Compare commits

...
31 Commits
Author SHA1 Message Date
ThePhaseless 7e9c2ba97d update readme 2025-05-18 23:22:19 +02:00
ThePhaseless 9fc9af3ba9 add unescaped chars test link 2025-05-18 01:14:32 +02:00
ThePhaseless 55526308f6 bump debian version to bookworm 2025-05-18 01:03:12 +02:00
ThePhaseless cdb3223a87 fix typo 2025-05-17 22:45:55 +00:00
ThePhaseless 329235ba5e add devcontainer stage 2025-05-17 22:45:47 +00:00
ThePhaseless 5031d1e554 set default values 2025-05-17 22:45:21 +00:00
ThePhaseless 090b5487e4 devcontainer tweaks 2025-05-17 20:50:13 +00:00
ThePhaseless c608bbc46e set shm size to prevent memory overload 2025-05-17 20:49:18 +00:00
ThePhaseless 46eff073b7 use base dockerfile for devcontainer 2025-05-17 18:45:59 +02:00
renovate[bot] a347b7046b Update dependency ruff to v0.11.10 (#174)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-15 23:03:52 +00:00
renovate[bot] 4658d04d2e Update dependency seleniumbase to v4.38.2 (#173)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-13 11:52:53 +00:00
renovate[bot] b6aa1a8c58 Update dependency seleniumbase to v4.38.0 (#169)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-10 02:02:57 +00:00
renovate[bot] 5bff9e1bc1 Update dependency ruff to v0.11.9 (#171)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-09 21:55:22 +00:00
renovate[bot] dbd16882de Update dependency ruff to v0.11.8 (#168)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-01 17:46:00 +00:00
renovate[bot] adc98e8cea Update dependency seleniumbase to v4.37.12 (#167)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-05-01 11:23:17 +00:00
renovate[bot] 8e7d007c6f Update dependency pydantic to v2.11.4 (#166)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-30 06:01:21 +00:00
renovate[bot] 51c1577d7c Update dependency seleniumbase to v4.37.10 (#165)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-29 20:40:54 +00:00
ThePhaseless 98f9480157 fix invalid requests response 2025-04-29 10:57:21 +02:00
renovate[bot] 2be9fa55a9 Update dependency seleniumbase to v4.37.9 (#164)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-29 06:08:17 +00:00
renovate[bot] 6520444d4e Update dependency seleniumbase to v4.37.7 (#160)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-25 16:40:57 +00:00
renovate[bot] 693d67bcfd Update dependency ruff to v0.11.7 (#159)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-25 03:24:57 +00:00
renovate[bot] b217778a79 Update dependency seleniumbase to v4.37.6 (#158)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-23 21:57:08 +00:00
renovate[bot] 3b18dfe522 Update dependency seleniumbase to v4.37.5 (#157)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-23 02:47:45 +00:00
renovate[bot] ee5b7fe027 Update dependency seleniumbase to v4.37.4 (#156)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-20 22:44:02 +00:00
renovate[bot] d2678643c0 Update dependency seleniumbase to v4.37.3 (#155)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-19 21:16:24 +00:00
renovate[bot] 343fdca493 Update dependency uvicorn to v0.34.2 (#154)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-19 10:43:47 +00:00
renovate[bot] 5a8edf13ab Update dependency ruff to v0.11.6 (#153)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-17 19:01:37 +00:00
ThePhaseless 1fa6b66f3a fixes ctrl+c on docker run 2025-04-17 11:38:52 +00:00
ThePhaseless fe797ba2ac add userAgent and version to healthcheck 2025-04-17 11:27:17 +00:00
ThePhaseless 409c0f9d8c [skip ci] add proxybase collaboration info 2025-04-14 10:38:02 +00:00
renovate[bot] d22e780219 Update dependency uvicorn to v0.34.1 (#149)
Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
2025-04-13 18:03:26 +00:00
14 changed files with 514 additions and 698 deletions
-4
View File
@@ -1,4 +0,0 @@
FROM ghcr.io/astral-sh/uv:debian
ENV UV_LINK_MODE=copy
RUN apt update && apt upgrade -y && apt install -y chromium chromium-driver xvfb git
+5 -25
View File
@@ -3,36 +3,16 @@
{
// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
"build": {
"dockerfile": "Dockerfile"
"dockerfile": "../Dockerfile",
"target": "devcontainer"
},
"customizations": {
"vscode": {
"extensions": [
"charliermarsh.ruff",
"-ms-python.autopep8",
"-ms-python.vscode-pylance"
],
"extensions": ["charliermarsh.ruff", "ms-python.python"],
"settings": {
"python.venvPath": "./venv"
}
}
},
// Features to add to the dev container. More info: https://containers.dev/features.
// "features": {},
// Use 'forwardPorts' to make a list of ports inside the container available locally.
// Use 'postCreateCommand' to run commands after the container is created.
// "postCreateCommand": "pip3 install --user -r requirements.txt",
// Configure tool-specific properties.
// "customizations": {},
// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
// "remoteUser": "root"
"name": "Byparr Dev Container",
"runArgs": [
"-p",
"8181:8191"
],
"features": {
"ghcr.io/devcontainers-extra/features/act:1": {},
"ghcr.io/devcontainers/features/desktop-lite:1": {}
}
}
"postCreateCommand": "uv sync --group test && cd .venv/lib/*/site-packages/seleniumbase/drivers && rm -f uc_driver && ln -s /usr/bin/chromedriver uc_driver"
}
-164
View File
@@ -1,164 +0,0 @@
# Byte-compiled / optimized / DLL files
__pycache__/
*.py[cod]
*$py.class
# C extensions
*.so
# Distribution / packaging
.Python
build/
develop-eggs/
dist/
downloads/
eggs/
.eggs/
lib/
lib64/
parts/
sdist/
var/
wheels/
share/python-wheels/
*.egg-info/
.installed.cfg
*.egg
MANIFEST
# PyInstaller
# Usually these files are written by a python script from a template
# before PyInstaller builds the exe, so as to inject date/other infos into it.
*.manifest
*.spec
# Installer logs
pip-log.txt
pip-delete-this-directory.txt
# Unit test / coverage reports
htmlcov/
.tox/
.nox/
.coverage
.coverage.*
.cache
nosetests.xml
coverage.xml
*.cover
*.py,cover
.hypothesis/
.pytest_cache/
cover/
# Translations
*.mo
*.pot
# Django stuff:
*.log
local_settings.py
db.sqlite3
db.sqlite3-journal
# Flask stuff:
instance/
.webassets-cache
# Scrapy stuff:
.scrapy
# Sphinx documentation
docs/_build/
# PyBuilder
.pybuilder/
target/
# Jupyter Notebook
.ipynb_checkpoints
# IPython
profile_default/
ipython_config.py
# pyenv
# For a library or package, you might want to ignore these files since the code is
# intended to run in multiple environments; otherwise, check them in:
# .python-version
# pipenv
# According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
# However, in case of collaboration, if having platform-specific dependencies or dependencies
# having no cross-platform support, pipenv may install dependencies that don't work, or not
# install all needed dependencies.
#Pipfile.lock
# poetry
# Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
# This is especially recommended for binary packages to ensure reproducibility, and is more
# commonly ignored for libraries.
# https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
#poetry.lock
# pdm
# Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
#pdm.lock
# pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
# in version control.
# https://pdm.fming.dev/latest/usage/project/#working-with-version-control
.pdm.toml
.pdm-python
.pdm-build/
# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
__pypackages__/
# Celery stuff
celerybeat-schedule
celerybeat.pid
# SageMath parsed files
*.sage.py
# Environments
.env
.venv
env/
venv/
ENV/
env.bak/
venv.bak/
# Spyder project settings
.spyderproject
.spyproject
# Rope project settings
.ropeproject
# mkdocs documentation
/site
# mypy
.mypy_cache/
.dmypy.json
dmypy.json
# Pyre type checker
.pyre/
# pytype static type analyzer
.pytype/
# Cython debug symbols
cython_debug/
# PyCharm
# JetBrains specific template is maintained in a separate JetBrains.gitignore that can
# be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
# and can be added to the global gitignore or merged into this file. For a more nuclear
# option (not recommended) you can uncomment the following to ignore the entire idea folder.
#.idea/
.extentions/
+1
View File
@@ -0,0 +1 @@
.gitignore
+14 -18
View File
@@ -1,19 +1,15 @@
{
"configurations": [
{
"console": "integratedTerminal",
"env": {
"LOG_LEVEL": "DEBUG"
},
"justMyCode": false,
"name": "Python Debugger: Main",
"program": "main.py",
"request": "launch",
"type": "debugpy"
},
],
// Use IntelliSense to learn about possible attributes.
// Hover to view descriptions of existing attributes.
// For more information, visit: https://go.microsoft.com/fwlink/?linkid=830387
"version": "0.2.0"
}
"configurations": [
{
"console": "integratedTerminal",
"env": {
"LOG_LEVEL": "DEBUG"
},
"justMyCode": false,
"name": "Python Debugger: Main",
"program": "main.py",
"request": "launch",
"type": "debugpy"
}
]
}
+19 -12
View File
@@ -1,17 +1,17 @@
FROM debian:bullseye-slim AS base
FROM debian:bookworm-slim AS base
ENV HOME=/root
ARG GITHUB_BUILD=false \
VERSION
ENV HOME=/root \
GITHUB_BUILD=${GITHUB_BUILD}\
ENV GITHUB_BUILD=${GITHUB_BUILD}\
VERSION=${VERSION}\
DEBIAN_FRONTEND=noninteractive \
PYTHONUNBUFFERED=1 \
# prevents python creating .pyc files
PYTHONDONTWRITEBYTECODE=1 \
DISPLAY=:0
ENV PATH="${HOME}/.local/bin:$PATH"
DISPLAY=:0\
PATH="${HOME}/.local/bin:$PATH"
WORKDIR /app
@@ -19,22 +19,29 @@ RUN apt-get update && \
apt-get install -y --no-install-recommends --no-install-suggests xauth xvfb scrot curl chromium chromium-driver ca-certificates
ADD https://astral.sh/uv/install.sh install.sh
RUN sh install.sh
RUN sh install.sh && uv --version
FROM base AS devcontainer
RUN apt install -y git && apt upgrade -y
ENV UV_LINK_MODE=copy
ENTRYPOINT [ "sleep", "infinity" ]
FROM base AS app
COPY pyproject.toml uv.lock ./
RUN --mount=type=cache,target=${HOME}/.cache/uv uv sync
# SeleniumBase does not come with an arm64 chromedriver binary
RUN cd .venv/lib/*/site-packages/seleniumbase/drivers && ln -s /usr/bin/chromedriver uc_driver
RUN cd .venv/lib/*/site-packages/seleniumbase/drivers && rm -f uc_driver && ln -s /usr/bin/chromedriver uc_driver
COPY . .
FROM base AS test
FROM app AS test
RUN --mount=type=cache,target=${HOME}/.cache/uv uv sync --group test
RUN ./test.sh
FROM base
FROM app
EXPOSE 8191
HEALTHCHECK --interval=15m --timeout=30s --start-period=5s --retries=3 CMD [ "curl", "http://localhost:8191/health" ]
CMD ["./cmd.sh"]
ENTRYPOINT ["uv", "run", "main.py"]
+7 -4
View File
@@ -35,10 +35,13 @@ An alternative to [FlareSolverr](https://github.com/FlareSolverr/FlareSolverr) a
| Environment Variable | Default | Description |
| -------------------- | ---------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `USE_XVFB` | `SeleniumBase default` | Use virtual desktop with Xvfb. (Linux only) (Can cause performance hog [#14](https://github.com/ThePhaseless/Byparr/issues/14)) |
| `USE_HEADLESS` | `SeleniumBase default` | Use headless chromium. |
| `PROXY` | None | Proxy to use in format: `protocol://username:password@host:port`. [SOCKS5 with authentication is not supported by Chrome](https://stackoverflow.com/questions/75602916/connection-to-private-proxy-socks5-with-chrome-webrequest-onauthrequired-and), see `compose.yaml` file for a workaround |
## Proxy Recommendation
Recently I've partnered with a *new in town* proxy service - ProxyBase - to offer affordable proxy services that seems to work seamlessly with Byparr! Using my affiliate code `byparr` (case sensitive!) when signing up will not only get you access to their cost-effective (**$0.69/GB with occasional promotions**) proxy network but will also help support the continued development of this project. ProxyBase's proxies can significantly improve your success rate when bypassing anti-bot challenges. [Check out ProxyBase](https://discord.gg/perwbTBxGf) and enhance your Byparr experience! Just remember that it uses `socks5` protocol, so check [Options](#options) section for more details.
## Tags
- `v*.*.*`/`latest` - Releases considered stable
@@ -53,18 +56,18 @@ See `compose.yaml`
### Docker
```bash
docker run -p 8191:8191 ghcr.io/thephaseless/byparr:latest
docker run --shm-size=2gb -p 8191:8191 ghcr.io/thephaseless/byparr:latest
```
### Local
```bash
uv sync && ./cmd.sh
uv sync && uv run main.py
```
## Need help with / TODO
- [x] Slimming container (only ~650 MB now!)
- [x] Slimming container (only ~1.11 GB now!)
- [x] Add more anti-bot challenges
- [x] Add doc strings
- [x] Implement versioning
-3
View File
@@ -1,3 +0,0 @@
#!/bin/sh
uv run main.py
+11 -8
View File
@@ -1,17 +1,20 @@
services:
byparr:
image: ghcr.io/thephaseless/byparr
image: ghcr.io/thephaseless/byparr:latest
restart: unless-stopped
shm_size: 2gb
build:
context: .
dockerfile: Dockerfile
# environment: # Uncomment if using pproxy
# - proxy=http://pproxy:8080
# # Uncomment below to use pproxy
# environment:
# - PROXY=http://pproxy:8080
volumes:
- ./screenshots:/app/screenshots # For screenshots when exception occurs
ports:
- "8191:8191"
# # Uncomment the following lines to enable pproxy
- ./screenshots:/app/screenshots # (optional) For screenshots when exception occurs
# # Uncomment below to use byparr outside of internal network
# ports:
# - "8191:8191"
# # Uncomment the following lines to enable pproxy for socks5 proxy
# pproxy:
# tty: true # Required for pproxy to work
# container_name: pproxy
@@ -20,4 +23,4 @@ services:
# command:
# - -vv
# - -l http://:8080
# - -r socks5://host:port#username:password
# - -r socks5://host:port#username:password # Fill in your proxy credentials and address
+4 -4
View File
@@ -10,9 +10,9 @@ readme = "README.md"
dependencies = [
"fastapi[standard]==0.115.12",
"pyautogui==0.9.54",
"pydantic==2.11.3",
"seleniumbase==4.37.2",
"uvicorn==0.34.0",
"pydantic==2.11.4",
"seleniumbase==4.38.2",
"uvicorn==0.34.2",
]
urls = { repository = "https://github.com/ThePhaseless/Byparr" }
@@ -24,7 +24,7 @@ test = [
"pytest-retry==1.7.0",
"pytest-xdist==3.6.1",
]
dev = ["deptry==0.23.0", "ruff==0.11.5"]
dev = ["deptry==0.23.0", "ruff==0.11.10"]
[tool.deptry.per_rule_ignores]
DEP002 = ["pyautogui"]
+5 -4
View File
@@ -8,12 +8,12 @@ from sbase import BaseCase
from src.consts import CHALLENGE_TITLES
from src.models import (
HealthcheckResponse,
LinkRequest,
LinkResponse,
Solution,
)
from .utils import get_sb, logger, save_screenshot
from src.utils import get_sb, logger, save_screenshot
router = APIRouter()
@@ -41,13 +41,14 @@ def health_check(sb: SeleniumDep):
detail="Health check failed",
)
return {"status": "ok"}
return HealthcheckResponse(user_agent=sb.get_user_agent())
@router.post("/v1")
def read_item(request: LinkRequest, sb: SeleniumDep) -> LinkResponse:
"""Handle POST requests."""
start_time = int(time.time() * 1000)
request.url = request.url.replace('"', "").strip()
sb.uc_open_with_reconnect(request.url)
logger.debug(f"Got webpage: {request.url}")
source_bs = sb.get_beautiful_soup()
@@ -74,7 +75,7 @@ def read_item(request: LinkRequest, sb: SeleniumDep) -> LinkResponse:
return LinkResponse(
message="Success",
solution=Solution(
userAgent=sb.get_user_agent(),
user_agent=sb.get_user_agent(),
url=sb.get_current_url(),
status=200,
cookies=cookies,
+1 -1
View File
@@ -10,7 +10,7 @@ from src.utils import logger
class LogRequest(BaseHTTPMiddleware):
async def dispatch(self, request, call_next):
"""Log requests."""
if request.url.path != "/v1":
if request.url.path != "/v1" or request.method != "POST":
return await call_next(request)
start_time = time.perf_counter()
+14 -22
View File
@@ -1,7 +1,7 @@
from __future__ import annotations
import time
from http import HTTPStatus
from http.client import INTERNAL_SERVER_ERROR
from typing import Any
from pydantic import BaseModel, Field
@@ -19,29 +19,21 @@ class LinkRequest(BaseModel):
max_timeout: int = Field(default=60)
class HealthcheckResponse(BaseModel):
model_config = {"alias_generator": to_camel, "populate_by_name": True}
msg: str = "Byparr is ready!"
version: str = consts.VERSION
user_agent: str
class Solution(BaseModel):
model_config = {"alias_generator": to_camel, "populate_by_name": True}
url: str
status: int
cookies: list
userAgent: str # noqa: N815 # Ignore to preserve compatibility
headers: dict[str, Any]
response: str
@classmethod
def invalid(cls, url: str):
"""
Return an empty Solution with default values.
Useful for returning an error response.
"""
return cls(
url=url,
status=HTTPStatus.INTERNAL_SERVER_ERROR,
cookies=[],
userAgent="",
headers={},
response="",
)
cookies: list = []
user_agent: str = ""
headers: dict[str, Any] = {}
response: str = ""
class LinkResponse(BaseModel):
@@ -63,6 +55,6 @@ class LinkResponse(BaseModel):
return cls(
status="error",
message="Invalid request",
solution=Solution.invalid(url),
solution=Solution(url=url, status=INTERNAL_SERVER_ERROR),
start_timestamp=int(time.time() * 1000),
)
+1
View File
@@ -15,6 +15,7 @@ test_websites = [
"https://extratorrent.st/",
"https://idope.se/",
"https://speed.cd/login",
'https://www.yggtorrent.top/engine/search?do=search&order=desc&sort=publish_date&name="UNESCAPED"+"DOUBLEQUOTES"&category=2145'
]
Generated
+432 -429
View File
File diff suppressed because it is too large Load Diff