mirror of
https://github.com/ThePhaseless/Byparr.git
synced 2026-09-24 22:03:30 +01:00
Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
9ead42863d | ||
|
|
89e9a176c7 | ||
|
|
d5c163f621 | ||
|
|
6694d45e74 | ||
|
|
b23b814e43 | ||
|
|
9353daaf1a | ||
|
|
5a35117299 | ||
|
|
ee8aeed9b1 | ||
|
|
c188d4fe85 | ||
|
|
4ecfc98c81 | ||
|
|
38f344a71c | ||
|
|
815faddcf2 | ||
|
|
999ca88a19 | ||
|
|
dd35795ffa | ||
|
|
147902be2c | ||
|
|
7e9c2ba97d | ||
|
|
9fc9af3ba9 | ||
|
|
55526308f6 | ||
|
|
cdb3223a87 | ||
|
|
329235ba5e | ||
|
|
5031d1e554 | ||
|
|
090b5487e4 | ||
|
|
c608bbc46e | ||
|
|
46eff073b7 | ||
|
|
a347b7046b | ||
|
|
4658d04d2e | ||
|
|
b6aa1a8c58 | ||
|
|
5bff9e1bc1 | ||
|
|
dbd16882de | ||
|
|
adc98e8cea | ||
|
|
8e7d007c6f | ||
|
|
51c1577d7c | ||
|
|
98f9480157 | ||
|
|
2be9fa55a9 | ||
|
|
6520444d4e | ||
|
|
693d67bcfd | ||
|
|
b217778a79 | ||
|
|
3b18dfe522 | ||
|
|
ee5b7fe027 | ||
|
|
d2678643c0 | ||
|
|
343fdca493 | ||
|
|
5a8edf13ab | ||
|
|
1fa6b66f3a | ||
|
|
fe797ba2ac | ||
|
|
409c0f9d8c | ||
|
|
d22e780219 |
@@ -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
|
||||
@@ -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
@@ -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/
|
||||
Symlink
+1
@@ -0,0 +1 @@
|
||||
.gitignore
|
||||
Vendored
+14
-18
@@ -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"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
+20
-13
@@ -1,40 +1,47 @@
|
||||
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
|
||||
|
||||
RUN apt-get update && \
|
||||
apt-get install -y --no-install-recommends --no-install-suggests xauth xvfb scrot curl chromium chromium-driver ca-certificates
|
||||
apt-get install -y --no-install-recommends --no-install-suggests xauth xvfb scrot curl chromium chromium-driver ca-certificates tini
|
||||
|
||||
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 ["/usr/bin/tini", "--", "uv", "run", "main.py"]
|
||||
|
||||
@@ -35,10 +35,14 @@ 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://client.proxybase.org/signup?ref=byparr
|
||||
) and enhance your Byparr experience!
|
||||
|
||||
## Tags
|
||||
|
||||
- `v*.*.*`/`latest` - Releases considered stable
|
||||
@@ -53,18 +57,18 @@ 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
|
||||
|
||||
+11
-8
@@ -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
|
||||
|
||||
+5
-6
@@ -10,21 +10,20 @@ 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==2.11.5",
|
||||
"seleniumbase==4.39.2",
|
||||
"uvicorn==0.34.3",
|
||||
]
|
||||
urls = { repository = "https://github.com/ThePhaseless/Byparr" }
|
||||
|
||||
[dependency-groups]
|
||||
test = [
|
||||
"httpx==0.28.1",
|
||||
"pytest-asyncio==0.26.0",
|
||||
"pytest-asyncio==1.0.0",
|
||||
"pytest-progress==1.3.0",
|
||||
"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==0.11.13"]
|
||||
|
||||
[tool.deptry.per_rule_ignores]
|
||||
DEP002 = ["pyautogui"]
|
||||
|
||||
+5
-4
@@ -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
@@ -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
@@ -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),
|
||||
)
|
||||
|
||||
@@ -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'
|
||||
]
|
||||
|
||||
|
||||
|
||||
Reference in New Issue
Block a user