
||||
run_blocking_io(dest_path.unlink, missing_ok=True)
|
||||
_discard_path(dest_path)
|
||||
raise
|
||||
else:
|
||||
return True
|
||||
|
||||
|
||||
def _move_via_copy(source_path: Path, dest_path: Path, max_attempts: int) -> Path:
|
||||
"""Deliver a move as copy + source unlink.
|
||||
|
||||
For destinations that reject rename. The source lives in TMP_DIR (which we
|
||||
own and can delete), so only the destination-side semantics change.
|
||||
"""
|
||||
final_path = atomic_copy(source_path, dest_path, max_attempts=max_attempts)
|
||||
_discard_path(source_path)
|
||||
return final_path
|
||||
|
||||
|
||||
def atomic_move(source_path: Path, dest_path: Path, max_attempts: int = 100) -> Path:
|
||||
"""Move a file with collision detection.
|
||||
|
||||
@@ -423,6 +530,11 @@ def atomic_move(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
ext = dest_path.suffix
|
||||
parent = dest_path.parent
|
||||
|
||||
# rename() removes a directory entry, so a destination that refuses deletes
|
||||
# cannot be moved into. Deliver it as copy + source unlink instead.
|
||||
if is_delete_denied(parent):
|
||||
return _move_via_copy(source_path, dest_path, max_attempts)
|
||||
|
||||
for attempt in range(max_attempts):
|
||||
try_path = dest_path if attempt == 0 else parent / f"{base}_{attempt}{ext}"
|
||||
|
||||
@@ -449,6 +561,13 @@ def atomic_move(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
run_blocking_io(try_path.unlink, missing_ok=True)
|
||||
continue
|
||||
except OSError as e:
|
||||
if _is_delete_denied_error(e):
|
||||
# Destination refuses the rename; fall back to copy + unlink source.
|
||||
mark_delete_denied(parent)
|
||||
if claimed:
|
||||
_discard_path(try_path)
|
||||
return _move_via_copy(source_path, dest_path, max_attempts)
|
||||
|
||||
# Cross-filesystem - copy to temp and publish atomically.
|
||||
if e.errno != errno.EXDEV:
|
||||
if claimed:
|
||||
@@ -497,7 +616,7 @@ def atomic_move(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
try:
|
||||
_verify_published_file(try_path, expected_size, "move")
|
||||
except Exception:
|
||||
run_blocking_io(try_path.unlink, missing_ok=True)
|
||||
_discard_path(try_path)
|
||||
raise
|
||||
|
||||
run_blocking_io(source_path.unlink)
|
||||
@@ -508,9 +627,18 @@ def atomic_move(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
if temp_path:
|
||||
run_blocking_io(temp_path.unlink, missing_ok=True)
|
||||
continue
|
||||
except _PublishDeniedError:
|
||||
# Destination is claimed but unrenameable; write into it directly.
|
||||
_copy_into_claimed(source_path, try_path, expected_size)
|
||||
if temp_path:
|
||||
_discard_path(temp_path)
|
||||
_discard_path(source_path)
|
||||
if attempt > 0:
|
||||
logger.info("File collision resolved: %s", try_path.name)
|
||||
return try_path
|
||||
except Exception:
|
||||
if temp_path:
|
||||
run_blocking_io(temp_path.unlink, missing_ok=True)
|
||||
_discard_path(temp_path)
|
||||
raise
|
||||
else:
|
||||
return try_path
|
||||
@@ -629,6 +757,17 @@ def atomic_copy(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
try_path = dest_path if attempt == 0 else parent / f"{base}_{attempt}{ext}"
|
||||
if run_blocking_io(try_path.exists):
|
||||
continue
|
||||
|
||||
# Known-undeletable destination: skip the temp file entirely, otherwise
|
||||
# every transfer would strand a `.shelfmark.*.tmp` we cannot clean up.
|
||||
if is_delete_denied(parent):
|
||||
if not _claim_destination(try_path):
|
||||
continue
|
||||
_copy_into_claimed(source_path, try_path, expected_size)
|
||||
if attempt > 0:
|
||||
logger.info("File collision resolved: %s", try_path.name)
|
||||
return try_path
|
||||
|
||||
temp_path: Path | None = None
|
||||
try:
|
||||
temp_path = _create_temp_path(try_path)
|
||||
@@ -680,14 +819,22 @@ def atomic_copy(source_path: Path, dest_path: Path, max_attempts: int = 100) ->
|
||||
try:
|
||||
_verify_published_file(try_path, expected_size, "copy")
|
||||
except Exception:
|
||||
run_blocking_io(try_path.unlink, missing_ok=True)
|
||||
_discard_path(try_path)
|
||||
raise
|
||||
|
||||
if attempt > 0:
|
||||
logger.info("File collision resolved: %s", try_path.name)
|
||||
except _PublishDeniedError:
|
||||
# The destination is claimed but unrenameable; write into it directly.
|
||||
_copy_into_claimed(source_path, try_path, expected_size)
|
||||
if temp_path:
|
||||
_discard_path(temp_path)
|
||||
if attempt > 0:
|
||||
logger.info("File collision resolved: %s", try_path.name)
|
||||
return try_path
|
||||
except Exception:
|
||||
if temp_path:
|
||||
run_blocking_io(temp_path.unlink, missing_ok=True)
|
||||
_discard_path(temp_path)
|
||||
raise
|
||||
else:
|
||||
return try_path
|
||||
|
||||
+292
-57
@@ -4,36 +4,46 @@ import random
|
||||
import time
|
||||
from http import HTTPStatus
|
||||
from io import BytesIO
|
||||
from threading import Event, Thread
|
||||
from typing import TYPE_CHECKING, NoReturn
|
||||
from urllib.parse import urljoin, urlparse
|
||||
|
||||
import requests
|
||||
from tqdm import tqdm
|
||||
|
||||
from shelfmark.bypass import BypassCancelledError
|
||||
from shelfmark.bypass import BypassCancelledError, cookie_store
|
||||
from shelfmark.bypass.challenge import challenge_marker
|
||||
from shelfmark.core.config import config as app_config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.request_helpers import coerce_bool, normalize_positive_int
|
||||
from shelfmark.download import network
|
||||
from shelfmark.download.activity import release_activity_grace, request_activity_grace
|
||||
from shelfmark.download.network import get_proxies, get_ssl_verify
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Callable
|
||||
from threading import Event
|
||||
from types import ModuleType
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
_RNG = random.SystemRandom()
|
||||
|
||||
_MAX_REDIRECTS = 5
|
||||
# Z-Library answers the first hit with a 503 whose only real payload is a Set-Cookie; echoing
|
||||
# that cookie back returns the 302 to the real page. Two attempts cover the handshake without
|
||||
# letting a server that keeps re-issuing cookies hold us in the loop.
|
||||
_MAX_COOKIE_HANDSHAKE_RETRIES = 2
|
||||
_HTTP_STATUS_FORBIDDEN = HTTPStatus.FORBIDDEN
|
||||
_HTTP_STATUS_NOT_FOUND = HTTPStatus.NOT_FOUND
|
||||
_HTTP_STATUS_RATE_LIMITED = HTTPStatus.TOO_MANY_REQUESTS
|
||||
_HTTP_STATUS_SERVICE_UNAVAILABLE = HTTPStatus.SERVICE_UNAVAILABLE
|
||||
_HTTP_STATUS_OK = HTTPStatus.OK
|
||||
_HTTP_STATUS_RANGE_NOT_SATISFIABLE = HTTPStatus.REQUESTED_RANGE_NOT_SATISFIABLE
|
||||
_HTTP_STATUS_PARTIAL_CONTENT = HTTPStatus.PARTIAL_CONTENT
|
||||
_HTTP_STATUS_NON_RETRYABLE = (_HTTP_STATUS_FORBIDDEN, _HTTP_STATUS_NOT_FOUND)
|
||||
_STATUS_CALLBACK_ERRORS = (AttributeError, KeyError, OSError, RuntimeError, TypeError, ValueError)
|
||||
# Added on top of the active bypasser's own budget so it reports its real failure before
|
||||
# stall detection cancels the download.
|
||||
_BYPASS_GRACE_SLACK_SECONDS = 30.0
|
||||
_BYPASSER_ERRORS = (
|
||||
AttributeError,
|
||||
BypassCancelledError,
|
||||
@@ -54,6 +64,18 @@ def _raise_too_many_redirects(message: str) -> NoReturn:
|
||||
raise requests.exceptions.TooManyRedirects(message)
|
||||
|
||||
|
||||
def _new_cookies(response: requests.Response, already_sent: dict[str, str]) -> dict[str, str]:
|
||||
"""Cookies a response set that we were not already echoing back.
|
||||
|
||||
Returning only the *new* ones is what makes the retry terminate: a server that keeps
|
||||
re-issuing the same cookie yields nothing here, so we stop instead of spinning.
|
||||
"""
|
||||
jar = getattr(response, "cookies", None)
|
||||
if not jar:
|
||||
return {}
|
||||
return {name: value for name, value in jar.items() if already_sent.get(name) != value}
|
||||
|
||||
|
||||
def _get_internal_bypasser() -> ModuleType:
|
||||
"""Lazy import of internal bypasser module."""
|
||||
global _internal_bypasser
|
||||
@@ -99,6 +121,19 @@ def _is_cf_bypass_enabled() -> bool:
|
||||
return coerce_bool(app_config.get("USE_CF_BYPASS", True))
|
||||
|
||||
|
||||
def _bypass_grace_seconds() -> float:
|
||||
"""How long a bypass may block before stall detection should give up on it.
|
||||
|
||||
Each bypasser knows its own retry/timeout budget, so ask the active one rather than
|
||||
duplicating the arithmetic here. The slack keeps the bypasser's own deadline expiring
|
||||
first, so the user sees its real error instead of a generic "Download stalled".
|
||||
"""
|
||||
bypasser = (
|
||||
_get_external_bypasser() if _is_using_external_bypasser() else _get_internal_bypasser()
|
||||
)
|
||||
return bypasser.max_duration_seconds() + _BYPASS_GRACE_SLACK_SECONDS
|
||||
|
||||
|
||||
def get_bypassed_page(
|
||||
url: str,
|
||||
selector: network.AAMirrorSelector | None = None,
|
||||
@@ -111,19 +146,13 @@ def get_bypassed_page(
|
||||
|
||||
|
||||
def get_cf_cookies_for_domain(domain: str) -> dict[str, str]:
|
||||
"""Get CF cookies - only available with internal bypasser."""
|
||||
if _is_using_external_bypasser():
|
||||
logger.debug("External bypasser in use, CF cookies not available for %s", domain)
|
||||
return {}
|
||||
return _get_internal_bypasser().get_cf_cookies_for_domain(domain)
|
||||
"""Get the clearance cookies won by whichever bypasser solved this domain."""
|
||||
return cookie_store.get_cf_cookies_for_domain(domain)
|
||||
|
||||
|
||||
def get_cf_user_agent_for_domain(domain: str) -> str | None:
|
||||
"""Get CF user agent - only available with internal bypasser."""
|
||||
if _is_using_external_bypasser():
|
||||
logger.debug("External bypasser in use, CF user agent not available for %s", domain)
|
||||
return None
|
||||
return _get_internal_bypasser().get_cf_user_agent_for_domain(domain)
|
||||
"""Get the User-Agent that solved this domain's challenge, if one is stored."""
|
||||
return cookie_store.get_cf_user_agent_for_domain(domain)
|
||||
|
||||
|
||||
def _apply_cf_bypass(url: str, headers: dict) -> dict:
|
||||
@@ -200,13 +229,66 @@ def _is_retryable_error(e: Exception) -> bool:
|
||||
return status is not None and status in RETRYABLE_CODES
|
||||
|
||||
|
||||
# Statuses that mean the host is gone rather than busy: 410 Gone and 451 Unavailable
|
||||
# For Legal Reasons are what a seized domain answers with.
|
||||
_DEAD_MIRROR_CODES = (410, 451)
|
||||
|
||||
|
||||
def _response_challenge_marker(response: requests.Response) -> str | None:
|
||||
"""The challenge marker in a response body, or None if it carries no challenge.
|
||||
|
||||
Content type is checked first so a JSON or octet-stream error body is never
|
||||
decoded just to be scanned; a missing header is scanned anyway, since an
|
||||
interstitial served without one is still an interstitial.
|
||||
"""
|
||||
content_type = response.headers.get("Content-Type", "")
|
||||
if content_type and "html" not in content_type.lower():
|
||||
return None
|
||||
try:
|
||||
return challenge_marker(response.text)
|
||||
except UnicodeDecodeError, ValueError:
|
||||
return None
|
||||
|
||||
|
||||
def _fatal_mirror_reason(e: Exception) -> str | None:
|
||||
"""Return why ``e`` proves the mirror is unusable, or None if it may recover.
|
||||
|
||||
Hard evidence only - the name does not resolve, nothing is listening, or the host
|
||||
says it is gone for good. A timeout, a 5xx or a challenge all mean the mirror is
|
||||
alive, and rotating off it discards the bypass clearance held for that domain.
|
||||
"""
|
||||
status = _get_status_code(e)
|
||||
if status is not None and status in _DEAD_MIRROR_CODES:
|
||||
return f"HTTP {status}"
|
||||
|
||||
# requests wraps the real cause; a read timeout subclasses ConnectionError for
|
||||
# some adapters, so exclude timeouts explicitly before inspecting the message.
|
||||
if isinstance(e, requests.exceptions.Timeout):
|
||||
return None
|
||||
if not isinstance(e, requests.exceptions.ConnectionError):
|
||||
return None
|
||||
|
||||
text = str(e).lower()
|
||||
if "nameresolutionerror" in text or "failed to resolve" in text or "name or service" in text:
|
||||
return "DNS does not resolve"
|
||||
if "connection refused" in text or "no route to host" in text:
|
||||
return "connection refused"
|
||||
return None
|
||||
|
||||
|
||||
def _try_rotation(
|
||||
original_url: str, current_url: str, selector: network.AAMirrorSelector
|
||||
original_url: str,
|
||||
current_url: str,
|
||||
selector: network.AAMirrorSelector,
|
||||
*,
|
||||
fatal_reason: str | None = None,
|
||||
) -> str | None:
|
||||
"""Try mirror/DNS rotation. Returns new URL or None."""
|
||||
aa_base_url = network.get_aa_base_url()
|
||||
if aa_base_url and current_url.startswith(aa_base_url):
|
||||
new_base, action = selector.next_mirror_or_rotate_dns()
|
||||
new_base, action = selector.next_mirror_or_rotate_dns(
|
||||
fatal=fatal_reason is not None, reason=fatal_reason or ""
|
||||
)
|
||||
if action in ("mirror", "dns") and new_base:
|
||||
new_url = selector.rewrite(original_url)
|
||||
logger.info("[%s] switching to: %s", action, new_url)
|
||||
@@ -238,8 +320,11 @@ def html_get_page(
|
||||
selector: Mirror selector used for AA mirror and DNS rotation.
|
||||
cancel_flag: Optional event used to abort retries early.
|
||||
status_callback: Optional callback for UI status updates.
|
||||
allow_bypasser_fallback: If False, 403 errors will trigger mirror rotation
|
||||
instead of switching to the bypasser. Use for search operations.
|
||||
allow_bypasser_fallback: Whether a challenge may be handed to the bypasser.
|
||||
If False, a 403 triggers mirror rotation instead, and an AA redirect loop
|
||||
gives up immediately rather than waiting on a browser solve. Use False for
|
||||
best-effort fetches whose result is optional (e.g. the download count on
|
||||
the details modal); search and detail pages pass True.
|
||||
use_bypasser: Whether to start with the bypasser instead of direct HTTP.
|
||||
include_response_url: If True, return `(html, final_url)` to expose the
|
||||
resolved response URL after redirects.
|
||||
@@ -253,6 +338,72 @@ def html_get_page(
|
||||
return html, response_url
|
||||
return html
|
||||
|
||||
def _run_bypasser(bypass_url: str) -> str | tuple[str, str]:
|
||||
"""Run the active bypasser for one URL and return its result.
|
||||
|
||||
Factored out so the redirect-loop handoff below can invoke it directly. That
|
||||
call site sits inside the inner redirect `while`, so it cannot reach the
|
||||
retry-loop branch above with `continue`, and with MAX_RETRY=1 there is no
|
||||
later attempt for that branch to run on either.
|
||||
"""
|
||||
if status_callback:
|
||||
status_callback("resolving", "Bypassing protection...")
|
||||
try:
|
||||
# A bypass is one long blocking call with no incremental progress, so
|
||||
# tell the orchestrator up front how long it may legitimately take
|
||||
# instead of trying to fake activity while it runs. Inside the try so a
|
||||
# bypasser that fails to load is still reported as a bypasser error.
|
||||
request_activity_grace(status_callback, _bypass_grace_seconds())
|
||||
result = get_bypassed_page(bypass_url, selector, cancel_flag)
|
||||
return _result(result or "", bypass_url)
|
||||
except _BYPASSER_ERRORS as e:
|
||||
logger.warning("Bypasser error: %s: %s", type(e).__name__, e)
|
||||
# Surface the real reason. Without this the caller only sees an empty
|
||||
# page and the download dies with a generic failure, hiding e.g. a
|
||||
# FlareSolverr 500 behind a silent wait.
|
||||
if status_callback and not isinstance(e, BypassCancelledError):
|
||||
try:
|
||||
status_callback("error", f"Bypass failed: {type(e).__name__}: {e}")
|
||||
except _STATUS_CALLBACK_ERRORS:
|
||||
logger.debug("Bypass error status callback failed", exc_info=True)
|
||||
return _result("", bypass_url)
|
||||
finally:
|
||||
release_activity_grace(status_callback)
|
||||
|
||||
def _bypass_handoff_allowed() -> bool:
|
||||
"""Whether a challenge on the current URL may be handed to the bypasser.
|
||||
|
||||
allow_bypasser_fallback is honoured for the same reason the 403 path honours it:
|
||||
callers such as the /dyn/md5/summary fetch behind the details modal pass False
|
||||
precisely so a best-effort request fails fast instead of holding the UI open for
|
||||
a minutes-long browser solve.
|
||||
"""
|
||||
return allow_bypasser_fallback and _is_cf_bypass_enabled() and not use_bypasser_now
|
||||
|
||||
def _purge_clearance(target_url: str) -> None:
|
||||
"""Drop the host's stored clearance cookies.
|
||||
|
||||
Called whenever the protection answered a request that *carried* cookies:
|
||||
being challenged while presenting them proves they no longer work, so keeping
|
||||
them only guarantees the same rejection on every later request. Applies to
|
||||
either bypasser, since both fill the same store.
|
||||
"""
|
||||
hostname = urlparse(target_url).hostname or ""
|
||||
# An empty domain means "clear every host" to the store, so skip the purge
|
||||
# rather than wipe clearance for sites that are working fine.
|
||||
if hostname:
|
||||
cookie_store.clear_cf_cookies(hostname)
|
||||
|
||||
def _redirect_loop_handoff(bypass_url: str) -> str | tuple[str, str]:
|
||||
"""Drop the host's stale clearance cookies, then bypass `bypass_url`.
|
||||
|
||||
A `?check=1` loop is how DDoS-Guard answers a clearance cookie that has gone
|
||||
stale, so the dead cookie has to go before the solve — otherwise it is merged
|
||||
back over the fresh one on the next request and the loop simply resumes.
|
||||
"""
|
||||
_purge_clearance(bypass_url)
|
||||
return _run_bypasser(bypass_url)
|
||||
|
||||
configured_retry = normalize_positive_int(app_config.MAX_RETRY)
|
||||
retry_limit = (
|
||||
retry if retry is not None else (configured_retry if configured_retry is not None else 1)
|
||||
@@ -261,6 +412,9 @@ def html_get_page(
|
||||
original_url = url
|
||||
current_url = selector.rewrite(original_url)
|
||||
use_bypasser_now = use_bypasser
|
||||
# Survives across attempts so a cookie won once is still presented on later retries.
|
||||
handshake_cookies: dict[str, str] = {}
|
||||
handshake_retries = 0
|
||||
|
||||
for attempt in range(1, retry_limit + 1):
|
||||
# Check for cancellation before each attempt
|
||||
@@ -271,36 +425,7 @@ def html_get_page(
|
||||
cookies: dict[str, str] = {}
|
||||
try:
|
||||
if use_bypasser_now and _is_cf_bypass_enabled():
|
||||
if status_callback:
|
||||
status_callback("resolving", "Bypassing protection...")
|
||||
heartbeat_stop = Event()
|
||||
heartbeat_thread: Thread | None = None
|
||||
if status_callback:
|
||||
|
||||
def _heartbeat() -> None:
|
||||
# Keep the download "alive" during long bypass operations so the orchestrator
|
||||
# doesn't flag it as stalled.
|
||||
if cancel_flag and cancel_flag.is_set():
|
||||
return
|
||||
try:
|
||||
status_callback("resolving", "Bypassing protection...")
|
||||
except _STATUS_CALLBACK_ERRORS:
|
||||
return
|
||||
|
||||
heartbeat_thread = Thread(
|
||||
target=_heartbeat, daemon=True, name="BypassHeartbeat"
|
||||
)
|
||||
heartbeat_thread.start()
|
||||
try:
|
||||
result = get_bypassed_page(current_url, selector, cancel_flag)
|
||||
return _result(result or "", current_url)
|
||||
except _BYPASSER_ERRORS as e:
|
||||
logger.warning("Bypasser error: %s: %s", type(e).__name__, e)
|
||||
return _result("", current_url)
|
||||
finally:
|
||||
heartbeat_stop.set()
|
||||
if heartbeat_thread:
|
||||
heartbeat_thread.join(timeout=1)
|
||||
return _run_bypasser(current_url)
|
||||
|
||||
logger.debug("GET: %s", current_url)
|
||||
|
||||
@@ -322,12 +447,60 @@ def html_get_page(
|
||||
current_url,
|
||||
proxies=get_proxies(current_url),
|
||||
timeout=REQUEST_TIMEOUT,
|
||||
cookies=cookies,
|
||||
# Bypasser-derived cookies win: they came from a real solved challenge.
|
||||
cookies={**handshake_cookies, **cookies},
|
||||
headers=headers,
|
||||
allow_redirects=allow_redirects,
|
||||
verify=get_ssl_verify(current_url),
|
||||
)
|
||||
|
||||
# Z-Library gates the first hit with a 503 that carries nothing but a
|
||||
# Set-Cookie; echoing it back yields the 302 to the real page. Without this
|
||||
# the cookie is dropped and every retry re-runs the same rejected request.
|
||||
if (
|
||||
response.status_code == _HTTP_STATUS_SERVICE_UNAVAILABLE
|
||||
and handshake_retries < _MAX_COOKIE_HANDSHAKE_RETRIES
|
||||
):
|
||||
issued = _new_cookies(response, handshake_cookies)
|
||||
if issued:
|
||||
handshake_cookies.update(issued)
|
||||
handshake_retries += 1
|
||||
logger.debug(
|
||||
"503 set %s cookie(s); retrying with them: %s",
|
||||
len(issued),
|
||||
current_url,
|
||||
)
|
||||
continue
|
||||
|
||||
# A 503 still serving a challenge is protection, not a busy origin. The
|
||||
# handshake above has nothing left to echo back, and 503 is in
|
||||
# RETRYABLE_CODES, so without this the request spends every attempt on
|
||||
# the same wall: the bypasser is only ever reached from the 403 branch
|
||||
# and the AA redirect rescues. Gate on the body, not the status, so a
|
||||
# genuine overloaded-origin 503 keeps its retry path.
|
||||
if response.status_code == _HTTP_STATUS_SERVICE_UNAVAILABLE:
|
||||
marker = _response_challenge_marker(response)
|
||||
if marker and _bypass_handoff_allowed():
|
||||
if cookies:
|
||||
# Challenged while presenting clearance means those cookies
|
||||
# are dead; same reasoning as the 403 branch below.
|
||||
logger.debug(
|
||||
"503 challenge with cookies presented; purging: %s", current_url
|
||||
)
|
||||
_purge_clearance(current_url)
|
||||
logger.info(
|
||||
"503 challenge detected (%s); switching to bypasser: %s",
|
||||
marker,
|
||||
current_url,
|
||||
)
|
||||
return _run_bypasser(current_url)
|
||||
if marker:
|
||||
logger.debug(
|
||||
"503 challenge (%s) but no bypasser handoff available: %s",
|
||||
marker,
|
||||
current_url,
|
||||
)
|
||||
|
||||
if is_aa_url and response.is_redirect:
|
||||
location = response.headers.get("Location", "")
|
||||
if not location:
|
||||
@@ -356,6 +529,7 @@ def html_get_page(
|
||||
current_url = new_url
|
||||
# Reset per-request state for the new host.
|
||||
headers = {"User-Agent": DOWNLOAD_HEADERS["User-Agent"]}
|
||||
handshake_cookies.clear()
|
||||
is_aa_url = network.should_rotate_dns_for_url(current_url)
|
||||
allow_redirects = not is_aa_url
|
||||
redirects_followed = 0
|
||||
@@ -370,9 +544,35 @@ def html_get_page(
|
||||
return _result("", current_url)
|
||||
|
||||
# Same-host redirect (relative or absolute) - follow manually.
|
||||
# DDoS-Guard gates AA /search behind a cookie probe: the 302 to
|
||||
# ?check=1 carries Set-Cookie (__ddg*) which must be echoed back on
|
||||
# the next hop, or the server just re-issues the redirect forever.
|
||||
issued = _new_cookies(response, handshake_cookies)
|
||||
if issued:
|
||||
handshake_cookies.update(issued)
|
||||
redirects_followed += 1
|
||||
if redirects_followed > _MAX_REDIRECTS:
|
||||
_raise_too_many_redirects(f"Too many redirects for {current_url}")
|
||||
# A same-host redirect loop on AA is not a network fault — it is
|
||||
# how DDoS-Guard presents a handshake that is unsolved, or whose
|
||||
# clearance cookie has gone stale: /search redirects to
|
||||
# /search&check=1, which redirects back, indefinitely. Hand it
|
||||
# straight to the bypasser rather than raising, which would send it
|
||||
# down the retry path to re-run the whole loop on every attempt
|
||||
# (10 x 6 = ~60 requests to AA) without ever offering the URL to the
|
||||
# bypasser. `continue` is no use here either — it would target this
|
||||
# inner redirect loop rather than the retry branch below.
|
||||
if _bypass_handoff_allowed():
|
||||
logger.info(
|
||||
"Redirect loop detected; switching to bypasser: %s", current_url
|
||||
)
|
||||
return _redirect_loop_handoff(current_url)
|
||||
# No bypasser to hand it to. Every AA mirror shares the challenge,
|
||||
# so rotating only collects another loop — give up now instead of
|
||||
# raising and burning the same ~60 requests over the retry budget.
|
||||
logger.warning(
|
||||
"Redirect loop and no bypasser available, giving up: %s", current_url
|
||||
)
|
||||
return _result("", current_url)
|
||||
current_url = redirect_url
|
||||
continue
|
||||
|
||||
@@ -384,6 +584,21 @@ def html_get_page(
|
||||
except Exception as e:
|
||||
status = _get_status_code(e)
|
||||
|
||||
# The same DDoS-Guard rescue, for the loops the manual AA follower above hands
|
||||
# back rather than resolving inline — an AA redirect missing its Location
|
||||
# header. TooManyRedirects carries no status, so the 403 rescue below never
|
||||
# fires and every retry would re-send the dead cookies. Scoped to the hosts
|
||||
# whose redirects we follow manually: elsewhere `requests` follows them itself,
|
||||
# and a loop there is an ordinary misconfiguration that a cookie purge and a
|
||||
# minutes-long browser solve would be the wrong answer to.
|
||||
if (
|
||||
isinstance(e, requests.exceptions.TooManyRedirects)
|
||||
and network.should_rotate_dns_for_url(current_url)
|
||||
and _bypass_handoff_allowed()
|
||||
):
|
||||
logger.info("Redirect loop detected; switching to bypasser: %s", current_url)
|
||||
return _redirect_loop_handoff(current_url)
|
||||
|
||||
# 403 = Cloudflare/DDoS-Guard protection
|
||||
if status == _HTTP_STATUS_FORBIDDEN:
|
||||
# If bypasser fallback is disabled, try mirrors instead
|
||||
@@ -400,18 +615,32 @@ def html_get_page(
|
||||
# (another concurrent download may have completed bypass and extracted cookies)
|
||||
parsed = urlparse(current_url)
|
||||
fresh_cookies = get_cf_cookies_for_domain(parsed.hostname or "")
|
||||
if fresh_cookies and not cookies:
|
||||
# Cookies are now available - retry with cookies before using bypasser
|
||||
if fresh_cookies and not cookies and attempt < retry_limit:
|
||||
# Cookies are now available - retry with cookies before using bypasser.
|
||||
# Guarded on there being a next attempt: `continue` on the last one
|
||||
# ends the retry loop and abandons the request without ever offering
|
||||
# the URL to the bypasser, and MAX_RETRY=1 is the supported setting.
|
||||
# Same reasoning as the bypasser invocation below.
|
||||
logger.debug(
|
||||
"403 but cookies now available - retrying with cookies: %s",
|
||||
current_url,
|
||||
)
|
||||
continue
|
||||
if cookies:
|
||||
# Challenged *while presenting* clearance: those cookies are
|
||||
# dead. Without this they survive the solve and get merged back
|
||||
# over the fresh ones, so every later request re-presents a
|
||||
# known-rejected cookie and is challenged again - the stale
|
||||
# retry that never ends.
|
||||
logger.debug("403 with cookies presented; purging: %s", current_url)
|
||||
_purge_clearance(current_url)
|
||||
logger.info("403 detected; switching to bypasser: %s", current_url)
|
||||
if status_callback:
|
||||
status_callback("resolving", "Bypassing protection...")
|
||||
use_bypasser_now = True
|
||||
continue
|
||||
# Invoke it here rather than setting use_bypasser_now and continuing.
|
||||
# The branch that acts on that flag runs at the top of the *next* retry
|
||||
# attempt, so under the supported MAX_RETRY=1 there is no next attempt
|
||||
# and the bypasser was never reached — a 403 simply ended the search.
|
||||
# Same reasoning as the redirect-loop handoffs.
|
||||
return _run_bypasser(current_url)
|
||||
logger.warning("403 error, giving up: %s", current_url)
|
||||
return _result("", current_url)
|
||||
|
||||
@@ -420,11 +649,17 @@ def html_get_page(
|
||||
logger.warning("404 error: %s", current_url)
|
||||
return _result("", current_url)
|
||||
|
||||
# Try mirror/DNS rotation on retryable errors
|
||||
if _is_retryable_error(e):
|
||||
new_url = _try_rotation(original_url, current_url, selector)
|
||||
# Try mirror/DNS rotation on retryable errors. A failure that proves the
|
||||
# mirror is unusable also drops it from this process's rotation, so the
|
||||
# next search does not pay for it again.
|
||||
fatal_reason = _fatal_mirror_reason(e)
|
||||
if fatal_reason or _is_retryable_error(e):
|
||||
new_url = _try_rotation(
|
||||
original_url, current_url, selector, fatal_reason=fatal_reason
|
||||
)
|
||||
if new_url:
|
||||
current_url = new_url
|
||||
handshake_cookies.clear()
|
||||
continue
|
||||
|
||||
# Retry with backoff
|
||||
|
||||
+313
-54
@@ -11,6 +11,7 @@ from socket import AddressFamily, SocketKind
|
||||
from typing import TYPE_CHECKING, Any, cast
|
||||
|
||||
import dns.resolver
|
||||
import httpx
|
||||
import requests
|
||||
from dns.exception import DNSException
|
||||
|
||||
@@ -277,6 +278,14 @@ _current_aa_url_index = 0
|
||||
_aa_urls: list[str] = [] # Initialized lazily in _initialize_aa_state()
|
||||
_aa_base_url: str = "" # Current active AA URL
|
||||
|
||||
# Mirrors quarantined for this process: domains that are not a working AA mirror at
|
||||
# all (NXDOMAIN, refused, or a 200 that isn't AA - seized/parked/for-sale domains all
|
||||
# land here). Kept separate from ordinary failures: a 403 challenge or a 5xx means the
|
||||
# mirror is alive and rotating away from it only discards the DDoS-Guard clearance we
|
||||
# hold for it. Deliberately in-memory only, so a restart re-probes everything.
|
||||
_dead_aa_urls: set[str] = set()
|
||||
_dead_aa_urls_lock = _RLock()
|
||||
|
||||
|
||||
def _ensure_initialized() -> None:
|
||||
"""Lazy guard so runtime setup happens once and late calls still work."""
|
||||
@@ -298,6 +307,24 @@ DNS_PROVIDERS = [
|
||||
("opendns", ["208.67.222.222", "208.67.220.220"], "https://doh.opendns.com/dns-query"),
|
||||
]
|
||||
|
||||
# httpx raises its own hierarchy, which shares no base class with requests', so a
|
||||
# wireformat failure would escape a requests-only except clause.
|
||||
_DOH_REQUEST_ERRORS = (OSError, ValueError, requests.RequestException, httpx.HTTPError)
|
||||
|
||||
|
||||
def _first_proxy(proxies: dict[str, str] | None) -> str | None:
|
||||
"""Pick a single proxy URL from a requests-style mapping, for httpx."""
|
||||
if not proxies:
|
||||
return None
|
||||
return proxies.get("https") or proxies.get("http") or None
|
||||
|
||||
|
||||
# DoH providers that speak RFC 8484 wireformat rather than the (non-standard) JSON API
|
||||
# Cloudflare and Google popularised. Verified against the live services: both reject a
|
||||
# ?name=&type= query outright - Quad9 with 505 (it also mandates HTTP/2 per RFC 8484
|
||||
# section 5.2, which requests cannot speak), OpenDNS with 400 "No valid query received".
|
||||
_DOH_WIREFORMAT_HOSTS = frozenset({"dns.quad9.net", "doh.opendns.com"})
|
||||
|
||||
# Domain patterns that should trigger DNS rotation on failure
|
||||
DNS_ROTATION_DOMAINS = [
|
||||
"annas-archive",
|
||||
@@ -462,8 +489,16 @@ class DoHResolver:
|
||||
# DNS cache: {(hostname, record_type): (ip_list, timestamp)}
|
||||
self._cache: dict[tuple[str, str], tuple[list[str], datetime]] = {}
|
||||
|
||||
# Different headers based on provider
|
||||
if "google" in self.base_url:
|
||||
# RFC 8484 providers get a separate transport: they need wireformat, and Quad9
|
||||
# additionally refuses HTTP/1.1, which requests has no way to upgrade from.
|
||||
self.use_wireformat = urllib.parse.urlparse(self.base_url).hostname in (
|
||||
_DOH_WIREFORMAT_HOSTS
|
||||
)
|
||||
self._http2_client: Any | None = None
|
||||
|
||||
if self.use_wireformat:
|
||||
self.session.headers.update({"Accept": "application/dns-message"})
|
||||
elif "google" in self.base_url:
|
||||
self.session.headers.update(
|
||||
{
|
||||
"Accept": "application/json",
|
||||
@@ -476,6 +511,35 @@ class DoHResolver:
|
||||
}
|
||||
)
|
||||
|
||||
def _get_http2_client(self) -> Any:
|
||||
"""Lazily build the HTTP/2 client used for RFC 8484 providers.
|
||||
|
||||
Built on first use so a resolver pointed at a JSON provider never opens an
|
||||
HTTP/2 connection pool it will not use.
|
||||
"""
|
||||
if self._http2_client is None:
|
||||
self._http2_client = httpx.Client(
|
||||
http2=True,
|
||||
timeout=10,
|
||||
verify=get_ssl_verify(self.base_url),
|
||||
proxy=_first_proxy(get_proxies(self.base_url)),
|
||||
)
|
||||
return self._http2_client
|
||||
|
||||
def _resolve_wireformat(self, hostname: str, record_type: str) -> list[str]:
|
||||
"""Resolve via RFC 8484: base64url query in, DNS message out."""
|
||||
from shelfmark.download import doh_wireformat
|
||||
|
||||
qtype = doh_wireformat.TYPE_AAAA if record_type == "AAAA" else doh_wireformat.TYPE_A
|
||||
param = doh_wireformat.encode_query_param(hostname, qtype)
|
||||
response = self._get_http2_client().get(
|
||||
self.base_url,
|
||||
params={"dns": param},
|
||||
headers={"Accept": "application/dns-message"},
|
||||
)
|
||||
response.raise_for_status()
|
||||
return doh_wireformat.decode_answer(response.content, qtype)
|
||||
|
||||
def _get_cached(self, hostname: str, record_type: str) -> list[str] | None:
|
||||
"""Get cached DNS result if still valid."""
|
||||
key = (hostname, record_type)
|
||||
@@ -525,34 +589,37 @@ class DoHResolver:
|
||||
return cached
|
||||
|
||||
try:
|
||||
params = {"name": hostname, "type": "AAAA" if record_type == "AAAA" else "A"}
|
||||
if self.use_wireformat:
|
||||
answers = self._resolve_wireformat(hostname, record_type)
|
||||
else:
|
||||
params = {"name": hostname, "type": "AAAA" if record_type == "AAAA" else "A"}
|
||||
|
||||
response = self.session.get(
|
||||
self.base_url,
|
||||
params=params,
|
||||
proxies=get_proxies(self.base_url),
|
||||
timeout=10, # Increased from 5s to handle slow network conditions
|
||||
verify=get_ssl_verify(self.base_url),
|
||||
)
|
||||
response.raise_for_status()
|
||||
response = self.session.get(
|
||||
self.base_url,
|
||||
params=params,
|
||||
proxies=get_proxies(self.base_url),
|
||||
timeout=10, # Increased from 5s to handle slow network conditions
|
||||
verify=get_ssl_verify(self.base_url),
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
data = response.json()
|
||||
if "Answer" not in data:
|
||||
logger.warning("DoH resolution failed for %s: %s", hostname, data)
|
||||
return []
|
||||
data = response.json()
|
||||
if "Answer" not in data:
|
||||
logger.warning("DoH resolution failed for %s: %s", hostname, data)
|
||||
return []
|
||||
|
||||
# Extract IP addresses from the response
|
||||
answers = [
|
||||
answer["data"]
|
||||
for answer in data["Answer"]
|
||||
if answer.get("type") == (28 if record_type == "AAAA" else 1)
|
||||
]
|
||||
# Extract IP addresses from the response
|
||||
answers = [
|
||||
answer["data"]
|
||||
for answer in data["Answer"]
|
||||
if answer.get("type") == (28 if record_type == "AAAA" else 1)
|
||||
]
|
||||
|
||||
# Cache the result
|
||||
self._set_cached(hostname, record_type, answers)
|
||||
|
||||
# Don't log here - the caller (custom_getaddrinfo) will log the final result
|
||||
except (OSError, ValueError, requests.RequestException) as e:
|
||||
except _DOH_REQUEST_ERRORS as e:
|
||||
logger.warning("DoH resolution failed for %s: %s", hostname, e)
|
||||
return []
|
||||
else:
|
||||
@@ -616,8 +683,6 @@ def create_custom_getaddrinfo(
|
||||
source: str,
|
||||
provider_label: str,
|
||||
res: Sequence[tuple[AddressFamily, SocketKind, int, str, tuple[Any, ...]]],
|
||||
*,
|
||||
is_bypass: bool = False,
|
||||
) -> None:
|
||||
"""Emit a unified resolver log with the IPs returned.
|
||||
|
||||
@@ -625,7 +690,6 @@ def create_custom_getaddrinfo(
|
||||
source: Description of resolver source
|
||||
provider_label: Label for the DNS provider
|
||||
res: Resolution results
|
||||
is_bypass: If True, log at DEBUG level (for local/IP addresses)
|
||||
|
||||
"""
|
||||
# Skip logging entirely for localhost to reduce noise
|
||||
@@ -641,11 +705,7 @@ def create_custom_getaddrinfo(
|
||||
ip = sockaddr[0]
|
||||
if isinstance(ip, str):
|
||||
ips.append(ip)
|
||||
msg = f"Resolved {host_str} via {source} [{provider_label}]: {ips}"
|
||||
if is_bypass:
|
||||
logger.debug(msg)
|
||||
else:
|
||||
logger.info(msg)
|
||||
logger.debug("Resolved %s via %s [%s]: %s", host_str, source, provider_label, ips)
|
||||
|
||||
# Skip custom resolution for IP addresses, local addresses, or if skip check passes
|
||||
if (
|
||||
@@ -655,7 +715,7 @@ def create_custom_getaddrinfo(
|
||||
):
|
||||
# Quietly bypass custom resolution for IP/local targets
|
||||
res = original_getaddrinfo(host, port, family, socket_type, proto, flags)
|
||||
_log_results("system resolver (bypass)", "system", res, is_bypass=True)
|
||||
_log_results("system resolver (bypass)", "system", res)
|
||||
return res
|
||||
|
||||
results: list[tuple[AddressFamily, SocketKind, int, str, tuple[Any, ...]]] = []
|
||||
@@ -852,6 +912,99 @@ def _init_custom_resolver_internal(servers: list[str]) -> dns.resolver.Resolver:
|
||||
return custom_resolver
|
||||
|
||||
|
||||
# --- ISP / network DNS interference detection ---------------------------------
|
||||
# Compare what the (tamperable) system resolver returns for a host against a
|
||||
# tamper-resistant DoH lookup. Divergent answers are a strong signal the network is
|
||||
# hijacking or NXDOMAIN-blocking the domain (a common reason AA downloads "work" but
|
||||
# land on an ISP block page). Used to surface an actionable hint to the user.
|
||||
_dns_interference_warned: set[str] = set()
|
||||
_dns_interference_active = False
|
||||
|
||||
|
||||
def _build_detection_doh_resolver() -> DoHResolver | None:
|
||||
"""Build a throwaway DoH resolver for interference checks (no socket patching).
|
||||
|
||||
Honours the DoH provider the user selected (``DNS_PROVIDERS[_current_dns_index]``),
|
||||
falling back to the first configured provider when none is active. The endpoint is
|
||||
pinned to the provider's own nameserver IP so resolving the DoH host can't be
|
||||
redirected by the very DNS layer the check is meant to detect.
|
||||
"""
|
||||
if 0 <= _current_dns_index < len(DNS_PROVIDERS):
|
||||
_name, servers, doh_url = DNS_PROVIDERS[_current_dns_index]
|
||||
elif DNS_PROVIDERS:
|
||||
_name, servers, doh_url = DNS_PROVIDERS[0]
|
||||
else:
|
||||
return None
|
||||
server_hostname = urllib.parse.urlparse(doh_url).hostname or ""
|
||||
if not server_hostname or not servers:
|
||||
return None
|
||||
return DoHResolver(doh_url, server_hostname, servers[0])
|
||||
|
||||
|
||||
def detect_dns_interference(hostname: str) -> dict[str, list[str]] | None:
|
||||
"""Detect network DNS interference by comparing system DNS against DoH.
|
||||
|
||||
Returns ``{"system_ips": [...], "doh_ips": [...]}`` when the two resolvers disagree
|
||||
(no overlapping IPs), otherwise None. No-op for IP literals / local hostnames and
|
||||
when DoH resolution is unavailable, so it never produces a false positive.
|
||||
"""
|
||||
host = (hostname or "").strip().lower()
|
||||
if not host or _is_ip_address(host) or _is_local_address(host):
|
||||
return None
|
||||
resolver = _build_detection_doh_resolver()
|
||||
if resolver is None:
|
||||
return None
|
||||
try:
|
||||
system_ips = {str(info[4][0]) for info in original_getaddrinfo(host, 443, socket.AF_INET)}
|
||||
except OSError:
|
||||
return None
|
||||
if not system_ips:
|
||||
return None
|
||||
doh_ips = {ip for ip in resolver.resolve(host, "A") if ip}
|
||||
if not doh_ips or (system_ips & doh_ips):
|
||||
return None
|
||||
return {"system_ips": sorted(system_ips), "doh_ips": sorted(doh_ips)}
|
||||
|
||||
|
||||
def note_possible_dns_interference(hostname: str) -> bool:
|
||||
"""Check ``hostname`` for DNS interference, logging an actionable warning once.
|
||||
|
||||
Returns True when interference has been detected this session. The check runs at
|
||||
most once per host to avoid repeated DoH lookups and log spam.
|
||||
"""
|
||||
global _dns_interference_active
|
||||
host = (hostname or "").strip().lower()
|
||||
if not host or host in _dns_interference_warned:
|
||||
return _dns_interference_active
|
||||
_dns_interference_warned.add(host)
|
||||
|
||||
result = detect_dns_interference(host)
|
||||
if not result:
|
||||
return _dns_interference_active
|
||||
|
||||
_dns_interference_active = True
|
||||
routing_via_doh = _current_dns_index >= 0 and bool(DOH_SERVER)
|
||||
remedy = (
|
||||
"Shelfmark is routing this domain through DNS-over-HTTPS to work around it."
|
||||
if routing_via_doh
|
||||
else "Enable DNS-over-HTTPS (USE_DOH=true) or set a custom DNS provider to bypass it."
|
||||
)
|
||||
logger.warning(
|
||||
"Possible ISP/network DNS interference for %s: system DNS resolves to %s but DoH "
|
||||
"resolves to %s. The network appears to be blocking or redirecting this domain. %s",
|
||||
host,
|
||||
result["system_ips"],
|
||||
result["doh_ips"],
|
||||
remedy,
|
||||
)
|
||||
return True
|
||||
|
||||
|
||||
def dns_interference_detected() -> bool:
|
||||
"""Whether network DNS interference has been detected this session."""
|
||||
return _dns_interference_active
|
||||
|
||||
|
||||
def init_doh_resolver(doh_server: str = "") -> DoHResolver | None:
|
||||
"""Initialize DNS over HTTPS resolver."""
|
||||
server = doh_server or DOH_SERVER
|
||||
@@ -922,14 +1075,18 @@ def rotate_dns_and_reset_aa() -> bool:
|
||||
configured_url = _get_configured_aa_url()
|
||||
|
||||
if configured_url == "auto":
|
||||
# Auto mode always resets to the first mirror to restart the cascade
|
||||
_current_aa_url_index = 0
|
||||
if _aa_urls:
|
||||
_aa_base_url = _aa_urls[0]
|
||||
# Auto mode always resets to the first mirror to restart the cascade. Skip any
|
||||
# quarantined ones: a new DNS provider cannot revive a parked or seized domain.
|
||||
with _dead_aa_urls_lock:
|
||||
restart_urls = [url for url in _aa_urls if url not in _dead_aa_urls] or _aa_urls
|
||||
if restart_urls:
|
||||
_aa_base_url = restart_urls[0]
|
||||
_current_aa_url_index = _aa_urls.index(_aa_base_url)
|
||||
logger.info("After DNS switch, resetting AA URL to: %s", _aa_base_url)
|
||||
_save_state(aa_url=_aa_base_url)
|
||||
else:
|
||||
_aa_base_url = ""
|
||||
_current_aa_url_index = 0
|
||||
logger.info("After DNS switch, AA URL remains unconfigured")
|
||||
else:
|
||||
# Keep the user's configured primary mirror (if it exists in the list),
|
||||
@@ -1099,8 +1256,17 @@ def _initialize_aa_state() -> None:
|
||||
global _aa_base_url, _current_aa_url_index, _aa_urls
|
||||
|
||||
# Build URL list from config
|
||||
previous_urls = _aa_urls
|
||||
_aa_urls = _build_aa_urls()
|
||||
|
||||
# Drop quarantine decisions only when the mirror list itself changed - they were
|
||||
# made about a list that no longer applies. This runs on every re-init (settings
|
||||
# sync, DNS rotation, helper subprocess startup), and clearing unconditionally
|
||||
# would resurrect a parked mirror mid-session.
|
||||
if previous_urls != _aa_urls:
|
||||
with _dead_aa_urls_lock:
|
||||
_dead_aa_urls.clear()
|
||||
|
||||
# Get configured base URL from config
|
||||
configured_url = _get_configured_aa_url()
|
||||
|
||||
@@ -1116,26 +1282,34 @@ def _initialize_aa_state() -> None:
|
||||
return
|
||||
|
||||
if configured_url == "auto":
|
||||
if state.get("aa_base_url") and state["aa_base_url"] in _aa_urls:
|
||||
_current_aa_url_index = _aa_urls.index(state["aa_base_url"])
|
||||
_aa_base_url = state["aa_base_url"]
|
||||
# Never restore or probe a mirror quarantined this session: re-init happens
|
||||
# often, and re-electing a parked domain costs a wasted request every time
|
||||
# (its parking page answers 200, so the probe would happily pick it).
|
||||
with _dead_aa_urls_lock:
|
||||
candidates = [url for url in _aa_urls if url not in _dead_aa_urls]
|
||||
restored = state.get("aa_base_url")
|
||||
if restored and restored in candidates:
|
||||
_current_aa_url_index = _aa_urls.index(restored)
|
||||
_aa_base_url = restored
|
||||
else:
|
||||
logger.debug("AA_BASE_URL: auto, checking available urls %s", _aa_urls)
|
||||
for i, url in enumerate(_aa_urls):
|
||||
logger.debug("AA_BASE_URL: auto, checking available urls %s", candidates)
|
||||
for url in candidates:
|
||||
try:
|
||||
response = requests.get(
|
||||
url, proxies=get_proxies(url), timeout=3, verify=get_ssl_verify(url)
|
||||
)
|
||||
if response.status_code == HTTPStatus.OK:
|
||||
_current_aa_url_index = i
|
||||
_current_aa_url_index = _aa_urls.index(url)
|
||||
_aa_base_url = url
|
||||
_save_state(aa_url=_aa_base_url)
|
||||
break
|
||||
except (OSError, requests.RequestException) as exc:
|
||||
logger.debug("Could not reach AA mirror candidate %s: %s", url, exc)
|
||||
if not _aa_base_url or _aa_base_url == "auto":
|
||||
_aa_base_url = _aa_urls[0]
|
||||
_current_aa_url_index = 0
|
||||
# Also covers the case where every probe failed and the previous base is
|
||||
# itself quarantined - keeping it would aim the next search at a dead host.
|
||||
if not _aa_base_url or _aa_base_url == "auto" or _aa_base_url not in candidates:
|
||||
_aa_base_url = (candidates or _aa_urls)[0]
|
||||
_current_aa_url_index = _aa_urls.index(_aa_base_url)
|
||||
elif configured_url not in _aa_urls:
|
||||
logger.info("AA_BASE_URL set to custom value %s; skipping auto-switch", configured_url)
|
||||
_aa_base_url = configured_url
|
||||
@@ -1233,24 +1407,77 @@ def is_aa_auto_mode() -> bool:
|
||||
|
||||
|
||||
def get_available_aa_urls() -> list[str]:
|
||||
"""Get list of configured AA URLs (copy)."""
|
||||
"""Get configured AA URLs (copy), minus any quarantined this process.
|
||||
|
||||
Falls back to the full list when every mirror has been quarantined: a wrong
|
||||
classification must not leave the app with nowhere to search.
|
||||
"""
|
||||
_ensure_initialized()
|
||||
return _aa_urls.copy()
|
||||
with _dead_aa_urls_lock:
|
||||
alive = [url for url in _aa_urls if url not in _dead_aa_urls]
|
||||
if not alive and _aa_urls:
|
||||
logger.warning("All AA mirrors quarantined; retrying the full list")
|
||||
_dead_aa_urls.clear()
|
||||
return _aa_urls.copy()
|
||||
return alive
|
||||
|
||||
|
||||
def set_aa_url_index(new_index: int) -> bool:
|
||||
"""Set AA base URL by index in available list; returns True if applied."""
|
||||
def _aa_base_for_url(url: str) -> str:
|
||||
"""Return the configured mirror base that ``url`` belongs to, if any."""
|
||||
for base in _aa_urls:
|
||||
if base and url.startswith(base):
|
||||
return base
|
||||
return ""
|
||||
|
||||
|
||||
def mark_aa_url_dead(url: str, reason: str) -> bool:
|
||||
"""Quarantine an AA mirror for the rest of this process.
|
||||
|
||||
Only for hard evidence that the host is not a working AA mirror. Transient
|
||||
failures (403 challenge, 429, 5xx, timeouts) must never come through here -
|
||||
quarantining a live mirror throws away its bypass clearance.
|
||||
"""
|
||||
_ensure_initialized()
|
||||
base = _aa_base_for_url(url) or url
|
||||
with _dead_aa_urls_lock:
|
||||
if base not in _aa_urls or base in _dead_aa_urls:
|
||||
return False
|
||||
# Keep at least one mirror in play, even if it is the failing one.
|
||||
if len([u for u in _aa_urls if u not in _dead_aa_urls]) <= 1:
|
||||
logger.warning("Not quarantining last remaining AA mirror %s (%s)", base, reason)
|
||||
return False
|
||||
_dead_aa_urls.add(base)
|
||||
logger.warning("Quarantined AA mirror %s for this session: %s", base, reason)
|
||||
return True
|
||||
|
||||
|
||||
def get_dead_aa_urls() -> set[str]:
|
||||
"""Return the mirrors quarantined this process (copy)."""
|
||||
with _dead_aa_urls_lock:
|
||||
return set(_dead_aa_urls)
|
||||
|
||||
|
||||
def set_aa_url(url: str) -> bool:
|
||||
"""Set the active AA base URL; returns True if applied."""
|
||||
_ensure_initialized()
|
||||
global _aa_base_url, _current_aa_url_index
|
||||
if new_index < 0 or new_index >= len(_aa_urls):
|
||||
if url not in _aa_urls:
|
||||
return False
|
||||
_current_aa_url_index = new_index
|
||||
_aa_base_url = _aa_urls[_current_aa_url_index]
|
||||
_current_aa_url_index = _aa_urls.index(url)
|
||||
_aa_base_url = url
|
||||
logger.info("Set AA URL to: %s", _aa_base_url)
|
||||
_save_state(aa_url=_aa_base_url)
|
||||
return True
|
||||
|
||||
|
||||
def set_aa_url_index(new_index: int) -> bool:
|
||||
"""Set AA base URL by index in the full configured list; True if applied."""
|
||||
_ensure_initialized()
|
||||
if new_index < 0 or new_index >= len(_aa_urls):
|
||||
return False
|
||||
return set_aa_url(_aa_urls[new_index])
|
||||
|
||||
|
||||
class AAMirrorSelector:
|
||||
"""Keep AA mirror switching consistent across call sites.
|
||||
|
||||
@@ -1264,6 +1491,10 @@ class AAMirrorSelector:
|
||||
def _ensure_fresh_state(self, *, reset_attempts: bool = False) -> None:
|
||||
_ensure_initialized()
|
||||
self.aa_urls = get_available_aa_urls()
|
||||
# Rotation walks the live mirrors, but rewriting has to recognise every
|
||||
# configured base: a URL built before a mirror was quarantined still points at
|
||||
# it, and failing to rewrite would send the retry back to the dead host.
|
||||
self.all_aa_urls = _aa_urls.copy()
|
||||
self._index = self._safe_index(get_aa_base_url())
|
||||
self.current_base = self.aa_urls[self._index] if self.aa_urls else ""
|
||||
if reset_attempts:
|
||||
@@ -1276,16 +1507,41 @@ class AAMirrorSelector:
|
||||
|
||||
def rewrite(self, url: str) -> str:
|
||||
"""Replace any known AA base in url with current_base."""
|
||||
for base in self.aa_urls:
|
||||
for base in self.all_aa_urls:
|
||||
if url.startswith(base):
|
||||
return url.replace(base, self.current_base, 1)
|
||||
return url
|
||||
|
||||
def next_mirror_or_rotate_dns(self, *, allow_dns: bool = True) -> tuple[str | None, str]:
|
||||
def quarantine_current(self, reason: str) -> bool:
|
||||
"""Quarantine the mirror this selector is on (hard failures only)."""
|
||||
if not self.current_base:
|
||||
return False
|
||||
dropped = mark_aa_url_dead(self.current_base, reason)
|
||||
if dropped:
|
||||
# Rebuild from the surviving mirrors so the dead one is out of the cycle.
|
||||
self._ensure_fresh_state(reset_attempts=False)
|
||||
return dropped
|
||||
|
||||
def next_mirror_or_rotate_dns(
|
||||
self, *, allow_dns: bool = True, fatal: bool = False, reason: str = ""
|
||||
) -> tuple[str | None, str]:
|
||||
"""Advance to the next mirror or rotate DNS if needed.
|
||||
|
||||
``fatal`` marks the current mirror as not-an-AA-mirror (NXDOMAIN, refused, a
|
||||
200 that isn't AA) and drops it from this process's rotation. Leave it False
|
||||
for anything the mirror can recover from - a challenge or a 5xx means the host
|
||||
is alive, and quarantining it would discard its bypass clearance.
|
||||
|
||||
Returns (new_base, action) where action is 'mirror', 'dns', or 'exhausted'.
|
||||
"""
|
||||
if fatal and self.quarantine_current(reason or "unusable mirror"):
|
||||
# Quarantining rebuilt the state onto a surviving mirror, so that mirror is
|
||||
# the next one to try - advancing again here would skip straight past it.
|
||||
self.attempts_this_dns += 1
|
||||
if self.current_base and is_aa_auto_mode():
|
||||
set_aa_url(self.current_base)
|
||||
return self.current_base, "mirror"
|
||||
|
||||
self.attempts_this_dns += 1
|
||||
max_attempts = len(self.aa_urls) if is_aa_auto_mode() else 1
|
||||
if self.attempts_this_dns >= max_attempts:
|
||||
@@ -1298,8 +1554,11 @@ class AAMirrorSelector:
|
||||
# Mirror is explicitly configured; do not fail over to other mirrors.
|
||||
return None, "exhausted"
|
||||
|
||||
if not self.aa_urls:
|
||||
return None, "exhausted"
|
||||
|
||||
next_index = (self._index + 1) % len(self.aa_urls)
|
||||
set_aa_url_index(next_index)
|
||||
set_aa_url(self.aa_urls[next_index])
|
||||
self._ensure_fresh_state(reset_attempts=False)
|
||||
return self.current_base, "mirror"
|
||||
|
||||
|
||||
@@ -12,7 +12,7 @@ from concurrent.futures import Future, ThreadPoolExecutor
|
||||
from email.utils import parseaddr
|
||||
from pathlib import Path
|
||||
from threading import Event, Lock
|
||||
from typing import Any
|
||||
from typing import TYPE_CHECKING, Any
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
@@ -24,6 +24,7 @@ from shelfmark.core.request_helpers import (
|
||||
)
|
||||
from shelfmark.core.utils import is_audiobook as check_audiobook
|
||||
from shelfmark.core.utils import transform_cover_url
|
||||
from shelfmark.download.activity import parse_activity_grace
|
||||
from shelfmark.download.fs import run_blocking_io
|
||||
from shelfmark.download.postprocess.pipeline import is_torrent_source, safe_cleanup_path
|
||||
from shelfmark.download.postprocess.router import post_process_download
|
||||
@@ -33,6 +34,9 @@ from shelfmark.release_sources import (
|
||||
get_source_display_name,
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from collections.abc import Iterable
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
_RNG = random.SystemRandom()
|
||||
|
||||
@@ -65,7 +69,16 @@ _last_progress_value: dict[str, float] = {}
|
||||
# De-duplicate status updates (keep-alive updates shouldn't spam clients)
|
||||
_last_status_event: dict[str, tuple[str, str | None]] = {}
|
||||
STALL_TIMEOUT = 300 # 5 minutes without progress/status update = stalled
|
||||
# Absolute deadlines (time.time()) until which stall detection is suppressed for a task.
|
||||
# Long single-shot operations (protection bypass, etc.) declare their own upper bound via
|
||||
# `shelfmark.download.activity` instead of faking progress. See set_activity_grace().
|
||||
_activity_grace: dict[str, float] = {}
|
||||
# A caller cannot buy immortality: the largest grace any operation may request. Must stay
|
||||
# above the largest budget any caller can declare (see http._bypass_grace_seconds).
|
||||
_MAX_ACTIVITY_GRACE_SECONDS = 960.0
|
||||
COORDINATOR_LOOP_ERROR_RETRY_DELAY = 1.0
|
||||
# Ceiling for the exponential backoff applied to repeated coordinator loop failures.
|
||||
_COORDINATOR_LOOP_ERROR_MAX_DELAY = 30.0
|
||||
_PROGRESS_BROADCAST_START_PERCENT = 1
|
||||
_PROGRESS_BROADCAST_COMPLETE_PERCENT = 99
|
||||
_PROGRESS_BROADCAST_MIN_DELTA = 10
|
||||
@@ -170,16 +183,19 @@ def _build_retry_resolution_fields(
|
||||
retry_download_url = normalize_optional_text(release_data.get("download_url"))
|
||||
protocol = normalize_optional_text(release_data.get("protocol"))
|
||||
source = normalize_optional_text(release_data.get("source"))
|
||||
retry_source_context: dict[str, Any] = {}
|
||||
if source is not None:
|
||||
handler = get_handler(source)
|
||||
source_retry_fields = handler.build_retry_resolution_fields(release_data)
|
||||
retry_download_url = (
|
||||
normalize_optional_text(source_retry_fields.get("retry_download_url"))
|
||||
or retry_download_url
|
||||
)
|
||||
protocol = (
|
||||
normalize_optional_text(source_retry_fields.get("retry_download_protocol")) or protocol
|
||||
)
|
||||
if "retry_download_url" in source_retry_fields:
|
||||
retry_download_url = normalize_optional_text(
|
||||
source_retry_fields.get("retry_download_url")
|
||||
)
|
||||
if "retry_download_protocol" in source_retry_fields:
|
||||
protocol = normalize_optional_text(source_retry_fields.get("retry_download_protocol"))
|
||||
raw_retry_source_context = source_retry_fields.get("retry_source_context")
|
||||
if isinstance(raw_retry_source_context, dict):
|
||||
retry_source_context = dict(raw_retry_source_context)
|
||||
|
||||
ratio_limit = _optional_number(release_data.get("ratio_limit"))
|
||||
if ratio_limit is None and config.get("PROWLARR_USE_SEED_PREFERENCES", False):
|
||||
@@ -202,6 +218,7 @@ def _build_retry_resolution_fields(
|
||||
),
|
||||
"retry_ratio_limit": ratio_limit,
|
||||
"retry_seeding_time_limit_minutes": seeding_time_limit_minutes,
|
||||
"retry_source_context": retry_source_context,
|
||||
"can_retry_without_staged_source": True,
|
||||
}
|
||||
|
||||
@@ -247,6 +264,7 @@ def queue_release(
|
||||
series_name = release_data.get("series_name") or extra.get("series_name")
|
||||
series_position = release_data.get("series_position") or extra.get("series_position")
|
||||
subtitle = release_data.get("subtitle") or extra.get("subtitle")
|
||||
language = release_data.get("language") or extra.get("language")
|
||||
|
||||
books_output_mode = (
|
||||
str(config.get("BOOKS_OUTPUT_MODE", "folder", user_id=user_id) or "folder")
|
||||
@@ -281,6 +299,7 @@ def queue_release(
|
||||
series_name=series_name,
|
||||
series_position=series_position,
|
||||
subtitle=subtitle,
|
||||
language=language,
|
||||
search_mode=search_mode,
|
||||
output_mode=output_mode,
|
||||
output_args=output_args,
|
||||
@@ -400,6 +419,7 @@ def serialize_task_for_retry(task: DownloadTask) -> dict[str, Any]:
|
||||
search_mode = normalized_search_mode or None
|
||||
|
||||
raw_output_args = getattr(task, "output_args", None)
|
||||
raw_retry_source_context = getattr(task, "retry_source_context", None)
|
||||
|
||||
return {
|
||||
"task_id": getattr(task, "task_id", None),
|
||||
@@ -415,6 +435,7 @@ def serialize_task_for_retry(task: DownloadTask) -> dict[str, Any]:
|
||||
"series_name": getattr(task, "series_name", None),
|
||||
"series_position": getattr(task, "series_position", None),
|
||||
"subtitle": getattr(task, "subtitle", None),
|
||||
"language": getattr(task, "language", None),
|
||||
"search_mode": search_mode,
|
||||
"output_mode": getattr(task, "output_mode", None),
|
||||
"output_args": dict(raw_output_args) if isinstance(raw_output_args, dict) else {},
|
||||
@@ -428,6 +449,9 @@ def serialize_task_for_retry(task: DownloadTask) -> dict[str, Any]:
|
||||
"retry_expected_hash": getattr(task, "retry_expected_hash", None),
|
||||
"retry_ratio_limit": getattr(task, "retry_ratio_limit", None),
|
||||
"retry_seeding_time_limit_minutes": getattr(task, "retry_seeding_time_limit_minutes", None),
|
||||
"retry_source_context": (
|
||||
dict(raw_retry_source_context) if isinstance(raw_retry_source_context, dict) else {}
|
||||
),
|
||||
"can_retry_without_staged_source": bool(
|
||||
getattr(task, "can_retry_without_staged_source", True)
|
||||
),
|
||||
@@ -453,6 +477,7 @@ def _restore_task_from_retry_payload(payload: object) -> DownloadTask | None:
|
||||
search_mode = None
|
||||
|
||||
output_args = payload.get("output_args")
|
||||
retry_source_context = payload.get("retry_source_context")
|
||||
|
||||
return DownloadTask(
|
||||
task_id=task_id,
|
||||
@@ -468,6 +493,7 @@ def _restore_task_from_retry_payload(payload: object) -> DownloadTask | None:
|
||||
series_name=normalize_optional_text(payload.get("series_name")),
|
||||
series_position=_optional_number(payload.get("series_position")),
|
||||
subtitle=normalize_optional_text(payload.get("subtitle")),
|
||||
language=normalize_optional_text(payload.get("language")),
|
||||
search_mode=search_mode,
|
||||
output_mode=normalize_optional_text(payload.get("output_mode")),
|
||||
output_args=dict(output_args) if isinstance(output_args, dict) else {},
|
||||
@@ -483,6 +509,9 @@ def _restore_task_from_retry_payload(payload: object) -> DownloadTask | None:
|
||||
retry_seeding_time_limit_minutes=_optional_positive_int(
|
||||
payload.get("retry_seeding_time_limit_minutes")
|
||||
),
|
||||
retry_source_context=(
|
||||
dict(retry_source_context) if isinstance(retry_source_context, dict) else {}
|
||||
),
|
||||
can_retry_without_staged_source=bool(payload.get("can_retry_without_staged_source", True)),
|
||||
)
|
||||
|
||||
@@ -633,6 +662,17 @@ def _download_task(task_id: str, cancel_flag: Event) -> str | None:
|
||||
update_download_progress(task_id, progress)
|
||||
|
||||
def status_callback(status: str, message: str | None = None) -> None:
|
||||
# Liveness hint from a long single-shot operation, not a user-visible status.
|
||||
# Handled here so it never reaches update_download_status (which dedupes status
|
||||
# transitions on purpose). See shelfmark.download.activity.
|
||||
grace = parse_activity_grace(status, message)
|
||||
if grace is not None:
|
||||
if grace > 0:
|
||||
set_activity_grace(task_id, grace)
|
||||
else:
|
||||
clear_activity_grace(task_id)
|
||||
return
|
||||
|
||||
status_key = status.lower()
|
||||
if status_key == "error":
|
||||
_capture_task_error(
|
||||
@@ -870,6 +910,7 @@ def _cleanup_progress_tracking(task_id: str) -> None:
|
||||
_last_activity.pop(task_id, None)
|
||||
_last_progress_value.pop(task_id, None)
|
||||
_last_status_event.pop(task_id, None)
|
||||
_activity_grace.pop(task_id, None)
|
||||
|
||||
|
||||
def _finalize_download_failure(task_id: str) -> None:
|
||||
@@ -917,6 +958,66 @@ def _process_single_download(task_id: str, cancel_flag: Event) -> None:
|
||||
ws_manager.broadcast_status_update(queue_status())
|
||||
|
||||
|
||||
def set_activity_grace(book_id: str, seconds: float) -> None:
|
||||
"""Suppress stall detection for `book_id` for up to `seconds` from now.
|
||||
|
||||
For long single-shot operations that cannot report incremental progress (protection
|
||||
bypass being the motivating case). The grace is a single absolute deadline computed
|
||||
once, so it cannot be extended into immortality by a keep-alive that carries no real
|
||||
liveness information - an operation that hangs forever is still cancelled once its
|
||||
declared budget expires.
|
||||
|
||||
Deliberately touches neither the queue nor the WebSocket: this is a liveness
|
||||
assertion, not a user-visible status transition.
|
||||
"""
|
||||
grace = _config_float(seconds, 0.0)
|
||||
grace = min(max(grace, 0.0), _MAX_ACTIVITY_GRACE_SECONDS)
|
||||
with _progress_lock:
|
||||
_activity_grace[book_id] = time.time() + grace
|
||||
|
||||
|
||||
def clear_activity_grace(book_id: str) -> None:
|
||||
"""Drop any activity grace for `book_id` and count this moment as activity.
|
||||
|
||||
Resetting `_last_activity` means a nested or abandoned grace degrades to a fresh
|
||||
full STALL_TIMEOUT window rather than an immediate stall.
|
||||
"""
|
||||
with _progress_lock:
|
||||
_activity_grace.pop(book_id, None)
|
||||
_last_activity[book_id] = time.time()
|
||||
|
||||
|
||||
def _find_stalled_tasks(task_ids: Iterable[str], now: float) -> list[str]:
|
||||
"""Return the task ids with no activity inside STALL_TIMEOUT and no active grace.
|
||||
|
||||
Holds `_progress_lock` for dict reads only - never call into `book_queue` from here,
|
||||
see _cancel_stalled_task().
|
||||
"""
|
||||
stalled: list[str] = []
|
||||
with _progress_lock:
|
||||
for task_id in task_ids:
|
||||
last_active = _last_activity.get(task_id, now)
|
||||
deadline = max(last_active + STALL_TIMEOUT, _activity_grace.get(task_id, 0.0))
|
||||
if now > deadline:
|
||||
stalled.append(task_id)
|
||||
return stalled
|
||||
|
||||
|
||||
def _cancel_stalled_task(task_id: str) -> None:
|
||||
"""Cancel a stalled download.
|
||||
|
||||
Must be called WITHOUT `_progress_lock` held. `book_queue.cancel_download` runs the
|
||||
terminal-status hooks, which reach a sqlite write that gevent does not patch; holding
|
||||
the progress lock across that blocks the hub and every other download worker.
|
||||
"""
|
||||
logger.warning("Download stalled for %s, cancelling", task_id)
|
||||
book_queue.cancel_download(task_id)
|
||||
book_queue.update_status_message(
|
||||
task_id,
|
||||
f"Download stalled (no activity for {STALL_TIMEOUT}s)",
|
||||
)
|
||||
|
||||
|
||||
def concurrent_download_loop() -> None:
|
||||
"""Run the main concurrent download coordinator."""
|
||||
max_workers = normalize_positive_int(config.MAX_CONCURRENT_DOWNLOADS) or 1
|
||||
@@ -926,6 +1027,7 @@ def concurrent_download_loop() -> None:
|
||||
with ThreadPoolExecutor(max_workers=max_workers, thread_name_prefix="Download") as executor:
|
||||
active_futures: dict[Future, tuple[str, Event]] = {} # Track active download futures
|
||||
stalled_tasks: set[str] = set() # Track tasks already cancelled due to stall
|
||||
consecutive_errors = 0
|
||||
|
||||
while True:
|
||||
try:
|
||||
@@ -976,19 +1078,14 @@ def concurrent_download_loop() -> None:
|
||||
|
||||
# Check for stalled downloads (no activity in STALL_TIMEOUT seconds)
|
||||
current_time = time.time()
|
||||
with _progress_lock:
|
||||
for _future, (task_id, _cancel_flag) in list(active_futures.items()):
|
||||
if task_id in stalled_tasks:
|
||||
continue
|
||||
last_active = _last_activity.get(task_id, current_time)
|
||||
if current_time - last_active > STALL_TIMEOUT:
|
||||
logger.warning("Download stalled for %s, cancelling", task_id)
|
||||
book_queue.cancel_download(task_id)
|
||||
book_queue.update_status_message(
|
||||
task_id,
|
||||
f"Download stalled (no activity for {STALL_TIMEOUT}s)",
|
||||
)
|
||||
stalled_tasks.add(task_id)
|
||||
candidates = [
|
||||
task_id
|
||||
for _future, (task_id, _cancel_flag) in list(active_futures.items())
|
||||
if task_id not in stalled_tasks
|
||||
]
|
||||
for task_id in _find_stalled_tasks(candidates, current_time):
|
||||
_cancel_stalled_task(task_id)
|
||||
stalled_tasks.add(task_id)
|
||||
|
||||
# Start new downloads if we have capacity
|
||||
while len(active_futures) < max_workers:
|
||||
@@ -1011,9 +1108,24 @@ def concurrent_download_loop() -> None:
|
||||
|
||||
# Brief sleep to prevent busy waiting
|
||||
time.sleep(main_loop_sleep_time)
|
||||
except (AttributeError, KeyError, OSError, RuntimeError, TypeError, ValueError) as e:
|
||||
consecutive_errors = 0
|
||||
# This loop is the only thing driving the download queue; if it exits, nothing
|
||||
# is ever picked up again and the app looks healthy while doing nothing (#823,
|
||||
# #1166). A narrow exception list let gevent's LoopExit and friends through, so
|
||||
# catch everything short of BaseException - GreenletExit and gevent.Timeout must
|
||||
# still propagate, and the tests' loop-stopping sentinels derive from
|
||||
# BaseException for exactly this reason.
|
||||
except Exception as e: # noqa: BLE001 - coordinator loop must never die
|
||||
consecutive_errors += 1
|
||||
logger.error_trace("Download coordinator loop error: %s", e)
|
||||
time.sleep(COORDINATOR_LOOP_ERROR_RETRY_DELAY)
|
||||
# Back off when the failure is persistent so we don't spin at 1Hz forever,
|
||||
# but keep the first delay unchanged for a normal transient blip.
|
||||
time.sleep(
|
||||
min(
|
||||
COORDINATOR_LOOP_ERROR_RETRY_DELAY * 2 ** min(consecutive_errors - 1, 5),
|
||||
_COORDINATOR_LOOP_ERROR_MAX_DELAY,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
# Download coordinator thread (started explicitly via start())
|
||||
|
||||
@@ -229,6 +229,7 @@ def _build_custom_script_payload(
|
||||
"series_name": context.task.series_name,
|
||||
"series_position": context.task.series_position,
|
||||
"subtitle": context.task.subtitle,
|
||||
"language": context.task.language,
|
||||
"original_download_path": context.task.original_download_path,
|
||||
},
|
||||
"output": {
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import contextlib
|
||||
import uuid
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from shelfmark.core.logger import setup_logger
|
||||
@@ -13,7 +12,11 @@ from shelfmark.core.utils import (
|
||||
from shelfmark.core.utils import (
|
||||
is_audiobook as check_audiobook,
|
||||
)
|
||||
from shelfmark.download.fs import run_blocking_io
|
||||
from shelfmark.download.fs import (
|
||||
clear_delete_denied,
|
||||
mark_delete_denied,
|
||||
run_blocking_io,
|
||||
)
|
||||
from shelfmark.download.permissions_debug import log_path_permission_context
|
||||
from shelfmark.release_sources import get_source
|
||||
|
||||
@@ -25,6 +28,8 @@ if TYPE_CHECKING:
|
||||
|
||||
logger = setup_logger("shelfmark.download.postprocess.pipeline")
|
||||
|
||||
_WRITE_PROBE_NAME = ".shelfmark_write_test.tmp"
|
||||
|
||||
|
||||
def validate_destination(
|
||||
destination: Path, status_callback: Callable[[str, str | None], None]
|
||||
@@ -52,7 +57,9 @@ def validate_destination(
|
||||
status_callback("error", f"Cannot create destination: {destination} ({exc})")
|
||||
return False
|
||||
|
||||
test_path = destination / f".shelfmark_write_test_{uuid.uuid4().hex}.tmp"
|
||||
# Stable name: on shares that refuse deletes the probe file cannot be cleaned
|
||||
# up, so reusing one name bounds the leftovers at a single hidden file.
|
||||
test_path = destination / _WRITE_PROBE_NAME
|
||||
|
||||
try:
|
||||
test_content = (
|
||||
@@ -60,7 +67,6 @@ def validate_destination(
|
||||
"It should've been automatically deleted. Feel free to delete it.\n"
|
||||
)
|
||||
run_blocking_io(test_path.write_text, test_content)
|
||||
run_blocking_io(test_path.unlink, missing_ok=True)
|
||||
except OSError as exc:
|
||||
logger.debug("Destination write probe path: %s", test_path)
|
||||
log_path_permission_context("destination_write_probe", destination)
|
||||
@@ -71,6 +77,23 @@ def validate_destination(
|
||||
run_blocking_io(destination.rmdir)
|
||||
return False
|
||||
|
||||
try:
|
||||
run_blocking_io(test_path.unlink, missing_ok=True)
|
||||
except OSError as exc:
|
||||
# Writable but not deletable, e.g. a Synology share with "Delete
|
||||
# subfolders and files" unticked. Not fatal: record it so transfers write
|
||||
# files in place instead of publishing a temp file via rename.
|
||||
mark_delete_denied(destination)
|
||||
logger.warning(
|
||||
"Destination %s is writable but refuses deletes (%s); leaving probe file %s "
|
||||
"behind and writing files in place",
|
||||
destination,
|
||||
exc,
|
||||
test_path.name,
|
||||
)
|
||||
else:
|
||||
clear_delete_denied(destination)
|
||||
|
||||
return True
|
||||
|
||||
|
||||
|
||||
@@ -7,6 +7,7 @@ from pathlib import Path
|
||||
from typing import TYPE_CHECKING
|
||||
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.utils import AUDIOBOOK_FORMATS
|
||||
from shelfmark.core.utils import is_audiobook as check_audiobook
|
||||
from shelfmark.download.archive import ArchiveExtractionError, extract_archive, is_archive
|
||||
from shelfmark.download.fs import run_blocking_io
|
||||
@@ -142,7 +143,7 @@ def scan_directory_tree(
|
||||
|
||||
is_audiobook = check_audiobook(content_type)
|
||||
if is_audiobook:
|
||||
trackable_exts = {".m4b", ".mp3", ".m4a", ".flac", ".ogg", ".wma", ".aac", ".wav"}
|
||||
trackable_exts = {f".{fmt}" for fmt in AUDIOBOOK_FORMATS}
|
||||
else:
|
||||
trackable_exts = {
|
||||
".pdf",
|
||||
@@ -367,7 +368,7 @@ def collect_staged_files(
|
||||
|
||||
is_audiobook = check_audiobook(task.content_type)
|
||||
if is_audiobook:
|
||||
trackable_exts = {".m4b", ".mp3", ".m4a", ".flac", ".ogg", ".wma", ".aac", ".wav"}
|
||||
trackable_exts = {f".{fmt}" for fmt in AUDIOBOOK_FORMATS}
|
||||
else:
|
||||
trackable_exts = {
|
||||
".pdf",
|
||||
|
||||
@@ -12,6 +12,7 @@ from shelfmark.core.naming import (
|
||||
assign_part_numbers,
|
||||
build_library_path,
|
||||
derive_primary_title,
|
||||
normalize_language_code,
|
||||
parse_naming_template,
|
||||
sanitize_filename,
|
||||
)
|
||||
@@ -63,6 +64,7 @@ def build_metadata_dict(task: DownloadTask) -> dict:
|
||||
"Year": task.year,
|
||||
"Series": task.series_name,
|
||||
"SeriesPosition": task.series_position,
|
||||
"Language": normalize_language_code(task.language),
|
||||
"User": task.username,
|
||||
}
|
||||
|
||||
|
||||
@@ -0,0 +1,134 @@
|
||||
"""Boot-time warm-up of the direct-download source.
|
||||
|
||||
The first AA search after a cold start pays for the whole cold path at once: DNS
|
||||
resolution, electing a live mirror, spinning up headless Chrome and solving the
|
||||
DDoS-Guard challenge. That is tens of seconds with the user sat at the search box.
|
||||
|
||||
Running one throwaway search shortly after boot moves that cost off the user's first
|
||||
search. It primes the DNS cache, elects (and quarantines) mirrors, and leaves the
|
||||
clearance cookie in the bypasser's per-domain cache, so the first real search reuses
|
||||
it instead of solving from scratch.
|
||||
|
||||
Runs on a daemon thread and swallows every failure: this is an optimisation, and a
|
||||
source that is down at boot must not affect startup or health.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import os
|
||||
import threading
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# Delay before the warm-up fires. Long enough that it does not compete with the rest
|
||||
# of startup (and with a container's own health probe) for the first request.
|
||||
_DEFAULT_DELAY_SECONDS = 15.0
|
||||
|
||||
_DEFAULT_QUERY = "The Great Gatsby"
|
||||
|
||||
_warmup_thread: threading.Thread | None = None
|
||||
_warmup_lock = threading.Lock()
|
||||
|
||||
|
||||
def _as_bool(value: object, *, default: bool) -> bool:
|
||||
"""Coerce a config value that may arrive as a string, bool or None."""
|
||||
if value is None:
|
||||
return default
|
||||
if isinstance(value, str):
|
||||
from shelfmark.config.env import string_to_bool
|
||||
|
||||
return string_to_bool(value)
|
||||
return bool(value)
|
||||
|
||||
|
||||
def _setting(key: str, default: object) -> object:
|
||||
"""Read a warm-up setting, preferring the deployment environment.
|
||||
|
||||
These keys are not in the settings registry, and ``config.get`` only consults the
|
||||
environment for keys it knows about - so reading config alone silently ignored
|
||||
SEARCH_WARMUP_ENABLED and always returned the default. Check os.environ first so
|
||||
the documented switches actually work.
|
||||
"""
|
||||
raw = os.environ.get(key)
|
||||
if raw is not None and raw.strip():
|
||||
return raw
|
||||
return config.get(key, default)
|
||||
|
||||
|
||||
def is_enabled() -> bool:
|
||||
"""Whether the boot-time warm-up search should run."""
|
||||
if not _as_bool(_setting("SEARCH_WARMUP_ENABLED", True), default=True):
|
||||
return False
|
||||
# Nothing to warm if the source is off, and no challenge to pre-solve without
|
||||
# the bypasser - a plain search is fast enough not to need this.
|
||||
if not _as_bool(_setting("DIRECT_DOWNLOAD_ENABLED", True), default=True):
|
||||
logger.debug("Search warm-up skipped: direct download disabled")
|
||||
return False
|
||||
return True
|
||||
|
||||
|
||||
def warmup_query() -> str:
|
||||
"""The query used to warm the source."""
|
||||
raw = _setting("SEARCH_WARMUP_QUERY", _DEFAULT_QUERY)
|
||||
query = str(raw).strip() if raw else ""
|
||||
return query or _DEFAULT_QUERY
|
||||
|
||||
|
||||
def run_warmup() -> bool:
|
||||
"""Run one warm-up search. Returns True if it produced results.
|
||||
|
||||
Never raises: every failure mode here is one the next real search would hit
|
||||
anyway, and reporting it is the search path's job, not the warm-up's.
|
||||
"""
|
||||
from shelfmark.core.mirrors import has_aa_mirror_configuration
|
||||
|
||||
if not has_aa_mirror_configuration():
|
||||
logger.debug("Search warm-up skipped: no Anna's Archive mirrors configured")
|
||||
return False
|
||||
|
||||
query = warmup_query()
|
||||
logger.info("Warming up direct download search (%r)", query)
|
||||
try:
|
||||
from shelfmark.core.models import SearchFilters
|
||||
from shelfmark.release_sources.direct_download import search_books
|
||||
|
||||
results = search_books(query, SearchFilters())
|
||||
except Exception:
|
||||
# Broad by design: a warm-up must never take the app down, and the source
|
||||
# raises everything from network errors to parse failures.
|
||||
logger.warning("Search warm-up did not complete; first user search may be slow")
|
||||
logger.debug("Search warm-up failure detail", exc_info=True)
|
||||
return False
|
||||
|
||||
if results:
|
||||
logger.info("Search warm-up complete: %s results, source is ready", len(results))
|
||||
return True
|
||||
logger.info("Search warm-up returned no results; source reachable but empty")
|
||||
return False
|
||||
|
||||
|
||||
def start(delay_seconds: float = _DEFAULT_DELAY_SECONDS) -> bool:
|
||||
"""Schedule the warm-up on a daemon thread. Safe to call multiple times."""
|
||||
global _warmup_thread
|
||||
|
||||
if not is_enabled():
|
||||
return False
|
||||
|
||||
with _warmup_lock:
|
||||
if _warmup_thread is not None and _warmup_thread.is_alive():
|
||||
logger.debug("Search warm-up already scheduled")
|
||||
return False
|
||||
|
||||
def _run() -> None:
|
||||
run_warmup()
|
||||
|
||||
_warmup_thread = threading.Timer(delay_seconds, _run)
|
||||
_warmup_thread.daemon = True
|
||||
_warmup_thread.name = "SearchWarmup"
|
||||
_warmup_thread.start()
|
||||
|
||||
logger.debug("Search warm-up scheduled in %ss", delay_seconds)
|
||||
return True
|
||||
+15
-16
@@ -38,7 +38,10 @@ from shelfmark.config.env import (
|
||||
string_to_bool,
|
||||
)
|
||||
from shelfmark.config.security import _migrate_security_settings
|
||||
from shelfmark.config.settings import _SUPPORTED_BOOK_LANGUAGE
|
||||
from shelfmark.config.settings import (
|
||||
_SUPPORTED_BOOK_LANGUAGE,
|
||||
migrate_audiobook_format_settings,
|
||||
)
|
||||
from shelfmark.core.activity_view_state_service import ActivityViewStateService
|
||||
from shelfmark.core.auth_modes import (
|
||||
get_auth_check_admin_status,
|
||||
@@ -80,8 +83,9 @@ from shelfmark.core.requests_service import (
|
||||
sync_delivery_states_from_queue_status,
|
||||
)
|
||||
from shelfmark.core.user_db import UserDB
|
||||
from shelfmark.core.utils import normalize_base_path
|
||||
from shelfmark.core.utils import AUDIOBOOK_FORMATS, normalize_base_path
|
||||
from shelfmark.download import orchestrator as backend
|
||||
from shelfmark.download import warmup
|
||||
from shelfmark.release_sources import (
|
||||
BrowseRecord,
|
||||
Release,
|
||||
@@ -118,7 +122,7 @@ BASE_PATH = normalize_base_path(normalize_optional_text(app_config.get("URL_BASE
|
||||
app = Flask(__name__)
|
||||
app.config["SEND_FILE_MAX_AGE_DEFAULT"] = 0 # Disable caching
|
||||
app.config["APPLICATION_ROOT"] = BASE_PATH or "/"
|
||||
wsgi_app = cast(Any, ProxyFix(app.wsgi_app))
|
||||
wsgi_app = cast(Any, ProxyFix(app.wsgi_app, x_host=1, x_port=1))
|
||||
if BASE_PATH:
|
||||
wsgi_app = cast(Any, PrefixMiddleware(wsgi_app, BASE_PATH, bypass_paths={"/api/health"}))
|
||||
app.wsgi_app = wsgi_app
|
||||
@@ -168,6 +172,9 @@ except ImportError as e:
|
||||
# Migrate legacy security settings if needed
|
||||
_migrate_security_settings()
|
||||
|
||||
# Widen audiobook formats for installs that still carry the old m4b/mp3-only default
|
||||
migrate_audiobook_format_settings()
|
||||
|
||||
# Initialize user database and register multi-user routes
|
||||
# If CONFIG_DIR doesn't exist or is read-only, multi-user features will be disabled
|
||||
_user_db_path = str(Path(os.environ.get("CONFIG_DIR", "/config")) / "users.db")
|
||||
@@ -200,6 +207,10 @@ except (sqlite3.OperationalError, OSError) as e:
|
||||
# Start download coordinator
|
||||
backend.start()
|
||||
|
||||
# Pre-solve the direct-download source's protection challenge in the background so the
|
||||
# first user search does not pay for a cold Chrome bypass. Never blocks startup.
|
||||
warmup.start()
|
||||
|
||||
# Rate limiting for login attempts
|
||||
# Map usernames to their failed-attempt counters and lockout timestamps.
|
||||
failed_login_attempts: dict[str, dict[str, Any]] = {}
|
||||
@@ -319,19 +330,7 @@ def get_auth_mode() -> str:
|
||||
|
||||
|
||||
_AUDIOBOOK_CATEGORY_RANGE = (3030, 3049)
|
||||
_AUDIOBOOK_FORMAT_HINTS = frozenset(
|
||||
{
|
||||
"m4b",
|
||||
"mp3",
|
||||
"m4a",
|
||||
"flac",
|
||||
"ogg",
|
||||
"wma",
|
||||
"aac",
|
||||
"wav",
|
||||
"opus",
|
||||
}
|
||||
)
|
||||
_AUDIOBOOK_FORMAT_HINTS = frozenset(AUDIOBOOK_FORMATS)
|
||||
|
||||
|
||||
def _contains_audiobook_format_hint(value: Any) -> bool:
|
||||
|
||||
@@ -24,12 +24,12 @@ Dataclass representing a book from a metadata provider:
|
||||
```python
|
||||
@dataclass
|
||||
class BookMetadata:
|
||||
provider: str # Internal provider name (e.g., "hardcover")
|
||||
provider_id: str # ID in that provider's system
|
||||
provider: str # Internal provider name (e.g., "hardcover")
|
||||
provider_id: str # ID in that provider's system
|
||||
title: str
|
||||
|
||||
# Optional fields
|
||||
provider_display_name: str # Human-readable name (e.g., "Hardcover")
|
||||
provider_display_name: str # Human-readable name (e.g., "Hardcover")
|
||||
authors: List[str]
|
||||
isbn_10: str
|
||||
isbn_13: str
|
||||
@@ -39,7 +39,7 @@ class BookMetadata:
|
||||
publish_year: int
|
||||
language: str
|
||||
genres: List[str]
|
||||
source_url: str # Link to book on provider's site
|
||||
source_url: str # Link to book on provider's site
|
||||
display_fields: List[DisplayField] # Provider-specific display data
|
||||
```
|
||||
|
||||
@@ -50,9 +50,9 @@ Provider-specific metadata for UI cards (ratings, page counts, reader counts, et
|
||||
```python
|
||||
@dataclass
|
||||
class DisplayField:
|
||||
label: str # e.g., "Rating", "Pages", "Readers"
|
||||
value: str # e.g., "4.5", "496", "8,041"
|
||||
icon: str # Icon name: "star", "book", "users", "editions"
|
||||
label: str # e.g., "Rating", "Pages", "Readers"
|
||||
value: str # e.g., "4.5", "496", "8,041"
|
||||
icon: str # Icon name: "star", "book", "users", "editions"
|
||||
```
|
||||
|
||||
### MetadataSearchOptions
|
||||
@@ -64,7 +64,7 @@ Unified search options that work across all providers:
|
||||
class MetadataSearchOptions:
|
||||
query: str
|
||||
search_type: SearchType = SearchType.GENERAL # GENERAL, TITLE, AUTHOR, ISBN
|
||||
language: str = None # ISO 639-1 code (e.g., "en")
|
||||
language: str = None # ISO 639-1 code (e.g., "en")
|
||||
sort: SortOrder = SortOrder.RELEVANCE
|
||||
limit: int = 40
|
||||
page: int = 1
|
||||
@@ -88,10 +88,10 @@ All providers must implement this interface:
|
||||
|
||||
```python
|
||||
class MetadataProvider(ABC):
|
||||
name: str # Internal identifier
|
||||
display_name: str # Human-readable name
|
||||
requires_auth: bool # True if API key required
|
||||
supported_sorts: List[SortOrder] # Supported sort options
|
||||
name: str # Internal identifier
|
||||
display_name: str # Human-readable name
|
||||
requires_auth: bool # True if API key required
|
||||
supported_sorts: List[SortOrder] # Supported sort options
|
||||
|
||||
@abstractmethod
|
||||
def search(self, options: MetadataSearchOptions) -> List[BookMetadata]:
|
||||
@@ -121,9 +121,9 @@ class MetadataProvider(ABC):
|
||||
```python
|
||||
from shelfmark.metadata_providers import register_provider
|
||||
|
||||
|
||||
@register_provider("my_provider")
|
||||
class MyProvider(MetadataProvider):
|
||||
...
|
||||
class MyProvider(MetadataProvider): ...
|
||||
```
|
||||
|
||||
### Getting Providers
|
||||
@@ -281,11 +281,13 @@ from shelfmark.config.env import (
|
||||
METADATA_CACHE_BOOK_TTL,
|
||||
)
|
||||
|
||||
|
||||
@cacheable(ttl=METADATA_CACHE_SEARCH_TTL, key_prefix="myprovider:search")
|
||||
def _search_cached(self, cache_key: str, options: MetadataSearchOptions):
|
||||
# Cached search implementation
|
||||
pass
|
||||
|
||||
|
||||
@cacheable(ttl=METADATA_CACHE_BOOK_TTL, key_prefix="myprovider:book")
|
||||
def get_book(self, book_id: str):
|
||||
# Cached book lookup
|
||||
@@ -302,6 +304,7 @@ from shelfmark.metadata_providers.openlibrary import RateLimiter
|
||||
# 90 requests per 60 seconds
|
||||
rate_limiter = RateLimiter(max_requests=90, window_seconds=60)
|
||||
|
||||
|
||||
def make_request(self):
|
||||
rate_limiter.wait_if_needed() # Blocks if rate limited
|
||||
# ... make request
|
||||
|
||||
@@ -709,3 +709,6 @@ with suppress(ImportError):
|
||||
|
||||
with suppress(ImportError):
|
||||
from shelfmark.metadata_providers import googlebooks as googlebooks
|
||||
|
||||
with suppress(ImportError):
|
||||
from shelfmark.metadata_providers import moly as moly
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
"""Hardcover.app metadata provider. Requires API key."""
|
||||
|
||||
import re
|
||||
import time
|
||||
from contextlib import suppress
|
||||
from dataclasses import dataclass
|
||||
from datetime import UTC, datetime
|
||||
@@ -47,6 +48,10 @@ HARDCOVER_PAGE_SIZE = 25 # Hardcover API returns max 25 results per page
|
||||
HARDCOVER_MIN_AUTHOR_PARTS = 2
|
||||
HARDCOVER_MIN_TYPEAHEAD_QUERY_LENGTH = 2
|
||||
HARDCOVER_MAX_SERIES_OPTIONS = 7
|
||||
# Hardcover hands out short opaque tokens now ("hc_pat_...") instead of the ~500 char
|
||||
# JWTs it used to, so the length floor only applies to keys without that prefix.
|
||||
HARDCOVER_API_KEY_PREFIX = "hc_pat_"
|
||||
HARDCOVER_BEARER_PREFIX_PATTERN = re.compile(r"^bearer\s+", re.IGNORECASE)
|
||||
HARDCOVER_API_KEY_MIN_LENGTH = 100
|
||||
HARDCOVER_LIST_URL_PATTERN = re.compile(
|
||||
r"^/(?:@([\w.-]+)/)?lists?/([\w-]+)/?$",
|
||||
@@ -317,6 +322,7 @@ query SearchFieldOptions(
|
||||
fields: $fields,
|
||||
weights: $weights
|
||||
) {
|
||||
error
|
||||
results
|
||||
}
|
||||
}
|
||||
@@ -535,13 +541,19 @@ SORT_MAPPING: dict[SortOrder, str] = {
|
||||
SortOrder.OLDEST: "release_year:asc",
|
||||
}
|
||||
|
||||
# Mapping from abstract search type to Hardcover fields parameter
|
||||
SEARCH_TYPE_FIELDS: dict[SearchType, str] = {
|
||||
SearchType.GENERAL: "title,isbns,series_names,author_names,alternative_titles",
|
||||
SearchType.TITLE: "title,alternative_titles",
|
||||
SearchType.AUTHOR: "author_names",
|
||||
# ISBN is handled separately via search_by_isbn()
|
||||
}
|
||||
# `fields` becomes Typesense's `query_by`, but Hardcover keeps `num_typos` and
|
||||
# `query_by_weights` as fixed-length presets per query_type. Passing a different
|
||||
# number of fields than the preset expects makes Typesense reject the whole search,
|
||||
# complaining that the number of num_typos values does not match the number of
|
||||
# query_by fields. So a Book search may only ever narrow to *these five* names --
|
||||
# a shorter list is rejected outright rather than searched, and any weights sent
|
||||
# alongside must match one-for-one.
|
||||
# Weights only bias ranking: a field weighted 0 still matches, so `fields` can no
|
||||
# longer restrict which fields a Book query looks at.
|
||||
BOOK_SEARCH_FIELDS = "title,alternative_titles,author_names,series_names,isbns"
|
||||
BOOK_SEARCH_FIELD_COUNT = 5
|
||||
BOOK_TITLE_WEIGHTS = "5,1,0,0,0"
|
||||
BOOK_TITLE_AUTHOR_WEIGHTS = "5,1,3,0,0"
|
||||
|
||||
SERIES_SEARCH_FIELDS = "name,books,author_name"
|
||||
SERIES_SEARCH_WEIGHTS = "2,1,1"
|
||||
@@ -549,10 +561,52 @@ SERIES_SEARCH_SORT = "_text_match:desc,readers_count:desc"
|
||||
AUTHOR_SUGGESTION_FIELDS = "name,name_personal,alternate_names"
|
||||
AUTHOR_SUGGESTION_WEIGHTS = "4,3,2"
|
||||
AUTHOR_SUGGESTION_SORT = "_text_match:desc,books_count:desc"
|
||||
TITLE_SUGGESTION_FIELDS = "title,alternative_titles"
|
||||
TITLE_SUGGESTION_WEIGHTS = "5,2"
|
||||
TITLE_SUGGESTION_FIELDS = BOOK_SEARCH_FIELDS
|
||||
TITLE_SUGGESTION_WEIGHTS = "5,2,0,0,0"
|
||||
TITLE_SUGGESTION_SORT = "_text_match:desc,users_count:desc"
|
||||
|
||||
# Hardcover forwards `sort` to Typesense's `sort_by` and rejects the whole search
|
||||
# if it does not like the value -- an unknown field, a bare field name with no
|
||||
# direction, more than three keys. A rejected search comes back as HTTP 200 with
|
||||
# no GraphQL errors and a null `results` body, which is otherwise indistinguishable
|
||||
# from "nothing matched"; the reason only shows up in the sibling `error` field,
|
||||
# so every search asks for it. Dropping `sort` from the request is the one shape
|
||||
# Hardcover always accepts -- an empty string is a value like any other and has
|
||||
# been rejected too -- so retry that way and keep the fallback sticky for a while
|
||||
# rather than paying for a doomed request on every search.
|
||||
SORT_FALLBACK_TTL = 900.0
|
||||
_sort_fallback_until = 0.0
|
||||
|
||||
|
||||
def _without_sort(variables: dict[str, Any]) -> dict[str, Any]:
|
||||
"""Drop `sort` entirely so Hardcover applies its own default ordering."""
|
||||
return {key: value for key, value in variables.items() if key != "sort"}
|
||||
|
||||
|
||||
def _search_payload_rejected(result: dict[str, Any] | None) -> bool:
|
||||
"""Report whether Hardcover answered a search with a null results body.
|
||||
|
||||
A search that genuinely matched nothing still returns a results object with
|
||||
``found: 0``; only a rejected search nulls it out entirely.
|
||||
"""
|
||||
if not isinstance(result, dict):
|
||||
return False
|
||||
root = result.get("search", result)
|
||||
if not isinstance(root, dict) or "results" not in root:
|
||||
return False
|
||||
return root["results"] is None
|
||||
|
||||
|
||||
def _search_rejection_reason(result: dict[str, Any] | None) -> str:
|
||||
"""Return Hardcover's explanation for a rejected search, if it sent one."""
|
||||
if not isinstance(result, dict):
|
||||
return ""
|
||||
root = result.get("search", result)
|
||||
if not isinstance(root, dict):
|
||||
return ""
|
||||
error = root.get("error")
|
||||
return error.strip() if isinstance(error, str) else ""
|
||||
|
||||
|
||||
def _combine_headline_description(headline: str | None, description: str | None) -> str | None:
|
||||
"""Combine headline (tagline) and description into a single description."""
|
||||
@@ -620,7 +674,7 @@ def _normalize_series_position(value: Any) -> float | None:
|
||||
def _normalize_hardcover_api_key(value: object) -> str:
|
||||
"""Normalize Hardcover API keys, stripping copied auth-header prefixes."""
|
||||
normalized_value = normalize_optional_text(value) or ""
|
||||
return normalized_value.removeprefix("Bearer ").strip()
|
||||
return HARDCOVER_BEARER_PREFIX_PATTERN.sub("", normalized_value.strip()).strip()
|
||||
|
||||
|
||||
def _normalize_search_text(value: str) -> str:
|
||||
@@ -986,13 +1040,15 @@ class HardcoverProvider(MetadataProvider):
|
||||
"""Build search query, fields, and weights based on provided values.
|
||||
|
||||
Returns (query, fields, weights) tuple. Fields/weights are None for general search.
|
||||
A narrowed search still sends all of BOOK_SEARCH_FIELDS -- Hardcover rejects a
|
||||
shorter list outright -- and leans on the weights to rank the wanted field first.
|
||||
"""
|
||||
if author and not title and not series:
|
||||
return author, None, None
|
||||
if title and not author and not series:
|
||||
return title, "title,alternative_titles", "5,1"
|
||||
return title, BOOK_SEARCH_FIELDS, BOOK_TITLE_WEIGHTS
|
||||
if author and title and not series:
|
||||
return f"{title} {author}", "title,alternative_titles,author_names", "5,1,3"
|
||||
return f"{title} {author}", BOOK_SEARCH_FIELDS, BOOK_TITLE_AUTHOR_WEIGHTS
|
||||
return default_query, None, None
|
||||
|
||||
def _detect_list_url(self, query: str) -> tuple[str | None, str] | None:
|
||||
@@ -1200,7 +1256,7 @@ class HardcoverProvider(MetadataProvider):
|
||||
if not self.api_key or len(normalized_query) < HARDCOVER_MIN_TYPEAHEAD_QUERY_LENGTH:
|
||||
return []
|
||||
|
||||
result = self._execute_query(
|
||||
result = self._execute_search_query(
|
||||
SEARCH_FIELD_OPTIONS_QUERY,
|
||||
{
|
||||
"query": normalized_query,
|
||||
@@ -1431,7 +1487,7 @@ class HardcoverProvider(MetadataProvider):
|
||||
logger.debug("Invalid Hardcover series id field value: %s", normalized_value)
|
||||
return None
|
||||
|
||||
result = self._execute_query(
|
||||
result = self._execute_search_query(
|
||||
SEARCH_FIELD_OPTIONS_QUERY,
|
||||
{
|
||||
"query": normalized_value,
|
||||
@@ -2358,6 +2414,7 @@ class HardcoverProvider(MetadataProvider):
|
||||
graphql_query = """
|
||||
query SearchBooks($query: String!, $limit: Int!, $page: Int!, $sort: String, $fields: String, $weights: String) {
|
||||
search(query: $query, query_type: "Book", per_page: $limit, page: $page, sort: $sort, fields: $fields, weights: $weights) {
|
||||
error
|
||||
results
|
||||
}
|
||||
}
|
||||
@@ -2366,6 +2423,7 @@ class HardcoverProvider(MetadataProvider):
|
||||
graphql_query = """
|
||||
query SearchBooks($query: String!, $limit: Int!, $page: Int!, $sort: String) {
|
||||
search(query: $query, query_type: "Book", per_page: $limit, page: $page, sort: $sort) {
|
||||
error
|
||||
results
|
||||
}
|
||||
}
|
||||
@@ -2386,7 +2444,7 @@ class HardcoverProvider(MetadataProvider):
|
||||
variables["weights"] = search_weights
|
||||
|
||||
try:
|
||||
result = self._execute_query(graphql_query, variables)
|
||||
result = self._execute_search_query(graphql_query, variables)
|
||||
if not result:
|
||||
logger.debug("Hardcover search: No result from API")
|
||||
return SearchResult(books=[], page=options.page, total_found=0, has_more=False)
|
||||
@@ -2654,6 +2712,54 @@ class HardcoverProvider(MetadataProvider):
|
||||
raise RuntimeError(msg) from e
|
||||
return None
|
||||
|
||||
def _execute_search_query(self, query: str, variables: dict[str, Any]) -> dict | None:
|
||||
"""Execute a search query, retrying without ``sort`` if Hardcover rejects it.
|
||||
|
||||
Returns None when the search was rejected, so callers report an empty
|
||||
result rather than silently treating a failure as "nothing matched".
|
||||
"""
|
||||
global _sort_fallback_until
|
||||
|
||||
sort = variables.get("sort")
|
||||
if sort and time.monotonic() < _sort_fallback_until:
|
||||
variables = _without_sort(variables)
|
||||
sort = None
|
||||
|
||||
result = self._execute_query(query, variables)
|
||||
if not _search_payload_rejected(result):
|
||||
return result
|
||||
|
||||
reason = _search_rejection_reason(result)
|
||||
if not sort:
|
||||
logger.error(
|
||||
"Hardcover rejected this search (query_type=%s, fields=%s): %s",
|
||||
variables.get("queryType", "Book"),
|
||||
variables.get("fields"),
|
||||
reason or "no error message",
|
||||
)
|
||||
return None
|
||||
|
||||
retry = self._execute_query(query, _without_sort(variables))
|
||||
if _search_payload_rejected(retry):
|
||||
# The sort was not the culprit, so leave sorting alone for other searches.
|
||||
logger.error(
|
||||
"Hardcover rejected this search (query_type=%s, fields=%s) with and without "
|
||||
"a sort order: %s",
|
||||
variables.get("queryType", "Book"),
|
||||
variables.get("fields"),
|
||||
_search_rejection_reason(retry) or reason or "no error message",
|
||||
)
|
||||
return None
|
||||
|
||||
logger.warning(
|
||||
"Hardcover rejected sort '%s' (%s); dropping the sort order from searches for %ss",
|
||||
sort,
|
||||
reason or "no error message",
|
||||
int(SORT_FALLBACK_TTL),
|
||||
)
|
||||
_sort_fallback_until = time.monotonic() + SORT_FALLBACK_TTL
|
||||
return retry
|
||||
|
||||
def _parse_search_result(self, item: dict) -> BookMetadata | None:
|
||||
"""Parse a search result item into BookMetadata."""
|
||||
try:
|
||||
@@ -2917,12 +3023,13 @@ def _test_hardcover_connection(current_values: dict[str, Any] | None = None) ->
|
||||
_save_connected_user(None, None)
|
||||
return {"success": False, "message": "API key is required"}
|
||||
|
||||
if key_len < HARDCOVER_API_KEY_MIN_LENGTH:
|
||||
is_prefixed_key = api_key.startswith(HARDCOVER_API_KEY_PREFIX)
|
||||
if not is_prefixed_key and key_len < HARDCOVER_API_KEY_MIN_LENGTH:
|
||||
return {
|
||||
"success": False,
|
||||
"message": (
|
||||
f"API key seems too short ({key_len} chars). "
|
||||
f"Expected {HARDCOVER_API_KEY_MIN_LENGTH}+ chars."
|
||||
f"API key seems too short ({key_len} chars). Expected a key starting "
|
||||
f"with {HARDCOVER_API_KEY_PREFIX} or {HARDCOVER_API_KEY_MIN_LENGTH}+ chars."
|
||||
),
|
||||
}
|
||||
|
||||
@@ -3029,7 +3136,7 @@ def hardcover_settings() -> list[SettingsField]:
|
||||
PasswordField(
|
||||
key="HARDCOVER_API_KEY",
|
||||
label="API Key",
|
||||
description="Get your API key from hardcover.app/account/api",
|
||||
description="Get your API key from hardcover.app/account/api (starts with hc_pat_)",
|
||||
required=True,
|
||||
),
|
||||
ActionButton(
|
||||
|
||||
@@ -0,0 +1,493 @@
|
||||
"""Moly.hu metadata provider. Hungarian book catalog, no API key required.
|
||||
|
||||
Scraping approach (search URL, book-page structure, language mapping) adapted
|
||||
from the Calibre Moly_hu plugin by Hoffer Csaba, Kloon, otapi, Dezso, Hokutya,
|
||||
seeder and contributors (GPL v3, mobileread.com).
|
||||
"""
|
||||
|
||||
import re
|
||||
import threading
|
||||
import time
|
||||
import unicodedata
|
||||
from collections import deque
|
||||
from typing import Any, ClassVar
|
||||
from urllib.parse import quote
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup, Tag
|
||||
|
||||
from shelfmark.core.cache import cacheable
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.settings_registry import (
|
||||
ActionButton,
|
||||
CheckboxField,
|
||||
HeadingField,
|
||||
SettingsField,
|
||||
register_settings,
|
||||
)
|
||||
from shelfmark.download.network import get_ssl_verify
|
||||
from shelfmark.metadata_providers import (
|
||||
BookMetadata,
|
||||
DisplayField,
|
||||
MetadataProvider,
|
||||
MetadataSearchOptions,
|
||||
SearchField,
|
||||
SearchType,
|
||||
SortOrder,
|
||||
TextSearchField,
|
||||
register_provider,
|
||||
)
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
MOLY_BASE_URL = "https://moly.hu"
|
||||
MOLY_BOOK_URL = f"{MOLY_BASE_URL}/konyvek/"
|
||||
MOLY_SEARCH_URL = f"{MOLY_BASE_URL}/kereses?query="
|
||||
|
||||
# Be polite: moly.hu is a small community site
|
||||
RATE_LIMIT_REQUESTS = 30
|
||||
RATE_LIMIT_WINDOW_SECONDS = 60
|
||||
|
||||
REQUEST_HEADERS = {
|
||||
"User-Agent": ("Mozilla/5.0 (X11; Linux x86_64; rv:128.0) Gecko/20100101 Firefox/128.0"),
|
||||
"Accept-Language": "hu,en;q=0.7",
|
||||
}
|
||||
|
||||
ISBN_13_LENGTH = 13
|
||||
|
||||
# Moly tags its foreign-language editions; everything else is Hungarian.
|
||||
# Mapping from the Calibre Moly_hu plugin.
|
||||
_LANGUAGE_TAG_MAP = {
|
||||
"angol nyelvű": "en",
|
||||
"n\xe9met nyelvű": "de",
|
||||
"francia nyelvű": "fr",
|
||||
"olasz nyelvű": "it",
|
||||
"spanyol nyelvű": "es",
|
||||
"orosz nyelvű": "ru",
|
||||
"t\xf6r\xf6k nyelvű": "tr",
|
||||
"g\xf6r\xf6g nyelvű": "el",
|
||||
"k\xednai nyelvű": "zh",
|
||||
"jap\xe1n nyelvű": "ja",
|
||||
}
|
||||
|
||||
|
||||
class RateLimiter:
|
||||
"""Simple sliding window rate limiter."""
|
||||
|
||||
def __init__(self, max_requests: int, window_seconds: int) -> None:
|
||||
"""Initialize rate limiter with max requests per time window."""
|
||||
self.max_requests = max_requests
|
||||
self.window_seconds = window_seconds
|
||||
self.timestamps: deque[float] = deque()
|
||||
self.lock = threading.Lock()
|
||||
|
||||
def wait_if_needed(self) -> None:
|
||||
"""Block until a request is allowed (thread-safe)."""
|
||||
wait_time = 0.0
|
||||
|
||||
with self.lock:
|
||||
now = time.time()
|
||||
cutoff = now - self.window_seconds
|
||||
while self.timestamps and self.timestamps[0] < cutoff:
|
||||
self.timestamps.popleft()
|
||||
if len(self.timestamps) >= self.max_requests:
|
||||
wait_time = self.timestamps[0] + self.window_seconds - now
|
||||
|
||||
if wait_time > 0:
|
||||
logger.debug("Rate limited, waiting %0.2fs", wait_time)
|
||||
time.sleep(wait_time)
|
||||
|
||||
with self.lock:
|
||||
now = time.time()
|
||||
cutoff = now - self.window_seconds
|
||||
while self.timestamps and self.timestamps[0] < cutoff:
|
||||
self.timestamps.popleft()
|
||||
self.timestamps.append(time.time())
|
||||
|
||||
|
||||
_rate_limiter = RateLimiter(RATE_LIMIT_REQUESTS, RATE_LIMIT_WINDOW_SECONDS)
|
||||
|
||||
|
||||
def _clean_text(value: str | None) -> str | None:
|
||||
"""Strip zero-width characters and collapse whitespace."""
|
||||
if value is None:
|
||||
return None
|
||||
value = value.replace("", "").replace("", "")
|
||||
return " ".join(value.split())
|
||||
|
||||
|
||||
def _normalize_for_match(value: str | None) -> str:
|
||||
"""Accent-insensitive, punctuation-insensitive comparison form."""
|
||||
if not value:
|
||||
return ""
|
||||
value = unicodedata.normalize("NFKD", value)
|
||||
value = "".join(char for char in value if not unicodedata.combining(char))
|
||||
value = "".join(char if char.isalnum() else " " for char in value)
|
||||
return " ".join(value.lower().split())
|
||||
|
||||
|
||||
def _absolute_url(url: str | None) -> str | None:
|
||||
if not url:
|
||||
return None
|
||||
if url.startswith(("http://", "https://")):
|
||||
return url
|
||||
return MOLY_BASE_URL + url
|
||||
|
||||
|
||||
def _valid_isbn(candidate: str) -> str | None:
|
||||
"""Return a normalized ISBN-10/13 (digits, with optional X check digit), else None."""
|
||||
digits = candidate.replace("-", "").strip()
|
||||
if len(digits) == ISBN_13_LENGTH and digits.isdigit():
|
||||
return digits
|
||||
if len(digits) == 10 and re.fullmatch(r"\d{9}[\dXx]", digits):
|
||||
return digits.upper()
|
||||
return None
|
||||
|
||||
|
||||
@register_provider("moly")
|
||||
class MolyProvider(MetadataProvider):
|
||||
"""Moly.hu metadata provider (HTML scraping, Hungarian catalog)."""
|
||||
|
||||
name = "moly"
|
||||
display_name = "Moly.hu"
|
||||
requires_auth = False
|
||||
supported_sorts: ClassVar[tuple[SortOrder, ...]] = (SortOrder.RELEVANCE,)
|
||||
search_fields: ClassVar[tuple[SearchField, ...]] = (
|
||||
TextSearchField(
|
||||
key="author",
|
||||
label="Author",
|
||||
description="Search by author name",
|
||||
),
|
||||
TextSearchField(
|
||||
key="title",
|
||||
label="Title",
|
||||
description="Search by book title",
|
||||
),
|
||||
)
|
||||
|
||||
def __init__(self) -> None:
|
||||
"""Initialize provider."""
|
||||
self.session = requests.Session()
|
||||
self.session.headers.update(REQUEST_HEADERS)
|
||||
|
||||
def is_available(self) -> bool:
|
||||
"""Moly.hu needs no authentication."""
|
||||
return True
|
||||
|
||||
def _fetch(self, url: str, timeout: int = 15) -> str | None:
|
||||
_rate_limiter.wait_if_needed()
|
||||
try:
|
||||
response = self.session.get(url, timeout=timeout, verify=get_ssl_verify(MOLY_BASE_URL))
|
||||
response.raise_for_status()
|
||||
except requests.Timeout:
|
||||
logger.warning("Moly.hu request timed out: %s", url)
|
||||
return None
|
||||
except requests.RequestException:
|
||||
logger.exception("Moly.hu request failed: %s", url)
|
||||
return None
|
||||
return response.text
|
||||
|
||||
def search(self, options: MetadataSearchOptions) -> list[BookMetadata]:
|
||||
"""Search moly.hu's site search."""
|
||||
if options.search_type == SearchType.ISBN:
|
||||
result = self.search_by_isbn(options.query)
|
||||
return [result] if result else []
|
||||
|
||||
# Moly's search is a single ranked page; no server-side pagination.
|
||||
if options.page > 1:
|
||||
return []
|
||||
|
||||
author_value = (options.fields.get("author") or "").strip()
|
||||
title_value = (options.fields.get("title") or "").strip()
|
||||
terms = " ".join(t for t in (author_value, title_value) if t)
|
||||
query = terms or options.query.strip()
|
||||
if not query:
|
||||
return []
|
||||
|
||||
fields_key = ":".join(f"{k}={v}" for k, v in sorted(options.fields.items()))
|
||||
cache_key = f"{query}:{options.search_type.value}:{options.limit}:{fields_key}"
|
||||
return self._search_cached(cache_key, query, options.limit) or []
|
||||
|
||||
@cacheable(ttl_key="METADATA_CACHE_SEARCH_TTL", ttl_default=300, key_prefix="moly:search")
|
||||
def _search_cached(self, cache_key: str, query: str, limit: int) -> list[BookMetadata] | None:
|
||||
# Return None (not []) on fetch failure so the failure is not cached.
|
||||
html = self._fetch(MOLY_SEARCH_URL + quote(query.encode("utf-8")))
|
||||
if html is None:
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
books: list[BookMetadata] = []
|
||||
seen: set[str] = set()
|
||||
|
||||
for anchor in soup.select("#content div.search_area a.book_selector"):
|
||||
href = anchor.get("href") or ""
|
||||
match = re.search(r"/konyvek/([^/?#]+)", str(href))
|
||||
if not match:
|
||||
continue
|
||||
slug = match.group(1)
|
||||
if slug in seen:
|
||||
continue
|
||||
|
||||
# No separator: moly wraps matched search terms in <strong> even
|
||||
# mid-word ("Lis<strong>a</strong> Jewell"), so inserting one
|
||||
# would split words at highlight boundaries.
|
||||
text = _clean_text(anchor.get_text()) or ""
|
||||
author, _, title = text.partition(":")
|
||||
if not title:
|
||||
# Result rows are "Author: Title"; skip anything else.
|
||||
continue
|
||||
author = author.strip()
|
||||
title = title.strip()
|
||||
|
||||
seen.add(slug)
|
||||
books.append(
|
||||
BookMetadata(
|
||||
provider=self.name,
|
||||
provider_id=slug,
|
||||
provider_display_name=self.display_name,
|
||||
title=title,
|
||||
authors=[author] if author else [],
|
||||
cover_url=self._cover_for_result(soup, text),
|
||||
source_url=MOLY_BOOK_URL + slug,
|
||||
language="hu",
|
||||
search_title=title,
|
||||
search_author=author or None,
|
||||
display_fields=self._result_display_fields(anchor),
|
||||
)
|
||||
)
|
||||
if len(books) >= limit:
|
||||
break
|
||||
|
||||
logger.info("Moly.hu search '%s' returned %s results", query, len(books))
|
||||
return books
|
||||
|
||||
def _cover_for_result(self, soup: BeautifulSoup, result_text: str) -> str | None:
|
||||
"""Find the search-result thumbnail whose alt matches 'Author: Title'."""
|
||||
target = _normalize_for_match(result_text)
|
||||
if not target:
|
||||
return None
|
||||
for img in soup.select("#content img.tooltip[alt]"):
|
||||
if _normalize_for_match(str(img.get("alt") or "")) == target:
|
||||
return _absolute_url(str(img.get("src") or "")) or None
|
||||
return None
|
||||
|
||||
def _result_display_fields(self, anchor: Tag) -> list[DisplayField]:
|
||||
fields: list[DisplayField] = []
|
||||
parent = anchor.parent
|
||||
if parent is None:
|
||||
return fields
|
||||
like = parent.select_one("span.like_count")
|
||||
if like:
|
||||
fields.append(
|
||||
DisplayField(label="Rating", value=like.get_text(strip=True), icon="star")
|
||||
)
|
||||
series = parent.select_one('a[href*="/sorozatok/"]')
|
||||
if series:
|
||||
fields.append(
|
||||
DisplayField(
|
||||
label="Series",
|
||||
value=series.get_text(strip=True).strip("()"),
|
||||
icon="editions",
|
||||
)
|
||||
)
|
||||
return fields
|
||||
|
||||
@cacheable(ttl_key="METADATA_CACHE_BOOK_TTL", ttl_default=600, key_prefix="moly:book")
|
||||
def get_book(self, book_id: str) -> BookMetadata | None:
|
||||
"""Get book details by moly.hu slug (e.g. 'mocsidzuki-mai-a-telihold-kavezo')."""
|
||||
html = self._fetch(MOLY_BOOK_URL + quote(book_id))
|
||||
if html is None:
|
||||
return None
|
||||
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
|
||||
title = self._parse_title(soup)
|
||||
authors = [_clean_text(a.get_text()) or "" for a in soup.select("#content div.authors a")]
|
||||
authors = [a for a in authors if a]
|
||||
if not title or not authors:
|
||||
logger.warning("Moly.hu book page missing title/authors: %s", book_id)
|
||||
return None
|
||||
|
||||
isbn_13, isbn_10 = self._parse_isbns(soup)
|
||||
series = self._parse_series(soup)
|
||||
tags = [_clean_text(t.get_text()) or "" for t in soup.select("#book_tags a.tag")]
|
||||
tags = [t for t in tags if t]
|
||||
|
||||
display_fields: list[DisplayField] = []
|
||||
rating = soup.select_one("#content .rating .like_count")
|
||||
if rating:
|
||||
display_fields.append(
|
||||
DisplayField(label="Rating", value=rating.get_text(strip=True), icon="star")
|
||||
)
|
||||
if series:
|
||||
display_fields.append(DisplayField(label="Series", value=series, icon="editions"))
|
||||
|
||||
return BookMetadata(
|
||||
provider=self.name,
|
||||
provider_id=book_id,
|
||||
provider_display_name=self.display_name,
|
||||
title=title,
|
||||
authors=authors,
|
||||
isbn_13=isbn_13,
|
||||
isbn_10=isbn_10,
|
||||
cover_url=self._parse_cover(soup),
|
||||
description=self._parse_description(soup),
|
||||
publisher=self._parse_publisher(soup),
|
||||
publish_year=self._parse_publish_year(soup),
|
||||
language=self._parse_language(tags),
|
||||
genres=tags,
|
||||
source_url=MOLY_BOOK_URL + book_id,
|
||||
search_title=title,
|
||||
search_author=authors[0],
|
||||
display_fields=display_fields,
|
||||
)
|
||||
|
||||
@cacheable(ttl_key="METADATA_CACHE_BOOK_TTL", ttl_default=600, key_prefix="moly:isbn")
|
||||
def search_by_isbn(self, isbn: str) -> BookMetadata | None:
|
||||
"""Moly's site search resolves ISBN queries directly."""
|
||||
isbn = isbn.replace("-", "").strip()
|
||||
if not isbn:
|
||||
return None
|
||||
html = self._fetch(MOLY_SEARCH_URL + quote(isbn))
|
||||
if html is None:
|
||||
return None
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
anchor = soup.select_one("#content div.search_area a.book_selector[href]")
|
||||
if not anchor:
|
||||
return None
|
||||
match = re.search(r"/konyvek/([^/?#]+)", str(anchor.get("href")))
|
||||
if not match:
|
||||
return None
|
||||
return self.get_book(match.group(1))
|
||||
|
||||
def _parse_title(self, soup: BeautifulSoup) -> str | None:
|
||||
node = soup.select_one("#content .head_title h1 span.item")
|
||||
if node:
|
||||
# The series link is nested inside this span; only direct text
|
||||
# belongs to the book title.
|
||||
direct = "".join(node.find_all(string=True, recursive=False))
|
||||
title = _clean_text(direct)
|
||||
if title:
|
||||
return title
|
||||
node = soup.select_one("#content .book > span")
|
||||
if node:
|
||||
return _clean_text(node.get_text())
|
||||
return None
|
||||
|
||||
def _parse_series(self, soup: BeautifulSoup) -> str | None:
|
||||
node = soup.select_one('#content h1 a[href*="/sorozatok/"]')
|
||||
if not node:
|
||||
return None
|
||||
return (_clean_text(node.get_text()) or "").strip("()") or None
|
||||
|
||||
def _parse_isbns(self, soup: BeautifulSoup) -> tuple[str | None, str | None]:
|
||||
isbn_13 = isbn_10 = None
|
||||
editions = soup.select("#content .items .edition") or soup.select("#content .items > div")
|
||||
for edition in editions:
|
||||
text = edition.get_text(" ")
|
||||
for candidate in re.findall(r"(?<!\d)[\d-]{10,17}(?!\d)", text):
|
||||
isbn = _valid_isbn(candidate)
|
||||
if not isbn:
|
||||
continue
|
||||
if len(isbn) == ISBN_13_LENGTH and not isbn_13:
|
||||
isbn_13 = isbn
|
||||
elif len(isbn) != ISBN_13_LENGTH and not isbn_10:
|
||||
isbn_10 = isbn
|
||||
if isbn_13:
|
||||
break
|
||||
return isbn_13, isbn_10
|
||||
|
||||
def _parse_cover(self, soup: BeautifulSoup) -> str | None:
|
||||
node = soup.select_one("#content .coverbox a.zoom[href]")
|
||||
if node:
|
||||
return _absolute_url(str(node.get("href")))
|
||||
img = soup.select_one("#content .coverbox img[src]")
|
||||
if img:
|
||||
return _absolute_url(str(img.get("src")))
|
||||
return None
|
||||
|
||||
def _parse_description(self, soup: BeautifulSoup) -> str | None:
|
||||
node = soup.select_one("#content #full_description")
|
||||
if node is None:
|
||||
node = soup.select_one("#content div.text")
|
||||
if node is None:
|
||||
return None
|
||||
spoiler_warning = "Vigyázat! Cselekményleírást tartalmaz."
|
||||
parts = []
|
||||
for text in node.stripped_strings:
|
||||
cleaned = _clean_text(text) or ""
|
||||
if cleaned.startswith(spoiler_warning):
|
||||
cleaned = cleaned[len(spoiler_warning) :].strip()
|
||||
if cleaned:
|
||||
parts.append(cleaned)
|
||||
return "\n".join(parts) or None
|
||||
|
||||
def _parse_publisher(self, soup: BeautifulSoup) -> str | None:
|
||||
node = soup.select_one('#content .items .edition a[href*="/kiadok/"]')
|
||||
if node:
|
||||
return _clean_text(node.get_text())
|
||||
return None
|
||||
|
||||
def _parse_publish_year(self, soup: BeautifulSoup) -> int | None:
|
||||
editions = soup.select("#content .items .edition") or soup.select("#content .items > div")
|
||||
for edition in editions:
|
||||
match = re.search(r"\b(\d{4})\b", edition.get_text(" "))
|
||||
if match:
|
||||
return int(match.group(1))
|
||||
return None
|
||||
|
||||
def _parse_language(self, tags: list[str]) -> str:
|
||||
for tag in tags:
|
||||
code = _LANGUAGE_TAG_MAP.get(tag.lower().strip())
|
||||
if code:
|
||||
return code
|
||||
return "hu"
|
||||
|
||||
|
||||
def _test_moly_connection() -> dict[str, Any]:
|
||||
"""Test connectivity to moly.hu."""
|
||||
try:
|
||||
provider = MolyProvider()
|
||||
response = provider.session.get(
|
||||
MOLY_SEARCH_URL + quote("teszt"),
|
||||
timeout=10,
|
||||
verify=get_ssl_verify(MOLY_BASE_URL),
|
||||
)
|
||||
response.raise_for_status()
|
||||
except requests.Timeout:
|
||||
return {"success": False, "message": "Connection timed out"}
|
||||
except requests.RequestException as e:
|
||||
return {"success": False, "message": f"Connection failed: {e}"}
|
||||
if "moly" in response.text.lower():
|
||||
return {"success": True, "message": "Successfully connected to moly.hu"}
|
||||
return {"success": False, "message": "Unexpected response from moly.hu"}
|
||||
|
||||
|
||||
@register_settings("moly", "Moly.hu", icon="library", order=54, group="metadata_providers")
|
||||
def moly_settings() -> list[SettingsField]:
|
||||
"""Moly.hu metadata provider settings."""
|
||||
return [
|
||||
HeadingField(
|
||||
key="moly_heading",
|
||||
title="Moly.hu",
|
||||
description=(
|
||||
"Hungarian community book catalog with excellent coverage of "
|
||||
"Hungarian editions and translations. No API key required."
|
||||
),
|
||||
link_url="https://moly.hu",
|
||||
link_text="moly.hu",
|
||||
),
|
||||
CheckboxField(
|
||||
key="MOLY_ENABLED",
|
||||
label="Enable Moly.hu",
|
||||
description="Enable Moly.hu as a metadata provider for book searches",
|
||||
default=False,
|
||||
),
|
||||
ActionButton(
|
||||
key="test_connection",
|
||||
label="Test Connection",
|
||||
description="Verify moly.hu is accessible",
|
||||
style="primary",
|
||||
callback=_test_moly_connection,
|
||||
),
|
||||
]
|
||||
@@ -163,6 +163,7 @@ class SortOption:
|
||||
|
||||
label: str # Display label in the sort dropdown
|
||||
sort_key: str # Field to sort by on the Release object
|
||||
default_direction: Literal["asc", "desc"] = "desc" # Which way "best first" runs
|
||||
|
||||
|
||||
@dataclass
|
||||
@@ -261,7 +262,12 @@ def serialize_column_config(config: ReleaseColumnConfig) -> dict[str, Any]:
|
||||
# Include extra sort options (sort entries not tied to a column)
|
||||
if config.extra_sort_options:
|
||||
result["extra_sort_options"] = [
|
||||
{"label": opt.label, "sort_key": opt.sort_key} for opt in config.extra_sort_options
|
||||
{
|
||||
"label": opt.label,
|
||||
"sort_key": opt.sort_key,
|
||||
"default_direction": opt.default_direction,
|
||||
}
|
||||
for opt in config.extra_sort_options
|
||||
]
|
||||
|
||||
# Include action button if specified (replaces default expand search)
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
import re
|
||||
import time
|
||||
from urllib.parse import quote
|
||||
from urllib.parse import quote, quote_plus
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
@@ -10,6 +10,7 @@ from bs4 import BeautifulSoup
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.download import http as downloader
|
||||
from shelfmark.release_sources.audiobookbay.utils import normalize_search_punctuation
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
@@ -98,8 +99,10 @@ def _encode_search_query(query: str, *, exact_phrase: bool) -> str:
|
||||
and not (search_query.startswith('"') and search_query.endswith('"'))
|
||||
):
|
||||
search_query = f'"{search_query}"'
|
||||
# Keep ABB-friendly encoding style (spaces as '+') while percent-encoding quotes.
|
||||
return search_query.replace('"', "%22").replace(" ", "+")
|
||||
# Keep ABB's space-as-'+' style, but percent-encode everything else: a bare
|
||||
# '&' would otherwise start a new query parameter, '%' would open an invalid
|
||||
# escape, and a literal '+' would arrive as a space.
|
||||
return quote_plus(search_query)
|
||||
|
||||
|
||||
def _normalize_result_url(url: str, hostname: str) -> str:
|
||||
@@ -153,6 +156,9 @@ def search_audiobookbay(
|
||||
|
||||
"""
|
||||
results = []
|
||||
# ABB matches the stored, untexturized title, so a curly apostrophe reaching
|
||||
# the search returns nothing at all rather than merely ranking worse.
|
||||
query = normalize_search_punctuation(query)
|
||||
rate_limit_delay = _coerce_non_negative_float(config.get("ABB_RATE_LIMIT_DELAY", 1.0), 1.0)
|
||||
session = requests.Session()
|
||||
|
||||
|
||||
@@ -9,6 +9,7 @@ if TYPE_CHECKING:
|
||||
from shelfmark.metadata_providers import BookMetadata
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.languages import normalize_language
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.release_sources import (
|
||||
ColumnAlign,
|
||||
@@ -22,7 +23,11 @@ from shelfmark.release_sources import (
|
||||
register_source,
|
||||
)
|
||||
from shelfmark.release_sources.audiobookbay import scraper
|
||||
from shelfmark.release_sources.audiobookbay.utils import normalize_hostname, parse_size
|
||||
from shelfmark.release_sources.audiobookbay.utils import (
|
||||
normalize_hostname,
|
||||
normalize_search_punctuation,
|
||||
parse_size,
|
||||
)
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
MIN_RELEVANCE_QUERY_WORD_LENGTH = 2
|
||||
@@ -43,41 +48,6 @@ def _coerce_positive_int(value: object, default: int) -> int:
|
||||
|
||||
|
||||
# Map language names to ISO 639-1 codes (matching frontend color maps)
|
||||
LANGUAGE_MAP = {
|
||||
"english": "en",
|
||||
"spanish": "es",
|
||||
"french": "fr",
|
||||
"german": "de",
|
||||
"italian": "it",
|
||||
"portuguese": "pt",
|
||||
"russian": "ru",
|
||||
"japanese": "ja",
|
||||
"chinese": "zh",
|
||||
"dutch": "nl",
|
||||
"swedish": "sv",
|
||||
"norwegian": "no",
|
||||
"danish": "da",
|
||||
"finnish": "fi",
|
||||
"polish": "pl",
|
||||
"czech": "cs",
|
||||
"hungarian": "hu",
|
||||
"korean": "ko",
|
||||
"arabic": "ar",
|
||||
"hebrew": "he",
|
||||
"turkish": "tr",
|
||||
"greek": "el",
|
||||
"hindi": "hi",
|
||||
"thai": "th",
|
||||
"vietnamese": "vi",
|
||||
"indonesian": "id",
|
||||
"ukrainian": "uk",
|
||||
"romanian": "ro",
|
||||
"bulgarian": "bg",
|
||||
"catalan": "ca",
|
||||
"croatian": "hr",
|
||||
"slovenian": "sl",
|
||||
"serbian": "sr",
|
||||
}
|
||||
|
||||
|
||||
def _split_title_and_author(raw_title: str) -> tuple[str, str | None]:
|
||||
@@ -119,8 +89,9 @@ def _map_language(language: str) -> str | None:
|
||||
if not language:
|
||||
return None
|
||||
|
||||
lang_lower = language.lower().strip()
|
||||
return LANGUAGE_MAP.get(lang_lower, lang_lower)
|
||||
# Fall back to the raw value so an unrecognised language is still shown
|
||||
# rather than silently dropped from the release row.
|
||||
return normalize_language(language) or language.lower().strip()
|
||||
|
||||
|
||||
def _parse_bitrate_to_kbps(bitrate: str | None) -> int | None:
|
||||
@@ -260,10 +231,12 @@ class AudiobookBaySource(ReleaseSource):
|
||||
deduped_queries[index + 1].lower(),
|
||||
)
|
||||
|
||||
# Extract query words for relevance checking
|
||||
# Extract query words for relevance checking. Both sides of the
|
||||
# comparison are punctuation-normalized: scraped titles carry the
|
||||
# typographic forms WordPress renders, queries carry the ASCII ones.
|
||||
query_words = {
|
||||
word.lower()
|
||||
for word in query_lower.split()
|
||||
for word in normalize_search_punctuation(query_lower).split()
|
||||
if len(word) > MIN_RELEVANCE_QUERY_WORD_LENGTH
|
||||
}
|
||||
|
||||
@@ -272,7 +245,7 @@ class AudiobookBaySource(ReleaseSource):
|
||||
try:
|
||||
raw_title = result["title"]
|
||||
title, author = _split_title_and_author(raw_title)
|
||||
title_for_filter = raw_title.lower()
|
||||
title_for_filter = normalize_search_punctuation(raw_title).lower()
|
||||
|
||||
# Basic relevance check: ensure title contains at least one query word
|
||||
# This filters out homepage "Latest" feed items that may leak through
|
||||
|
||||
@@ -2,6 +2,63 @@
|
||||
|
||||
import re
|
||||
|
||||
# WordPress texturizes punctuation on output only: a post stored as "The
|
||||
# Stranger's Wife" is rendered as "The Stranger’s Wife". ABB's search matches the
|
||||
# stored value, so a query carrying the typographic form matches nothing -- and
|
||||
# because ABB ANDs its search terms, one such term empties the entire result set.
|
||||
# Book metadata and phone keyboards both hand us the typographic forms, so map
|
||||
# them back before they reach a search or a title comparison.
|
||||
_ASCII_PUNCTUATION = str.maketrans(
|
||||
{
|
||||
# Single quotes
|
||||
"‘": "'", # left single quotation mark
|
||||
"’": "'", # right single quotation mark
|
||||
"‚": "'", # single low-9 quotation mark
|
||||
"‛": "'", # single high-reversed-9 quotation mark
|
||||
"′": "'", # prime
|
||||
"´": "'", # acute accent
|
||||
"`": "'", # grave accent
|
||||
# Double quotes
|
||||
"“": '"', # left double quotation mark
|
||||
"”": '"', # right double quotation mark
|
||||
"„": '"', # double low-9 quotation mark
|
||||
"‟": '"', # double high-reversed-9 quotation mark
|
||||
"″": '"', # double prime
|
||||
# Dashes
|
||||
"‐": "-", # hyphen
|
||||
"‑": "-", # non-breaking hyphen
|
||||
"‒": "-", # figure dash
|
||||
"–": "-", # en dash
|
||||
"—": "-", # em dash
|
||||
"―": "-", # horizontal bar
|
||||
"−": "-", # minus sign
|
||||
"﹘": "-", # small em dash
|
||||
"﹣": "-", # small hyphen-minus
|
||||
"-": "-", # fullwidth hyphen-minus
|
||||
# Ellipsis
|
||||
"…": "...", # horizontal ellipsis
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def normalize_search_punctuation(text: str) -> str:
|
||||
"""Replace typographic punctuation with the ASCII forms ABB stores.
|
||||
|
||||
Each character is mapped individually rather than collapsing runs, so an
|
||||
ASCII "--" is left alone: only characters ABB cannot have stored are
|
||||
rewritten.
|
||||
|
||||
Args:
|
||||
text: A search query, or a scraped title being compared against one.
|
||||
|
||||
Returns:
|
||||
The text with curly quotes, dashes and ellipses mapped to ASCII.
|
||||
|
||||
"""
|
||||
if not text:
|
||||
return text
|
||||
return text.translate(_ASCII_PUNCTUATION)
|
||||
|
||||
|
||||
def normalize_hostname(raw: str | None) -> str:
|
||||
"""Normalize a user-supplied hostname for URL construction.
|
||||
|
||||
@@ -18,6 +18,7 @@ from bs4.element import NavigableString
|
||||
|
||||
from shelfmark.config.env import DEBUG_SKIP_SOURCES, TMP_DIR
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.languages import language_alias_map
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.models import DownloadTask, SearchFilters, build_filename
|
||||
from shelfmark.core.utils import CONTENT_TYPES, get_aa_content_type_dir
|
||||
@@ -267,7 +268,7 @@ def _fold_text(value: str) -> str:
|
||||
|
||||
|
||||
def _language_alias_to_code() -> dict[str, str]:
|
||||
"""Build alias→code map from bundled language metadata (lazy, cached)."""
|
||||
"""Alias to code map, delegating to the shared language data."""
|
||||
global _LANGUAGE_ALIAS_TO_CODE
|
||||
cached = _LANGUAGE_ALIAS_TO_CODE
|
||||
if cached is not None:
|
||||
@@ -278,35 +279,7 @@ def _language_alias_to_code() -> dict[str, str]:
|
||||
if cached is not None:
|
||||
return cached
|
||||
|
||||
mapping: dict[str, str] = {}
|
||||
data_path = Path(__file__).resolve().parents[2] / "data" / "book-languages.json"
|
||||
|
||||
try:
|
||||
raw = json.loads(data_path.read_text(encoding="utf-8"))
|
||||
except OSError, ValueError, TypeError:
|
||||
_LANGUAGE_ALIAS_TO_CODE = {}
|
||||
return _LANGUAGE_ALIAS_TO_CODE
|
||||
|
||||
if not isinstance(raw, list):
|
||||
_LANGUAGE_ALIAS_TO_CODE = {}
|
||||
return _LANGUAGE_ALIAS_TO_CODE
|
||||
|
||||
for item in raw:
|
||||
if not isinstance(item, dict):
|
||||
continue
|
||||
code = _normalize_language_token(str(item.get("code", "")))
|
||||
name = _normalize_language_token(str(item.get("language", "")))
|
||||
if not code:
|
||||
continue
|
||||
mapping.setdefault(code, code)
|
||||
mapping.setdefault(code.replace("-", "_"), code)
|
||||
mapping.setdefault(code.split("-")[0], code)
|
||||
mapping.setdefault(_fold_text(code), code)
|
||||
if name:
|
||||
mapping.setdefault(name, code)
|
||||
mapping.setdefault(_fold_text(name), code)
|
||||
|
||||
_LANGUAGE_ALIAS_TO_CODE = mapping
|
||||
_LANGUAGE_ALIAS_TO_CODE = language_alias_map()
|
||||
return _LANGUAGE_ALIAS_TO_CODE
|
||||
|
||||
|
||||
@@ -566,6 +539,98 @@ class SearchUnavailableError(SourceUnavailableError):
|
||||
"""Raised when Anna's Archive cannot be reached via any mirror/DNS."""
|
||||
|
||||
|
||||
# Markers that prove a 200 really came from Anna's Archive, and markers that mean we
|
||||
# are looking at a protection interstitial rather than the site. A page with neither
|
||||
# is a domain that answers but is not AA - seized, parked or for sale.
|
||||
#
|
||||
# Deliberately structural rather than the domain name: a parking page's whole job is
|
||||
# to display the domain it is squatting on, so "annas-archive" matches the very pages
|
||||
# this is meant to catch. These paths only exist on the real site.
|
||||
_AA_PAGE_MARKERS = (
|
||||
"/md5/",
|
||||
"aarecord",
|
||||
"anna's archive",
|
||||
"/dyn/",
|
||||
"/datasets",
|
||||
"/fast_download",
|
||||
"/slow_download",
|
||||
)
|
||||
_CHALLENGE_MARKERS = (
|
||||
"ddos-guard",
|
||||
"just a moment",
|
||||
"cloudflare",
|
||||
"checking your browser",
|
||||
"cf-browser-verification",
|
||||
)
|
||||
|
||||
|
||||
def _looks_like_aa_page(html: str) -> bool:
|
||||
"""Whether ``html`` is recognisably Anna's Archive itself."""
|
||||
lowered = html.lower()
|
||||
return any(marker in lowered for marker in _AA_PAGE_MARKERS)
|
||||
|
||||
|
||||
def _looks_like_challenge_page(html: str) -> bool:
|
||||
"""Whether ``html`` is a protection interstitial rather than the site behind it."""
|
||||
lowered = html.lower()
|
||||
return any(marker in lowered for marker in _CHALLENGE_MARKERS)
|
||||
|
||||
|
||||
def _fetch_search_table(url: str, selector: network.AAMirrorSelector) -> tuple[str, Tag | None]:
|
||||
"""Fetch the AA search page, retrying past mirrors that are not actually AA.
|
||||
|
||||
A parked or seized domain answers 200 with a page that has no results table and no
|
||||
"No files found." - indistinguishable from a broken search unless we check whether
|
||||
the response looks like AA at all. Those mirrors are quarantined for the session so
|
||||
later searches skip them instead of paying the timeout again.
|
||||
"""
|
||||
attempt_url = url
|
||||
for _ in range(len(network.get_available_aa_urls()) or 1):
|
||||
response = downloader.html_get_page(
|
||||
attempt_url, selector=selector, allow_bypasser_fallback=True
|
||||
)
|
||||
if not response:
|
||||
# Network/mirror exhaustion path bubbles up so API can notify clients
|
||||
msg = "Unable to reach download source. Network restricted or mirrors are blocked."
|
||||
raise SearchUnavailableError(msg)
|
||||
|
||||
html = _html_response_text(response)
|
||||
soup = BeautifulSoup(html, "html.parser")
|
||||
table = soup.find("table")
|
||||
if isinstance(table, Tag):
|
||||
return html, table
|
||||
if table is not None:
|
||||
msg = f"Expected results table tag, got {type(table).__name__}"
|
||||
raise TypeError(msg)
|
||||
if "No files found." in html:
|
||||
# A real, genuinely empty answer from a healthy mirror.
|
||||
return html, None
|
||||
if _looks_like_challenge_page(html):
|
||||
# The bypass did not actually clear the protection - the interstitial is
|
||||
# what came back. Rotating is pointless (every mirror shares the same
|
||||
# protection) and reporting it as an empty result is worse: the user is
|
||||
# told their query found nothing when the search never ran.
|
||||
msg = (
|
||||
"Anna's Archive answered with an unsolved protection challenge. "
|
||||
"Check that the bypasser is reachable and working."
|
||||
)
|
||||
raise SearchUnavailableError(msg)
|
||||
if _looks_like_aa_page(html):
|
||||
# A real AA response in a shape the caller should report as drift.
|
||||
# Not the mirror's fault.
|
||||
return html, None
|
||||
|
||||
new_base, action = selector.next_mirror_or_rotate_dns(
|
||||
fatal=True, reason="responded without an Anna's Archive page"
|
||||
)
|
||||
if action not in ("mirror", "dns") or not new_base:
|
||||
return html, None
|
||||
attempt_url = selector.rewrite(url)
|
||||
logger.info("Retrying search on %s", new_base)
|
||||
|
||||
return "", None
|
||||
|
||||
|
||||
def search_books(query: str, filters: SearchFilters) -> list[BrowseRecord]:
|
||||
"""Search for books matching the query.
|
||||
|
||||
@@ -628,15 +693,9 @@ def search_books(query: str, filters: SearchFilters) -> list[BrowseRecord]:
|
||||
f"{filters_query}"
|
||||
)
|
||||
|
||||
html = downloader.html_get_page(url, selector=selector, allow_bypasser_fallback=False)
|
||||
if not html:
|
||||
# Network/mirror exhaustion path bubbles up so API can notify clients
|
||||
msg = "Unable to reach download source. Network restricted or mirrors are blocked."
|
||||
raise SearchUnavailableError(msg)
|
||||
|
||||
soup = BeautifulSoup(_html_response_text(html), "html.parser")
|
||||
tbody = soup.find("table")
|
||||
|
||||
# AA gates /search behind a DDoS-Guard JS challenge, which every mirror shares. Rotating
|
||||
# to another mirror only collects another 403, so let the bypasser solve it.
|
||||
html, tbody = _fetch_search_table(url, selector)
|
||||
if tbody is None:
|
||||
if "No files found." in html:
|
||||
logger.info("No books found for query: %s", query)
|
||||
@@ -684,7 +743,8 @@ def get_book_info(book_id: str, *, fetch_download_count: bool = True) -> BrowseR
|
||||
"""
|
||||
url = f"{network.get_aa_base_url()}/md5/{book_id}"
|
||||
selector = network.AAMirrorSelector()
|
||||
html = downloader.html_get_page(url, selector=selector, allow_bypasser_fallback=False)
|
||||
# Same challenge as search: the detail page is gated on every mirror, so bypass it.
|
||||
html = downloader.html_get_page(url, selector=selector, allow_bypasser_fallback=True)
|
||||
|
||||
if not html:
|
||||
msg = "Unable to reach download source. Network restricted or mirrors are blocked."
|
||||
@@ -912,6 +972,9 @@ def _parse_book_info_page(
|
||||
if fetch_download_count:
|
||||
try:
|
||||
summary_url = f"{network.get_aa_base_url()}/dyn/md5/summary/{book_id}"
|
||||
# Unlike search and the detail page above, this one stays off the bypasser: a
|
||||
# download count is decoration on the details modal, not worth holding the
|
||||
# modal open for a browser solve. If it is gated, drop it and move on.
|
||||
summary_response = downloader.html_get_page(
|
||||
summary_url, selector=network.AAMirrorSelector(), allow_bypasser_fallback=False
|
||||
)
|
||||
@@ -1621,6 +1684,12 @@ def _extract_slow_download_url(
|
||||
|
||||
link_texts = [a.get_text(strip=True)[:50] for a in soup.find_all("a", href=True)[:10]]
|
||||
logger.warning("No download URL found. First 10 links: %s", link_texts)
|
||||
# A bypassed page with no AA download links often means the network served a wrong
|
||||
# page (e.g. an ISP block page) instead of Anna's Archive. Probe for DNS interference
|
||||
# so we can give the user an actionable hint instead of a generic failure.
|
||||
host = urlparse(link).hostname or ""
|
||||
if host:
|
||||
network.note_possible_dns_interference(host)
|
||||
return ""
|
||||
|
||||
|
||||
@@ -2053,7 +2122,14 @@ class DirectDownloadHandler(DownloadHandler):
|
||||
return None
|
||||
|
||||
if not success_url:
|
||||
status_callback("error", "All download sources failed")
|
||||
if network.dns_interference_detected():
|
||||
status_callback(
|
||||
"error",
|
||||
"All sources failed - your network/ISP appears to be blocking "
|
||||
"Anna's Archive. Enable DNS-over-HTTPS in settings.",
|
||||
)
|
||||
else:
|
||||
status_callback("error", "All download sources failed")
|
||||
return None
|
||||
|
||||
# Return temp path - orchestrator handles post-processing (archive extraction, ingest)
|
||||
|
||||
@@ -25,6 +25,8 @@ logger = setup_logger(__name__)
|
||||
# Timing
|
||||
SOCKET_TIMEOUT = 300.0 # 5 minutes - long because we wait for DCC offers
|
||||
RECV_BUFFER = 4096
|
||||
# How often a deadline-bound read wakes up to re-check the clock
|
||||
POLL_INTERVAL = 2.0
|
||||
|
||||
# IRC channel user prefixes that indicate elevated status (ops, voice, etc.)
|
||||
# These are the download bots/servers
|
||||
@@ -248,11 +250,22 @@ class IRCClient:
|
||||
|
||||
# 366 = RPL_ENDOFNAMES - channel join is complete
|
||||
if msg.command == "366":
|
||||
logger.info(
|
||||
"Joined #%s - %s servers online",
|
||||
channel,
|
||||
len(self.online_servers),
|
||||
)
|
||||
if not self.online_servers:
|
||||
# Joining a channel that doesn't exist on this network
|
||||
# silently creates an empty one, so an empty name list is
|
||||
# the only hint that the channel name is wrong.
|
||||
logger.warning(
|
||||
"Joined #%s but no servers are online - the channel may "
|
||||
"be empty or not exist on %s",
|
||||
channel,
|
||||
self.server,
|
||||
)
|
||||
else:
|
||||
logger.info(
|
||||
"Joined #%s - %s servers online",
|
||||
channel,
|
||||
len(self.online_servers),
|
||||
)
|
||||
return
|
||||
|
||||
# Check for errors (e.g., banned, channel doesn't exist)
|
||||
@@ -296,27 +309,47 @@ class IRCClient:
|
||||
data = f"{message}\r\n".encode()
|
||||
self._socket.sendall(data)
|
||||
|
||||
def _recv_lines(self) -> Iterator[str]:
|
||||
"""Receive and yield complete CRLF-delimited IRC lines."""
|
||||
sock = self._require_socket()
|
||||
while True:
|
||||
# Check if we have a complete line in buffer
|
||||
while "\r\n" in self._buffer:
|
||||
line, self._buffer = self._buffer.split("\r\n", 1)
|
||||
if line:
|
||||
yield line
|
||||
def _recv_lines(self, deadline: float | None = None) -> Iterator[str]:
|
||||
"""Receive and yield complete CRLF-delimited IRC lines.
|
||||
|
||||
# Read more data
|
||||
try:
|
||||
data = sock.recv(RECV_BUFFER)
|
||||
if not data:
|
||||
return # Connection closed
|
||||
self._buffer += data.decode("utf-8", errors="replace")
|
||||
except TimeoutError:
|
||||
continue # Keep waiting
|
||||
except OSError as e:
|
||||
logger.warning("Socket error: %s", e)
|
||||
return # Connection error
|
||||
A deadline stops the read once it passes, even if nothing ever arrives.
|
||||
Callers time out by watching the messages they receive, so on a channel
|
||||
with no traffic at all there is nothing to watch: the recv would just
|
||||
keep blocking for SOCKET_TIMEOUT and retrying forever.
|
||||
"""
|
||||
sock = self._require_socket()
|
||||
original_timeout = sock.gettimeout()
|
||||
|
||||
try:
|
||||
while True:
|
||||
# Check if we have a complete line in buffer
|
||||
while "\r\n" in self._buffer:
|
||||
line, self._buffer = self._buffer.split("\r\n", 1)
|
||||
if line:
|
||||
yield line
|
||||
|
||||
if deadline is not None:
|
||||
remaining = deadline - time.time()
|
||||
if remaining <= 0:
|
||||
return
|
||||
# Wake up often enough to notice the deadline pass
|
||||
sock.settimeout(min(remaining, POLL_INTERVAL))
|
||||
|
||||
# Read more data
|
||||
try:
|
||||
data = sock.recv(RECV_BUFFER)
|
||||
if not data:
|
||||
return # Connection closed
|
||||
self._buffer += data.decode("utf-8", errors="replace")
|
||||
except TimeoutError:
|
||||
continue # Keep waiting (the deadline is re-checked above)
|
||||
except OSError as e:
|
||||
logger.warning("Socket error: %s", e)
|
||||
return # Connection error
|
||||
finally:
|
||||
if deadline is not None:
|
||||
with suppress(OSError):
|
||||
sock.settimeout(original_timeout)
|
||||
|
||||
def _parse_message(self, line: str) -> IRCMessage:
|
||||
"""Parse an IRC message line into components.
|
||||
@@ -427,9 +460,14 @@ class IRCClient:
|
||||
return False
|
||||
return True
|
||||
|
||||
def read_messages(self, *, auto_handle: bool = True) -> Iterator[IRCMessage]:
|
||||
def read_messages(
|
||||
self,
|
||||
*,
|
||||
auto_handle: bool = True,
|
||||
deadline: float | None = None,
|
||||
) -> Iterator[IRCMessage]:
|
||||
"""Read and yield IRC messages, optionally auto-handling PING/VERSION."""
|
||||
for line in self._recv_lines():
|
||||
for line in self._recv_lines(deadline):
|
||||
msg = self._parse_message(line)
|
||||
|
||||
# Auto-handle certain events
|
||||
@@ -453,13 +491,9 @@ class IRCClient:
|
||||
) -> DCCOffer | None:
|
||||
"""Wait for a DCC SEND offer. Returns None on timeout or no results."""
|
||||
target_event = IRCEvent.SEARCH_RESULT if result_type else IRCEvent.BOOK_RESULT
|
||||
start = time.time()
|
||||
|
||||
for msg in self.read_messages():
|
||||
if time.time() - start > timeout:
|
||||
logger.warning("Timeout waiting for DCC offer")
|
||||
return None
|
||||
deadline = time.time() + timeout
|
||||
|
||||
for msg in self.read_messages(deadline=deadline):
|
||||
if msg.event == target_event:
|
||||
if not self._is_allowed_dcc_sender(msg, expected_senders):
|
||||
continue
|
||||
@@ -491,6 +525,8 @@ class IRCClient:
|
||||
count = match.group(1)
|
||||
logger.info("Found %s matches", count)
|
||||
|
||||
if time.time() >= deadline:
|
||||
logger.warning("Timeout waiting for DCC offer")
|
||||
return None
|
||||
|
||||
@property
|
||||
|
||||
@@ -11,6 +11,7 @@ from typing import TYPE_CHECKING
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.utils import ARCHIVE_FORMATS, AUDIOBOOK_FORMATS
|
||||
from shelfmark.core.utils import is_audiobook as check_audiobook
|
||||
|
||||
if TYPE_CHECKING:
|
||||
@@ -18,11 +19,8 @@ if TYPE_CHECKING:
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# All recognized formats for parsing IRC result lines.
|
||||
# This comprehensive list is used to identify file extensions in results.
|
||||
# User-configured formats are used separately for filtering.
|
||||
ALL_RECOGNIZED_FORMATS = {
|
||||
# Ebook formats
|
||||
# Ebook formats recognized in IRC result lines.
|
||||
EBOOK_FORMATS = (
|
||||
"epub",
|
||||
"mobi",
|
||||
"azw3",
|
||||
@@ -41,19 +39,17 @@ ALL_RECOGNIZED_FORMATS = {
|
||||
"cbz",
|
||||
"cdr",
|
||||
"jpg",
|
||||
"rar",
|
||||
"zip",
|
||||
# Audiobook formats
|
||||
"m4b",
|
||||
"mp3",
|
||||
"m4a",
|
||||
"flac",
|
||||
"ogg",
|
||||
"wma",
|
||||
"aac",
|
||||
"wav",
|
||||
"opus",
|
||||
}
|
||||
)
|
||||
|
||||
# All recognized formats for parsing IRC result lines.
|
||||
# This comprehensive list is used to identify file extensions in results.
|
||||
# User-configured formats are used separately for filtering.
|
||||
# Ordered longest-first so that scanning a line matches "azw3" before "azw" and "docx"
|
||||
# before "doc". It used to be a set, which made the winning format for a line naming more
|
||||
# than one extension depend on set iteration order, and therefore vary between restarts.
|
||||
ALL_RECOGNIZED_FORMATS = tuple(
|
||||
sorted({*EBOOK_FORMATS, *ARCHIVE_FORMATS, *AUDIOBOOK_FORMATS}, key=len, reverse=True)
|
||||
)
|
||||
|
||||
|
||||
def _normalize_config_formats(raw_formats: object) -> set[str]:
|
||||
@@ -84,13 +80,22 @@ def _get_supported_formats(content_type: str | None = None) -> set[str]:
|
||||
|
||||
# Regex to parse result lines
|
||||
# Format: !Server Author - Title.format ::INFO:: size
|
||||
#
|
||||
# The extension is matched against the known formats rather than a bare \w+. A bare \w+
|
||||
# happily matched the decimal point in the size, so a line with no file extension parsed
|
||||
# as format="5mb" out of "::INFO:: 620.5MB" - taking the title and size down with it, and
|
||||
# leaving the result to be discarded by every format filter downstream. Restricting the
|
||||
# alternation makes such a line fall through to SIMPLE_RESULT_REGEX and come back as
|
||||
# "unknown", which is what the rest of the parser already expects.
|
||||
_FORMAT_ALTERNATION = "|".join(re.escape(fmt) for fmt in ALL_RECOGNIZED_FORMATS)
|
||||
RESULT_LINE_REGEX = re.compile(
|
||||
r"^!(\S+)\s+" # !ServerName
|
||||
r"(.+?)\s+-\s+" # Author Name -
|
||||
r"(.+?)\.(\w+)" # Title.format
|
||||
rf"(.+?)\.({_FORMAT_ALTERNATION})\b" # Title.format
|
||||
r"(?:\s+::INFO::\s*(.+?))?" # Optional ::INFO:: metadata
|
||||
r"(?:\s+::HASH::\s*(\S+))?" # Optional ::HASH::
|
||||
r"\s*$"
|
||||
r"\s*$",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
# Simpler fallback pattern
|
||||
@@ -187,18 +192,54 @@ def parse_result_line(line: str) -> SearchResult | None:
|
||||
return None
|
||||
|
||||
|
||||
# Words that mark an archive as holding an audiobook rather than an ebook. Multi-file
|
||||
# audiobooks ship as .rar/.zip, so for those the extension says nothing about the content
|
||||
# and the release name is the only evidence there is.
|
||||
_AUDIOBOOK_MARKER_REGEX = re.compile(
|
||||
r"\b(?:audio ?books?|unabridged|abridged|narrat(?:ed|or)|audible|\d+ ?kbps|"
|
||||
+ "|".join(re.escape(fmt) for fmt in AUDIOBOOK_FORMATS)
|
||||
+ r")\b",
|
||||
re.IGNORECASE,
|
||||
)
|
||||
|
||||
_AUDIOBOOK_FORMAT_SET = frozenset(AUDIOBOOK_FORMATS)
|
||||
_EBOOK_FORMAT_SET = frozenset(EBOOK_FORMATS)
|
||||
|
||||
|
||||
def detect_content_type(result: SearchResult) -> str:
|
||||
"""Classify a parsed result as an audiobook or an ebook.
|
||||
|
||||
Extension alone is not enough. It settles the plain cases, but the common audiobook
|
||||
release is a .rar or .zip of MP3s, which is indistinguishable by extension from an
|
||||
ebook archive - so for containers (and for lines with no usable extension) the
|
||||
release name decides.
|
||||
"""
|
||||
if result.format in _AUDIOBOOK_FORMAT_SET:
|
||||
return "audiobook"
|
||||
if result.format in _EBOOK_FORMAT_SET:
|
||||
return "ebook"
|
||||
return "audiobook" if _AUDIOBOOK_MARKER_REGEX.search(result.full_line) else "ebook"
|
||||
|
||||
|
||||
def parse_results_file(content: str, content_type: str | None = None) -> list[SearchResult]:
|
||||
"""Parse a search results file into SearchResult objects."""
|
||||
results = []
|
||||
supported = _get_supported_formats(content_type)
|
||||
requested = "audiobook" if check_audiobook(content_type) else "ebook"
|
||||
|
||||
for line in content.splitlines():
|
||||
result = parse_result_line(line)
|
||||
if result and (result.format in supported or result.format == "unknown"):
|
||||
# Filter to user's configured formats
|
||||
if not result:
|
||||
continue
|
||||
# Classify first, then apply the user's format filter within that bucket. Doing it
|
||||
# the other way round is what lost audiobooks entirely: an audiobook .rar matched
|
||||
# neither the ebook nor the audiobook format list, so it fell out of both.
|
||||
if detect_content_type(result) != requested:
|
||||
continue
|
||||
if result.format in supported or result.format == "unknown":
|
||||
results.append(result)
|
||||
|
||||
logger.info("Parsed %s results from search file", len(results))
|
||||
logger.info("Parsed %s %s results from search file", len(results), requested)
|
||||
return results
|
||||
|
||||
|
||||
|
||||
@@ -72,7 +72,10 @@ def irc_settings() -> list[SettingsField]:
|
||||
key="IRC_CHANNEL",
|
||||
label="Channel",
|
||||
placeholder="e.g. ebooks",
|
||||
description="Channel name without the # prefix",
|
||||
description=(
|
||||
"Channel name without the # prefix. Used for all searches unless a "
|
||||
"separate audiobook channel is configured below."
|
||||
),
|
||||
required=True,
|
||||
env_supported=True,
|
||||
),
|
||||
@@ -95,6 +98,42 @@ def irc_settings() -> list[SettingsField]:
|
||||
required=True,
|
||||
env_supported=True,
|
||||
),
|
||||
HeadingField(
|
||||
key="audiobook_heading",
|
||||
title="Audiobooks",
|
||||
description=(
|
||||
"Most networks index audiobooks in the same channel as ebooks, so leaving "
|
||||
"these blank is the right setting for almost everyone. On irc.irchighway.net "
|
||||
"the audiobooks are in #ebooks and #bookz is effectively inactive — pointing "
|
||||
"this at an empty channel just returns no results. Only fill these in when "
|
||||
"your network really does index audiobooks elsewhere (Undernet's #bookz, for "
|
||||
"example). Audiobooks are usually posted as archives, so keep ZIP and RAR "
|
||||
"enabled under Supported Audiobook Formats or the releases are filtered out."
|
||||
),
|
||||
),
|
||||
TextField(
|
||||
key="IRC_AUDIOBOOK_CHANNEL",
|
||||
label="Audiobook channel",
|
||||
placeholder="e.g. bookz",
|
||||
description=(
|
||||
"Optional. Channel name (without the # prefix) for networks that index "
|
||||
"audiobooks separately, such as Undernet's bookz. Leave blank (the usual "
|
||||
"setting) to search the main channel above for audiobooks too."
|
||||
),
|
||||
required=False,
|
||||
env_supported=True,
|
||||
),
|
||||
TextField(
|
||||
key="IRC_AUDIOBOOK_SEARCH_BOT",
|
||||
label="Audiobook search bot",
|
||||
placeholder="e.g. search",
|
||||
description=(
|
||||
"Optional. Search bot for the audiobook channel. Leave blank to reuse "
|
||||
"the main search bot above. Only used when an audiobook channel is set."
|
||||
),
|
||||
required=False,
|
||||
env_supported=True,
|
||||
),
|
||||
HeadingField(
|
||||
key="cache_heading",
|
||||
title="Search Cache",
|
||||
|
||||
@@ -240,6 +240,19 @@ class IRCReleaseSource(ReleaseSource):
|
||||
nick = _config_text("IRC_NICK")
|
||||
search_bot = _config_text("IRC_SEARCH_BOT")
|
||||
|
||||
# A few networks index audiobooks in a separate channel from ebooks (Undernet's
|
||||
# #bookz, say). When an audiobook channel is configured and an audiobook was
|
||||
# requested, route the search there (with its own search bot if set). Otherwise
|
||||
# fall back to the main channel/bot — that is the common case, since most networks
|
||||
# (irchighway included) serve both formats from the one channel.
|
||||
if is_audiobook(content_type):
|
||||
audiobook_channel = _config_text("IRC_AUDIOBOOK_CHANNEL")
|
||||
if audiobook_channel:
|
||||
channel = audiobook_channel
|
||||
audiobook_search_bot = _config_text("IRC_AUDIOBOOK_SEARCH_BOT")
|
||||
if audiobook_search_bot:
|
||||
search_bot = audiobook_search_bot
|
||||
|
||||
# Never post an unaddressed query to the channel. A bare book title looks like
|
||||
# spam to everyone else in the channel and gets the nick banned. Searches must
|
||||
# be addressed to a search bot ("@<bot> <query>").
|
||||
|
||||
@@ -14,10 +14,6 @@ from shelfmark.release_sources.prowlarr.torznab import parse_torznab_xml
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# Newznab standard book category IDs
|
||||
NEWZNAB_BOOKS = 7000
|
||||
NEWZNAB_AUDIOBOOKS = 3030
|
||||
|
||||
|
||||
class NewznabClient:
|
||||
"""Client for any Newznab-compatible indexer API."""
|
||||
|
||||
@@ -8,6 +8,7 @@ from shelfmark.core.settings_registry import (
|
||||
HeadingField,
|
||||
PasswordField,
|
||||
SettingsField,
|
||||
TagListField,
|
||||
TextField,
|
||||
register_settings,
|
||||
)
|
||||
@@ -86,6 +87,30 @@ def newznab_config_settings() -> list[SettingsField]:
|
||||
callback=_test_newznab_connection,
|
||||
show_when={"field": "NEWZNAB_ENABLED", "value": True},
|
||||
),
|
||||
TagListField(
|
||||
key="NEWZNAB_EBOOK_CATEGORIES",
|
||||
label="Ebook Categories",
|
||||
description=(
|
||||
"Newznab category IDs searched for ebooks. Most indexers use the standard 7000, "
|
||||
"but some use custom IDs. Leave empty to use 7000."
|
||||
),
|
||||
placeholder="7000",
|
||||
default=["7000"],
|
||||
normalize_urls=False,
|
||||
show_when={"field": "NEWZNAB_ENABLED", "value": True},
|
||||
),
|
||||
TagListField(
|
||||
key="NEWZNAB_AUDIOBOOK_CATEGORIES",
|
||||
label="Audiobook Categories",
|
||||
description=(
|
||||
"Newznab category IDs searched for audiobooks. Most indexers use the standard "
|
||||
"3030, but some use custom IDs. Leave empty to use 3030."
|
||||
),
|
||||
placeholder="3030",
|
||||
default=["3030"],
|
||||
normalize_urls=False,
|
||||
show_when={"field": "NEWZNAB_ENABLED", "value": True},
|
||||
),
|
||||
CheckboxField(
|
||||
key="NEWZNAB_AUTO_EXPAND",
|
||||
label="Auto-expand search on no results",
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
import time
|
||||
from typing import TYPE_CHECKING, ClassVar
|
||||
|
||||
@@ -39,15 +40,93 @@ from shelfmark.release_sources.prowlarr.source import (
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# Newznab category IDs
|
||||
_AUDIOBOOK_CATS = [3030]
|
||||
_BOOK_CATS = [7000]
|
||||
# Standard Newznab category IDs, used when the indexer's categories aren't configured.
|
||||
_DEFAULT_AUDIOBOOK_CATS = [3030]
|
||||
_DEFAULT_BOOK_CATS = [7000]
|
||||
|
||||
# Reuse the same timeout constant as Prowlarr.
|
||||
NEWZNAB_SEARCH_TIMEOUT_SECONDS = _SEARCH_TIMEOUT
|
||||
|
||||
|
||||
def _newznab_result_to_release(result: dict, content_type: str = "ebook") -> Release:
|
||||
def _parse_category_ids(raw: object) -> list[int]:
|
||||
"""Parse a configured category setting into Newznab category IDs.
|
||||
|
||||
Accepts a list of values or a comma/whitespace separated string. Entries that
|
||||
aren't positive integers are skipped, and duplicates are dropped.
|
||||
"""
|
||||
if raw is None:
|
||||
return []
|
||||
|
||||
values = list(raw) if isinstance(raw, (list, tuple)) else [raw]
|
||||
|
||||
category_ids: list[int] = []
|
||||
for value in values:
|
||||
for token in re.split(r"[,\s]+", str(value).strip()):
|
||||
if not token:
|
||||
continue
|
||||
try:
|
||||
category_id = int(token)
|
||||
except ValueError:
|
||||
logger.warning("Newznab: ignoring invalid category ID '%s'", token)
|
||||
continue
|
||||
if category_id > 0 and category_id not in category_ids:
|
||||
category_ids.append(category_id)
|
||||
|
||||
return category_ids
|
||||
|
||||
|
||||
def _configured_categories(content_type: str) -> list[int]:
|
||||
"""Return the categories to search for a content type, falling back to defaults."""
|
||||
if content_type == "audiobook":
|
||||
key, defaults = "NEWZNAB_AUDIOBOOK_CATEGORIES", _DEFAULT_AUDIOBOOK_CATS
|
||||
else:
|
||||
key, defaults = "NEWZNAB_EBOOK_CATEGORIES", _DEFAULT_BOOK_CATS
|
||||
|
||||
return _parse_category_ids(config.get(key, None)) or list(defaults)
|
||||
|
||||
|
||||
def _result_category_ids(categories: object) -> set[int]:
|
||||
"""Extract numeric category IDs from a result's categories field."""
|
||||
if not isinstance(categories, (list, tuple)):
|
||||
return set()
|
||||
|
||||
category_ids: set[int] = set()
|
||||
for cat in categories:
|
||||
raw = cat.get("id") if isinstance(cat, dict) else cat
|
||||
try:
|
||||
category_ids.add(int(raw)) # type: ignore[arg-type]
|
||||
except TypeError, ValueError:
|
||||
continue
|
||||
return category_ids
|
||||
|
||||
|
||||
def _resolve_content_type(
|
||||
categories: object,
|
||||
content_type: str,
|
||||
searched_categories: list[int] | None,
|
||||
) -> str:
|
||||
"""Resolve a result's content type, honouring custom indexer categories.
|
||||
|
||||
Indexers using non-standard IDs (e.g. 7100 for ebooks) fall outside the standard
|
||||
ranges, so trust the searched content type when the result carries a category we
|
||||
explicitly asked for.
|
||||
"""
|
||||
category_list = list(categories) if isinstance(categories, (list, tuple)) else []
|
||||
detected = _detect_content_type_from_categories(category_list, content_type)
|
||||
if (
|
||||
detected == "other"
|
||||
and searched_categories
|
||||
and _result_category_ids(category_list) & set(searched_categories)
|
||||
):
|
||||
return "audiobook" if content_type == "audiobook" else "book"
|
||||
return detected
|
||||
|
||||
|
||||
def _newznab_result_to_release(
|
||||
result: dict,
|
||||
content_type: str = "ebook",
|
||||
searched_categories: list[int] | None = None,
|
||||
) -> Release:
|
||||
"""Convert a parsed Newznab XML result dict to a Release object."""
|
||||
raw_title = result.get("title", "Unknown")
|
||||
size_bytes = result.get("size")
|
||||
@@ -125,7 +204,7 @@ def _newznab_result_to_release(result: dict, content_type: str = "ebook") -> Rel
|
||||
indexer=indexer,
|
||||
seeders=seeders if is_torrent else None,
|
||||
peers=peers_display,
|
||||
content_type=_detect_content_type_from_categories(categories, content_type),
|
||||
content_type=_resolve_content_type(categories, content_type, searched_categories),
|
||||
extra={
|
||||
"publish_date": result.get("publishDate"),
|
||||
"categories": categories,
|
||||
@@ -230,12 +309,7 @@ class NewznabSource(ReleaseSource):
|
||||
return []
|
||||
|
||||
# Category selection — omit categories when expanding search
|
||||
if expand_search:
|
||||
categories = None
|
||||
elif content_type == "audiobook":
|
||||
categories = [3030]
|
||||
else:
|
||||
categories = [7000]
|
||||
categories = None if expand_search else _configured_categories(content_type)
|
||||
|
||||
auto_expand = config.get("NEWZNAB_AUTO_EXPAND", False)
|
||||
deadline = time.monotonic() + NEWZNAB_SEARCH_TIMEOUT_SECONDS
|
||||
@@ -283,7 +357,7 @@ class NewznabSource(ReleaseSource):
|
||||
logger.exception("Newznab search failed")
|
||||
return []
|
||||
|
||||
results = [_newznab_result_to_release(r, content_type) for r in all_results]
|
||||
results = [_newznab_result_to_release(r, content_type, categories) for r in all_results]
|
||||
|
||||
if results:
|
||||
nzb_count = sum(1 for r in results if r.protocol == ReleaseProtocol.NZB)
|
||||
|
||||
@@ -158,36 +158,55 @@ class ProwlarrClient:
|
||||
logger.info("Prowlarr connection successful: version %s", version)
|
||||
return True, f"Connected to Prowlarr {version}"
|
||||
|
||||
def get_indexers(self) -> list[dict[str, Any]]:
|
||||
"""Get all configured indexers."""
|
||||
def get_indexers(self, *, raise_on_error: bool = False) -> list[dict[str, Any]]:
|
||||
"""Get all configured indexers.
|
||||
|
||||
Args:
|
||||
raise_on_error: When True, propagate API failures instead of
|
||||
returning an empty list. Callers that must distinguish
|
||||
"no indexers" from "the request failed" should set this.
|
||||
|
||||
"""
|
||||
try:
|
||||
return _normalize_json_object_list(
|
||||
self._request("GET", "/api/v1/indexer"),
|
||||
context="Prowlarr indexer list",
|
||||
)
|
||||
except _PROWLARR_CLIENT_ERRORS:
|
||||
if raise_on_error:
|
||||
raise
|
||||
logger.exception("Failed to get indexers")
|
||||
return []
|
||||
|
||||
def get_enabled_indexers_detailed(self) -> list[dict[str, Any]]:
|
||||
def get_enabled_indexers_detailed(
|
||||
self, *, raise_on_error: bool = False
|
||||
) -> list[dict[str, Any]]:
|
||||
"""Get enabled indexers, including implementation metadata.
|
||||
|
||||
Note: Prowlarr indexer "name" is user-configurable; prefer
|
||||
"implementation"/"implementationName" for stable identification.
|
||||
"""
|
||||
indexers = self.get_indexers()
|
||||
indexers = self.get_indexers(raise_on_error=raise_on_error)
|
||||
return [idx for idx in indexers if idx.get("enable", False)]
|
||||
|
||||
def get_enriched_indexer_ids(self, *, restrict_to: list[int] | None = None) -> list[int]:
|
||||
def get_enriched_indexer_ids(
|
||||
self,
|
||||
*,
|
||||
restrict_to: list[int] | None = None,
|
||||
indexers: list[dict[str, Any]] | None = None,
|
||||
) -> list[int]:
|
||||
"""Return enabled indexer IDs that benefit from extra Torznab handling.
|
||||
|
||||
Args:
|
||||
restrict_to: Optional list of candidate indexer IDs to consider.
|
||||
indexers: Optional already-fetched enabled indexer list, so callers
|
||||
that need the full records for other reasons can avoid a second
|
||||
round trip.
|
||||
|
||||
"""
|
||||
enriched_ids: list[int] = []
|
||||
|
||||
for idx in self.get_enabled_indexers_detailed():
|
||||
for idx in indexers if indexers is not None else self.get_enabled_indexers_detailed():
|
||||
idx_id_int = coerce_int_like(idx.get("id"))
|
||||
if idx_id_int is None:
|
||||
continue
|
||||
@@ -214,10 +233,17 @@ class ProwlarrClient:
|
||||
|
||||
Prowlarr exposes seedTime in minutes, which is also the unit expected by
|
||||
torrent clients.
|
||||
|
||||
Raises:
|
||||
requests.exceptions.RequestException (and other client errors) when
|
||||
the indexer list cannot be fetched. An empty dict strictly means
|
||||
"no share limits are configured", never "the request failed" -
|
||||
callers rely on this to avoid silently dropping seed limits.
|
||||
|
||||
"""
|
||||
settings_by_indexer: dict[int, IndexerSeedSettings] = {}
|
||||
|
||||
for idx in self.get_enabled_indexers_detailed():
|
||||
for idx in self.get_enabled_indexers_detailed(raise_on_error=True):
|
||||
idx_id_int = coerce_int_like(idx.get("id"))
|
||||
if idx_id_int is None:
|
||||
continue
|
||||
|
||||
@@ -1,10 +1,15 @@
|
||||
"""Prowlarr download handler - resolves releases and delegates lifecycle to shared clients."""
|
||||
|
||||
from typing import TYPE_CHECKING, Any
|
||||
from urllib.parse import urlparse
|
||||
|
||||
import requests
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.request_helpers import normalize_optional_text
|
||||
from shelfmark.core.search_plan import build_release_search_plan
|
||||
from shelfmark.core.utils import normalize_http_url
|
||||
from shelfmark.download.clients import (
|
||||
DownloadClient,
|
||||
get_client,
|
||||
@@ -23,9 +28,13 @@ from shelfmark.download.clients.base_handler import (
|
||||
DownloadRequest,
|
||||
ExternalClientHandler,
|
||||
)
|
||||
from shelfmark.metadata_providers import BookMetadata
|
||||
from shelfmark.release_sources import register_handler
|
||||
from shelfmark.release_sources.prowlarr.cache import get_release, remove_release
|
||||
from shelfmark.release_sources.prowlarr.api import IndexerSeedSettings, ProwlarrClient
|
||||
from shelfmark.release_sources.prowlarr.cache import cache_release, get_release, remove_release
|
||||
from shelfmark.release_sources.prowlarr.source import ProwlarrSource
|
||||
from shelfmark.release_sources.prowlarr.utils import (
|
||||
build_source_id,
|
||||
coerce_int_like,
|
||||
get_preferred_download_url,
|
||||
get_protocol,
|
||||
@@ -37,6 +46,16 @@ if TYPE_CHECKING:
|
||||
from shelfmark.core.models import DownloadTask
|
||||
|
||||
logger = setup_logger(__name__)
|
||||
|
||||
# Errors that ProwlarrClient can raise when fetching indexer settings.
|
||||
_SEED_SETTINGS_FALLBACK_ERRORS = (
|
||||
requests.exceptions.RequestException,
|
||||
OSError,
|
||||
RuntimeError,
|
||||
TypeError,
|
||||
ValueError,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"ProwlarrHandler",
|
||||
"POLL_INTERVAL",
|
||||
@@ -49,6 +68,11 @@ __all__ = [
|
||||
POLL_INTERVAL = _DEFAULT_POLL_INTERVAL
|
||||
COMPLETED_PATH_RETRY_INTERVAL = _DEFAULT_COMPLETED_PATH_RETRY_INTERVAL
|
||||
COMPLETED_PATH_MAX_ATTEMPTS = _DEFAULT_COMPLETED_PATH_MAX_ATTEMPTS
|
||||
EXPIRED_LINK_REFRESH_ERROR = (
|
||||
"The indexer download link expired and the release could not be refreshed. "
|
||||
"Search again for a fresh result."
|
||||
)
|
||||
HASH_DETECTION_ERROR = "Could not determine torrent hash from URL"
|
||||
|
||||
|
||||
def _coerce_positive_minutes(raw_minutes: object) -> int | None:
|
||||
@@ -62,6 +86,47 @@ def _coerce_positive_minutes(raw_minutes: object) -> int | None:
|
||||
class ProwlarrHandler(ExternalClientHandler):
|
||||
"""Handler for Prowlarr downloads via configured torrent or usenet client."""
|
||||
|
||||
@staticmethod
|
||||
def _build_prowlarr_client() -> ProwlarrClient | None:
|
||||
"""Build a ProwlarrClient from config, or None if not configured."""
|
||||
raw_url = config.get("PROWLARR_URL", "")
|
||||
raw_api_key = config.get("PROWLARR_API_KEY", "")
|
||||
url = normalize_optional_text(raw_url) if isinstance(raw_url, str) else None
|
||||
api_key = normalize_optional_text(raw_api_key) if isinstance(raw_api_key, str) else None
|
||||
if not url or not api_key:
|
||||
return None
|
||||
normalized_url = normalize_http_url(url)
|
||||
if not normalized_url:
|
||||
return None
|
||||
return ProwlarrClient(normalized_url, api_key)
|
||||
|
||||
def _fetch_seed_settings_fallback(self, raw_indexer_id: object) -> IndexerSeedSettings | None:
|
||||
"""Fetch share limits for one indexer directly from Prowlarr.
|
||||
|
||||
Used when the cached release is missing its search-time seed-limit
|
||||
enrichment so that transient failures during search cannot cause a
|
||||
torrent to be added without its configured share limits.
|
||||
"""
|
||||
indexer_id = coerce_int_like(raw_indexer_id)
|
||||
if indexer_id is None:
|
||||
return None
|
||||
|
||||
client = self._build_prowlarr_client()
|
||||
if client is None:
|
||||
return None
|
||||
|
||||
try:
|
||||
settings = client.get_indexer_seed_settings(restrict_to=[indexer_id])
|
||||
except _SEED_SETTINGS_FALLBACK_ERRORS:
|
||||
logger.warning(
|
||||
"Grab-time seed settings fallback failed for indexerId=%s",
|
||||
indexer_id,
|
||||
exc_info=True,
|
||||
)
|
||||
return None
|
||||
|
||||
return settings.get(indexer_id)
|
||||
|
||||
def _get_client(self, protocol: str) -> DownloadClient | None:
|
||||
"""Compatibility shim so module-level patching still works in tests."""
|
||||
return get_client(protocol)
|
||||
@@ -81,18 +146,30 @@ class ProwlarrHandler(ExternalClientHandler):
|
||||
|
||||
def build_retry_resolution_fields(self, release_data: dict[str, Any]) -> dict[str, Any]:
|
||||
source_id = normalize_optional_text(release_data.get("source_id"))
|
||||
if source_id is None:
|
||||
return {}
|
||||
extra = release_data.get("extra")
|
||||
if not isinstance(extra, dict):
|
||||
extra = {}
|
||||
|
||||
prowlarr_result = get_release(source_id)
|
||||
if prowlarr_result is None:
|
||||
return {}
|
||||
retry_source_context: dict[str, Any] = {}
|
||||
indexer_id = release_data.get("indexer_id") or extra.get("indexer_id")
|
||||
if indexer_id is not None:
|
||||
retry_source_context["indexer_id"] = indexer_id
|
||||
|
||||
indexer = normalize_optional_text(release_data.get("indexer") or extra.get("indexer"))
|
||||
if indexer is not None and indexer.lower() != "unknown":
|
||||
retry_source_context["indexer"] = indexer
|
||||
|
||||
info_url = normalize_optional_text(release_data.get("info_url") or extra.get("info_url"))
|
||||
if info_url is not None:
|
||||
retry_source_context["info_url"] = info_url
|
||||
|
||||
if source_id is not None:
|
||||
retry_source_context["source_id"] = source_id
|
||||
|
||||
return {
|
||||
"retry_download_url": normalize_optional_text(
|
||||
get_preferred_download_url(prowlarr_result)
|
||||
),
|
||||
"retry_download_protocol": normalize_optional_text(get_protocol(prowlarr_result)),
|
||||
"retry_download_url": None,
|
||||
"retry_download_protocol": None,
|
||||
"retry_source_context": retry_source_context,
|
||||
}
|
||||
|
||||
@classmethod
|
||||
@@ -139,13 +216,12 @@ class ProwlarrHandler(ExternalClientHandler):
|
||||
# Look up the cached release
|
||||
prowlarr_result = get_release(task.task_id)
|
||||
if not prowlarr_result:
|
||||
restored_request = self._restore_download_request_from_task(task)
|
||||
if restored_request is None:
|
||||
logger.warning("Release cache miss: %s", task.task_id)
|
||||
status_callback("error", "Release not found in cache (may have expired)")
|
||||
logger.info("Prowlarr release cache miss, refreshing: %s", task.task_id)
|
||||
prowlarr_result = self._refresh_release(task)
|
||||
if prowlarr_result is None:
|
||||
logger.warning("Prowlarr release refresh failed: %s", task.task_id)
|
||||
status_callback("error", EXPIRED_LINK_REFRESH_ERROR)
|
||||
return None
|
||||
logger.info("Restored Prowlarr download request for retry: %s", task.task_id)
|
||||
return restored_request
|
||||
|
||||
# Extract download URL
|
||||
download_url = get_preferred_download_url(prowlarr_result)
|
||||
@@ -171,6 +247,28 @@ class ProwlarrHandler(ExternalClientHandler):
|
||||
seeding_time_limit = _coerce_positive_minutes(raw_configured_seed_time)
|
||||
ratio_limit = float(raw_configured_ratio) if raw_configured_ratio is not None else None
|
||||
|
||||
# Fallback: search-time enrichment can be missing when the indexer
|
||||
# settings fetch transiently failed during the search (#795).
|
||||
# Re-resolve the limits from Prowlarr at grab time so torrents are
|
||||
# never sent to the client without their configured share limits.
|
||||
if seeding_time_limit is None and ratio_limit is None and protocol == "torrent":
|
||||
fallback = self._fetch_seed_settings_fallback(prowlarr_result.get("indexerId"))
|
||||
if fallback:
|
||||
seeding_time_limit = _coerce_positive_minutes(
|
||||
fallback.get("seeding_time_limit_minutes")
|
||||
)
|
||||
raw_ratio = fallback.get("ratio_limit")
|
||||
ratio_limit = float(raw_ratio) if raw_ratio is not None else None
|
||||
|
||||
if seeding_time_limit is None and ratio_limit is None and protocol == "torrent":
|
||||
logger.warning(
|
||||
"Prowlarr seed preferences are enabled but no share limits "
|
||||
"could be resolved for release '%s' (indexerId=%s); the "
|
||||
"torrent will use the client's global limits",
|
||||
release_name,
|
||||
prowlarr_result.get("indexerId"),
|
||||
)
|
||||
|
||||
return DownloadRequest(
|
||||
url=download_url,
|
||||
protocol=protocol,
|
||||
@@ -180,6 +278,92 @@ class ProwlarrHandler(ExternalClientHandler):
|
||||
ratio_limit=ratio_limit,
|
||||
)
|
||||
|
||||
def _refresh_release(self, task: DownloadTask) -> dict[str, Any] | None:
|
||||
"""Re-query Prowlarr and cache the exact original release if it still exists."""
|
||||
title = normalize_optional_text(task.title)
|
||||
if title is None:
|
||||
return None
|
||||
|
||||
context = getattr(task, "retry_source_context", None)
|
||||
if not isinstance(context, dict):
|
||||
context = {}
|
||||
|
||||
indexer = normalize_optional_text(context.get("indexer"))
|
||||
book = BookMetadata(
|
||||
provider="shelfmark",
|
||||
provider_id=task.task_id,
|
||||
title=title,
|
||||
authors=[task.author] if task.author else [],
|
||||
search_title=title,
|
||||
search_author=task.author,
|
||||
)
|
||||
plan = build_release_search_plan(
|
||||
book,
|
||||
indexers=[indexer] if indexer is not None else None,
|
||||
)
|
||||
|
||||
source = ProwlarrSource()
|
||||
results = source.search(book, plan, content_type=task.content_type or "ebook")
|
||||
for release in results:
|
||||
raw_release = get_release(release.source_id)
|
||||
if raw_release is None:
|
||||
continue
|
||||
if not self._raw_release_matches_task(raw_release, task.task_id):
|
||||
continue
|
||||
|
||||
cache_release(task.task_id, raw_release)
|
||||
logger.info("Refreshed Prowlarr release: %s", task.task_id)
|
||||
return raw_release
|
||||
|
||||
return None
|
||||
|
||||
@staticmethod
|
||||
def _raw_release_matches_task(raw_release: dict[str, Any], task_id: str) -> bool:
|
||||
wanted = normalize_optional_text(task_id)
|
||||
if wanted is None:
|
||||
return False
|
||||
|
||||
bare = [
|
||||
identity
|
||||
for identity in (
|
||||
normalize_optional_text(raw_release.get("guid")),
|
||||
normalize_optional_text(raw_release.get("infoUrl")),
|
||||
)
|
||||
if identity is not None
|
||||
]
|
||||
|
||||
identities = [*bare, build_source_id(raw_release)]
|
||||
indexer_id = coerce_int_like(raw_release.get("indexerId"))
|
||||
if indexer_id is not None:
|
||||
identities.extend(f"{indexer_id}:{identity}" for identity in bare)
|
||||
|
||||
return wanted in identities
|
||||
|
||||
def _refresh_download_request_after_add_failure(
|
||||
self,
|
||||
*,
|
||||
task: DownloadTask,
|
||||
request: DownloadRequest,
|
||||
error: Exception,
|
||||
status_callback: Callable[[str, str | None], None],
|
||||
) -> DownloadRequest | None:
|
||||
"""Refresh once when a cached Prowlarr torrent proxy URL has expired."""
|
||||
if request.protocol != "torrent":
|
||||
return None
|
||||
if HASH_DETECTION_ERROR not in str(error):
|
||||
return None
|
||||
|
||||
parsed = urlparse(request.url)
|
||||
if parsed.scheme.lower() not in {"http", "https"}:
|
||||
return None
|
||||
|
||||
logger.info("Refreshing stale Prowlarr torrent URL for %s", task.task_id)
|
||||
remove_release(task.task_id)
|
||||
refreshed_request = self._resolve_download(task, status_callback)
|
||||
if refreshed_request is None:
|
||||
raise RuntimeError(EXPIRED_LINK_REFRESH_ERROR) from error
|
||||
return refreshed_request
|
||||
|
||||
def _on_download_complete(self, task: DownloadTask) -> None:
|
||||
"""Remove completed release from the Prowlarr cache."""
|
||||
remove_release(task.task_id)
|
||||
|
||||
@@ -190,6 +190,18 @@ def prowlarr_config_settings() -> list[SettingsField]:
|
||||
description="Automatically retry search without category filtering if no results are found",
|
||||
show_when={"field": "PROWLARR_ENABLED", "value": True},
|
||||
),
|
||||
CheckboxField(
|
||||
key="PROWLARR_COLLAPSE_DUPLICATES",
|
||||
label="Show one row per release",
|
||||
default=True,
|
||||
description=(
|
||||
"Collapse a release that several indexer entries returned down to a single row, "
|
||||
"keeping the entry with the best Prowlarr priority. Turn this off to see every "
|
||||
"entry that carried it, which is what makes results from filter-specific entries "
|
||||
"(freeleech and the like) visible."
|
||||
),
|
||||
show_when={"field": "PROWLARR_ENABLED", "value": True},
|
||||
),
|
||||
CheckboxField(
|
||||
key="PROWLARR_USE_SEED_PREFERENCES",
|
||||
label="Use Prowlarr seed preferences",
|
||||
|
||||
@@ -2,16 +2,21 @@
|
||||
|
||||
import re
|
||||
import time
|
||||
from threading import Lock
|
||||
from typing import TYPE_CHECKING, ClassVar, NoReturn
|
||||
|
||||
import requests
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from shelfmark.core.search_plan import ReleaseSearchPlan
|
||||
from shelfmark.metadata_providers import BookMetadata
|
||||
|
||||
from shelfmark.core.config import config
|
||||
from shelfmark.core.languages import normalize_language
|
||||
from shelfmark.core.logger import setup_logger
|
||||
from shelfmark.core.request_helpers import normalize_optional_text
|
||||
from shelfmark.core.search_plan import ReleaseSearchVariant
|
||||
from shelfmark.core.utils import AUDIOBOOK_FORMATS as CORE_AUDIOBOOK_FORMATS
|
||||
from shelfmark.core.utils import normalize_http_url
|
||||
from shelfmark.release_sources import (
|
||||
ColumnAlign,
|
||||
@@ -30,6 +35,7 @@ from shelfmark.release_sources import (
|
||||
from shelfmark.release_sources.prowlarr.api import IndexerSeedSettings, ProwlarrClient
|
||||
from shelfmark.release_sources.prowlarr.cache import cache_release
|
||||
from shelfmark.release_sources.prowlarr.utils import (
|
||||
build_source_id,
|
||||
coerce_float_like,
|
||||
coerce_int_like,
|
||||
get_protocol,
|
||||
@@ -41,6 +47,14 @@ _SIZE_UNIT_BASE = 1024
|
||||
_TWO_FORMATS = 2
|
||||
_PROWLARR_SOURCE_ERRORS = (AttributeError, OSError, RuntimeError, TypeError, ValueError)
|
||||
|
||||
# Prowlarr indexer priority is 1-50 and lower is preferred; unknown sorts last.
|
||||
_UNRANKED_INDEXER_RANK = 51
|
||||
|
||||
# Errors that can surface from ProwlarrClient.get_indexer_seed_settings(). The
|
||||
# client raises requests exceptions (subclasses of OSError via IOError lineage
|
||||
# is not guaranteed), so include RequestException explicitly.
|
||||
_PROWLARR_SEED_SETTINGS_ERRORS = (*_PROWLARR_SOURCE_ERRORS, requests.exceptions.RequestException)
|
||||
|
||||
|
||||
def _raise_timeout_error(message: str) -> NoReturn:
|
||||
raise TimeoutError(message)
|
||||
@@ -61,6 +75,118 @@ def _coerce_indexer_id(value: object) -> int | None:
|
||||
return coerce_int_like(value)
|
||||
|
||||
|
||||
def _identity_text(value: object) -> str | None:
|
||||
"""Trimmed text for an identity field, or None when there is nothing usable."""
|
||||
if isinstance(value, str):
|
||||
return value.strip() or None
|
||||
if isinstance(value, (int, float)) and not isinstance(value, bool):
|
||||
return str(value)
|
||||
return None
|
||||
|
||||
|
||||
def _release_identity(result: dict) -> str | None:
|
||||
"""Identify the underlying release, independent of which indexer surfaced it.
|
||||
|
||||
Strong identifiers only. Title is deliberately excluded because matching on
|
||||
it here would merge two genuinely different releases that happen to share a
|
||||
name, and every caller of this either drops or overwrites a row on a match.
|
||||
Returns None when nothing identifies the result.
|
||||
"""
|
||||
for field in ("guid", "downloadUrl", "magnetUrl", "infoUrl"):
|
||||
identity = _identity_text(result.get(field))
|
||||
if identity is not None:
|
||||
return identity
|
||||
return None
|
||||
|
||||
|
||||
def _result_dedup_key(result: dict) -> tuple[int | None, str] | None:
|
||||
"""Dedup key for a raw Prowlarr result, or None if it cannot be identified.
|
||||
|
||||
One tracker is often configured in Prowlarr as several indexer entries that
|
||||
differ only by a server-side search filter, say a "freeleech only" entry
|
||||
alongside an unfiltered one. Those entries return the same guid for the same
|
||||
torrent, so keying on the guid alone throws away the filtered entry's copy
|
||||
and with it the only signal that the release matched the filter. Including
|
||||
the indexer id keeps the entries distinct.
|
||||
|
||||
Title is an acceptable last resort here, unlike in _release_identity, because
|
||||
the indexer id is part of the key: it only ever collapses a literal repeat
|
||||
from one indexer, never two rows from different entries.
|
||||
"""
|
||||
identity = _release_identity(result) or _identity_text(result.get("title"))
|
||||
if identity is None:
|
||||
return None
|
||||
return (_coerce_indexer_id(result.get("indexerId")), identity)
|
||||
|
||||
|
||||
def _build_indexer_priority(indexers: list[dict]) -> dict[int, int]:
|
||||
"""Map indexer id to the priority configured in Prowlarr. Lower is preferred.
|
||||
|
||||
Users already rank their indexers in Prowlarr, and on trackers configured as
|
||||
several entries that ranking is usually the meaningful one: a "freeleech
|
||||
only" entry is typically given a better priority than the unfiltered entry
|
||||
beside it. Reusing it avoids asking for the same ordering a second time.
|
||||
"""
|
||||
priority: dict[int, int] = {}
|
||||
for indexer in indexers:
|
||||
indexer_id = _coerce_indexer_id(indexer.get("id"))
|
||||
if indexer_id is None:
|
||||
continue
|
||||
rank = coerce_int_like(indexer.get("priority"))
|
||||
if rank is not None:
|
||||
priority[indexer_id] = rank
|
||||
|
||||
return priority
|
||||
|
||||
|
||||
def _rank_for_indexer_id(indexer_id: object, priority: dict[int, int]) -> int:
|
||||
"""Preference rank for an indexer id. Lower wins, unknown ranks last."""
|
||||
coerced = _coerce_indexer_id(indexer_id)
|
||||
if coerced is None:
|
||||
return _UNRANKED_INDEXER_RANK
|
||||
return priority.get(coerced, _UNRANKED_INDEXER_RANK)
|
||||
|
||||
|
||||
def _indexer_rank(result: dict, priority: dict[int, int]) -> int:
|
||||
"""Preference rank of the indexer that surfaced a raw result."""
|
||||
return _rank_for_indexer_id(result.get("indexerId"), priority)
|
||||
|
||||
|
||||
def _release_indexer_rank(release: Release, priority: dict[int, int]) -> int:
|
||||
"""Preference rank of the indexer that surfaced a converted release."""
|
||||
return _rank_for_indexer_id(release.extra.get("indexer_id"), priority)
|
||||
|
||||
|
||||
def _collapse_duplicate_indexer_results(
|
||||
results: list[dict], priority: dict[int, int]
|
||||
) -> list[dict]:
|
||||
"""Reduce a release to a single row, keeping the preferred indexer entry.
|
||||
|
||||
Opt-in behaviour for users who want one row per torrent. Ties keep the
|
||||
result that was queried first, and the winner holds the loser's position so
|
||||
the overall result order stays stable.
|
||||
"""
|
||||
position_by_identity: dict[str, int] = {}
|
||||
kept: list[dict] = []
|
||||
|
||||
for result in results:
|
||||
identity = _release_identity(result)
|
||||
if identity is None:
|
||||
kept.append(result)
|
||||
continue
|
||||
|
||||
existing_position = position_by_identity.get(identity)
|
||||
if existing_position is None:
|
||||
position_by_identity[identity] = len(kept)
|
||||
kept.append(result)
|
||||
continue
|
||||
|
||||
if _indexer_rank(result, priority) < _indexer_rank(kept[existing_position], priority):
|
||||
kept[existing_position] = result
|
||||
|
||||
return kept
|
||||
|
||||
|
||||
def _parse_size(size_bytes: int | None) -> str | None:
|
||||
"""Convert bytes to human-readable size string."""
|
||||
if size_bytes is None or size_bytes <= 0:
|
||||
@@ -97,55 +223,11 @@ EBOOK_FORMATS = [
|
||||
]
|
||||
|
||||
# Common audiobook formats
|
||||
AUDIOBOOK_FORMATS = ["m4b", "mp3", "m4a", "flac", "ogg", "wma", "aac", "wav", "opus"]
|
||||
AUDIOBOOK_FORMATS = list(CORE_AUDIOBOOK_FORMATS)
|
||||
|
||||
# Combined list for format detection (audiobook formats first for priority)
|
||||
ALL_BOOK_FORMATS = AUDIOBOOK_FORMATS + EBOOK_FORMATS
|
||||
|
||||
# Map 3-char MAM language codes to 2-char ISO codes used by frontend color maps
|
||||
MAM_LANGUAGE_MAP = {
|
||||
"eng": "en",
|
||||
"ita": "it",
|
||||
"spa": "es",
|
||||
"fra": "fr",
|
||||
"fre": "fr",
|
||||
"ger": "de",
|
||||
"deu": "de",
|
||||
"por": "pt",
|
||||
"rus": "ru",
|
||||
"jpn": "ja",
|
||||
"jap": "ja",
|
||||
"chi": "zh",
|
||||
"zho": "zh",
|
||||
"dut": "nl",
|
||||
"nld": "nl",
|
||||
"swe": "sv",
|
||||
"nor": "no",
|
||||
"dan": "da",
|
||||
"fin": "fi",
|
||||
"pol": "pl",
|
||||
"cze": "cs",
|
||||
"ces": "cs",
|
||||
"hun": "hu",
|
||||
"kor": "ko",
|
||||
"ara": "ar",
|
||||
"heb": "he",
|
||||
"tur": "tr",
|
||||
"gre": "el",
|
||||
"ell": "el",
|
||||
"hin": "hi",
|
||||
"tha": "th",
|
||||
"vie": "vi",
|
||||
"ind": "id",
|
||||
"ukr": "uk",
|
||||
"rom": "ro",
|
||||
"ron": "ro",
|
||||
"bul": "bg",
|
||||
"cat": "ca",
|
||||
"hrv": "hr",
|
||||
"slv": "sl",
|
||||
"srp": "sr",
|
||||
}
|
||||
|
||||
# Backend safeguard: cap total Prowlarr search time per request.
|
||||
PROWLARR_SEARCH_TIMEOUT_SECONDS = 120.0
|
||||
@@ -193,8 +275,9 @@ def _extract_mam_language(raw_title: str) -> str | None:
|
||||
|
||||
for token in tokens:
|
||||
lang_code = token.lower()
|
||||
if lang_code in MAM_LANGUAGE_MAP:
|
||||
return MAM_LANGUAGE_MAP[lang_code]
|
||||
resolved = normalize_language(lang_code)
|
||||
if resolved is not None:
|
||||
return resolved
|
||||
|
||||
return None
|
||||
|
||||
@@ -379,8 +462,7 @@ def _prowlarr_result_to_release(
|
||||
formats_display = _formats_display(formats)
|
||||
language_detected = _extract_mam_language(str(raw_title or ""))
|
||||
|
||||
# Build the source_id from GUID or generate from indexer + title
|
||||
source_id = result.get("guid") or f"{indexer}:{hash(raw_title)}"
|
||||
source_id = build_source_id(result)
|
||||
|
||||
# Cache the raw Prowlarr result so handler can look it up by source_id
|
||||
cache_release(source_id, result)
|
||||
@@ -443,6 +525,36 @@ def _prowlarr_result_to_release(
|
||||
)
|
||||
|
||||
|
||||
# Last successfully fetched per-indexer share limits. Used as a fallback when
|
||||
# a transient Prowlarr API failure prevents fetching fresh settings during a
|
||||
# search, so results are never silently cached without seed limits (#795).
|
||||
_seed_settings_lock = Lock()
|
||||
_last_known_seed_settings: dict[int, IndexerSeedSettings] = {}
|
||||
|
||||
|
||||
def _fetch_indexer_seed_settings(
|
||||
client: ProwlarrClient,
|
||||
indexer_ids: list[int] | None,
|
||||
) -> dict[int, IndexerSeedSettings]:
|
||||
"""Fetch per-indexer share limits, falling back to last-known-good on failure."""
|
||||
try:
|
||||
fetched = client.get_indexer_seed_settings(restrict_to=indexer_ids)
|
||||
except _PROWLARR_SEED_SETTINGS_ERRORS:
|
||||
with _seed_settings_lock:
|
||||
fallback = dict(_last_known_seed_settings)
|
||||
logger.warning(
|
||||
"Failed to fetch Prowlarr indexer seed settings; "
|
||||
"falling back to last known settings for %s indexer(s)",
|
||||
len(fallback),
|
||||
exc_info=True,
|
||||
)
|
||||
return fallback
|
||||
|
||||
with _seed_settings_lock:
|
||||
_last_known_seed_settings.update(fetched)
|
||||
return fetched
|
||||
|
||||
|
||||
def _apply_indexer_seed_settings(
|
||||
result: dict,
|
||||
indexer_seed_settings: dict[int, IndexerSeedSettings],
|
||||
@@ -574,6 +686,11 @@ class ProwlarrSource(ReleaseSource):
|
||||
],
|
||||
extra_sort_options=[
|
||||
SortOption(label="Peers", sort_key="seeders"),
|
||||
SortOption(
|
||||
label="Indexer priority",
|
||||
sort_key="extra.indexer_priority",
|
||||
default_direction="asc",
|
||||
),
|
||||
],
|
||||
grid_template="minmax(0,2fr) minmax(140px,1fr) 50px 50px 90px 80px",
|
||||
leading_cell=LeadingCellConfig(
|
||||
@@ -779,11 +896,15 @@ class ProwlarrSource(ReleaseSource):
|
||||
try:
|
||||
auto_expand_enabled = config.get("PROWLARR_AUTO_EXPAND", False)
|
||||
deadline = time.monotonic() + PROWLARR_SEARCH_TIMEOUT_SECONDS
|
||||
enabled_indexers = client.get_enabled_indexers_detailed()
|
||||
indexer_priority = _build_indexer_priority(enabled_indexers)
|
||||
# Some indexers benefit from title+author queries and extra format detection.
|
||||
enriched_indexer_ids = client.get_enriched_indexer_ids(restrict_to=indexer_ids)
|
||||
enriched_indexer_ids = client.get_enriched_indexer_ids(
|
||||
restrict_to=indexer_ids, indexers=enabled_indexers
|
||||
)
|
||||
enriched_indexer_ids_set = set(enriched_indexer_ids)
|
||||
indexer_seed_settings = (
|
||||
client.get_indexer_seed_settings(restrict_to=indexer_ids)
|
||||
_fetch_indexer_seed_settings(client, indexer_ids)
|
||||
if config.get("PROWLARR_USE_SEED_PREFERENCES", False)
|
||||
else {}
|
||||
)
|
||||
@@ -821,7 +942,7 @@ class ProwlarrSource(ReleaseSource):
|
||||
|
||||
return results
|
||||
|
||||
seen_keys: set[str] = set()
|
||||
seen_keys: set[tuple[int | None, str]] = set()
|
||||
all_results: list[dict] = []
|
||||
|
||||
for idx, variant in enumerate(variants, start=1):
|
||||
@@ -849,18 +970,22 @@ class ProwlarrSource(ReleaseSource):
|
||||
self.last_search_type = "expanded"
|
||||
|
||||
for r in raw_results:
|
||||
key = (
|
||||
r.get("guid")
|
||||
or r.get("downloadUrl")
|
||||
or r.get("magnetUrl")
|
||||
or r.get("infoUrl")
|
||||
or f"{r.get('indexerId')}:{r.get('title')}"
|
||||
)
|
||||
if key in seen_keys:
|
||||
continue
|
||||
seen_keys.add(key)
|
||||
key = _result_dedup_key(r)
|
||||
if key is not None:
|
||||
if key in seen_keys:
|
||||
continue
|
||||
seen_keys.add(key)
|
||||
all_results.append(r)
|
||||
|
||||
if config.get("PROWLARR_COLLAPSE_DUPLICATES", True):
|
||||
before_collapse = len(all_results)
|
||||
all_results = _collapse_duplicate_indexer_results(all_results, indexer_priority)
|
||||
if len(all_results) != before_collapse:
|
||||
logger.debug(
|
||||
"Prowlarr: collapsed %s duplicate result(s) across indexer entries",
|
||||
before_collapse - len(all_results),
|
||||
)
|
||||
|
||||
results: list[Release] = []
|
||||
enriched_source_ids: set[str] = set()
|
||||
|
||||
@@ -879,13 +1004,19 @@ class ProwlarrSource(ReleaseSource):
|
||||
content_type,
|
||||
enable_format_detection=is_enriched,
|
||||
)
|
||||
if idx_id_int is not None and idx_id_int in indexer_priority:
|
||||
release.extra["indexer_priority"] = indexer_priority[idx_id_int]
|
||||
results.append(release)
|
||||
|
||||
if is_enriched:
|
||||
enriched_source_ids.add(release.source_id)
|
||||
|
||||
# Sort results: enriched indexers first, then others
|
||||
results.sort(key=lambda r: 0 if r.source_id in enriched_source_ids else 1)
|
||||
results.sort(
|
||||
key=lambda r: (
|
||||
_release_indexer_rank(r, indexer_priority),
|
||||
0 if r.source_id in enriched_source_ids else 1,
|
||||
)
|
||||
)
|
||||
|
||||
if results:
|
||||
torrent_count = sum(1 for r in results if r.protocol == ReleaseProtocol.TORRENT)
|
||||
|
||||
@@ -32,6 +32,28 @@ def coerce_int_like(value: object) -> int | None:
|
||||
return int(normalized)
|
||||
|
||||
|
||||
def build_source_id(result: dict) -> str:
|
||||
"""Build the Release.source_id for a raw Prowlarr result.
|
||||
|
||||
Qualified by the indexer id because one tracker is often configured in
|
||||
Prowlarr as several indexer entries that differ only by a server-side search
|
||||
filter, and those entries return the same guid for the same torrent. Without
|
||||
the qualifier the entries collide in the release cache and a grab routes
|
||||
through whichever entry happened to cache last.
|
||||
"""
|
||||
guid = result.get("guid")
|
||||
if guid:
|
||||
base = str(guid)
|
||||
else:
|
||||
indexer = result.get("indexer", "Unknown")
|
||||
base = f"{indexer}:{hash(result.get('title', 'Unknown'))}"
|
||||
|
||||
indexer_id = coerce_int_like(result.get("indexerId"))
|
||||
if indexer_id is None:
|
||||
return base
|
||||
return f"{indexer_id}:{base}"
|
||||
|
||||
|
||||
def coerce_float_like(value: object) -> float | None:
|
||||
"""Return a float for float-like config/API values, else None."""
|
||||
if isinstance(value, bool):
|
||||
|
||||
Generated
+1462
-669
File diff suppressed because it is too large
Load Diff
+15
-15
@@ -17,24 +17,24 @@
|
||||
"test:unit": "vitest run"
|
||||
},
|
||||
"dependencies": {
|
||||
"@tailwindcss/vite": "^4.3.0",
|
||||
"react": "^19.2.7",
|
||||
"react-dom": "^19.2.7",
|
||||
"react-router-dom": "^7.17.0",
|
||||
"@tailwindcss/vite": "^4.3.3",
|
||||
"react": "^19.2.8",
|
||||
"react-dom": "^19.2.8",
|
||||
"react-router-dom": "^7.18.2",
|
||||
"socket.io-client": "^4.7.5"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@types/node": "^25.9.3",
|
||||
"@types/react": "^19.2.17",
|
||||
"@types/react-dom": "^19.2.3",
|
||||
"@vitejs/plugin-react": "^6.0.2",
|
||||
"knip": "^6.16.1",
|
||||
"oxfmt": "^0.54.0",
|
||||
"oxlint": "^1.69.0",
|
||||
"oxlint-tsgolint": "^0.23.0",
|
||||
"@types/node": "^26.2.0",
|
||||
"@types/react": "^19.2.18",
|
||||
"@types/react-dom": "^19.2.4",
|
||||
"@vitejs/plugin-react": "^6.0.5",
|
||||
"knip": "^6.32.1",
|
||||
"oxfmt": "^0.63.0",
|
||||
"oxlint": "^1.78.0",
|
||||
"oxlint-tsgolint": "^7.0.2001",
|
||||
"tailwindcss": "^4.2.2",
|
||||
"typescript": "^6.0.3",
|
||||
"vite": "^8.0.16",
|
||||
"vitest": "^4.1.8"
|
||||
"typescript": "^7.0.2",
|
||||
"vite": "^8.2.1",
|
||||
"vitest": "^4.1.10"
|
||||
}
|
||||
}
|
||||
|
||||
@@ -1098,6 +1098,9 @@ function App() {
|
||||
series_name: book.series_name,
|
||||
series_position: book.series_position,
|
||||
subtitle: book.subtitle,
|
||||
// From the release, never the book: book.language is the provider's
|
||||
// canonical edition, which would mislabel a translated release.
|
||||
language: release.language ?? undefined,
|
||||
};
|
||||
},
|
||||
[],
|
||||
|
||||
@@ -382,7 +382,11 @@ export const ReleaseCell = ({
|
||||
className={`flex items-center ${alignClass} gap-1.5 truncate text-xs text-gray-600 dark:text-gray-300`}
|
||||
>
|
||||
<span className={`h-2 w-2 shrink-0 rounded-full ${dotColor}`} title={protocolLabel} />
|
||||
<span className="truncate">{displayValue}</span>
|
||||
{/* Titled because one tracker can appear as several indexer entries whose
|
||||
names share a prefix, and truncation would make the rows look identical */}
|
||||
<span className="truncate" title={displayValue}>
|
||||
{displayValue}
|
||||
</span>
|
||||
{peers && <span className="shrink-0 text-gray-400 dark:text-gray-500">{peers}</span>}
|
||||
</div>
|
||||
);
|
||||
|
||||
@@ -956,7 +956,7 @@ const ReleaseModalSession = ({
|
||||
const fromExtra = (columnConfig.extra_sort_options || []).map((opt) => ({
|
||||
label: opt.label,
|
||||
sortKey: opt.sort_key,
|
||||
defaultDirection: 'desc' as const, // Extra sort options are typically numeric (e.g., peers)
|
||||
defaultDirection: opt.default_direction ?? ('desc' as const),
|
||||
}));
|
||||
return [...fromColumns, ...fromExtra];
|
||||
}, [sortableColumns, columnConfig.extra_sort_options]);
|
||||
|
||||
@@ -67,6 +67,7 @@ export const CardView = ({
|
||||
};
|
||||
|
||||
return (
|
||||
// eslint-disable-next-line jsx-a11y/no-noninteractive-element-interactions -- mouse handlers drive a decorative hover shadow only; no interactive behavior requiring keyboard support
|
||||
<article
|
||||
className="book-card space-between animate-pop-up relative flex h-full w-full flex-col transition-shadow duration-300 max-sm:h-[180px] max-sm:flex-row sm:max-w-[292px] sm:flex-col"
|
||||
style={{
|
||||
|
||||
@@ -70,6 +70,7 @@ export const CompactView = ({
|
||||
};
|
||||
|
||||
return (
|
||||
// eslint-disable-next-line jsx-a11y/no-noninteractive-element-interactions -- mouse handlers drive a decorative hover shadow only; no interactive behavior requiring keyboard support
|
||||
<article
|
||||
className="book-card animate-pop-up relative flex! h-[180px]! w-full flex-row! transition-shadow duration-300"
|
||||
style={{
|
||||
|
||||
@@ -21,7 +21,6 @@ import {
|
||||
normalizeUserOverrideSections,
|
||||
UserOverridesSections,
|
||||
} from './users';
|
||||
import type { PerUserSettings } from './users/types';
|
||||
import { UserAccountCardContent, UserEditActions, UserIdentityHeader } from './users/UserCard';
|
||||
import { useUserOverridesState } from './users/useUserOverridesState';
|
||||
|
||||
@@ -153,7 +152,7 @@ const SelfSettingsModalSession = ({
|
||||
normalizeUserOverrideSections(context.visibleUserSettingsSections, 'self'),
|
||||
);
|
||||
applyUserOverridesContext({
|
||||
settings: (context.user.settings || {}) as PerUserSettings,
|
||||
settings: context.user.settings || {},
|
||||
userOverridableKeys: context.userOverridableKeys || [],
|
||||
});
|
||||
setEditPassword('');
|
||||
|
||||
@@ -188,6 +188,7 @@ export function Tooltip({
|
||||
isVisible &&
|
||||
coords &&
|
||||
createPortal(
|
||||
// eslint-disable-next-line jsx-a11y/no-noninteractive-element-interactions -- interactive tooltip stays open while hovered; keyboard users are served by focus handlers on the trigger element
|
||||
<div
|
||||
ref={tooltipRef}
|
||||
role="tooltip"
|
||||
|
||||
@@ -146,7 +146,7 @@ export const useUsersFetch = ({ onShowToast }: UseUsersFetchParams) => {
|
||||
if (fullUser.settings) {
|
||||
userSettings = {
|
||||
...fullUser.settings,
|
||||
} as PerUserSettings;
|
||||
};
|
||||
}
|
||||
const userOverridableSettings = new Set<string>();
|
||||
|
||||
@@ -162,7 +162,7 @@ export const useUsersFetch = ({ onShowToast }: UseUsersFetchParams) => {
|
||||
userSettings = {
|
||||
...userSettings,
|
||||
...deliveryResult.value.userOverrides,
|
||||
} as PerUserSettings;
|
||||
};
|
||||
}
|
||||
deliveryResult.value.keys.forEach((key) => userOverridableSettings.add(key));
|
||||
}
|
||||
@@ -173,7 +173,7 @@ export const useUsersFetch = ({ onShowToast }: UseUsersFetchParams) => {
|
||||
userSettings = {
|
||||
...userSettings,
|
||||
...searchResult.value.userOverrides,
|
||||
} as PerUserSettings;
|
||||
};
|
||||
}
|
||||
searchResult.value.keys.forEach((key) => userOverridableSettings.add(key));
|
||||
}
|
||||
@@ -184,7 +184,7 @@ export const useUsersFetch = ({ onShowToast }: UseUsersFetchParams) => {
|
||||
userSettings = {
|
||||
...userSettings,
|
||||
...notificationResult.value.userOverrides,
|
||||
} as PerUserSettings;
|
||||
};
|
||||
}
|
||||
notificationResult.value.keys.forEach((key) => userOverridableSettings.add(key));
|
||||
}
|
||||
|
||||
@@ -144,6 +144,11 @@ const mapApiErrorToActionResult = (error: unknown): ActionResult | null => {
|
||||
// Default request timeout in milliseconds (30 seconds)
|
||||
const DEFAULT_TIMEOUT_MS = 30000;
|
||||
|
||||
// Release searches can be long-running: a source behind Cloudflare/DDoS-Guard has
|
||||
// to spin up the bypasser and solve the challenge before any results come back,
|
||||
// which routinely takes well over the default timeout.
|
||||
const SEARCH_TIMEOUT_MS = 180000;
|
||||
|
||||
// Utility function for JSON fetch with credentials and timeout
|
||||
async function fetchJSON<T>(
|
||||
url: string,
|
||||
@@ -235,6 +240,8 @@ export const searchBooks = async (query: string): Promise<Book[]> => {
|
||||
if (!query) return [];
|
||||
const response = await fetchJSON<ReleasesResponse>(
|
||||
`${API_BASE}/releases?source=direct_download&${query}`,
|
||||
{},
|
||||
SEARCH_TIMEOUT_MS,
|
||||
);
|
||||
return response.releases.map(transformReleaseToDirectBook);
|
||||
};
|
||||
@@ -500,6 +507,7 @@ export type DownloadReleasePayload = {
|
||||
series_name?: string;
|
||||
series_position?: number;
|
||||
subtitle?: string;
|
||||
language?: string; // Release language code, for the {Language} naming variable
|
||||
search_author?: string;
|
||||
search_mode?: 'direct' | 'universal';
|
||||
};
|
||||
|
||||
@@ -48,4 +48,47 @@ describe('namingTemplatePreview', () => {
|
||||
expect(preview.unknownTokens).toEqual(['NotAThing']);
|
||||
expect(preview.value).toBe('Arthur Conan Doyle');
|
||||
});
|
||||
|
||||
it('offers Language as a core variable for both content types', () => {
|
||||
const language = NAMING_TEMPLATE_TOKENS.find((token) => token.token === 'Language');
|
||||
|
||||
expect(language?.group).toBe('Core');
|
||||
expect(language?.audiobookOnly).toBeFalsy();
|
||||
});
|
||||
|
||||
it('separates translated editions into their own folder', () => {
|
||||
const template = '{Author}/{Title}{ (Language)}';
|
||||
|
||||
const swedish = renderNamingTemplate(
|
||||
template,
|
||||
{
|
||||
...SAMPLE_NAMING_METADATA,
|
||||
Author: 'Andy Weir',
|
||||
Title: 'Project Hail Mary',
|
||||
Language: 'sv',
|
||||
},
|
||||
{ allowPathSeparators: true },
|
||||
);
|
||||
const english = renderNamingTemplate(
|
||||
template,
|
||||
{ ...SAMPLE_NAMING_METADATA, Author: 'Andy Weir', Title: 'Project Hail Mary', Language: '' },
|
||||
{ allowPathSeparators: true },
|
||||
);
|
||||
|
||||
expect(swedish.value).toBe('Andy Weir/Project Hail Mary (sv)');
|
||||
expect(english.value).toBe('Andy Weir/Project Hail Mary');
|
||||
expect(swedish.value).not.toBe(english.value);
|
||||
});
|
||||
|
||||
it('keeps the picker and the known-token list in lockstep', () => {
|
||||
// KNOWN_TOKENS is a hand-maintained duplicate of the Python list. A token
|
||||
// added to the picker but not to it would render as an unknown variable.
|
||||
for (const token of NAMING_TEMPLATE_TOKENS) {
|
||||
const preview = renderNamingTemplate(`{${token.token}}`, SAMPLE_NAMING_METADATA, {
|
||||
allowPathSeparators: true,
|
||||
});
|
||||
|
||||
expect(preview.unknownTokens, `${token.token} is missing from KNOWN_TOKENS`).toEqual([]);
|
||||
}
|
||||
});
|
||||
});
|
||||
|
||||
@@ -138,4 +138,29 @@ describe('requestPayload utilities', () => {
|
||||
);
|
||||
expect(getRequestSuccessMessage(payloadUntitled)).toBe('Request submitted: Untitled');
|
||||
});
|
||||
|
||||
it('takes the language from the release, not the book', () => {
|
||||
// book.language is the metadata provider's canonical edition. Using it would
|
||||
// label a Swedish release "en" and put both editions back in one folder.
|
||||
const data = buildReleaseDataFromMetadataRelease(
|
||||
{ ...baseBook, language: 'en' },
|
||||
{ ...baseRelease, language: 'sv' },
|
||||
'ebook',
|
||||
);
|
||||
|
||||
expect(data.language).toBe('sv');
|
||||
});
|
||||
|
||||
it('leaves language undefined when the release has none', () => {
|
||||
const data = buildReleaseDataFromMetadataRelease(baseBook, baseRelease, 'ebook');
|
||||
|
||||
expect(data.language).toBeUndefined();
|
||||
});
|
||||
|
||||
it('uses the book language when browsing a source directly', () => {
|
||||
// In direct mode the book record IS the release record.
|
||||
const data = buildReleaseDataFromDirectBook({ ...baseBook, language: 'de' });
|
||||
|
||||
expect(data.language).toBe('de');
|
||||
});
|
||||
});
|
||||
|
||||
@@ -414,6 +414,7 @@ export interface LeadingCellConfig {
|
||||
export interface ExtraSortOption {
|
||||
label: string; // Display label in the sort dropdown
|
||||
sort_key: string; // Field to sort by on the Release object
|
||||
default_direction?: 'asc' | 'desc'; // Which way "best first" runs (defaults to desc)
|
||||
}
|
||||
|
||||
export interface SourceActionButton {
|
||||
|
||||
@@ -48,6 +48,13 @@ export const NAMING_TEMPLATE_TOKENS: NamingTemplateToken[] = [
|
||||
value: '1902',
|
||||
group: 'Core',
|
||||
},
|
||||
{
|
||||
token: 'Language',
|
||||
label: 'Language',
|
||||
description: 'Release language code, so translations do not share a folder',
|
||||
value: 'en',
|
||||
group: 'Core',
|
||||
},
|
||||
{
|
||||
token: 'User',
|
||||
label: 'User',
|
||||
@@ -98,6 +105,7 @@ const KNOWN_TOKENS = [
|
||||
'primarytitle',
|
||||
'originalname',
|
||||
'partnumber',
|
||||
'language',
|
||||
'subtitle',
|
||||
'author',
|
||||
'series',
|
||||
|
||||
@@ -90,6 +90,7 @@ export const buildReleaseDataFromMetadataRelease = (
|
||||
series_position: book.series_position,
|
||||
series_count: book.series_count,
|
||||
subtitle: book.subtitle,
|
||||
language: release.language,
|
||||
...(isSourceBackedReleaseContext ? { search_mode: 'direct' as const } : {}),
|
||||
};
|
||||
};
|
||||
@@ -106,6 +107,8 @@ export const buildReleaseDataFromDirectBook = (book: Book) => {
|
||||
size: book.size,
|
||||
preview: book.preview,
|
||||
content_type: 'ebook' as const,
|
||||
// Browsing a source directly means the book record IS the release record.
|
||||
language: book.language,
|
||||
search_mode: 'direct' as const,
|
||||
};
|
||||
};
|
||||
|
||||
@@ -169,6 +169,7 @@ uv run pytest tests/ --cov=shelfmark -m "not integration"
|
||||
```python
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
|
||||
class TestMyFeature:
|
||||
def test_something(self, monkeypatch):
|
||||
# Mock config values
|
||||
@@ -188,6 +189,7 @@ class TestMyFeature:
|
||||
import pytest
|
||||
from .conftest import APIClient, DownloadTracker
|
||||
|
||||
|
||||
@pytest.mark.e2e
|
||||
class TestMyEndpoint:
|
||||
def test_endpoint_works(self, protected_api_client: APIClient):
|
||||
|
||||
@@ -317,6 +317,44 @@ class TestSearchAudiobookbay:
|
||||
assert "s=%22test+query%22" in requested_url
|
||||
assert "cat=undefined%2Cundefined" in requested_url
|
||||
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.downloader.html_get_page")
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.config.get")
|
||||
def test_search_audiobookbay_normalizes_curly_apostrophe(self, mock_config_get, mock_html_get):
|
||||
"""Test curly apostrophes are searched as the ASCII form ABB stores."""
|
||||
mock_config_get.return_value = 0.0
|
||||
mock_html_get.return_value = (SAMPLE_SEARCH_HTML, "https://audiobookbay.lu/?s=x")
|
||||
|
||||
scraper.search_audiobookbay(
|
||||
"the stranger’s wife",
|
||||
max_pages=1,
|
||||
hostname="audiobookbay.lu",
|
||||
)
|
||||
|
||||
requested_url = mock_html_get.call_args.args[0]
|
||||
assert "s=the+stranger%27s+wife" in requested_url
|
||||
assert "%E2%80%99" not in requested_url
|
||||
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.downloader.html_get_page")
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.config.get")
|
||||
def test_search_audiobookbay_percent_encodes_reserved_characters(
|
||||
self, mock_config_get, mock_html_get
|
||||
):
|
||||
"""Test reserved characters cannot break out of the search parameter."""
|
||||
mock_config_get.return_value = 0.0
|
||||
mock_html_get.return_value = (SAMPLE_SEARCH_HTML, "https://audiobookbay.lu/?s=x")
|
||||
|
||||
scraper.search_audiobookbay(
|
||||
"sense & sensibility 100% c++",
|
||||
max_pages=1,
|
||||
hostname="audiobookbay.lu",
|
||||
)
|
||||
|
||||
requested_url = mock_html_get.call_args.args[0]
|
||||
assert "s=sense+%26+sensibility+100%25+c%2B%2B" in requested_url
|
||||
# The only surviving '&' introduces the legacy category parameter.
|
||||
assert requested_url.count("&") == 1
|
||||
assert requested_url.endswith("&cat=undefined%2Cundefined")
|
||||
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.downloader.html_get_page")
|
||||
@patch("shelfmark.release_sources.audiobookbay.scraper.config.get")
|
||||
def test_search_audiobookbay_always_uses_legacy_category_query(
|
||||
|
||||
@@ -0,0 +1,103 @@
|
||||
"""Cluster 7 (audiobook/ABB) parse-contract guards.
|
||||
|
||||
ABB forces ``https://`` for search and detail fetches, so it can't be exercised
|
||||
hermetically in the HTTP e2e docker platform. Its recurring bugs are instead in
|
||||
*parsing*: magnet/info-hash extraction ("Fix ABB magnet parsing", and the
|
||||
qbittorrent hash-length issue #386) and DOM/layout drift. These contract tests
|
||||
feed golden HTML through the real scraper — the same fail-on-drift philosophy as
|
||||
the AA layout-drift guard — and run in normal CI.
|
||||
|
||||
They deliberately cover cases the existing ``test_scraper.py`` does not: info-hash
|
||||
*normalization* (whitespace/case), the in-page magnet *fallback*, and a layout
|
||||
drift that must degrade to an empty result rather than crash.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import re
|
||||
from unittest.mock import patch
|
||||
|
||||
from shelfmark.release_sources.audiobookbay import scraper
|
||||
|
||||
# Detail page where the Info Hash is lowercase and split by whitespace/newlines —
|
||||
# the exact shape that produced malformed magnets / wrong hash lengths (#386).
|
||||
DETAIL_HTML_MESSY_HASH = """
|
||||
<html><body><table>
|
||||
<tr><td>Info Hash</td><td>abc123def456789012345678
|
||||
901234567890abcd</td></tr>
|
||||
<tr><td>Tracker 1</td><td>udp://tracker.openbittorrent.com:80</td></tr>
|
||||
</table></body></html>
|
||||
"""
|
||||
|
||||
# Info Hash cell is junk, but a full magnet link is posted elsewhere on the page.
|
||||
DETAIL_HTML_MAGNET_FALLBACK = """
|
||||
<html><body>
|
||||
<table><tr><td>Info Hash</td><td>n/a</td></tr></table>
|
||||
<p>Mirror: magnet:?xt=urn:btih:1111111111111111111111111111111111111111&dn=x</p>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
# DOM drift: results are present but the .post / .postTitle structure changed.
|
||||
SEARCH_HTML_LAYOUT_DRIFT = """
|
||||
<html><body>
|
||||
<article class="result-card">
|
||||
<header><a href="/abss/drifted/">Drifted Audiobook - Author</a></header>
|
||||
<span class="lang">English</span>
|
||||
</article>
|
||||
</body></html>
|
||||
"""
|
||||
|
||||
|
||||
def _patch_detail(html: str):
|
||||
return patch(
|
||||
"shelfmark.release_sources.audiobookbay.scraper.downloader.html_get_page",
|
||||
return_value=html,
|
||||
)
|
||||
|
||||
|
||||
def test_info_hash_is_normalized_to_canonical_btih() -> None:
|
||||
"""Whitespace/newlines are stripped and the hash upper-cased to a valid
|
||||
40-char btih (regression for #386 / 'Fix ABB magnet parsing')."""
|
||||
with _patch_detail(DETAIL_HTML_MESSY_HASH):
|
||||
magnet = scraper.extract_magnet_link("https://audiobookbay.lu/abss/x/", "audiobookbay.lu")
|
||||
assert magnet is not None, "messy-but-valid info hash should still yield a magnet"
|
||||
btih = re.search(r"xt=urn:btih:([0-9A-Fa-f]+)", magnet)
|
||||
assert btih is not None, magnet
|
||||
assert btih.group(1) == "ABC123DEF456789012345678901234567890ABCD"
|
||||
assert len(btih.group(1)) == 40
|
||||
assert "tr=" in magnet # tracker carried through
|
||||
|
||||
|
||||
def test_magnet_fallback_when_info_hash_cell_is_junk() -> None:
|
||||
"""When the Info Hash cell is invalid, the scraper recovers the hash from an
|
||||
in-page magnet link rather than failing."""
|
||||
with _patch_detail(DETAIL_HTML_MAGNET_FALLBACK):
|
||||
magnet = scraper.extract_magnet_link("https://audiobookbay.lu/abss/y/", "audiobookbay.lu")
|
||||
assert magnet is not None
|
||||
assert "btih:1111111111111111111111111111111111111111" in magnet
|
||||
|
||||
|
||||
def test_missing_info_hash_returns_none_not_crash() -> None:
|
||||
"""No hash anywhere -> None (clean failure), never an exception."""
|
||||
with _patch_detail("<html><body><p>nothing here</p></body></html>"):
|
||||
assert (
|
||||
scraper.extract_magnet_link("https://audiobookbay.lu/abss/z/", "audiobookbay.lu")
|
||||
is None
|
||||
)
|
||||
|
||||
|
||||
def test_search_layout_drift_degrades_to_empty() -> None:
|
||||
"""A changed results DOM yields zero parsed results without raising — the
|
||||
ABB analogue of the AA layout-drift guard."""
|
||||
with (
|
||||
patch(
|
||||
"shelfmark.release_sources.audiobookbay.scraper.downloader.html_get_page",
|
||||
return_value=(SEARCH_HTML_LAYOUT_DRIFT, "https://audiobookbay.lu/?s=test"),
|
||||
),
|
||||
patch(
|
||||
"shelfmark.release_sources.audiobookbay.scraper.config.get",
|
||||
return_value=0.0,
|
||||
),
|
||||
):
|
||||
results = scraper.search_audiobookbay("test", max_pages=1, hostname="audiobookbay.lu")
|
||||
assert results == [], f"drifted DOM should parse to no results, got {results!r}"
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user