mirror
/
auto-archiver
kopia lustrzana https://github.com/bellingcat/auto-archiver
1
0
Forkuj 0
Kod Zgłoszenia Packages Projekty Wydania Wiki Aktywność

Fix the extractor args for new list structure.

pull/222/head
erinhmclark 2025-03-17 14:17:31 +00:00
rodzic f5bbfe5d1c
commit 5daeae994a
2 zmienionych plików z 53 dodań i 37 usunięć
Pokaż statystyki Ściągnij plik aktualizacji Ściągnij plik porównania Expand all files Collapse all files

53
poetry.lock wygenerowano
Wyświetl plik

@ -1,4 +1,4 @@
# This file is automatically @generated by Poetry 2.1.1 and should not be changed by hand.
# This file is automatically @generated by Poetry 2.0.1 and should not be changed by hand.
[[package]]
name = "accessible-pygments"
@ -51,7 +51,7 @@ typing_extensions = {version = ">=4.5", markers = "python_version < \"3.13\""}
[package.extras]
doc = ["Sphinx (>=7.4,<8.0)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx_rtd_theme"]
test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "trustme", "truststore (>=0.9.1) ; python_version >= \"3.10\"", "uvloop (>=0.21) ; platform_python_implementation == \"CPython\" and platform_system != \"Windows\" and python_version < \"3.14\""]
test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "trustme", "truststore (>=0.9.1)", "uvloop (>=0.21)"]
trio = ["trio (>=0.26.1)"]
[[package]]
@ -94,12 +94,12 @@ files = [
]
[package.extras]
benchmark = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
cov = ["cloudpickle ; platform_python_implementation == \"CPython\"", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
dev = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
benchmark = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-codspeed", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
cov = ["cloudpickle", "coverage[toml] (>=5.3)", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
dev = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pre-commit-uv", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphinxcontrib-towncrier", "towncrier (<24.7)"]
tests = ["cloudpickle ; platform_python_implementation == \"CPython\"", "hypothesis", "mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-xdist[psutil]"]
tests-mypy = ["mypy (>=1.11.1) ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\"", "pytest-mypy-plugins ; platform_python_implementation == \"CPython\" and python_version >= \"3.10\""]
tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
[[package]]
name = "authlib"
@ -145,7 +145,7 @@ files = [
]
[package.extras]
dev = ["backports.zoneinfo ; python_version < \"3.9\"", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata ; sys_platform == \"win32\""]
dev = ["backports.zoneinfo", "freezegun (>=1.0,<2.0)", "jinja2 (>=3.0)", "pytest (>=6.0)", "pytest-cov", "pytz", "setuptools", "tzdata"]
[[package]]
name = "beautifulsoup4"
@ -170,6 +170,21 @@ charset-normalizer = ["charset-normalizer"]
html5lib = ["html5lib"]
lxml = ["lxml"]
[[package]]
name = "bgutil-ytdlp-pot-provider"
version = "0.7.4"
description = ""
optional = false
python-versions = ">=3.8"
groups = ["main"]
files = [
{file = "bgutil_ytdlp_pot_provider-0.7.4-py3-none-any.whl", hash = "sha256:5f0b1d884fec66dff703c421ea06f5fc9b11022d9c0babdaa0cab13ed99b9d77"},
{file = "bgutil_ytdlp_pot_provider-0.7.4.tar.gz", hash = "sha256:b6c1462b8f979540078085cd82462ef967b8b70cd0810d469243a31f5081e5c6"},
]
[package.dependencies]
yt-dlp-get-pot = ">=0.1.1"
[[package]]
name = "boto3"
version = "1.37.8"
@ -781,7 +796,7 @@ files = [
[package.extras]
docs = ["furo (>=2024.8.6)", "sphinx (>=8.1.3)", "sphinx-autodoc-typehints (>=3)"]
testing = ["covdefaults (>=2.3)", "coverage (>=7.6.10)", "diff-cover (>=9.2.1)", "pytest (>=8.3.4)", "pytest-asyncio (>=0.25.2)", "pytest-cov (>=6)", "pytest-mock (>=3.14)", "pytest-timeout (>=2.3.1)", "virtualenv (>=20.28.1)"]
typing = ["typing-extensions (>=4.12.2) ; python_version < \"3.11\""]
typing = ["typing-extensions (>=4.12.2)"]
[[package]]
name = "future"
@ -816,7 +831,7 @@ requests = ">=2.18.0,<3.0.0.dev0"
[package.extras]
async-rest = ["google-auth[aiohttp] (>=2.35.0,<3.0.dev0)"]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio (>=1.49.1,<2.0dev) ; python_version >= \"3.11\"", "grpcio-status (>=1.33.2,<2.0.dev0)", "grpcio-status (>=1.49.1,<2.0.dev0) ; python_version >= \"3.11\""]
grpc = ["grpcio (>=1.33.2,<2.0dev)", "grpcio (>=1.49.1,<2.0dev)", "grpcio-status (>=1.33.2,<2.0.dev0)", "grpcio-status (>=1.49.1,<2.0.dev0)"]
grpcgcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"]
grpcio-gcp = ["grpcio-gcp (>=0.2.2,<1.0.dev0)"]
@ -1115,7 +1130,7 @@ colorama = {version = ">=0.3.4", markers = "sys_platform == \"win32\""}
win32-setctime = {version = ">=1.0.0", markers = "sys_platform == \"win32\""}
[package.extras]
dev = ["Sphinx (==8.1.3) ; python_version >= \"3.11\"", "build (==1.2.2) ; python_version >= \"3.11\"", "colorama (==0.4.5) ; python_version < \"3.8\"", "colorama (==0.4.6) ; python_version >= \"3.8\"", "exceptiongroup (==1.1.3) ; python_version >= \"3.7\" and python_version < \"3.11\"", "freezegun (==1.1.0) ; python_version < \"3.8\"", "freezegun (==1.5.0) ; python_version >= \"3.8\"", "mypy (==v0.910) ; python_version < \"3.6\"", "mypy (==v0.971) ; python_version == \"3.6\"", "mypy (==v1.13.0) ; python_version >= \"3.8\"", "mypy (==v1.4.1) ; python_version == \"3.7\"", "myst-parser (==4.0.0) ; python_version >= \"3.11\"", "pre-commit (==4.0.1) ; python_version >= \"3.9\"", "pytest (==6.1.2) ; python_version < \"3.8\"", "pytest (==8.3.2) ; python_version >= \"3.8\"", "pytest-cov (==2.12.1) ; python_version < \"3.8\"", "pytest-cov (==5.0.0) ; python_version == \"3.8\"", "pytest-cov (==6.0.0) ; python_version >= \"3.9\"", "pytest-mypy-plugins (==1.9.3) ; python_version >= \"3.6\" and python_version < \"3.8\"", "pytest-mypy-plugins (==3.1.0) ; python_version >= \"3.8\"", "sphinx-rtd-theme (==3.0.2) ; python_version >= \"3.11\"", "tox (==3.27.1) ; python_version < \"3.8\"", "tox (==4.23.2) ; python_version >= \"3.8\"", "twine (==6.0.1) ; python_version >= \"3.11\""]
dev = ["Sphinx (==8.1.3)", "build (==1.2.2)", "colorama (==0.4.5)", "colorama (==0.4.6)", "exceptiongroup (==1.1.3)", "freezegun (==1.1.0)", "freezegun (==1.5.0)", "mypy (==v0.910)", "mypy (==v0.971)", "mypy (==v1.13.0)", "mypy (==v1.4.1)", "myst-parser (==4.0.0)", "pre-commit (==4.0.1)", "pytest (==6.1.2)", "pytest (==8.3.2)", "pytest-cov (==2.12.1)", "pytest-cov (==5.0.0)", "pytest-cov (==6.0.0)", "pytest-mypy-plugins (==1.9.3)", "pytest-mypy-plugins (==3.1.0)", "sphinx-rtd-theme (==3.0.2)", "tox (==3.27.1)", "tox (==4.23.2)", "twine (==6.0.1)"]
[[package]]
name = "markdown-it-py"
@ -1594,7 +1609,7 @@ docs = ["furo", "olefile", "sphinx (>=8.1)", "sphinx-copybutton", "sphinx-inline
fpx = ["olefile"]
mic = ["olefile"]
tests = ["check-manifest", "coverage (>=7.4.2)", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout", "trove-classifiers (>=2024.10.12)"]
typing = ["typing-extensions ; python_version < \"3.10\""]
typing = ["typing-extensions"]
xmp = ["defusedxml"]
[[package]]
@ -3018,7 +3033,7 @@ files = [
pysocks = {version = ">=1.5.6,<1.5.7 || >1.5.7,<2.0", optional = true, markers = "extra == \"socks\""}
[package.extras]
brotli = ["brotli (>=1.0.9) ; platform_python_implementation == \"CPython\"", "brotlicffi (>=0.8.0) ; platform_python_implementation != \"CPython\""]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
h2 = ["h2 (>=4,<5)"]
socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
zstd = ["zstandard (>=0.18.0)"]
@ -3041,7 +3056,7 @@ h11 = ">=0.8"
typing-extensions = {version = ">=4.0", markers = "python_version < \"3.11\""}
[package.extras]
standard = ["colorama (>=0.4) ; sys_platform == \"win32\"", "httptools (>=0.6.3)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1) ; sys_platform != \"win32\" and sys_platform != \"cygwin\" and platform_python_implementation != \"PyPy\"", "watchfiles (>=0.13)", "websockets (>=10.4)"]
standard = ["colorama (>=0.4)", "httptools (>=0.6.3)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
[[package]]
name = "virtualenv"
@ -3062,7 +3077,7 @@ platformdirs = ">=3.9.1,<5"
[package.extras]
docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.2,!=7.3)", "sphinx-argparse (>=0.4)", "sphinxcontrib-towncrier (>=0.2.1a0)", "towncrier (>=23.6)"]
test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8) ; platform_python_implementation == \"PyPy\" or platform_python_implementation == \"CPython\" and sys_platform == \"win32\" and python_version >= \"3.13\"", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10) ; platform_python_implementation == \"CPython\""]
test = ["covdefaults (>=2.3)", "coverage (>=7.2.7)", "coverage-enable-subprocess (>=1)", "flaky (>=3.7)", "packaging (>=23.1)", "pytest (>=7.4)", "pytest-env (>=0.8.2)", "pytest-freezer (>=0.4.8)", "pytest-mock (>=3.11.1)", "pytest-randomly (>=3.12)", "pytest-timeout (>=2.1)", "setuptools (>=68)", "time-machine (>=2.10)"]
[[package]]
name = "vk-api"
@ -3324,7 +3339,7 @@ files = [
]
[package.extras]
dev = ["black (>=19.3b0) ; python_version >= \"3.6\"", "pytest (>=4.6.2)"]
dev = ["black (>=19.3b0)", "pytest (>=4.6.2)"]
[[package]]
name = "wsproto"
@ -3355,8 +3370,8 @@ files = [
[package.extras]
build = ["build", "hatchling", "pip", "setuptools (>=71.0.2)", "wheel"]
curl-cffi = ["curl-cffi (==0.5.10) ; os_name == \"nt\" and implementation_name == \"cpython\"", "curl-cffi (>=0.5.10,!=0.6.*,<0.7.2) ; os_name != \"nt\" and implementation_name == \"cpython\""]
default = ["brotli ; implementation_name == \"cpython\"", "brotlicffi ; implementation_name != \"cpython\"", "certifi", "mutagen", "pycryptodomex", "requests (>=2.32.2,<3)", "urllib3 (>=1.26.17,<3)", "websockets (>=13.0)"]
curl-cffi = ["curl-cffi (==0.5.10)", "curl-cffi (>=0.5.10,!=0.6.*,<0.7.2)"]
default = ["brotli", "brotlicffi", "certifi", "mutagen", "pycryptodomex", "requests (>=2.32.2,<3)", "urllib3 (>=1.26.17,<3)", "websockets (>=13.0)"]
dev = ["autopep8 (>=2.0,<3.0)", "pre-commit", "pytest (>=8.1,<9.0)", "pytest-rerunfailures (>=14.0,<15.0)", "ruff (>=0.9.0,<0.10.0)"]
pyinstaller = ["pyinstaller (>=6.11.1)"]
secretstorage = ["cffi", "secretstorage"]
@ -3378,4 +3393,4 @@ files = [
[metadata]
lock-version = "2.1"
python-versions = ">=3.10,<3.13"
content-hash = "beb354960b8d8af491a13e09cb565c7e3099a2b150167c16147aa0438e970018"
content-hash = "830a11953091225cfc5f9cb8fb7e06c9be468695492ee4487093f988e4ac1956"

29
src/auto_archiver/modules/generic_extractor/generic_extractor.py
Wyświetl plik

@ -404,12 +404,20 @@ class GenericExtractor(Extractor):
"--write-subs" if self.subtitles else "--no-write-subs",
"--write-auto-subs" if self.subtitles else "--no-write-auto-subs",
"--live-from-start" if self.live_from_start else "--no-live-from-start",
"--proxy",
self.proxy if self.proxy else "",
f"--max-downloads {self.max_downloads}" if self.max_downloads != "inf" else "",
f"--playlist-end {self.max_downloads}" if self.max_downloads != "inf" else "",
# TODO: Move this to documentation
# Note: add the --verbose flag for debugging
"--verbose",
]
# proxy handling
if self.proxy:
ydl_options.extend(["--proxy", self.proxy])
# max_downloads handling
if self.max_downloads != "inf":
ydl_options.extend(["--max-downloads", str(self.max_downloads)])
ydl_options.extend(["--playlist-end", str(self.max_downloads)])
# set up auth
auth = self.auth_for_site(url, extract_cookies=False)
# order of importance: username/password -> api_key -> cookie -> cookies_from_browser -> cookies_file
@ -428,22 +436,15 @@ class GenericExtractor(Extractor):
logger.debug(f"Using cookies from file {auth['cookies_file']} for {url}")
ydl_options.extend(("--cookies", auth["cookies_file"]))
# Applying user-defined extractor_args
if self.extractor_args:
logger.info(f"Applying user-defined extractor_args")
ydl_options.setdefault('extractor_args', {})
for key, args in self.extractor_args.items():
logger.debug(f"Setting extractor_args: {key}")
if isinstance(args, dict):
# Site specific arguments (e.g., youtube: somekey=value)
ydl_options['extractor_args'].setdefault(key, {}).update(args)
arg_str = ";".join(f"{k}={v}" for k, v in args.items())
else:
# General extractor_args (e.g., somekey=value)
ydl_options['extractor_args'][key] = args
arg_str = str(args)
ydl_options.extend(["--extractor-args", f"{key}:{arg_str}"])
if self.ytdlp_args:
logger.debug("Adding additional ytdlp arguments: {self.ytdlp_args}")