etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-22 02:15:12 +00:00
Code Issues Projects Releases Wiki Activity

Merge branch 'yt-dlp:master' into mercadolibre

Browse source
This commit is contained in:
Alvear Devs 2024-08-12 17:29:47 -03:00 committed by GitHub
commit e79bcc5691
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
950 changed files with 12697 additions and 9626 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
.github/workflows/build.yml vendored
View file

@ -237,27 +237,43 @@ jobs:
macos:
needs: process
if: inputs.macos
permissions:
contents: read
actions: write # For cleaning up cache
runs-on: macos-12
steps:
- uses: actions/checkout@v4
# NB: Building universal2 does not work with python from actions/setup-python
- name: Restore cached requirements
id: restore-cache
uses: actions/cache/restore@v4
env:
SEGMENT_DOWNLOAD_TIMEOUT_MINS: 1
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
- name: Install Requirements
run: |
brew install coreutils
python3 devscripts/install_deps.py --user -o --include build
python3 -m venv ~/yt-dlp-build-venv
source ~/yt-dlp-build-venv/bin/activate
python3 devscripts/install_deps.py -o --include build
python3 devscripts/install_deps.py --print --include pyinstaller > requirements.txt
# We need to ignore wheels otherwise we break universal2 builds
python3 -m pip install -U --user --no-binary :all: -r requirements.txt
python3 -m pip install -U --no-binary :all: -r requirements.txt
# We need to fuse our own universal2 wheels for curl_cffi
python3 -m pip install -U --user delocate
python3 -m pip install -U delocate
mkdir curl_cffi_whls curl_cffi_universal2
python3 devscripts/install_deps.py --print -o --include curl-cffi > requirements.txt
for platform in "macosx_11_0_arm64" "macosx_11_0_x86_64"; do
python3 -m pip download \
--only-binary=:all: \
--platform "${platform}" \
--pre -d curl_cffi_whls \
-d curl_cffi_whls \
-r requirements.txt
done
( # Overwrite x86_64-only libs with fat/universal2 libs or else Pyinstaller will do the opposite
@ -274,9 +290,10 @@ jobs:
)
python3 -m delocate.cmd.delocate_fuse curl_cffi_whls/curl_cffi*.whl -w curl_cffi_universal2
python3 -m delocate.cmd.delocate_fuse curl_cffi_whls/cffi*.whl -w curl_cffi_universal2
cd curl_cffi_universal2
for wheel in ./*cffi*.whl; do mv -n -- "${wheel}" "${wheel/x86_64/universal2}"; done
python3 -m pip install -U --user ./*cffi*.whl
for wheel in curl_cffi_universal2/*cffi*.whl; do
mv -n -- "${wheel}" "${wheel/x86_64/universal2}"
done
python3 -m pip install --force-reinstall -U curl_cffi_universal2/*cffi*.whl
- name: Prepare
run: |
@ -284,6 +301,7 @@ jobs:
python3 devscripts/make_lazy_extractors.py
- name: Build
run: |
source ~/yt-dlp-build-venv/bin/activate
python3 -m bundle.pyinstaller --target-architecture universal2 --onedir
(cd ./dist/yt-dlp_macos && zip -r ../yt-dlp_macos.zip .)
python3 -m bundle.pyinstaller --target-architecture universal2
@ -307,6 +325,24 @@ jobs:
dist/yt-dlp_macos.zip
compression-level: 0
- name: Cleanup cache
if: steps.restore-cache.outputs.cache-hit == 'true'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
cache_key: cache-reqs-${{ github.job }}
repository: ${{ github.repository }}
branch: ${{ github.ref }}
run: |
gh extension install actions/gh-actions-cache
gh actions-cache delete "${cache_key}" -R "${repository}" -B "${branch}" --confirm
- name: Cache requirements
uses: actions/cache/save@v4
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
macos_legacy:
needs: process
if: inputs.macos_legacy
@ -489,6 +525,10 @@ jobs:
# make sure SHA sums are also printed to stdout
sha256sum -- * | tee ../SHA2-256SUMS
sha512sum -- * | tee ../SHA2-512SUMS
# also print as permanent annotations to the summary page
while read -r shasum; do
echo "::notice title=${shasum##* }::sha256: ${shasum% *}"
done < ../SHA2-256SUMS
- name: Make Update spec
run: |

3
.github/workflows/release-master.yml vendored
View file

@ -24,6 +24,7 @@ jobs:
source: master
permissions:
contents: write
packages: write
packages: write # For package cache
actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing
secrets: inherit

3
.github/workflows/release-nightly.yml vendored
View file

@ -37,6 +37,7 @@ jobs:
source: nightly
permissions:
contents: write
packages: write
packages: write # For package cache
actions: write # For cleaning up cache
id-token: write # mandatory for trusted publishing
secrets: inherit

3
.github/workflows/release.yml vendored
View file

@ -228,7 +228,8 @@ jobs:
origin: ${{ needs.prepare.outputs.target_repo }}
permissions:
contents: read
packages: write # For package cache
packages: write # For package cache
actions: write # For cleaning up cache
secrets:
GPG_SIGNING_KEY: ${{ secrets.GPG_SIGNING_KEY }}

2
.gitignore vendored
View file

@ -51,7 +51,6 @@ cookies
*.srt
*.ssa
*.swf
*.swp
*.tt
*.ttml
*.url
@ -119,6 +118,7 @@ yt-dlp.zip
.vscode
*.sublime-*
*.code-workspace
*.swp
# Lazy extractors
*/extractor/lazy_extractors.py

14
CONTRIBUTING.md
View file

@ -127,7 +127,7 @@ ### Are you willing to share account details if needed?
### Is the website primarily used for piracy?
We follow [youtube-dl's policy](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) to not support services that is primarily used for infringing copyright. Additionally, it has been decided to not to support porn sites that specialize in fakes. We also cannot support any service that serves only [DRM protected content](https://en.wikipedia.org/wiki/Digital_rights_management).
We follow [youtube-dl's policy](https://github.com/ytdl-org/youtube-dl#can-you-add-support-for-this-anime-video-site-or-site-which-shows-current-movies-for-free) to not support services that is primarily used for infringing copyright. Additionally, it has been decided to not to support porn sites that specialize in fakes. We also cannot support any service that serves only [DRM protected content](https://en.wikipedia.org/wiki/Digital_rights_management).
@ -215,8 +215,8 @@ ## Adding support for a new site
```python
from .common import InfoExtractor
class YourExtractorIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?yourextractor\.com/watch/(?P<id>[0-9]+)'
_TESTS = [{
@ -244,7 +244,7 @@ ## Adding support for a new site
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
# TODO more code goes here, for example ...
title = self._html_search_regex(r'<h1>(.+?)</h1>', webpage, 'title')
@ -266,7 +266,7 @@ ## Adding support for a new site
$ hatch fmt --check
```
You can use `hatch fmt` to automatically fix problems.
You can use `hatch fmt` to automatically fix problems. Rules that the linter/formatter enforces should not be disabled with `# noqa` unless a maintainer requests it. The only exception allowed is for old/printf-style string formatting in GraphQL query templates (use `# noqa: UP031`).
1. Make sure your code works under all [Python](https://www.python.org/) versions supported by yt-dlp, namely CPython and PyPy for Python 3.8 and above. Backward compatibility is not required for even older versions of Python.
1. When the tests pass, [add](https://git-scm.com/docs/git-add) the new files, [commit](https://git-scm.com/docs/git-commit) them and [push](https://git-scm.com/docs/git-push) the result, like this:
@ -320,7 +320,7 @@ #### Example
```python
meta = self._download_json(url, video_id)
```
Assume at this point `meta`'s layout is:
```python
@ -750,7 +750,7 @@ ### Use convenience conversion and parsing functions
Use `traverse_obj` and `try_call` (superseeds `dict_get` and `try_get`) for safe metadata extraction from parsed JSON.
Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction.
Use `unified_strdate` for uniform `upload_date` or any `YYYYMMDD` meta field extraction, `unified_timestamp` for uniform `timestamp` extraction, `parse_filesize` for `filesize` extraction, `parse_count` for count meta fields extraction, `parse_resolution`, `parse_duration` for `duration` extraction, `parse_age_limit` for `age_limit` extraction.
Explore [`yt_dlp/utils/`](yt_dlp/utils/) for more useful convenience functions.

26
CONTRIBUTORS
View file

@ -631,3 +631,29 @@ voidful
vtexier
WyohKnott
trueauracoral
ASertacAkkaya
axpauls
chilinux
hafeoz
JSubelj
jucor
megumintyan
mgedmin
Niluge-KiWi
peisenwang
TheZ3ro
tippfehlr
varunchopra
DrakoCpp
PatrykMis
DinhHuy2010
exterrestris
harbhim
LeSuisse
DunnesH
iancmy
mokrueger
luvyana
szantnerb
hugepower
scribblemaniac

228
Changelog.md
View file

@ -4,6 +4,234 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2024.08.06
#### Core changes
- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly)
- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac)
- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly)
- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower)
- **youtube**
- [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly)
- [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev)
### 2024.08.01
#### Core changes
- **utils**: `unified_timestamp`: [Recognize Sunday](https://github.com/yt-dlp/yt-dlp/commit/6daf2c27c0464fba98337be30de0b66d520d0db1) ([#10589](https://github.com/yt-dlp/yt-dlp/issues/10589)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **abematv**: [Fix availability extraction](https://github.com/yt-dlp/yt-dlp/commit/ef36d517f9b05785d61abca7691d9ab7d63cc75c) ([#10569](https://github.com/yt-dlp/yt-dlp/issues/10569)) by [middlingphys](https://github.com/middlingphys)
- **cbc.ca**: player: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/94a1c5e642e468cebeb51f74c6c220434cb47d96) ([#10302](https://github.com/yt-dlp/yt-dlp/issues/10302)) by [bashonly](https://github.com/bashonly), [trainman261](https://github.com/trainman261)
- **discoveryplus**: [Support olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/0b7728618417e1aa382722a4d29b916b594d4459) ([#10566](https://github.com/yt-dlp/yt-dlp/issues/10566)) by [bashonly](https://github.com/bashonly)
- **kick**: clips: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/bb3936ae2b3ce96d0b53f9e17cad1082058f032b) ([#10572](https://github.com/yt-dlp/yt-dlp/issues/10572)) by [luvyana](https://github.com/luvyana)
- **learningonscreen**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/fe15d3178e242803ae7a934b90137f13598eba2e) ([#10590](https://github.com/yt-dlp/yt-dlp/issues/10590)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- **mediaklikk**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7e3e4779ad13e4511c9ba3869879e53f0267bd7a) ([#10605](https://github.com/yt-dlp/yt-dlp/issues/10605)) by [szantnerb](https://github.com/szantnerb)
- **mlbtv**: [Fix makeup game extraction](https://github.com/yt-dlp/yt-dlp/commit/4b69e1b53ea21e631cd5dd68ff531e2f1671ec17) ([#10607](https://github.com/yt-dlp/yt-dlp/issues/10607)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2f1ddfe12a2c174bc777264c5c8ffe7ca0922d94) ([#10604](https://github.com/yt-dlp/yt-dlp/issues/10604)) by [bashonly](https://github.com/bashonly)
- **tva**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/28d485714fef88937c82635438afba5db81f9089) ([#10567](https://github.com/yt-dlp/yt-dlp/issues/10567)) by [bashonly](https://github.com/bashonly)
- **tver**: [Support olympic URLs](https://github.com/yt-dlp/yt-dlp/commit/5260696b1cba77161828941fdb38f09f14ac6c60) ([#10600](https://github.com/yt-dlp/yt-dlp/issues/10600)) by [vvto33](https://github.com/vvto33)
- **vimeo**: review: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/2b6df93a243bdfb9d6bb5c1e18020625cd02d465) ([#10598](https://github.com/yt-dlp/yt-dlp/issues/10598)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Change default player clients to `ios,tv`](https://github.com/yt-dlp/yt-dlp/commit/efb42763dec23ccf6a2e3bac3afbfefce8efd012) ([#10457](https://github.com/yt-dlp/yt-dlp/issues/10457)) by [seproDev](https://github.com/seproDev)
- [Fix `n` function name extraction for player `20dfca59`](https://github.com/yt-dlp/yt-dlp/commit/011b4a04db2a636c3ef0a0ad4e2d3ae482c9fd76) ([#10611](https://github.com/yt-dlp/yt-dlp/issues/10611)) by [bashonly](https://github.com/bashonly)
- [Fix age-verification workaround](https://github.com/yt-dlp/yt-dlp/commit/d19fcb934269465fd707e68a87f735ec6983e93d) ([#10610](https://github.com/yt-dlp/yt-dlp/issues/10610)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- [Player client maintenance](https://github.com/yt-dlp/yt-dlp/commit/0e539617a41913c7da1edd74fb6543c10ad727b3) ([#10573](https://github.com/yt-dlp/yt-dlp/issues/10573)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **cleanup**: Miscellaneous: [ffd7781](https://github.com/yt-dlp/yt-dlp/commit/ffd7781d6588926f820b44a34b9e6e3068fb9f97) by [bashonly](https://github.com/bashonly)
### 2024.07.25
#### Extractor changes
- **abematv**: [Adapt key retrieval to request handler framework](https://github.com/yt-dlp/yt-dlp/commit/a3bab4752a2b3d56e5a59b4e0411bb8f695c010b) ([#10491](https://github.com/yt-dlp/yt-dlp/issues/10491)) by [bashonly](https://github.com/bashonly)
- **facebook**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/1a34a802f44a1dab8f642c79c3cc810e21541d3b) ([#10531](https://github.com/yt-dlp/yt-dlp/issues/10531)) by [bashonly](https://github.com/bashonly)
- **mlbtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f0993391e6052ec8f7aacc286609564f226943b9) ([#10515](https://github.com/yt-dlp/yt-dlp/issues/10515)) by [bashonly](https://github.com/bashonly)
- **tiktok**: [Fix and deprioritize JSON subtitles](https://github.com/yt-dlp/yt-dlp/commit/2f97779f335ac069ecccd9c7bf81abf4a83cfe7a) ([#10516](https://github.com/yt-dlp/yt-dlp/issues/10516)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Fix chapters extraction](https://github.com/yt-dlp/yt-dlp/commit/a0a1bc3d8d8e3bb9a48a06e835815a0460e90e77) ([#10544](https://github.com/yt-dlp/yt-dlp/issues/10544)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix `n` function name extraction for player `3400486c`](https://github.com/yt-dlp/yt-dlp/commit/713b4cd18f00556771af8cfdd9cea6cc1a09e948) ([#10542](https://github.com/yt-dlp/yt-dlp/issues/10542)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**: [Pin `setuptools` version](https://github.com/yt-dlp/yt-dlp/commit/e046db8a116b1c320d4785daadd48ea0b22a3987) ([#10493](https://github.com/yt-dlp/yt-dlp/issues/10493)) by [bashonly](https://github.com/bashonly)
### 2024.07.16
#### Core changes
- [Fix `noprogress` if `test=True` with `--quiet` and `--verbose`](https://github.com/yt-dlp/yt-dlp/commit/66ce3d76d87af3f81cc9dfec4be4704016cb1cdb) ([#10454](https://github.com/yt-dlp/yt-dlp/issues/10454)) by [Grub4K](https://github.com/Grub4K)
- [Support `auto-tty` and `no_color-tty` for `--color`](https://github.com/yt-dlp/yt-dlp/commit/d9cbced493cae2008508d94a2db5dd98be7c01fc) ([#10453](https://github.com/yt-dlp/yt-dlp/issues/10453)) by [Grub4K](https://github.com/Grub4K)
- **update**: [Fix network error handling](https://github.com/yt-dlp/yt-dlp/commit/ed1b9ed93dd90d2cc960c0d8eaa9d919db224203) ([#10486](https://github.com/yt-dlp/yt-dlp/issues/10486)) by [bashonly](https://github.com/bashonly)
- **utils**: `parse_codecs`: [Fix parsing of mixed case codec strings](https://github.com/yt-dlp/yt-dlp/commit/cc0070f6496e501d77352bad475fb02d6a86846a) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **adn**: [Adjust for .com domain change](https://github.com/yt-dlp/yt-dlp/commit/959b7a379b8e5da059d110a63339c964b6265736) ([#10399](https://github.com/yt-dlp/yt-dlp/issues/10399)) by [infanf](https://github.com/infanf)
- **afreecatv**: [Fix login and use `legacy_ssl`](https://github.com/yt-dlp/yt-dlp/commit/4cd41469243624d90b7a2009b95cbe0609343efe) ([#10440](https://github.com/yt-dlp/yt-dlp/issues/10440)) by [bashonly](https://github.com/bashonly)
- **box**: [Support enterprise URLs](https://github.com/yt-dlp/yt-dlp/commit/705f5b84dec75cc7af97f42fd1530e8062735970) ([#10419](https://github.com/yt-dlp/yt-dlp/issues/10419)) by [seproDev](https://github.com/seproDev)
- **digitalconcerthall**: [Extract HEVC and FLAC formats](https://github.com/yt-dlp/yt-dlp/commit/e62fa6b0e0186f8c5666c2c5ab64cf191abdafc1) ([#10470](https://github.com/yt-dlp/yt-dlp/issues/10470)) by [bashonly](https://github.com/bashonly)
- **dplay**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/39e6c4cb44b9292e89ac0afec3cd0afc2ae8775f) ([#10471](https://github.com/yt-dlp/yt-dlp/issues/10471)) by [bashonly](https://github.com/bashonly)
- **epidemicsound**: [Support sound effects URLs](https://github.com/yt-dlp/yt-dlp/commit/8531d2b03bac9cc746f2ee8098aaf8f115505f5b) ([#10436](https://github.com/yt-dlp/yt-dlp/issues/10436)) by [iancmy](https://github.com/iancmy)
- **generic**: [Fix direct video link extensions](https://github.com/yt-dlp/yt-dlp/commit/b9afb99e7c34d0eb15ddc6689cd7d20eebfda68e) ([#10468](https://github.com/yt-dlp/yt-dlp/issues/10468)) by [bashonly](https://github.com/bashonly)
- **picarto**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/bacd18b7df08b4995644fd12cee1f8c8e8636bc7) ([#10414](https://github.com/yt-dlp/yt-dlp/issues/10414)) by [Frankgoji](https://github.com/Frankgoji)
- **soundcloud**: permalink, user: [Extract tracks only](https://github.com/yt-dlp/yt-dlp/commit/22870b81bad97dfa6307a7add44753b2dffc76a9) ([#10463](https://github.com/yt-dlp/yt-dlp/issues/10463)) by [DunnesH](https://github.com/DunnesH)
- **tiktok**: live: [Fix room ID extraction](https://github.com/yt-dlp/yt-dlp/commit/d2189d3d36987ebeac426fd70a60a5fe86325a2b) ([#10408](https://github.com/yt-dlp/yt-dlp/issues/10408)) by [mokrueger](https://github.com/mokrueger)
- **tv5monde**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/9b95a6765a5f6325af99c4aca961587f0c426e8c) ([#10417](https://github.com/yt-dlp/yt-dlp/issues/10417)) by [bashonly](https://github.com/bashonly) (With fixes in [cc1a309](https://github.com/yt-dlp/yt-dlp/commit/cc1a3098c00995c6aebc2a16bd1050a66bad64db))
- **youtube**
- [Avoid poToken experiment player responses](https://github.com/yt-dlp/yt-dlp/commit/8b8b442cb005a8d85315f301615f83fb736b967a) ([#10456](https://github.com/yt-dlp/yt-dlp/issues/10456)) by [seproDev](https://github.com/seproDev) (With fixes in [16da8ef](https://github.com/yt-dlp/yt-dlp/commit/16da8ef9937ff76632dfef02e5062c5ba99c8ea2))
- [Invalidate nsig cache from < 2024.07.09](https://github.com/yt-dlp/yt-dlp/commit/04e17ba20a139f1b3e30ec4bafa3fba26888f0b3) ([#10401](https://github.com/yt-dlp/yt-dlp/issues/10401)) by [bashonly](https://github.com/bashonly)
- [Reduce android client priority](https://github.com/yt-dlp/yt-dlp/commit/b85eef0a615a01304f88a3847309c667e09a20df) ([#10467](https://github.com/yt-dlp/yt-dlp/issues/10467)) by [seproDev](https://github.com/seproDev)
#### Networking changes
- [Add `legacy_ssl` request extension](https://github.com/yt-dlp/yt-dlp/commit/150ecc45d9cacc919550c13b04fd998ac5103a6b) ([#10448](https://github.com/yt-dlp/yt-dlp/issues/10448)) by [coletdjnz](https://github.com/coletdjnz)
- **Request Handler**: curl_cffi: [Support `curl_cffi` 0.7.X](https://github.com/yt-dlp/yt-dlp/commit/42bfca00a6b460fc053514cdd7ac6f5b5daddf0c) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- **build**
- [Include `curl_cffi` in `yt-dlp_linux`](https://github.com/yt-dlp/yt-dlp/commit/4521f30d1479315cd5c3bf4abdad19391952df98) by [bashonly](https://github.com/bashonly)
- [Pin `curl-cffi` to 0.5.10 for Windows](https://github.com/yt-dlp/yt-dlp/commit/ac30941ae682f71eab010877c9a977736a61d3cf) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [89a161e](https://github.com/yt-dlp/yt-dlp/commit/89a161e8c62569a662deda1c948664152efcb6b4) by [bashonly](https://github.com/bashonly)
### 2024.07.09
#### Core changes
- [Do not alter default format selection when simulated](https://github.com/yt-dlp/yt-dlp/commit/0b570f2a90ce2363ba06089217514d644e7be2e0) ([#9862](https://github.com/yt-dlp/yt-dlp/issues/9862)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **youtube**: [Remove broken `n` function extraction fallback](https://github.com/yt-dlp/yt-dlp/commit/7ead7332af69422cee931aec3faa277288e9e212) ([#10396](https://github.com/yt-dlp/yt-dlp/issues/10396)) by [pukkandan](https://github.com/pukkandan), [seproDev](https://github.com/seproDev)
### 2024.07.08
#### Core changes
- **jsinterp**: [Implement `Function.prototype` resolving for `call` and `apply`](https://github.com/yt-dlp/yt-dlp/commit/6c056ea7aeb03660281653a9668547f2548f194f) ([#10392](https://github.com/yt-dlp/yt-dlp/issues/10392)) by [Grub4K](https://github.com/Grub4K)
#### Extractor changes
- **soundcloud**: [Fix rate-limit handling](https://github.com/yt-dlp/yt-dlp/commit/4b50b292cc98534fb8c7cdf0ae5cb85862f7ebfc) ([#10389](https://github.com/yt-dlp/yt-dlp/issues/10389)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix JS `n` function name extraction](https://github.com/yt-dlp/yt-dlp/commit/297b0a379282a15c80d82d51f3757c961db2dae1) ([#10390](https://github.com/yt-dlp/yt-dlp/issues/10390)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
### 2024.07.07
#### Important changes
- Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)
- A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors
#### Core changes
- [Address gaps in allowed extensions](https://github.com/yt-dlp/yt-dlp/commit/2469119490d7e0397ebbf5c5ae327316f955eef2) ([#10362](https://github.com/yt-dlp/yt-dlp/issues/10362)) by [bashonly](https://github.com/bashonly)
- [Fix `--ignore-no-formats-error`](https://github.com/yt-dlp/yt-dlp/commit/cc767e9490056efaaa11c186b0d032e4b4969180) ([#10345](https://github.com/yt-dlp/yt-dlp/issues/10345)) by [Grub4K](https://github.com/Grub4K)
#### Extractor changes
- **abematv**: [Extract availability](https://github.com/yt-dlp/yt-dlp/commit/2a1a1b8e67e864289ac7ba5d05ec63dbb19a639f) ([#10348](https://github.com/yt-dlp/yt-dlp/issues/10348)) by [middlingphys](https://github.com/middlingphys)
- **chzzk**: [Extract with API v3](https://github.com/yt-dlp/yt-dlp/commit/4862a29854d4044120e3f97b52199711ad04bee1) ([#10363](https://github.com/yt-dlp/yt-dlp/issues/10363)) by [hui1601](https://github.com/hui1601)
- **douyutv**: [Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/commit/6075a029dba70a89675ae1250e7cdfd91f0eba41) ([#10347](https://github.com/yt-dlp/yt-dlp/issues/10347)) by [LeSuisse](https://github.com/LeSuisse)
- **jiosaavn**: playlist: [Support featured playlists](https://github.com/yt-dlp/yt-dlp/commit/f0f867f008a1728f5f6ac1224b9e014b5d27f817) ([#10382](https://github.com/yt-dlp/yt-dlp/issues/10382)) by [harbhim](https://github.com/harbhim)
- **vidyard**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/00766ece0c5c7a80781a4ff677198c5fb69d9dc0) ([#10155](https://github.com/yt-dlp/yt-dlp/issues/10155)) by [exterrestris](https://github.com/exterrestris)
- **vimeo**: [Fix password-protected video extraction](https://github.com/yt-dlp/yt-dlp/commit/c1c9bb4adb42d0d93a2fb5d93a7de0a87b6ba884) ([#10341](https://github.com/yt-dlp/yt-dlp/issues/10341)) by [bashonly](https://github.com/bashonly)
- **vtv**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/987a1f94c24275f2b0cd82e719956687415dd732) ([#10173](https://github.com/yt-dlp/yt-dlp/issues/10173)) by [DinhHuy2010](https://github.com/DinhHuy2010)
- **yle_areena**
- [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/4cdc976bd861b5835601ae402bef543eacd88f3d) ([#10380](https://github.com/yt-dlp/yt-dlp/issues/10380)) by [seproDev](https://github.com/seproDev)
- [Fix subtitle extraction](https://github.com/yt-dlp/yt-dlp/commit/0d174e8bed32081eb38ef7f5d1a1282ae154f517) ([#10379](https://github.com/yt-dlp/yt-dlp/issues/10379)) by [Grub4K](https://github.com/Grub4K)
#### Misc. changes
- **cleanup**: Miscellaneous: [b337d29](https://github.com/yt-dlp/yt-dlp/commit/b337d2989ce0614651d363383f6f743d977248ef) by [bashonly](https://github.com/bashonly)
### 2024.07.02
#### Core changes
- [Fix `--compat-opt allow-unsafe-ext`](https://github.com/yt-dlp/yt-dlp/commit/773bbb181506856ffda95496ab60c1c9603f1f71) ([#10336](https://github.com/yt-dlp/yt-dlp/issues/10336)) by [bashonly](https://github.com/bashonly), [rdamas](https://github.com/rdamas)
#### Extractor changes
- **banbye**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7509791385ba88cb7ec0ab17e826681f4af4b66e) ([#10332](https://github.com/yt-dlp/yt-dlp/issues/10332)) by [PatrykMis](https://github.com/PatrykMis), [seproDev](https://github.com/seproDev)
- **murrtube**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6403530e2dfe259a87afe444708c4f3024cc45b8) ([#9249](https://github.com/yt-dlp/yt-dlp/issues/9249)) by [DrakoCpp](https://github.com/DrakoCpp)
- **zaiko**: [Support JWT video URLs](https://github.com/yt-dlp/yt-dlp/commit/7799e518956387bb3c1064c9beae26eab8d5044a) ([#10130](https://github.com/yt-dlp/yt-dlp/issues/10130)) by [pzhlkj6612](https://github.com/pzhlkj6612)
#### Postprocessor changes
- **embedthumbnail**: [Fix embedding with mutagen](https://github.com/yt-dlp/yt-dlp/commit/d502f4c6d95b74896f40070d07229997f0850f31) ([#10337](https://github.com/yt-dlp/yt-dlp/issues/10337)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **cleanup**: Miscellaneous: [93d33cb](https://github.com/yt-dlp/yt-dlp/commit/93d33cb29af9e2e84369ac43589d50ce8e0160ef) by [bashonly](https://github.com/bashonly)
### 2024.07.01
#### Important changes
- Security: [[CVE-2024-38519](https://nvd.nist.gov/vuln/detail/CVE-2024-38519)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)
- Unsafe extensions are now blocked from being downloaded
#### Core changes
- [Add `playlist_channel` and `playlist_channel_id` fields](https://github.com/yt-dlp/yt-dlp/commit/55e3e6fd21e741ec5ae3d8624de5e5ea345810eb) ([#10266](https://github.com/yt-dlp/yt-dlp/issues/10266)) by [bashonly](https://github.com/bashonly)
- [Disallow unsafe extensions (CVE-2024-38519)](https://github.com/yt-dlp/yt-dlp/commit/5ce582448ececb8d9c30c8c31f58330090ced03a) by [Grub4K](https://github.com/Grub4K)
- **cookies**: [Fix `--cookies-from-browser` DE detection on Linux](https://github.com/yt-dlp/yt-dlp/commit/a8520244b8642880e4d35925e9e49eff94d548de) ([#10237](https://github.com/yt-dlp/yt-dlp/issues/10237)) by [peisenwang](https://github.com/peisenwang)
#### Extractor changes
- **afreecatv**
- [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/e8352ad6599de7b5371dc39a1a1edc7890aaedb4) ([#10174](https://github.com/yt-dlp/yt-dlp/issues/10174)) by [hui1601](https://github.com/hui1601)
- catchstory: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/054a3ba7d1293f9fbe21800d62d1e5ddcbded238) ([#10235](https://github.com/yt-dlp/yt-dlp/issues/10235)) by [hui1601](https://github.com/hui1601)
- **bilibili**: [Support legacy formats](https://github.com/yt-dlp/yt-dlp/commit/1d6ab17d0752ee9cf19e3e63c7dec7b600d3f228) ([#9117](https://github.com/yt-dlp/yt-dlp/issues/9117)) by [c-basalt](https://github.com/c-basalt), [GD-Slime](https://github.com/GD-Slime)
- **bitchute**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/5b1a2aa978d0074cee278e7659f32f52ecc4ab53) ([#10301](https://github.com/yt-dlp/yt-dlp/issues/10301)) by [seproDev](https://github.com/seproDev)
- **brightcove**: [Upgrade requests to HTTPS](https://github.com/yt-dlp/yt-dlp/commit/90c3721a322756bb7f4ca10ceb73744500bee37e) ([#10202](https://github.com/yt-dlp/yt-dlp/issues/10202)) by [bashonly](https://github.com/bashonly)
- **cloudflarestream**: [Fix `_VALID_URL` and embed extraction](https://github.com/yt-dlp/yt-dlp/commit/7aa322c02cec54eb77154a89da7e400194f0bd03) ([#10215](https://github.com/yt-dlp/yt-dlp/issues/10215)) by [bashonly](https://github.com/bashonly)
- **cloudycdn**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/b758877afa225747fba81c8a580e27583a231734) ([#10271](https://github.com/yt-dlp/yt-dlp/issues/10271)) by [Caesim404](https://github.com/Caesim404)
- **digitalconcerthall**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/2a4f2e82dbeeb0c9130883c83dac689d5260c871) ([#10152](https://github.com/yt-dlp/yt-dlp/issues/10152)) by [seproDev](https://github.com/seproDev), [tippfehlr](https://github.com/tippfehlr)
- **facebook**: reel: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/8ca1d57ed08d00efa117820a5a82f763b20e2d1d) ([#10232](https://github.com/yt-dlp/yt-dlp/issues/10232)) by [bashonly](https://github.com/bashonly)
- **francetv**
- [Detect and raise errors for DRM](https://github.com/yt-dlp/yt-dlp/commit/3690c2f59827c79a1bbe388a7c1ae75db7477db2) ([#10165](https://github.com/yt-dlp/yt-dlp/issues/10165)) by [bashonly](https://github.com/bashonly)
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/081708d6074dfbb907e25af61ba530bba0d4b31d) ([#10177](https://github.com/yt-dlp/yt-dlp/issues/10177)) by [bashonly](https://github.com/bashonly)
- **generic**: [Add `key_query` extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/5dbac313ae4e3e8521dfe2e1a6a048a98ff4b4fe) by [bashonly](https://github.com/bashonly)
- **graspop**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1d369b4096d79233e0ac2c93762746a64d7a69c8) ([#10268](https://github.com/yt-dlp/yt-dlp/issues/10268)) by [Niluge-KiWi](https://github.com/Niluge-KiWi)
- **jiocinema**: series: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/61714f46956f61612032bba857aed7ad1387eccd) ([#10139](https://github.com/yt-dlp/yt-dlp/issues/10139)) by [varunchopra](https://github.com/varunchopra)
- **khanacademy**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/4093eb1fcc29a0e2aea9adfcba479787d9ae0c0c) ([#9136](https://github.com/yt-dlp/yt-dlp/issues/9136)) by [c-basalt](https://github.com/c-basalt)
- **laracasts**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/b8da8a98f897599095d4ef1644b8c5fd39921118) ([#10055](https://github.com/yt-dlp/yt-dlp/issues/10055)) by [ASertacAkkaya](https://github.com/ASertacAkkaya), [seproDev](https://github.com/seproDev)
- **matchtv**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/f3411af12e209bc5624e1ac31271b8aabe2d3c90) ([#10190](https://github.com/yt-dlp/yt-dlp/issues/10190)) by [megumintyan](https://github.com/megumintyan)
- **mediasite**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/0953209a857c51648aee89d205c086b0e1dd3864) ([#10273](https://github.com/yt-dlp/yt-dlp/issues/10273)) by [bashonly](https://github.com/bashonly)
- **microsoftembed**: [Add extractors for dev materials](https://github.com/yt-dlp/yt-dlp/commit/9200bc70c94546b2191bb6fbfc9cea98a919cc56) ([#9177](https://github.com/yt-dlp/yt-dlp/issues/9177)) by [c-basalt](https://github.com/c-basalt)
- **mlbtv**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/61edf57f8f13f6dfd81154174e647eb5fdd26089) ([#10296](https://github.com/yt-dlp/yt-dlp/issues/10296)) by [bashonly](https://github.com/bashonly)
- **neteasemusic**: [Extract more formats from new API](https://github.com/yt-dlp/yt-dlp/commit/7a03f88c40b80d3cf54f68edd9d4bdd6aa527570) ([#10258](https://github.com/yt-dlp/yt-dlp/issues/10258)) by [hafeoz](https://github.com/hafeoz)
- **nhkradiru**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b8e2a5e0e1030076f833917906e19bb6c7b318f6) ([#10106](https://github.com/yt-dlp/yt-dlp/issues/10106)) by [garret1317](https://github.com/garret1317)
- **nuum**: [Fix formats extraction](https://github.com/yt-dlp/yt-dlp/commit/aefede25561a06cba398d4f593eee2fbe942693b) ([#10316](https://github.com/yt-dlp/yt-dlp/issues/10316)) by [DmitryScaletta](https://github.com/DmitryScaletta)
- **orf**
- on
- [Add `prefer_segments_playlist` extractor-arg](https://github.com/yt-dlp/yt-dlp/commit/e6a22834df1776ec4e486526f6df2bf53cb7e06f) ([#10314](https://github.com/yt-dlp/yt-dlp/issues/10314)) by [seproDev](https://github.com/seproDev)
- [Support segmented episodes](https://github.com/yt-dlp/yt-dlp/commit/8b46ad4d8b8ee8c5472af0cde863baa89ca3f425) ([#10053](https://github.com/yt-dlp/yt-dlp/issues/10053)) by [seproDev](https://github.com/seproDev)
- **patreoncampaign**: [Fix `campaign_id` extraction](https://github.com/yt-dlp/yt-dlp/commit/2e5a47da400b645aadbda6afd1156bd89c744f48) ([#10070](https://github.com/yt-dlp/yt-dlp/issues/10070)) by [bashonly](https://github.com/bashonly)
- **podbayfm**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/d4b52ce3fcb8d9578ed12365648eaba8718c603e) ([#10195](https://github.com/yt-dlp/yt-dlp/issues/10195)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- **pokergo**: [Make metadata extraction non-fatal](https://github.com/yt-dlp/yt-dlp/commit/36e8dd832579b5375a0f6626af4268b86b4eb21a) ([#10319](https://github.com/yt-dlp/yt-dlp/issues/10319)) by [axpauls](https://github.com/axpauls)
- **qqmusic**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/4f5d7be3c5590bb257d8ff521572aee9839ab754) ([#9768](https://github.com/yt-dlp/yt-dlp/issues/9768)) by [c-basalt](https://github.com/c-basalt)
- **rtvslo.si**: show: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/92a1c4abaeeba9a69d611c57b73555cb1a1f00ad) ([#8418](https://github.com/yt-dlp/yt-dlp/issues/8418)) by [JSubelj](https://github.com/JSubelj), [seproDev](https://github.com/seproDev)
- **soundcloud**: [Fix `download` format extraction](https://github.com/yt-dlp/yt-dlp/commit/e53e56b73543799638fa6abb0c78f8b091aa84e1) ([#10125](https://github.com/yt-dlp/yt-dlp/issues/10125)) by [bashonly](https://github.com/bashonly)
- **sproutvideo**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/d6c2c2bc84f1434255be5c73baeb17d893d2c0d4) ([#10098](https://github.com/yt-dlp/yt-dlp/issues/10098)) by [bashonly](https://github.com/bashonly), [TheZ3ro](https://github.com/TheZ3ro)
- **tiktok**
- [Detect and raise when login is required](https://github.com/yt-dlp/yt-dlp/commit/ea88129784fcbb6987161df9ba05909325d8e2e9) ([#10124](https://github.com/yt-dlp/yt-dlp/issues/10124)) by [bashonly](https://github.com/bashonly)
- [Fix API extraction](https://github.com/yt-dlp/yt-dlp/commit/96472d72f29550c25c5dcedcde02c38c192b0011) ([#10216](https://github.com/yt-dlp/yt-dlp/issues/10216)) by [bashonly](https://github.com/bashonly)
- **tubitv**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/bef9a9e5361fd7a72e21d0f1a8c8afb70d89e8c5) ([#9975](https://github.com/yt-dlp/yt-dlp/issues/9975)) by [chilinux](https://github.com/chilinux)
- series: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d7d861811c15585a4f7ec9d5ae68d2ac28de28a0) ([#10116](https://github.com/yt-dlp/yt-dlp/issues/10116)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/d4b99a233314bf31f9c842035ea9884673d5313a) ([#10327](https://github.com/yt-dlp/yt-dlp/issues/10327)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Extract all formats from multi-language m3u8s](https://github.com/yt-dlp/yt-dlp/commit/9bd85019931927a99b0fe0dc58ac51acca9fbe72) ([#9875](https://github.com/yt-dlp/yt-dlp/issues/9875)) by [bashonly](https://github.com/bashonly), [clienthax](https://github.com/clienthax)
- [Skip formats if nsig decoding fails](https://github.com/yt-dlp/yt-dlp/commit/800ec085ccf98420584d8bb38c20a2c079669b09) ([#10223](https://github.com/yt-dlp/yt-dlp/issues/10223)) by [bashonly](https://github.com/bashonly)
- [Suppress "Unavailable videos are hidden" warning](https://github.com/yt-dlp/yt-dlp/commit/24f3097ea9a470a984d0454dc013cafa2325f5f8) ([#10159](https://github.com/yt-dlp/yt-dlp/issues/10159)) by [mgedmin](https://github.com/mgedmin)
- tab: [Fix channel metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/a0d9967f6822fc279e86bce33464194985148727) ([#10071](https://github.com/yt-dlp/yt-dlp/issues/10071)) by [bashonly](https://github.com/bashonly), [shoxie007](https://github.com/shoxie007)
#### Downloader changes
- **hls**: [Apply `extra_param_to_key_url` from info dict](https://github.com/yt-dlp/yt-dlp/commit/ca8885edd93bdf8912af6c22ee335b6222cb9ba9) by [bashonly](https://github.com/bashonly)
#### Postprocessor changes
- **embedthumbnail**: [Fix postprocessor](https://github.com/yt-dlp/yt-dlp/commit/f2a4ea1794718e4dc0148bc172cb877f1080903b) ([#10248](https://github.com/yt-dlp/yt-dlp/issues/10248)) by [Grub4K](https://github.com/Grub4K)
#### Networking changes
- **Request Handler**: requests: [Bump minimum `requests` version to 2.32.2](https://github.com/yt-dlp/yt-dlp/commit/db50f19d76c6870a5a13d0cab9287d684fd7449a) ([#10079](https://github.com/yt-dlp/yt-dlp/issues/10079)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **build**
- [Bump Pyinstaller to `>=6.7.0` for all builds](https://github.com/yt-dlp/yt-dlp/commit/5fdd13006a1c5d78642c8d3c4c7df0448273c2ae) ([#10069](https://github.com/yt-dlp/yt-dlp/issues/10069)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- [Cache dependencies for `macos` job](https://github.com/yt-dlp/yt-dlp/commit/46c1b7cfec1d0e6155083ca7e6948674c64ecb97) ([#10088](https://github.com/yt-dlp/yt-dlp/issues/10088)) by [bashonly](https://github.com/bashonly)
- [Use `macos-12` image for `yt-dlp_macos`](https://github.com/yt-dlp/yt-dlp/commit/03334d639d5282cd4107edb32c623ba400262fc4) ([#10063](https://github.com/yt-dlp/yt-dlp/issues/10063)) by [bashonly](https://github.com/bashonly)
- **cleanup**
- [Add more ruff rules](https://github.com/yt-dlp/yt-dlp/commit/add96eb9f84cfffe85682bf2fb85135746994ee8) ([#10149](https://github.com/yt-dlp/yt-dlp/issues/10149)) by [seproDev](https://github.com/seproDev)
- [Bump ruff to 0.5.x](https://github.com/yt-dlp/yt-dlp/commit/7814c50948a2b9a4c746441ecbc509ae563d5d1f) ([#10282](https://github.com/yt-dlp/yt-dlp/issues/10282)) by [seproDev](https://github.com/seproDev)
- Miscellaneous: [6aaf96a](https://github.com/yt-dlp/yt-dlp/commit/6aaf96a3d6e7d0d426e97e11a2fcf52fda00e733) by [bashonly](https://github.com/bashonly), [c-basalt](https://github.com/c-basalt), [jucor](https://github.com/jucor), [seproDev](https://github.com/seproDev)
- **test**: download: [Raise on network errors](https://github.com/yt-dlp/yt-dlp/commit/54a63e80af82791d2f0985bd0176bb182963fd5f) ([#10283](https://github.com/yt-dlp/yt-dlp/issues/10283)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
### 2024.05.27
#### Extractor changes

7
Collaborators.md
View file

@ -61,3 +61,10 @@ ## [Grub4K](https://github.com/Grub4K)
* Reworked internals like `traverse_obj`, various core refactors and bugs fixes
* Implemented proper progress reporting for parallel downloads
* Improved/fixed/added Bundestag, crunchyroll, pr0gramm, Twitter, WrestleUniverse etc
## [sepro](https://github.com/seproDev)
* UX improvements: Warn when ffmpeg is missing, warn when double-clicking exe
* Code cleanup: Remove dead extractors, mark extractors as broken, enable/apply ruff rules
* Improved/fixed/added ArdMediathek, DRTV, Floatplane, MagentaMusik, Naver, Nebula, OnDemandKorea, Vbox7 etc

2
Makefile
View file

@ -21,7 +21,7 @@ clean-test:
rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.swp *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS

113
README.md
View file

@ -141,7 +141,7 @@ ## UPDATE
If you [installed with pip](https://github.com/yt-dlp/yt-dlp/wiki/Installation#with-pip), simply re-run the same command that was used to install the program
For other third-party package managers, see [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/Installation#third-party-package-managers) or refer their documentation
For other third-party package managers, see [the wiki](https://github.com/yt-dlp/yt-dlp/wiki/Installation#third-party-package-managers) or refer to their documentation
<a id="update-channels"></a>
@ -184,10 +184,10 @@ ## DEPENDENCIES
### Strongly recommended
* [**ffmpeg** and **ffprobe**](https://www.ffmpeg.org) - Required for [merging separate video and audio files](#format-selection) as well as for various [post-processing](#post-processing-options) tasks. License [depends on the build](https://www.ffmpeg.org/legal.html)
* [**ffmpeg** and **ffprobe**](https://www.ffmpeg.org) - Required for [merging separate video and audio files](#format-selection), as well as for various [post-processing](#post-processing-options) tasks. License [depends on the build](https://www.ffmpeg.org/legal.html)
There are bugs in ffmpeg that cause various issues when used alongside yt-dlp. Since ffmpeg is such an important dependency, we provide [custom builds](https://github.com/yt-dlp/FFmpeg-Builds#ffmpeg-static-auto-builds) with patches for some of these issues at [yt-dlp/FFmpeg-Builds](https://github.com/yt-dlp/FFmpeg-Builds). See [the readme](https://github.com/yt-dlp/FFmpeg-Builds#patches-applied) for details on the specific issues solved by these builds
**Important**: What you need is ffmpeg *binary*, **NOT** [the Python package of the same name](https://pypi.org/project/ffmpeg)
### Networking
@ -198,11 +198,11 @@ ### Networking
#### Impersonation
The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting.
The following provide support for impersonating browser requests. This may be required for some sites that employ TLS fingerprinting.
* [**curl_cffi**](https://github.com/yifeikong/curl_cffi) (recommended) - Python binding for [curl-impersonate](https://github.com/lwthiker/curl-impersonate). Provides impersonation targets for Chrome, Edge and Safari. Licensed under [MIT](https://github.com/yifeikong/curl_cffi/blob/main/LICENSE)
* Can be installed with the `curl-cffi` group, e.g. `pip install "yt-dlp[default,curl-cffi]"`
* Currently only included in `yt-dlp.exe` and `yt-dlp_macos` builds
* Currently included in `yt-dlp.exe`, `yt-dlp_linux` and `yt-dlp_macos` builds
### Metadata
@ -275,7 +275,7 @@ ### Standalone Py2Exe Builds (Windows)
### Related scripts
* **`devscripts/install_deps.py`** - Install dependencies for yt-dlp.
* **`devscripts/update-version.py`** - Update the version number based on current date.
* **`devscripts/update-version.py`** - Update the version number based on the current date.
* **`devscripts/set-variant.py`** - Set the build variant of the executable.
* **`devscripts/make_changelog.py`** - Create a markdown changelog using short commit messages and update `CONTRIBUTORS` file.
* **`devscripts/make_lazy_extractors.py`** - Create lazy extractors. Running this before building the binaries (any variant) will improve their startup performance. Set the environment variable `YTDLP_NO_LAZY_EXTRACTORS=1` if you wish to forcefully disable lazy extractor loading.
@ -368,7 +368,9 @@ ## General Options:
stderr) to apply the setting to. Can be one
of "always", "auto" (default), "never", or
"no_color" (use non color terminal
sequences). Can be used multiple times
sequences). Use "auto-tty" or "no_color-tty"
to decide based on terminal support only.
Can be used multiple times
--compat-options OPTS Options that can help keep compatibility
with youtube-dl or youtube-dlc
configurations by reverting some of the
@ -456,8 +458,8 @@ ## Video Selection:
is not present, and "&" to check multiple
conditions. Use a "\" to escape "&" or
quotes if needed. If used multiple times,
the filter matches if atleast one of the
conditions are met. E.g. --match-filter
the filter matches if at least one of the
conditions is met. E.g. --match-filter
!is_live --match-filter "like_count>?100 &
description~='(?i)\bcats \& dogs\b'" matches
only videos that are not live OR those that
@ -674,7 +676,7 @@ ## Filesystem Options:
PROFILE to load cookies from, and the
CONTAINER name (if Firefox) ("none" for no
container) can be given with their
respective seperators. By default, all
respective separators. By default, all
containers of the most recently accessed
profile are used. Currently supported
keyrings are: basictext, gnomekeyring,
@ -1036,7 +1038,7 @@ ## Post-Processing Options:
--print/--output), "before_dl" (before each
video download), "post_process" (after each
video download; default), "after_move"
(after moving video file to it's final
(after moving video file to its final
locations), "after_video" (after downloading
and processing all formats of a video), or
"playlist" (at end of playlist). This option
@ -1125,7 +1127,7 @@ # CONFIGURATION
* `/etc/yt-dlp/config`
* `/etc/yt-dlp/config.txt`
E.g. with the following configuration file yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
E.g. with the following configuration file, yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
```
# Lines starting with # are comments
@ -1142,7 +1144,7 @@ # Save all videos under YouTube directory in your home directory
-o ~/YouTube/%(title)s.%(ext)s
```
**Note**: Options in configuration file are just the same options aka switches used in regular command line calls; thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. They must also be quoted when necessary as-if it were a UNIX shell.
**Note**: Options in configuration file are just the same options aka switches used in regular command line calls; thus there **must be no whitespace** after `-` or `--`, e.g. `-o` or `--proxy` but not `- o` or `-- proxy`. They must also be quoted when necessary, as if it were a UNIX shell.
You can use `--ignore-config` if you want to disable all configuration files for a particular yt-dlp run. If `--ignore-config` is found inside any configuration file, no further configuration will be loaded. For example, having the option in the portable configuration file prevents loading of home, user, and system configurations. Additionally, (for backward compatibility) if `--ignore-config` is found inside the system configuration file, the user configuration is not loaded.
@ -1154,12 +1156,12 @@ ### Configuration file encoding
### Authentication with netrc
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every yt-dlp execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per-extractor basis. For that you will need to create a `.netrc` file in `--netrc-location` and restrict permissions to read/write by only you:
You may also want to configure automatic credentials storage for extractors that support authentication (by providing login and password with `--username` and `--password`) in order not to pass credentials as command line arguments on every yt-dlp execution and prevent tracking plain text passwords in the shell command history. You can achieve this using a [`.netrc` file](https://stackoverflow.com/tags/.netrc/info) on a per-extractor basis. For that, you will need to create a `.netrc` file in `--netrc-location` and restrict permissions to read/write by only you:
```
touch ${HOME}/.netrc
chmod a-rwx,u+rw ${HOME}/.netrc
```
After that you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase:
After that, you can add credentials for an extractor in the following format, where *extractor* is the name of the extractor in lowercase:
```
machine <extractor> login <username> password <password>
```
@ -1201,7 +1203,7 @@ # OUTPUT TEMPLATE
The field names themselves (the part inside the parenthesis) can also have some special formatting:
1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a dot `.` separator; e.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`. You can do Python slicing with colon `:`; E.g. `%(id.3:7:-1)s`, `%(formats.:.format_id)s`. Curly braces `{}` can be used to build dictionaries with only specific keys; e.g. `%(formats.:.{format_id,height})#j`. An empty field name `%()s` refers to the entire infodict; e.g. `%(.{id,title})s`. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields
1. **Object traversal**: The dictionaries and lists available in metadata can be traversed by using a dot `.` separator; e.g. `%(tags.0)s`, `%(subtitles.en.-1.ext)s`. You can do Python slicing with colon `:`; E.g. `%(id.3:7)s`, `%(id.6:2:-1)s`, `%(formats.:.format_id)s`. Curly braces `{}` can be used to build dictionaries with only specific keys; e.g. `%(formats.:.{format_id,height})#j`. An empty field name `%()s` refers to the entire infodict; e.g. `%(.{id,title})s`. Note that all the fields that become available using this method are not listed below. Use `-j` to see such fields
1. **Arithmetic**: Simple arithmetic can be done on numeric fields using `+`, `-` and `*`. E.g. `%(playlist_index+10)03d`, `%(n_entries+1-playlist_index)d`
@ -1222,7 +1224,7 @@ # OUTPUT TEMPLATE
%(name[.keys][addition][>strf][,alternate][&replacement][|default])[flags][width][.precision][length]type
```
Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. E.g. `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates is empty, that type of file will not be written. E.g. `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video.
Additionally, you can set different output templates for the various metadata files separately from the general output template by specifying the type of file followed by the template separated by a colon `:`. The different file types supported are `subtitle`, `thumbnail`, `description`, `annotation` (deprecated), `infojson`, `link`, `pl_thumbnail`, `pl_description`, `pl_infojson`, `chapter`, `pl_video`. E.g. `-o "%(title)s.%(ext)s" -o "thumbnail:%(title)s\%(title)s.%(ext)s"` will put the thumbnails in a folder with the same name as the video. If any of the templates is empty, that type of file will not be written. E.g. `--write-thumbnail -o "thumbnail:"` will write thumbnails only for playlists and not for video.
<a id="outtmpl-postprocess-note"></a>
@ -1282,13 +1284,15 @@ # OUTPUT TEMPLATE
- `n_entries` (numeric): Total number of extracted items in the playlist
- `playlist_id` (string): Identifier of the playlist that contains the video
- `playlist_title` (string): Name of the playlist that contains the video
- `playlist` (string): `playlist_id` or `playlist_title`
- `playlist` (string): `playlist_title` if available or else `playlist_id`
- `playlist_count` (numeric): Total number of items in the playlist. May not be known if entire playlist is not extracted
- `playlist_index` (numeric): Index of the video in the playlist padded with leading zeros according the final index
- `playlist_autonumber` (numeric): Position of the video in the playlist download queue padded with leading zeros according to the total length of the playlist
- `playlist_uploader` (string): Full name of the playlist uploader
- `playlist_uploader_id` (string): Nickname or id of the playlist uploader
- `webpage_url` (string): A URL to the video webpage which if given to yt-dlp should allow to get the same result again
- `playlist_channel` (string): Display name of the channel that uploaded the playlist
- `playlist_channel_id` (string): Identifier of the channel that uploaded the playlist
- `webpage_url` (string): A URL to the video webpage which, if given to yt-dlp, should yield the same result again
- `webpage_url_basename` (string): The basename of the webpage URL
- `webpage_url_domain` (string): The domain of the webpage URL
- `original_url` (string): The URL given by the user (or same as `webpage_url` for playlist entries)
@ -1304,10 +1308,10 @@ # OUTPUT TEMPLATE
- `chapter_number` (numeric): Number of the chapter the video belongs to
- `chapter_id` (string): Id of the chapter the video belongs to
Available for the video that is an episode of some series or programme:
Available for the video that is an episode of some series or program:
- `series` (string): Title of the series or programme the video episode belongs to
- `series_id` (string): Id of the series or programme the video episode belongs to
- `series` (string): Title of the series or program the video episode belongs to
- `series_id` (string): Id of the series or program the video episode belongs to
- `season` (string): Title of the season the video episode belongs to
- `season_number` (numeric): Number of the season the video episode belongs to
- `season_id` (string): Id of the season the video episode belongs to
@ -1347,9 +1351,9 @@ # OUTPUT TEMPLATE
- `thumbnails_table` (table): The thumbnail format table as printed by `--list-thumbnails`
- `subtitles_table` (table): The subtitle format table as printed by `--list-subs`
- `automatic_captions_table` (table): The automatic subtitle format table as printed by `--list-subs`
Available only after the video is downloaded (`post_process`/`after_move`):
- `filepath`: Actual path of downloaded video file
Available only in `--sponsorblock-chapter-title`:
@ -1364,7 +1368,7 @@ # OUTPUT TEMPLATE
Each aforementioned sequence when referenced in an output template will be replaced by the actual value corresponding to the sequence name. E.g. for `-o %(title)s-%(id)s.%(ext)s` and an mp4 video with title `yt-dlp test video` and id `BaW_jenozKc`, this will result in a `yt-dlp test video-BaW_jenozKc.mp4` file created in the current directory.
**Note**: Some of the sequences are not guaranteed to be present since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
**Note**: Some of the sequences are not guaranteed to be present, since they depend on the metadata obtained by a particular extractor. Such sequences will be replaced with placeholder value provided with `--output-na-placeholder` (`NA` by default).
**Tip**: Look at the `-j` output to identify which fields are available for the particular URL
@ -1442,7 +1446,7 @@ # FORMAT SELECTION
- `all`: Select **all formats** separately
- `mergeall`: Select and **merge all formats** (Must be used with `--audio-multistreams`, `--video-multistreams` or both)
- `b*`, `best*`: Select the best quality format that **contains either** a video or an audio or both (ie; `vcodec!=none or acodec!=none`)
- `b*`, `best*`: Select the best quality format that **contains either** a video or an audio or both (i.e.; `vcodec!=none or acodec!=none`)
- `b`, `best`: Select the best quality format that **contains both** video and audio. Equivalent to `best*[vcodec!=none][acodec!=none]`
- `bv`, `bestvideo`: Select the best quality **video-only** format. Equivalent to `best*[acodec=none]`
- `bv*`, `bestvideo*`: Select the best quality format that **contains video**. It may also contain audio. Equivalent to `best*[vcodec!=none]`
@ -1455,7 +1459,7 @@ # FORMAT SELECTION
- `wa`, `worstaudio`: Select the worst quality audio-only format. Equivalent to `worst*[vcodec=none]`
- `wa*`, `worstaudio*`: Select the worst quality format that contains audio. It may also contain video. Equivalent to `worst*[acodec!=none]`
For example, to download the worst quality video-only format you can use `-f worstvideo`. It is however recommended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-S +size` or more rigorously, `-S +size,+br,+res,+fps` instead of `-f worst`. See [Sorting Formats](#sorting-formats) for more details.
For example, to download the worst quality video-only format you can use `-f worstvideo`. It is, however, recommended not to use `worst` and related options. When your format selector is `worst`, the format which is worst in all respects is selected. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-S +size` or more rigorously, `-S +size,+br,+res,+fps` instead of `-f worst`. See [Sorting Formats](#sorting-formats) for more details.
You can select the n'th best format of a type by using `best<type>.<n>`. For example, `best.2` will select the 2nd best combined format. Similarly, `bv*.3` will select the 3rd best format that contains a video stream.
@ -1505,7 +1509,7 @@ ## Filtering Formats
Any string comparison may be prefixed with negation `!` in order to produce an opposite comparison, e.g. `!*=` (does not contain). The comparand of a string comparison needs to be quoted with either double or single quotes if it contains spaces or special characters other than `._-`.
**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
**Note**: None of the aforementioned meta fields are guaranteed to be present since this solely depends on the metadata obtained by the particular extractor, i.e. the metadata offered by the website. Any other field made available by the extractor can also be used for filtering.
Formats for which the value is not known are excluded unless you put a question mark (`?`) after the operator. You can combine format filters, so `-f "bv[height<=?720][tbr>500]"` selects up to 720p videos (or videos where the height is not known) with a bitrate of at least 500 kbps. You can also use the filters with `all` to download all formats that satisfy the filter, e.g. `-f "all[vcodec=none]"` selects all audio-only formats.
@ -1544,14 +1548,14 @@ ## Sorting Formats
- `abr`: Average audio bitrate in [kbps](## "1000 bits/sec")
- `br`: Average bitrate in [kbps](## "1000 bits/sec"), `tbr`/`vbr`/`abr`
- `asr`: Audio sample rate in Hz
**Deprecation warning**: Many of these fields have (currently undocumented) aliases, that may be removed in a future version. It is recommended to use only the documented field names.
All fields, unless specified otherwise, are sorted in descending order. To reverse this, prefix the field with a `+`. E.g. `+res` prefers format with the smallest resolution. Additionally, you can suffix a preferred value for the fields, separated by a `:`. E.g. `res:720` prefers larger videos, but no larger than 720p and the smallest video if there are no videos less than 720p. For `codec` and `ext`, you can provide two preferred values, the first for video and the second for audio. E.g. `+codec:avc:m4a` (equivalent to `+vcodec:avc,+acodec:m4a`) sets the video codec preference to `h264` > `h265` > `vp9` > `vp9.2` > `av01` > `vp8` > `h263` > `theora` and audio codec preference to `mp4a` > `aac` > `vorbis` > `opus` > `mp3` > `ac3` > `dts`. You can also make the sorting prefer the nearest values to the provided by using `~` as the delimiter. E.g. `filesize~1G` prefers the format with filesize closest to 1 GiB.
The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behaviour can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
The fields `hasvid` and `ie_pref` are always given highest priority in sorting, irrespective of the user-defined order. This behavior can be changed by using `--format-sort-force`. Apart from these, the default order used is: `lang,quality,res,fps,hdr:12,vcodec:vp9.2,channels,acodec,size,br,asr,proto,ext,hasaud,source,id`. The extractors may override this default order, but they cannot override the user-provided order.
Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. dolby vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.
Note that the default has `vcodec:vp9.2`; i.e. `av1` is not preferred. Similarly, the default for hdr is `hdr:12`; i.e. Dolby Vision is not preferred. These choices are made since DV and AV1 formats are not yet fully compatible with most devices. This may be changed in the future as more devices become capable of smoothly playing back these formats.
If your format selector is `worst`, the last item is selected after sorting. This means it will select the format that is worst in all respects. Most of the time, what you actually want is the video with the smallest filesize instead. So it is generally better to use `-f best -S +size,+br,+res,+fps`.
@ -1754,7 +1758,7 @@ # Replace all spaces and "_" in title and uploader with a `-`
# EXTRACTOR ARGUMENTS
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=android_embedded,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Some extractors accept additional arguments which can be passed using `--extractor-args KEY:ARGS`. `ARGS` is a `;` (semicolon) separated string of `ARG=VAL1,VAL2`. E.g. `--extractor-args "youtube:player-client=mediaconnect,web;formats=incomplete" --extractor-args "funimation:version=uncut"`
Note: In CLI, `ARG` can use `-` instead of `_`; e.g. `youtube:player-client"` becomes `youtube:player_client"`
@ -1763,7 +1767,7 @@ # EXTRACTOR ARGUMENTS
#### youtube
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music`, `_embedded`, `_embedscreen`, `_creator` (e.g. `web_embedded`); and `mweb`, `mweb_embedscreen` and `tv_embedded` (agegate bypass) with no variants. By default, `ios,web` is used, but `tv_embedded` and `creator` variants are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. The `android` clients will always be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)
@ -1771,7 +1775,7 @@ #### youtube
* E.g. `all,all,1000,10` will get a maximum of 1000 replies total, with up to 10 replies per thread. `1000,all,100` will get a maximum of 1000 comments, with a maximum of 100 replies total
* `formats`: Change the types of formats to return. `dashy` (convert HTTP to DASH), `duplicate` (identical content but different URLs or protocol; includes `dashy`), `incomplete` (cannot be downloaded completely - live dash and post-live m3u8)
* `innertube_host`: Innertube API host to use for all API requests; e.g. `studio.youtube.com`, `youtubei.googleapis.com`. Note that cookies exported from one subdomain will not work on others
* `innertube_key`: Innertube API key to use for all API requests
* `innertube_key`: Innertube API key to use for all API requests. By default, no API key is used
* `raise_incomplete_data`: `Incomplete Data Received` raises an error instead of reporting a warning
#### youtubetab (YouTube playlists, channels, feeds, etc.)
@ -1779,8 +1783,9 @@ #### youtubetab (YouTube playlists, channels, feeds, etc.)
* `approximate_date`: Extract approximate `upload_date` and `timestamp` in flat-playlist. This may cause date-based filters to be slightly off
#### generic
* `fragment_query`: Passthrough any query in mpd/m3u8 manifest URLs to their fragments if no value is provided, or else apply the query string given as `fragment_query=VALUE`. Does not apply to ffmpeg
* `fragment_query`: Passthrough any query in mpd/m3u8 manifest URLs to their fragments if no value is provided, or else apply the query string given as `fragment_query=VALUE`. Note that if the stream has an HLS AES-128 key, then the query parameters will be passed to the key URI as well, unless the `key_query` extractor-arg is passed, or unless an external key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg
* `variant_query`: Passthrough the master m3u8 URL query to its variant playlist URLs if no value is provided, or else apply the query string given as `variant_query=VALUE`
* `key_query`: Passthrough the master m3u8 URL query to its HLS AES-128 decryption key URI if no value is provided, or else apply the query string given as `key_query=VALUE`. Note that this will have no effect if the key URI is provided via the `hls_key` extractor-arg. Does not apply to ffmpeg
* `hls_key`: An HLS AES-128 key URI *or* key (as hex), and optionally the IV (as hex), in the form of `(URI|KEY)[,IV]`; e.g. `generic:hls_key=ABCDEF1234567980,0xFEDCBA0987654321`. Passing any of these values will force usage of the native HLS downloader and override the corresponding values found in the m3u8 playlist
* `is_live`: Bypass live HLS detection and manually set `live_status` - a value of `false` will set `not_live`, any other value (or no value) will set `is_live`
@ -1848,7 +1853,16 @@ #### afreecatvlive
* `cdn`: One or more CDN IDs to use with the API call for stream URLs, e.g. `gcp_cdn`, `gs_cdn_pc_app`, `gs_cdn_mobile_web`, `gs_cdn_pc_web`
#### soundcloud
* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3`
* `formats`: Formats to request from the API. Requested values should be in the format of `{protocol}_{extension}` (omitting the bitrate), e.g. `hls_opus,http_aac`. The `*` character functions as a wildcard, e.g. `*_mp3`, and can be passed by itself to request all formats. Known protocols include `http`, `hls` and `hls-aes`; known extensions include `aac`, `opus` and `mp3`. Original `download` formats are always extracted. Default is `http_aac,hls_aac,http_opus,hls_opus,http_mp3,hls_mp3`
#### orfon (orf:on)
* `prefer_segments_playlist`: Prefer a playlist of program segments instead of a single complete video when available. If individual segments are desired, use `--concat-playlist never --extractor-args "orfon:prefer_segments_playlist"`
#### bilibili
* `prefer_multi_flv`: Prefer extracting flv formats over mp4 for older videos that still provide legacy formats
#### digitalconcerthall
* `prefer_combined_hls`: Prefer extracting combined/pre-merged video and audio HLS formats. This will exclude 4K/HEVC video and lossless/FLAC audio formats, which are only available as split video/audio HLS formats
**Note**: These options may be changed/removed in the future without concern for backward compatibility
@ -1859,16 +1873,16 @@ # PLUGINS
Note that **all** plugins are imported even if not invoked, and that **there are no checks** performed on plugin code. **Use plugins at your own risk and only if you trust the code!**
Plugins can be of `<type>`s `extractor` or `postprocessor`.
- Extractor plugins do not need to be enabled from the CLI and are automatically invoked when the input URL is suitable for it.
- Extractor plugins take priority over builtin extractors.
Plugins can be of `<type>`s `extractor` or `postprocessor`.
- Extractor plugins do not need to be enabled from the CLI and are automatically invoked when the input URL is suitable for it.
- Extractor plugins take priority over built-in extractors.
- Postprocessor plugins can be invoked using `--use-postprocessor NAME`.
Plugins are loaded from the namespace packages `yt_dlp_plugins.extractor` and `yt_dlp_plugins.postprocessor`.
In other words, the file structure on the disk looks something like:
yt_dlp_plugins/
extractor/
myplugin.py
@ -1916,7 +1930,7 @@ ## Developing Plugins
See the [yt-dlp-sample-plugins](https://github.com/yt-dlp/yt-dlp-sample-plugins) repo for a template plugin package and the [Plugin Development](https://github.com/yt-dlp/yt-dlp/wiki/Plugin-Development) section of the wiki for a plugin development guide.
All public classes with a name ending in `IE`/`PP` are imported from each file for extractors and postprocessors repectively. This respects underscore prefix (e.g. `_MyBasePluginIE` is private) and `__all__`. Modules can similarly be excluded by prefixing the module name with an underscore (e.g. `_myplugin.py`).
All public classes with a name ending in `IE`/`PP` are imported from each file for extractors and postprocessors respectively. This respects underscore prefix (e.g. `_MyBasePluginIE` is private) and `__all__`. Modules can similarly be excluded by prefixing the module name with an underscore (e.g. `_myplugin.py`).
To replace an existing extractor with a subclass of one, set the `plugin_name` class keyword argument (e.g. `class MyPluginIE(ABuiltInIE, plugin_name='myplugin')` will replace `ABuiltInIE` with `MyPluginIE`). Since the extractor replaces the parent, you should exclude the subclass extractor from being imported separately by making it private using one of the methods described above.
@ -1928,7 +1942,7 @@ # EMBEDDING YT-DLP
yt-dlp makes the best effort to be a good command-line program, and thus should be callable from any programming language.
Your program should avoid parsing the normal stdout since they may change in future versions. Instead they should use options such as `-J`, `--print`, `--progress-template`, `--exec` etc to create console output that you can reliably reproduce and parse.
Your program should avoid parsing the normal stdout since they may change in future versions. Instead, they should use options such as `-J`, `--print`, `--progress-template`, `--exec` etc to create console output that you can reliably reproduce and parse.
From a Python program, you can embed yt-dlp in a more powerful fashion, like this:
@ -2210,16 +2224,25 @@ ### Differences in default behavior
* yt-dlp versions between 2021.11.10 and 2023.06.21 estimated `filesize_approx` values for fragmented/manifest formats. This was added for convenience in [f2fe69](https://github.com/yt-dlp/yt-dlp/commit/f2fe69c7b0d208bdb1f6292b4ae92bc1e1a7444a), but was reverted in [0dff8e](https://github.com/yt-dlp/yt-dlp/commit/0dff8e4d1e6e9fb938f4256ea9af7d81f42fd54f) due to the potentially extreme inaccuracy of the estimated values. Use `--compat-options manifest-filesize-approx` to keep extracting the estimated values
* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
* The sub-modules `swfinterp`, `casefold` are removed.
* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
For ease of use, a few more compat options are available:
* `--compat-options all`: Use all compat options (Do NOT use)
* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx`
* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx`
* `--compat-options all`: Use all compat options (**Do NOT use this!**)
* `--compat-options youtube-dl`: Same as `--compat-options all,-multistreams,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
* `--compat-options youtube-dlc`: Same as `--compat-options all,-no-live-chat,-no-youtube-channel-redirect,-playlist-match-filter,-manifest-filesize-approx,-allow-unsafe-ext`
* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization,no-youtube-prefer-utc-upload-date`
* `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
* `--compat-options 2023`: Currently does nothing. Use this to enable all future compat options
The following compat options restore vulnerable behavior from before security patches:
* `--compat-options allow-unsafe-ext`: Allow files with any extension (including unsafe ones) to be downloaded ([GHSA-79w7-vh3h-8g4j](<https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j>))
> :warning: Only use if a valid file download is rejected because its extension is detected as uncommon
>
> **This option can enable remote code execution! Consider [opening an issue](<https://github.com/yt-dlp/yt-dlp/issues/new/choose>) instead!**
### Deprecated options
These are all the deprecated options and the current alternative to achieve the same effect

2
bundle/docker/static/entrypoint.sh
View file

@ -2,7 +2,7 @@
set -e
source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
python -m devscripts.install_deps --include secretstorage
python -m devscripts.install_deps --include secretstorage --include curl-cffi
python -m devscripts.make_lazy_extractors
python devscripts/update-version.py -c "${channel}" -r "${origin}" "${version}"
python -m bundle.pyinstaller

2
bundle/py2exe.py
View file

@ -44,7 +44,7 @@ def main():
'Cryptodome',
# requests >=2.32.0 breaks py2exe builds due to certifi dependency
'requests',
'urllib3'
'urllib3',
],
'dll_excludes': ['w9xpopen.exe', 'crypt32.dll'],
# Modules that are only imported dynamically must be added here

8
bundle/pyinstaller.py
View file

@ -68,7 +68,7 @@ def exe(onedir):
'dist/',
onedir and f'{name}/',
name,
OS_NAME == 'win32' and '.exe'
OS_NAME == 'win32' and '.exe',
)))
@ -113,7 +113,7 @@ def windows_set_version(exe, version):
),
kids=[
StringFileInfo([StringTable('040904B0', [
StringStruct('Comments', 'yt-dlp%s Command Line Interface' % suffix),
StringStruct('Comments', f'yt-dlp{suffix} Command Line Interface'),
StringStruct('CompanyName', 'https://github.com/yt-dlp'),
StringStruct('FileDescription', 'yt-dlp%s' % (MACHINE and f' ({MACHINE})')),
StringStruct('FileVersion', version),
@ -123,8 +123,8 @@ def windows_set_version(exe, version):
StringStruct('ProductName', f'yt-dlp{suffix}'),
StringStruct(
'ProductVersion', f'{version}{suffix} on Python {platform.python_version()}'),
])]), VarFileInfo([VarStruct('Translation', [0, 1200])])
]
])]), VarFileInfo([VarStruct('Translation', [0, 1200])]),
],
))

8
devscripts/bash-completion.py
View file

@ -9,8 +9,8 @@
import yt_dlp
BASH_COMPLETION_FILE = "completions/bash/yt-dlp"
BASH_COMPLETION_TEMPLATE = "devscripts/bash-completion.in"
BASH_COMPLETION_FILE = 'completions/bash/yt-dlp'
BASH_COMPLETION_TEMPLATE = 'devscripts/bash-completion.in'
def build_completion(opt_parser):
@ -21,9 +21,9 @@ def build_completion(opt_parser):
opts_flag.append(option.get_opt_string())
with open(BASH_COMPLETION_TEMPLATE) as f:
template = f.read()
with open(BASH_COMPLETION_FILE, "w") as f:
with open(BASH_COMPLETION_FILE, 'w') as f:
# just using the special char
filled_template = template.replace("{{flags}}", " ".join(opts_flag))
filled_template = template.replace('{{flags}}', ' '.join(opts_flag))
f.write(filled_template)

16
devscripts/changelog_override.json
View file

@ -169,5 +169,21 @@
"when": "5c019f6328ad40d66561eac3c4de0b3cd070d0f6",
"short": "[cleanup] Misc (#9765)",
"authors": ["bashonly", "Grub4K", "seproDev"]
},
{
"action": "change",
"when": "e6a22834df1776ec4e486526f6df2bf53cb7e06f",
"short": "[ie/orf:on] Add `prefer_segments_playlist` extractor-arg (#10314)",
"authors": ["seproDev"]
},
{
"action": "add",
"when": "6aaf96a3d6e7d0d426e97e11a2fcf52fda00e733",
"short": "[priority] Security: [[CVE-2024-38519](https://nvd.nist.gov/vuln/detail/CVE-2024-38519)] [Properly sanitize file-extension to prevent file system modification and RCE](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-79w7-vh3h-8g4j)\n - Unsafe extensions are now blocked from being downloaded"
},
{
"action": "add",
"when": "6075a029dba70a89675ae1250e7cdfd91f0eba41",
"short": "[priority] Security: [[ie/douyutv] Do not use dangerous javascript source/URL](https://github.com/yt-dlp/yt-dlp/security/advisories/GHSA-3v33-3wmw-3785)\n - A dependency on potentially malicious third-party JavaScript code has been removed from the Douyu extractors"
}
]

2
devscripts/cli_to_api.py Normal file → Executable file
View file

@ -1,3 +1,5 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys

10
devscripts/make_changelog.py
View file

@ -223,10 +223,10 @@ def format_single_change(self, info: CommitInfo):
return message if not sep else f'{message}{sep}{rest}'
def _format_message_link(self, message, hash):
assert message or hash, 'Improperly defined commit message or override'
message = message if message else hash[:HASH_LENGTH]
return f'[{message}]({self.repo_url}/commit/{hash})' if hash else message
def _format_message_link(self, message, commit_hash):
assert message or commit_hash, 'Improperly defined commit message or override'
message = message if message else commit_hash[:HASH_LENGTH]
return f'[{message}]({self.repo_url}/commit/{commit_hash})' if commit_hash else message
def _format_issues(self, issues):
return ', '.join(f'[#{issue}]({self.repo_url}/issues/{issue})' for issue in issues)
@ -356,7 +356,7 @@ def apply_overrides(self, overrides):
logger.info(f'CHANGE {self._commits[commit.hash]} -> {commit}')
self._commits[commit.hash] = commit
self._commits = {key: value for key, value in reversed(self._commits.items())}
self._commits = dict(reversed(self._commits.items()))
def groups(self):
group_dict = defaultdict(list)

12
devscripts/make_readme.py
View file

@ -51,7 +51,7 @@ def apply_patch(text, patch):
),
( # Headings
r'(?m)^ (\w.+\n)( (?=\w))?',
r'## \1'
r'## \1',
),
( # Fixup `--date` formatting
rf'(?m)( --date DATE.+({delim}[^\[]+)*)\[.+({delim}.+)*$',
@ -61,26 +61,26 @@ def apply_patch(text, patch):
),
( # Do not split URLs
rf'({delim[:-1]})? (?P<label>\[\S+\] )?(?P<url>https?({delim})?:({delim})?/({delim})?/(({delim})?\S+)+)\s',
lambda mobj: ''.join((delim, mobj.group('label') or '', re.sub(r'\s+', '', mobj.group('url')), '\n'))
lambda mobj: ''.join((delim, mobj.group('label') or '', re.sub(r'\s+', '', mobj.group('url')), '\n')),
),
( # Do not split "words"
rf'(?m)({delim}\S+)+$',
lambda mobj: ''.join((delim, mobj.group(0).replace(delim, '')))
lambda mobj: ''.join((delim, mobj.group(0).replace(delim, ''))),
),
( # Allow overshooting last line
rf'(?m)^(?P<prev>.+)${delim}(?P<current>.+)$(?!{delim})',
lambda mobj: (mobj.group().replace(delim, ' ')
if len(mobj.group()) - len(delim) + 1 <= max_width + ALLOWED_OVERSHOOT
else mobj.group())
else mobj.group()),
),
( # Avoid newline when a space is available b/w switch and description
DISABLE_PATCH, # This creates issues with prepare_manpage
r'(?m)^(\s{4}-.{%d})(%s)' % (switch_col_width - 6, delim),
r'\1 '
r'\1 ',
),
( # Replace brackets with a Markdown link
r'SponsorBlock API \((http.+)\)',
r'[SponsorBlock API](\1)'
r'[SponsorBlock API](\1)',
),
)

2
devscripts/set-variant.py
View file

@ -30,7 +30,7 @@ def property_setter(name, value):
opts = parse_options()
transform = compose_functions(
property_setter('VARIANT', opts.variant),
property_setter('UPDATE_HINT', opts.update_message)
property_setter('UPDATE_HINT', opts.update_message),
)
write_file(VERSION_FILE, transform(read_file(VERSION_FILE)))

2
devscripts/update-version.py
View file

@ -24,7 +24,7 @@ def get_new_version(version, revision):
else:
old_version = read_version().split('.')
if version.split('.') == old_version[:3]:
revision = str(int((old_version + [0])[3]) + 1)
revision = str(int(([*old_version, 0])[3]) + 1)
return f'{version}.{revision}' if revision else version

16
devscripts/zsh-completion.py
View file

@ -9,15 +9,15 @@
import yt_dlp
ZSH_COMPLETION_FILE = "completions/zsh/_yt-dlp"
ZSH_COMPLETION_TEMPLATE = "devscripts/zsh-completion.in"
ZSH_COMPLETION_FILE = 'completions/zsh/_yt-dlp'
ZSH_COMPLETION_TEMPLATE = 'devscripts/zsh-completion.in'
def build_completion(opt_parser):
opts = [opt for group in opt_parser.option_groups
for opt in group.option_list]
opts_file = [opt for opt in opts if opt.metavar == "FILE"]
opts_dir = [opt for opt in opts if opt.metavar == "DIR"]
opts_file = [opt for opt in opts if opt.metavar == 'FILE']
opts_dir = [opt for opt in opts if opt.metavar == 'DIR']
fileopts = []
for opt in opts_file:
@ -38,11 +38,11 @@ def build_completion(opt_parser):
with open(ZSH_COMPLETION_TEMPLATE) as f:
template = f.read()
template = template.replace("{{fileopts}}", "|".join(fileopts))
template = template.replace("{{diropts}}", "|".join(diropts))
template = template.replace("{{flags}}", " ".join(flags))
template = template.replace('{{fileopts}}', '|'.join(fileopts))
template = template.replace('{{diropts}}', '|'.join(diropts))
template = template.replace('{{flags}}', ' '.join(flags))
with open(ZSH_COMPLETION_FILE, "w") as f:
with open(ZSH_COMPLETION_FILE, 'w') as f:
f.write(template)

138
pyproject.toml
View file

@ -9,6 +9,7 @@ maintainers = [
{name = "Grub4K", email = "contact@grub4k.xyz"},
{name = "bashonly", email = "bashonly@protonmail.com"},
{name = "coletdjnz", email = "coletdjnz@protonmail.com"},
{name = "sepro", email = "sepro@sepr0.com"},
]
description = "A feature-rich command-line audio/video downloader"
readme = "README.md"
@ -53,7 +54,10 @@ dependencies = [
[project.optional-dependencies]
default = []
curl-cffi = ["curl-cffi==0.5.10; implementation_name=='cpython'"]
curl-cffi = [
"curl-cffi==0.5.10; os_name=='nt' and implementation_name=='cpython'",
"curl-cffi>=0.5.10,!=0.6.*,<0.8; os_name!='nt' and implementation_name=='cpython'",
]
secretstorage = [
"cffi",
"secretstorage",
@ -62,7 +66,7 @@ build = [
"build",
"hatchling",
"pip",
"setuptools",
"setuptools>=71.0.2", # 71.0.0 broke pyinstaller
"wheel",
]
dev = [
@ -72,7 +76,7 @@ dev = [
]
static-analysis = [
"autopep8~=2.0",
"ruff~=0.4.4",
"ruff~=0.5.0",
]
test = [
"pytest~=8.1",
@ -183,21 +187,85 @@ line-length = 120
[tool.ruff.lint]
ignore = [
"E402", # module level import not at top of file
"E501", # line too long
"E731", # do not assign a lambda expression, use a def
"E741", # ambiguous variable name
"E402", # module-import-not-at-top-of-file
"E501", # line-too-long
"E731", # lambda-assignment
"E741", # ambiguous-variable-name
"UP036", # outdated-version-block
"B006", # mutable-argument-default
"B008", # function-call-in-default-argument
"B011", # assert-false
"B017", # assert-raises-exception
"B023", # function-uses-loop-variable (false positives)
"B028", # no-explicit-stacklevel
"B904", # raise-without-from-inside-except
"C401", # unnecessary-generator-set
"C402", # unnecessary-generator-dict
"PIE790", # unnecessary-placeholder
"SIM102", # collapsible-if
"SIM108", # if-else-block-instead-of-if-exp
"SIM112", # uncapitalized-environment-variables
"SIM113", # enumerate-for-loop
"SIM114", # if-with-same-arms
"SIM115", # open-file-with-context-handler
"SIM117", # multiple-with-statements
"SIM223", # expr-and-false
"SIM300", # yoda-conditions
"TD001", # invalid-todo-tag
"TD002", # missing-todo-author
"TD003", # missing-todo-link
"PLE0604", # invalid-all-object (false positives)
"PLE0643", # potential-index-error (false positives)
"PLW0603", # global-statement
"PLW1510", # subprocess-run-without-check
"PLW2901", # redefined-loop-name
"RUF001", # ambiguous-unicode-character-string
"RUF012", # mutable-class-default
"RUF100", # unused-noqa (flake8 has slightly different behavior)
]
select = [
"E", # pycodestyle errors
"W", # pycodestyle warnings
"F", # pyflakes
"I", # import order
"E", # pycodestyle Error
"W", # pycodestyle Warning
"F", # Pyflakes
"I", # isort
"Q", # flake8-quotes
"N803", # invalid-argument-name
"N804", # invalid-first-argument-name-for-class-method
"UP", # pyupgrade
"B", # flake8-bugbear
"A", # flake8-builtins
"COM", # flake8-commas
"C4", # flake8-comprehensions
"FA", # flake8-future-annotations
"ISC", # flake8-implicit-str-concat
"ICN003", # banned-import-from
"PIE", # flake8-pie
"T20", # flake8-print
"RSE", # flake8-raise
"RET504", # unnecessary-assign
"SIM", # flake8-simplify
"TID251", # banned-api
"TD", # flake8-todos
"PLC", # Pylint Convention
"PLE", # Pylint Error
"PLW", # Pylint Warning
"RUF", # Ruff-specific rules
]
[tool.ruff.lint.per-file-ignores]
"devscripts/lazy_load_template.py" = ["F401"]
"!yt_dlp/extractor/**.py" = ["I"]
"devscripts/lazy_load_template.py" = [
"F401", # unused-import
]
"!yt_dlp/extractor/**.py" = [
"I", # isort
"ICN003", # banned-import-from
"T20", # flake8-print
"A002", # builtin-argument-shadowing
"C408", # unnecessary-collection-call
]
"yt_dlp/jsinterp.py" = [
"UP031", # printf-string-formatting
]
[tool.ruff.lint.isort]
known-first-party = [
@ -207,6 +275,50 @@ known-first-party = [
]
relative-imports-order = "closest-to-furthest"
[tool.ruff.lint.flake8-quotes]
docstring-quotes = "double"
multiline-quotes = "single"
inline-quotes = "single"
avoid-escape = false
[tool.ruff.lint.pep8-naming]
classmethod-decorators = [
"yt_dlp.utils.classproperty",
]
[tool.ruff.lint.flake8-import-conventions]
banned-from = [
"base64",
"datetime",
"functools",
"glob",
"hashlib",
"itertools",
"json",
"math",
"os",
"pathlib",
"random",
"re",
"string",
"sys",
"time",
"urllib.parse",
"uuid",
"xml",
]
[tool.ruff.lint.flake8-tidy-imports.banned-api]
"yt_dlp.compat.compat_str".msg = "Use `str` instead."
"yt_dlp.compat.compat_b64decode".msg = "Use `base64.b64decode` instead."
"yt_dlp.compat.compat_urlparse".msg = "Use `urllib.parse` instead."
"yt_dlp.compat.compat_parse_qs".msg = "Use `urllib.parse.parse_qs` instead."
"yt_dlp.compat.compat_urllib_parse_unquote".msg = "Use `urllib.parse.unquote` instead."
"yt_dlp.compat.compat_urllib_parse_urlencode".msg = "Use `urllib.parse.urlencode` instead."
"yt_dlp.compat.compat_urllib_parse_urlparse".msg = "Use `urllib.parse.urlparse` instead."
"yt_dlp.compat.compat_shlex_quote".msg = "Use `yt_dlp.utils.shell_quote` instead."
"yt_dlp.utils.error_to_compat_str".msg = "Use `str` instead."
[tool.autopep8]
max_line_length = 120
recursive = true

38
supportedsites.md
View file

@ -46,6 +46,7 @@ # Supported sites
- **aenetworks:show**
- **AeonCo**
- **afreecatv**: [*afreecatv*](## "netrc machine") afreecatv.com
- **afreecatv:catchstory**: [*afreecatv*](## "netrc machine") afreecatv.com catch story
- **afreecatv:live**: [*afreecatv*](## "netrc machine") afreecatv.com livestreams
- **afreecatv:user**
- **AirTV**
@ -353,7 +354,6 @@ # Supported sites
- **DigitallySpeaking**
- **Digiteka**
- **DiscogsReleasePlaylist**
- **Discovery**
- **DiscoveryLife**
- **DiscoveryNetworksDe**
- **DiscoveryPlus**
@ -362,7 +362,6 @@ # Supported sites
- **DiscoveryPlusItaly**
- **DiscoveryPlusItalyShow**
- **Disney**
- **DIYNetwork**
- **dlf**
- **dlf:corpus**: DLF Multi-feed Archives
- **dlive:stream**
@ -515,7 +514,6 @@ # Supported sites
- **GlattvisionTVLive**: [*glattvisiontv*](## "netrc machine")
- **GlattvisionTVRecordings**: [*glattvisiontv*](## "netrc machine")
- **Glide**: Glide mobile video messages (glide.me)
- **GlobalCyclingNetworkPlus**
- **GlobalPlayerAudio**
- **GlobalPlayerAudioEpisode**
- **GlobalPlayerLive**
@ -542,6 +540,7 @@ # Supported sites
- **Goshgay**
- **GoToStage**
- **GPUTechConf**
- **Graspop**
- **Gronkh**
- **gronkh:feed**
- **gronkh:vods**
@ -656,10 +655,11 @@ # Supported sites
- **Ketnet**
- **khanacademy**
- **khanacademy:unit**
- **Kick**
- **kick:clips**
- **kick:live**
- **kick:vod**
- **Kicker**
- **KickStarter**
- **KickVOD**
- **kinja:embed**
- **KinoPoisk**
- **Kommunetv**
@ -678,6 +678,8 @@ # Supported sites
- **la7.it**
- **la7.it:​pod:episode**
- **la7.it:podcast**
- **laracasts**
- **laracasts:series**
- **LastFM**
- **LastFMPlaylist**
- **LastFMUser**
@ -689,6 +691,7 @@ # Supported sites
- **Lcp**
- **LcpPlay**
- **Le**: 乐视网
- **LearningOnScreen**
- **Lecture2Go**: (**Currently broken**)
- **Lecturio**: [*lecturio*](## "netrc machine")
- **LecturioCourse**: [*lecturio*](## "netrc machine")
@ -775,7 +778,12 @@ # Supported sites
- **MelonVOD**
- **Metacritic**
- **mewatch**
- **MicrosoftBuild**
- **MicrosoftEmbed**
- **MicrosoftLearnEpisode**
- **MicrosoftLearnPlaylist**
- **MicrosoftLearnSession**
- **MicrosoftMedius**
- **microsoftstream**: Microsoft Stream
- **mildom**: Record ongoing live by specific user in Mildom
- **mildom:clip**: Clip in Mildom
@ -811,8 +819,6 @@ # Supported sites
- **MotherlessGroup**
- **MotherlessUploader**
- **Motorsport**: motorsport.com (**Currently broken**)
- **MotorTrend**
- **MotorTrendOnDemand**
- **MovieFap**
- **Moviepilot**
- **MoviewPlay**
@ -830,7 +836,7 @@ # Supported sites
- **MTVUutisetArticle**: (**Currently broken**)
- **MuenchenTV**: münchen.tv (**Currently broken**)
- **MujRozhlas**
- **Murrtube**: (**Currently broken**)
- **Murrtube**
- **MurrtubeUser**: Murrtube user profile (**Currently broken**)
- **MuseAI**
- **MuseScore**
@ -838,8 +844,6 @@ # Supported sites
- **MusicdexArtist**
- **MusicdexPlaylist**
- **MusicdexSong**
- **mva**: Microsoft Virtual Academy videos
- **mva:course**: Microsoft Virtual Academy courses
- **Mx3**
- **Mx3Neo**
- **Mx3Volksmusik**
@ -1131,13 +1135,13 @@ # Supported sites
- **QingTing**
- **qqmusic**: QQ音乐
- **qqmusic:album**: QQ音乐 - 专辑
- **qqmusic:mv**: QQ音乐 - MV
- **qqmusic:playlist**: QQ音乐 - 歌单
- **qqmusic:singer**: QQ音乐 - 歌手
- **qqmusic:toplist**: QQ音乐 - 排行榜
- **QuantumTV**: [*quantumtv*](## "netrc machine")
- **QuantumTVLive**: [*quantumtv*](## "netrc machine")
- **QuantumTVRecordings**: [*quantumtv*](## "netrc machine")
- **Qub**
- **R7**: (**Currently broken**)
- **R7Article**: (**Currently broken**)
- **Radiko**
@ -1237,6 +1241,7 @@ # Supported sites
- **rtve.es:television**
- **RTVS**
- **rtvslo.si**
- **rtvslo.si:show**
- **RudoVideo**
- **Rule34Video**
- **Rumble**
@ -1360,6 +1365,7 @@ # Supported sites
- **SpreakerShowPage**
- **SpringboardPlatform**
- **Sprout**
- **SproutVideo**
- **sr:mediathek**: Saarländischer Rundfunk (**Currently broken**)
- **SRGSSR**
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
@ -1494,8 +1500,8 @@ # Supported sites
- **Tube8**: (**Currently broken**)
- **TubeTuGraz**: [*tubetugraz*](## "netrc machine") tube.tugraz.at
- **TubeTuGrazSeries**: [*tubetugraz*](## "netrc machine")
- **TubiTv**: [*tubitv*](## "netrc machine")
- **TubiTvShow**
- **tubitv**: [*tubitv*](## "netrc machine")
- **tubitv:series**
- **Tumblr**: [*tumblr*](## "netrc machine")
- **TuneInPodcast**
- **TuneInPodcastEpisode**
@ -1512,9 +1518,9 @@ # Supported sites
- **tv5unis**
- **tv5unis:video**
- **tv8.it**
- **TVA**
- **TVANouvelles**
- **TVANouvellesArticle**
- **tvaplus**: TVA+
- **TVC**
- **TVCArticle**
- **TVer**
@ -1607,6 +1613,8 @@ # Supported sites
- **VidioPremier**: [*vidio*](## "netrc machine")
- **VidLii**
- **Vidly**
- **vids.io**
- **Vidyard**
- **viewlift**
- **viewlift:embed**
- **Viidea**
@ -1654,6 +1662,8 @@ # Supported sites
- **VRT**: VRT NWS, Flanders News, Flandern Info and Sporza
- **VrtNU**: [*vrtnu*](## "netrc machine") VRT MAX
- **VTM**: (**Currently broken**)
- **VTV**
- **VTVGo**
- **VTXTV**: [*vtxtv*](## "netrc machine")
- **VTXTVLive**: [*vtxtv*](## "netrc machine")
- **VTXTVRecordings**: [*vtxtv*](## "netrc machine")

10
test/conftest.py
View file

@ -22,8 +22,8 @@ def handler(request):
class HandlerWrapper(handler):
RH_KEY = handler.RH_KEY
def __init__(self, *args, **kwargs):
super().__init__(logger=FakeLogger, *args, **kwargs)
def __init__(self, **kwargs):
super().__init__(logger=FakeLogger, **kwargs)
return HandlerWrapper
@ -54,11 +54,11 @@ def skip_handlers_if(request, handler):
def pytest_configure(config):
config.addinivalue_line(
"markers", "skip_handler(handler): skip test for the given handler",
'markers', 'skip_handler(handler): skip test for the given handler',
)
config.addinivalue_line(
"markers", "skip_handler_if(handler): skip test for the given handler if condition is true"
'markers', 'skip_handler_if(handler): skip test for the given handler if condition is true',
)
config.addinivalue_line(
"markers", "skip_handlers_if(handler): skip test for handlers when the condition is true"
'markers', 'skip_handlers_if(handler): skip test for handlers when the condition is true',
)

32
test/helper.py
View file

@ -16,8 +16,8 @@
import pytest
is_download_test = pytest.mark.download
else:
def is_download_test(testClass):
return testClass
def is_download_test(test_class):
return test_class
def get_params(override=None):
@ -45,10 +45,10 @@ def try_rm(filename):
def report_warning(message, *args, **kwargs):
'''
"""
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
"""
if sys.stderr.isatty() and compat_os_name != 'nt':
_msg_header = '\033[0;33mWARNING:\033[0m'
else:
@ -138,15 +138,14 @@ def expect_value(self, got, expected, field):
elif isinstance(expected, list) and isinstance(got, list):
self.assertEqual(
len(expected), len(got),
'Expect a list of length %d, but got a list of length %d for field %s' % (
len(expected), len(got), field))
f'Expect a list of length {len(expected)}, but got a list of length {len(got)} for field {field}')
for index, (item_got, item_expected) in enumerate(zip(got, expected)):
type_got = type(item_got)
type_expected = type(item_expected)
self.assertEqual(
type_expected, type_got,
'Type mismatch for list item at index %d for field %s, expected %r, got %r' % (
index, field, type_expected, type_got))
f'Type mismatch for list item at index {index} for field {field}, '
f'expected {type_expected!r}, got {type_got!r}')
expect_value(self, item_got, item_expected, field)
else:
if isinstance(expected, str) and expected.startswith('md5:'):
@ -224,7 +223,7 @@ def sanitize(key, value):
test_info_dict.pop('display_id')
# Remove deprecated fields
for old in YoutubeDL._deprecated_multivalue_fields.keys():
for old in YoutubeDL._deprecated_multivalue_fields:
test_info_dict.pop(old, None)
# release_year may be generated from release_date
@ -246,11 +245,11 @@ def expect_info_dict(self, got_dict, expected_dict):
if expected_dict.get('ext'):
mandatory_fields.extend(('url', 'ext'))
for key in mandatory_fields:
self.assertTrue(got_dict.get(key), 'Missing mandatory field %s' % key)
self.assertTrue(got_dict.get(key), f'Missing mandatory field {key}')
# Check for mandatory fields that are automatically set by YoutubeDL
if got_dict.get('_type', 'video') == 'video':
for key in ['webpage_url', 'extractor', 'extractor_key']:
self.assertTrue(got_dict.get(key), 'Missing field: %s' % key)
self.assertTrue(got_dict.get(key), f'Missing field: {key}')
test_info_dict = sanitize_got_info_dict(got_dict)
@ -258,7 +257,7 @@ def expect_info_dict(self, got_dict, expected_dict):
if missing_keys:
def _repr(v):
if isinstance(v, str):
return "'%s'" % v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n')
return "'{}'".format(v.replace('\\', '\\\\').replace("'", "\\'").replace('\n', '\\n'))
elif isinstance(v, type):
return v.__name__
else:
@ -275,8 +274,7 @@ def _repr(v):
write_string(info_dict_str.replace('\n', '\n '), out=sys.stderr)
self.assertFalse(
missing_keys,
'Missing keys in test definition: %s' % (
', '.join(sorted(missing_keys))))
'Missing keys in test definition: {}'.format(', '.join(sorted(missing_keys))))
def assertRegexpMatches(self, text, regexp, msg=None):
@ -285,9 +283,9 @@ def assertRegexpMatches(self, text, regexp, msg=None):
else:
m = re.match(regexp, text)
if not m:
note = 'Regexp didn\'t match: %r not found' % (regexp)
note = f'Regexp didn\'t match: {regexp!r} not found'
if len(text) < 1000:
note += ' in %r' % text
note += f' in {text!r}'
if msg is None:
msg = note
else:
@ -310,7 +308,7 @@ def assertLessEqual(self, got, expected, msg=None):
def assertEqual(self, got, expected, msg=None):
if not (got == expected):
if got != expected:
if msg is None:
msg = f'{got!r} not equal to {expected!r}'
self.assertTrue(got == expected, msg)

138
test/test_InfoExtractor.py
View file

@ -262,19 +262,19 @@ def test_search_json_ld_realworld(self):
''',
{
'chapters': [
{"title": "Explosie Turnhout", "start_time": 70, "end_time": 440},
{"title": "Jaarwisseling", "start_time": 440, "end_time": 1179},
{"title": "Natuurbranden Colorado", "start_time": 1179, "end_time": 1263},
{"title": "Klimaatverandering", "start_time": 1263, "end_time": 1367},
{"title": "Zacht weer", "start_time": 1367, "end_time": 1383},
{"title": "Financiële balans", "start_time": 1383, "end_time": 1484},
{"title": "Club Brugge", "start_time": 1484, "end_time": 1575},
{"title": "Mentale gezondheid bij topsporters", "start_time": 1575, "end_time": 1728},
{"title": "Olympische Winterspelen", "start_time": 1728, "end_time": 1873},
{"title": "Sober oudjaar in Nederland", "start_time": 1873, "end_time": 2079.23}
{'title': 'Explosie Turnhout', 'start_time': 70, 'end_time': 440},
{'title': 'Jaarwisseling', 'start_time': 440, 'end_time': 1179},
{'title': 'Natuurbranden Colorado', 'start_time': 1179, 'end_time': 1263},
{'title': 'Klimaatverandering', 'start_time': 1263, 'end_time': 1367},
{'title': 'Zacht weer', 'start_time': 1367, 'end_time': 1383},
{'title': 'Financiële balans', 'start_time': 1383, 'end_time': 1484},
{'title': 'Club Brugge', 'start_time': 1484, 'end_time': 1575},
{'title': 'Mentale gezondheid bij topsporters', 'start_time': 1575, 'end_time': 1728},
{'title': 'Olympische Winterspelen', 'start_time': 1728, 'end_time': 1873},
{'title': 'Sober oudjaar in Nederland', 'start_time': 1873, 'end_time': 2079.23},
],
'title': 'Het journaal - Aflevering 365 (Seizoen 2021)'
}, {}
'title': 'Het journaal - Aflevering 365 (Seizoen 2021)',
}, {},
),
(
# test multiple thumbnails in a list
@ -301,13 +301,13 @@ def test_search_json_ld_realworld(self):
'thumbnails': [{'url': 'https://www.rainews.it/cropgd/640x360/dl/img/2021/12/30/1640886376927_GettyImages.jpg'}],
},
{},
)
),
]
for html, expected_dict, search_json_ld_kwargs in _TESTS:
expect_dict(
self,
self.ie._search_json_ld(html, None, **search_json_ld_kwargs),
expected_dict
expected_dict,
)
def test_download_json(self):
@ -366,7 +366,7 @@ def test_parse_html5_media_entries(self):
'height': 740,
'tbr': 1500,
}],
'thumbnail': '//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg'
'thumbnail': '//pics.r18.com/digital/amateur/mgmr105/mgmr105jp.jpg',
})
# from https://www.csfd.cz/
@ -419,9 +419,9 @@ def test_parse_html5_media_entries(self):
'height': 1080,
}],
'subtitles': {
'cs': [{'url': 'https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt'}]
'cs': [{'url': 'https://video.csfd.cz/files/subtitles/163/344/163344115_4c388b.srt'}],
},
'thumbnail': 'https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360'
'thumbnail': 'https://img.csfd.cz/files/images/film/video/preview/163/344/163344118_748d20.png?h360',
})
# from https://tamasha.com/v/Kkdjw
@ -452,7 +452,7 @@ def test_parse_html5_media_entries(self):
'ext': 'mp4',
'format_id': '144p',
'height': 144,
}]
}],
})
# from https://www.directvnow.com
@ -470,7 +470,7 @@ def test_parse_html5_media_entries(self):
'formats': [{
'ext': 'mp4',
'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
}]
}],
})
# from https://www.directvnow.com
@ -488,7 +488,7 @@ def test_parse_html5_media_entries(self):
'formats': [{
'url': 'https://cdn.directv.com/content/dam/dtv/prod/website_directvnow-international/videos/DTVN_hdr_HBO_v3.mp4',
'ext': 'mp4',
}]
}],
})
# from https://www.klarna.com/uk/
@ -547,8 +547,8 @@ def test_extract_jwplayer_data_realworld(self):
'id': 'XEgvuql4',
'formats': [{
'url': 'rtmp://192.138.214.154/live/sjclive',
'ext': 'flv'
}]
'ext': 'flv',
}],
})
# from https://www.pornoxo.com/videos/7564/striptease-from-sexy-secretary/
@ -588,8 +588,8 @@ def test_extract_jwplayer_data_realworld(self):
'thumbnail': 'https://t03.vipstreamservice.com/thumbs/pxo-full/2009-12/14/a4b2157147afe5efa93ce1978e0265289c193874e02597.flv-full-13.jpg',
'formats': [{
'url': 'https://cdn.pornoxo.com/key=MF+oEbaxqTKb50P-w9G3nA,end=1489689259,ip=104.199.146.27/ip=104.199.146.27/speed=6573765/buffer=3.0/2009-12/4b2157147afe5efa93ce1978e0265289c193874e02597.flv',
'ext': 'flv'
}]
'ext': 'flv',
}],
})
# from http://www.indiedb.com/games/king-machine/videos
@ -610,12 +610,12 @@ def test_extract_jwplayer_data_realworld(self):
'formats': [{
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode_mp4/king-machine-trailer.mp4',
'height': 360,
'ext': 'mp4'
'ext': 'mp4',
}, {
'url': 'http://cdn.dbolical.com/cache/videos/games/1/50/49678/encode720p_mp4/king-machine-trailer.mp4',
'height': 720,
'ext': 'mp4'
}]
'ext': 'mp4',
}],
})
def test_parse_m3u8_formats(self):
@ -866,7 +866,7 @@ def test_parse_m3u8_formats(self):
'height': 1080,
'vcodec': 'avc1.64002a',
}],
{}
{},
),
(
'bipbop_16x9',
@ -990,45 +990,45 @@ def test_parse_m3u8_formats(self):
'en': [{
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/eng/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}, {
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/eng_forced/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}],
'fr': [{
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/fra/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}, {
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/fra_forced/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}],
'es': [{
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/spa/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}, {
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/spa_forced/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}],
'ja': [{
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/jpn/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}, {
'url': 'https://devstreaming-cdn.apple.com/videos/streaming/examples/bipbop_16x9/subtitles/jpn_forced/prog_index.m3u8',
'ext': 'vtt',
'protocol': 'm3u8_native'
'protocol': 'm3u8_native',
}],
}
},
),
]
for m3u8_file, m3u8_url, expected_formats, expected_subs in _TEST_CASES:
with open('./test/testdata/m3u8/%s.m3u8' % m3u8_file, encoding='utf-8') as f:
with open(f'./test/testdata/m3u8/{m3u8_file}.m3u8', encoding='utf-8') as f:
formats, subs = self.ie._parse_m3u8_formats_and_subtitles(
f.read(), m3u8_url, ext='mp4')
self.ie._sort_formats(formats)
@ -1366,14 +1366,14 @@ def test_parse_mpd_formats(self):
'url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/manifest.mpd',
'fragment_base_url': 'https://sdn-global-streaming-cache-3qsdn.akamaized.net/stream/3144/files/17/07/672975/3144-kZT4LWMQw6Rh7Kpd.ism/dash/',
'protocol': 'http_dash_segments',
}
]
},
],
},
)
),
]
for mpd_file, mpd_url, mpd_base_url, expected_formats, expected_subtitles in _TEST_CASES:
with open('./test/testdata/mpd/%s.mpd' % mpd_file, encoding='utf-8') as f:
with open(f'./test/testdata/mpd/{mpd_file}.mpd', encoding='utf-8') as f:
formats, subtitles = self.ie._parse_mpd_formats_and_subtitles(
compat_etree_fromstring(f.read().encode()),
mpd_base_url=mpd_base_url, mpd_url=mpd_url)
@ -1408,7 +1408,7 @@ def test_parse_ism_formats(self):
'sampling_rate': 48000,
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video-100',
@ -1431,7 +1431,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401FDA0544EFFC2D002CBC40000003004000000C03C60CA80000000168EF32C8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video-326',
@ -1454,7 +1454,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401FDA0241FE23FFC3BC83BA44000003000400000300C03C60CA800000000168EF32C8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video-698',
@ -1477,7 +1477,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401FDA0350BFB97FF06AF06AD1000003000100000300300F1832A00000000168EF32C8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video-1493',
@ -1500,7 +1500,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401FDA011C3DE6FFF0D890D871000003000100000300300F1832A00000000168EF32C8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video-4482',
@ -1523,7 +1523,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401FDA01A816F97FFC1ABC1AB440000003004000000C03C60CA80000000168EF32C8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}],
{
@ -1538,10 +1538,10 @@ def test_parse_ism_formats(self):
'duration': 8880746666,
'timescale': 10000000,
'fourcc': 'TTML',
'codec_private_data': ''
}
}
]
'codec_private_data': '',
},
},
],
},
),
(
@ -1571,7 +1571,7 @@ def test_parse_ism_formats(self):
'sampling_rate': 48000,
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'audio_deu_1-224',
@ -1597,7 +1597,7 @@ def test_parse_ism_formats(self):
'sampling_rate': 48000,
'channels': 6,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-23',
@ -1622,7 +1622,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '000000016742C00CDB06077E5C05A808080A00000300020000030009C0C02EE0177CC6300F142AE00000000168CA8DC8',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-403',
@ -1647,7 +1647,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D4014E98323B602D4040405000003000100000300320F1429380000000168EAECF2',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-680',
@ -1672,7 +1672,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401EE981405FF2E02D4040405000000300100000030320F162D3800000000168EAECF2',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-1253',
@ -1698,7 +1698,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401EE981405FF2E02D4040405000000300100000030320F162D3800000000168EAECF2',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-2121',
@ -1723,7 +1723,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D401EECA0601BD80B50101014000003000400000300C83C58B6580000000168E93B3C80',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-3275',
@ -1748,7 +1748,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D4020ECA02802DD80B501010140000003004000000C83C60C65800000000168E93B3C80',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-5300',
@ -1773,7 +1773,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D4028ECA03C0113F2E02D4040405000000300100000030320F18319600000000168E93B3C80',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}, {
'format_id': 'video_deu-8079',
@ -1798,7 +1798,7 @@ def test_parse_ism_formats(self):
'codec_private_data': '00000001674D4028ECA03C0113F2E02D4040405000000300100000030320F18319600000000168E93B3C80',
'channels': 2,
'bits_per_sample': 16,
'nal_unit_length_field': 4
'nal_unit_length_field': 4,
},
}],
{},
@ -1806,7 +1806,7 @@ def test_parse_ism_formats(self):
]
for ism_file, ism_url, expected_formats, expected_subtitles in _TEST_CASES:
with open('./test/testdata/ism/%s.Manifest' % ism_file, encoding='utf-8') as f:
with open(f'./test/testdata/ism/{ism_file}.Manifest', encoding='utf-8') as f:
formats, subtitles = self.ie._parse_ism_formats_and_subtitles(
compat_etree_fromstring(f.read().encode()), ism_url=ism_url)
self.ie._sort_formats(formats)
@ -1827,12 +1827,12 @@ def test_parse_f4m_formats(self):
'tbr': 2148,
'width': 1280,
'height': 720,
}]
}],
),
]
for f4m_file, f4m_url, expected_formats in _TEST_CASES:
with open('./test/testdata/f4m/%s.f4m' % f4m_file, encoding='utf-8') as f:
with open(f'./test/testdata/f4m/{f4m_file}.f4m', encoding='utf-8') as f:
formats = self.ie._parse_f4m_formats(
compat_etree_fromstring(f.read().encode()),
f4m_url, None)
@ -1873,13 +1873,13 @@ def test_parse_xspf(self):
}, {
'manifest_url': 'https://example.org/src/foo_xspf.xspf',
'url': 'https://example.com/track3.mp3',
}]
}]
}],
}],
),
]
for xspf_file, xspf_url, expected_entries in _TEST_CASES:
with open('./test/testdata/xspf/%s.xspf' % xspf_file, encoding='utf-8') as f:
with open(f'./test/testdata/xspf/{xspf_file}.xspf', encoding='utf-8') as f:
entries = self.ie._parse_xspf(
compat_etree_fromstring(f.read().encode()),
xspf_file, xspf_url=xspf_url, xspf_base_url=xspf_url)
@ -1902,7 +1902,7 @@ def test_response_with_expected_status_returns_content(self):
server_thread.start()
(content, urlh) = self.ie._download_webpage_handle(
'http://127.0.0.1:%d/teapot' % port, None,
f'http://127.0.0.1:{port}/teapot', None,
expected_status=TEAPOT_RESPONSE_STATUS)
self.assertEqual(content, TEAPOT_RESPONSE_BODY)

78
test/test_YoutubeDL.py
View file

@ -4,10 +4,12 @@
import os
import sys
import unittest
from unittest.mock import patch
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import contextlib
import copy
import json
@ -129,8 +131,8 @@ def test(inp, *expected, multi=False):
'allow_multiple_audio_streams': multi,
})
ydl.process_ie_result(info_dict.copy())
downloaded = map(lambda x: x['format_id'], ydl.downloaded_info_dicts)
self.assertEqual(list(downloaded), list(expected))
downloaded = [x['format_id'] for x in ydl.downloaded_info_dicts]
self.assertEqual(downloaded, list(expected))
test('20/47', '47')
test('20/71/worst', '35')
@ -515,13 +517,37 @@ def test_format_filtering(self):
self.assertEqual(downloaded_ids, ['D', 'C', 'B'])
ydl = YDL({'format': 'best[height<40]'})
try:
with contextlib.suppress(ExtractorError):
ydl.process_ie_result(info_dict)
except ExtractorError:
pass
self.assertEqual(ydl.downloaded_info_dicts, [])
def test_default_format_spec(self):
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', False)
def test_default_format_spec_without_ffmpeg(self):
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'outtmpl': '-'})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.available', True)
@patch('yt_dlp.postprocessor.ffmpeg.FFmpegMergerPP.can_merge', lambda _: True)
def test_default_format_spec_with_ffmpeg(self):
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
@ -529,13 +555,13 @@ def test_default_format_spec(self):
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'simulate': True})
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
ydl = YDL({'outtmpl': '-'})
self.assertEqual(ydl._default_format_spec({}), 'best/bestvideo+bestaudio')
ydl = YDL({})
self.assertEqual(ydl._default_format_spec({}, download=False), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({}), 'bestvideo*+bestaudio/best')
self.assertEqual(ydl._default_format_spec({'is_live': True}), 'best/bestvideo+bestaudio')
@ -652,8 +678,8 @@ def test_add_extra_info(self):
'formats': [
{'id': 'id 1', 'height': 1080, 'width': 1920},
{'id': 'id 2', 'height': 720},
{'id': 'id 3'}
]
{'id': 'id 3'},
],
}
def test_prepare_outtmpl_and_filename(self):
@ -773,7 +799,7 @@ def expect_same_infodict(out):
test('%(formats)j', (json.dumps(FORMATS), None))
test('%(formats)#j', (
json.dumps(FORMATS, indent=4),
json.dumps(FORMATS, indent=4).replace(':', '：').replace('"', "＂").replace('\n', ' ')
json.dumps(FORMATS, indent=4).replace(':', '：').replace('"', '＂').replace('\n', ' '),
))
test('%(title5).3B', 'á')
test('%(title5)U', 'áéí 𝐀')
@ -843,8 +869,8 @@ def gen():
# Empty filename
test('%(foo|)s-%(bar|)s.%(ext)s', '-.mp4')
# test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # fixme
# test('%(foo|)s', ('', '_')) # fixme
# test('%(foo|)s.%(ext)s', ('.mp4', '_.mp4')) # FIXME: ?
# test('%(foo|)s', ('', '_')) # FIXME: ?
# Environment variable expansion for prepare_filename
os.environ['__yt_dlp_var'] = 'expanded'
@ -861,7 +887,7 @@ def gen():
test('Hello %(title1)s', 'Hello $PATH')
test('Hello %(title2)s', 'Hello %PATH%')
test('%(title3)s', ('foo/bar\\test', 'foo⧸bar⧹test'))
test('folder/%(title3)s', ('folder/foo/bar\\test', 'folder%sfoo⧸bar⧹test' % os.path.sep))
test('folder/%(title3)s', ('folder/foo/bar\\test', f'folder{os.path.sep}foo⧸bar⧹test'))
def test_format_note(self):
ydl = YoutubeDL()
@ -883,22 +909,22 @@ def run(self, info):
f.write('EXAMPLE')
return [info['filepath']], info
def run_pp(params, PP):
def run_pp(params, pp):
with open(filename, 'w') as f:
f.write('EXAMPLE')
ydl = YoutubeDL(params)
ydl.add_post_processor(PP())
ydl.add_post_processor(pp())
ydl.post_process(filename, {'filepath': filename})
run_pp({'keepvideo': True}, SimplePP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
self.assertTrue(os.path.exists(filename), f'{filename} doesn\'t exist')
self.assertTrue(os.path.exists(audiofile), f'{audiofile} doesn\'t exist')
os.unlink(filename)
os.unlink(audiofile)
run_pp({'keepvideo': False}, SimplePP)
self.assertFalse(os.path.exists(filename), '%s exists' % filename)
self.assertTrue(os.path.exists(audiofile), '%s doesn\'t exist' % audiofile)
self.assertFalse(os.path.exists(filename), f'{filename} exists')
self.assertTrue(os.path.exists(audiofile), f'{audiofile} doesn\'t exist')
os.unlink(audiofile)
class ModifierPP(PostProcessor):
@ -908,7 +934,7 @@ def run(self, info):
return [], info
run_pp({'keepvideo': False}, ModifierPP)
self.assertTrue(os.path.exists(filename), '%s doesn\'t exist' % filename)
self.assertTrue(os.path.exists(filename), f'{filename} doesn\'t exist')
os.unlink(filename)
def test_match_filter(self):
@ -920,7 +946,7 @@ def test_match_filter(self):
'duration': 30,
'filesize': 10 * 1024,
'playlist_id': '42',
'uploader': "變態妍字幕版 太妍 тест",
'uploader': '變態妍字幕版 太妍 тест',
'creator': "тест ' 123 ' тест--",
'webpage_url': 'http://example.com/watch?v=shenanigans',
}
@ -933,7 +959,7 @@ def test_match_filter(self):
'description': 'foo',
'filesize': 5 * 1024,
'playlist_id': '43',
'uploader': "тест 123",
'uploader': 'тест 123',
'webpage_url': 'http://example.com/watch?v=SHENANIGANS',
}
videos = [first, second]
@ -1180,7 +1206,7 @@ def _real_extract(self, url):
})
return {
'id': video_id,
'title': 'Video %s' % video_id,
'title': f'Video {video_id}',
'formats': formats,
}
@ -1194,8 +1220,8 @@ def _entries(self):
'_type': 'url_transparent',
'ie_key': VideoIE.ie_key(),
'id': video_id,
'url': 'video:%s' % video_id,
'title': 'Video Transparent %s' % video_id,
'url': f'video:{video_id}',
'title': f'Video Transparent {video_id}',
}
def _real_extract(self, url):

12
test/test_aes.py
View file

@ -87,7 +87,7 @@ def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode()
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8])
+ b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae'
+ b'\x17\x15\x93\xab\x8d\x80V\xcdV\xe0\t\xcdo\xc2\xa5\xd8ksM\r\xe27N\xae',
).decode()
decrypted = (aes_decrypt_text(encrypted, password, 16))
self.assertEqual(decrypted, self.secret_msg)
@ -95,7 +95,7 @@ def test_decrypt_text(self):
password = intlist_to_bytes(self.key).decode()
encrypted = base64.b64encode(
intlist_to_bytes(self.iv[:8])
+ b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83'
+ b'\x0b\xe6\xa4\xd9z\x0e\xb8\xb9\xd0\xd4i_\x85\x1d\x99\x98_\xe5\x80\xe7.\xbf\xa5\x83',
).decode()
decrypted = (aes_decrypt_text(encrypted, password, 32))
self.assertEqual(decrypted, self.secret_msg)
@ -132,16 +132,16 @@ def test_pad_block(self):
block = [0x21, 0xA0, 0x43, 0xFF]
self.assertEqual(pad_block(block, 'pkcs7'),
block + [0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C])
[*block, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C, 0x0C])
self.assertEqual(pad_block(block, 'iso7816'),
block + [0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
[*block, 0x80, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
self.assertEqual(pad_block(block, 'whitespace'),
block + [0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20])
[*block, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20])
self.assertEqual(pad_block(block, 'zero'),
block + [0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
[*block, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00])
block = list(range(16))
for mode in ('pkcs7', 'iso7816', 'whitespace', 'zero'):

10
test/test_compat.py
View file

@ -15,8 +15,8 @@
from yt_dlp.compat import (
compat_etree_fromstring,
compat_expanduser,
compat_urllib_parse_unquote,
compat_urllib_parse_urlencode,
compat_urllib_parse_unquote, # noqa: TID251
compat_urllib_parse_urlencode, # noqa: TID251
)
from yt_dlp.compat.urllib.request import getproxies
@ -24,15 +24,15 @@
class TestCompat(unittest.TestCase):
def test_compat_passthrough(self):
with self.assertWarns(DeprecationWarning):
compat.compat_basestring
_ = compat.compat_basestring
with self.assertWarns(DeprecationWarning):
compat.WINDOWS_VT_MODE
_ = compat.WINDOWS_VT_MODE
self.assertEqual(urllib.request.getproxies, getproxies)
with self.assertWarns(DeprecationWarning):
compat.compat_pycrypto_AES # Must not raise error
_ = compat.compat_pycrypto_AES # Must not raise error
def test_compat_expanduser(self):
old_home = os.environ.get('HOME')

2
test/test_config.py
View file

@ -71,7 +71,7 @@ def _generate_expected_groups():
Path('/etc/yt-dlp.conf'),
Path('/etc/yt-dlp/config'),
Path('/etc/yt-dlp/config.txt'),
]
],
}

133
test/test_cookies.py
View file

@ -67,6 +67,7 @@ def test_get_desktop_environment(self):
({'XDG_CURRENT_DESKTOP': 'GNOME'}, _LinuxDesktopEnvironment.GNOME),
({'XDG_CURRENT_DESKTOP': 'GNOME:GNOME-Classic'}, _LinuxDesktopEnvironment.GNOME),
({'XDG_CURRENT_DESKTOP': 'GNOME : GNOME-Classic'}, _LinuxDesktopEnvironment.GNOME),
({'XDG_CURRENT_DESKTOP': 'ubuntu:GNOME'}, _LinuxDesktopEnvironment.GNOME),
({'XDG_CURRENT_DESKTOP': 'Unity', 'DESKTOP_SESSION': 'gnome-fallback'}, _LinuxDesktopEnvironment.GNOME),
({'XDG_CURRENT_DESKTOP': 'KDE', 'KDE_SESSION_VERSION': '5'}, _LinuxDesktopEnvironment.KDE5),
@ -106,7 +107,7 @@ def test_chrome_cookie_decryptor_linux_v11(self):
def test_chrome_cookie_decryptor_windows_v10(self):
with MonkeyPatch(cookies, {
'_get_windows_v10_key': lambda *args, **kwargs: b'Y\xef\xad\xad\xeerp\xf0Y\xe6\x9b\x12\xc2<z\x16]\n\xbb\xb8\xcb\xd7\x9bA\xc3\x14e\x99{\xd6\xf4&'
'_get_windows_v10_key': lambda *args, **kwargs: b'Y\xef\xad\xad\xeerp\xf0Y\xe6\x9b\x12\xc2<z\x16]\n\xbb\xb8\xcb\xd7\x9bA\xc3\x14e\x99{\xd6\xf4&',
}):
encrypted_value = b'v10T\xb8\xf3\xb8\x01\xa7TtcV\xfc\x88\xb8\xb8\xef\x05\xb5\xfd\x18\xc90\x009\xab\xb1\x893\x85)\x87\xe1\xa9-\xa3\xad='
value = '32101439'
@ -121,17 +122,17 @@ def test_chrome_cookie_decryptor_mac_v10(self):
self.assertEqual(decryptor.decrypt(encrypted_value), value)
def test_safari_cookie_parsing(self):
cookies = \
b'cook\x00\x00\x00\x01\x00\x00\x00i\x00\x00\x01\x00\x01\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00Y' \
b'\x00\x00\x00\x00\x00\x00\x00 \x00\x00\x00\x00\x00\x00\x008\x00\x00\x00B\x00\x00\x00F\x00\x00\x00H' \
b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x03\xa5>\xc3A\x00\x00\x80\xc3\x07:\xc3A' \
b'localhost\x00foo\x00/\x00test%20%3Bcookie\x00\x00\x00\x054\x07\x17 \x05\x00\x00\x00Kbplist00\xd1\x01' \
b'\x02_\x10\x18NSHTTPCookieAcceptPolicy\x10\x02\x08\x0b&\x00\x00\x00\x00\x00\x00\x01\x01\x00\x00\x00' \
b'\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00('
cookies = (
b'cook\x00\x00\x00\x01\x00\x00\x00i\x00\x00\x01\x00\x01\x00\x00\x00\x10\x00\x00\x00\x00\x00\x00\x00Y'
b'\x00\x00\x00\x00\x00\x00\x00 \x00\x00\x00\x00\x00\x00\x008\x00\x00\x00B\x00\x00\x00F\x00\x00\x00H'
b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x03\xa5>\xc3A\x00\x00\x80\xc3\x07:\xc3A'
b'localhost\x00foo\x00/\x00test%20%3Bcookie\x00\x00\x00\x054\x07\x17 \x05\x00\x00\x00Kbplist00\xd1\x01'
b'\x02_\x10\x18NSHTTPCookieAcceptPolicy\x10\x02\x08\x0b&\x00\x00\x00\x00\x00\x00\x01\x01\x00\x00\x00'
b'\x00\x00\x00\x00\x03\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00(')
jar = parse_safari_cookies(cookies)
self.assertEqual(len(jar), 1)
cookie = list(jar)[0]
cookie = next(iter(jar))
self.assertEqual(cookie.domain, 'localhost')
self.assertEqual(cookie.port, None)
self.assertEqual(cookie.path, '/')
@ -164,7 +165,7 @@ def _run_tests(self, *cases):
attributes = {
key: value
for key, value in dict(morsel).items()
if value != ""
if value != ''
}
self.assertEqual(attributes, expected_attributes, message)
@ -174,133 +175,133 @@ def test_parsing(self):
self._run_tests(
# Copied from https://github.com/python/cpython/blob/v3.10.7/Lib/test/test_http_cookies.py
(
"Test basic cookie",
"chips=ahoy; vienna=finger",
{"chips": "ahoy", "vienna": "finger"},
'Test basic cookie',
'chips=ahoy; vienna=finger',
{'chips': 'ahoy', 'vienna': 'finger'},
),
(
"Test quoted cookie",
'Test quoted cookie',
'keebler="E=mc2; L=\\"Loves\\"; fudge=\\012;"',
{"keebler": 'E=mc2; L="Loves"; fudge=\012;'},
{'keebler': 'E=mc2; L="Loves"; fudge=\012;'},
),
(
"Allow '=' in an unquoted value",
"keebler=E=mc2",
{"keebler": "E=mc2"},
'keebler=E=mc2',
{'keebler': 'E=mc2'},
),
(
"Allow cookies with ':' in their name",
"key:term=value:term",
{"key:term": "value:term"},
'key:term=value:term',
{'key:term': 'value:term'},
),
(
"Allow '[' and ']' in cookie values",
"a=b; c=[; d=r; f=h",
{"a": "b", "c": "[", "d": "r", "f": "h"},
'a=b; c=[; d=r; f=h',
{'a': 'b', 'c': '[', 'd': 'r', 'f': 'h'},
),
(
"Test basic cookie attributes",
'Test basic cookie attributes',
'Customer="WILE_E_COYOTE"; Version=1; Path=/acme',
{"Customer": ("WILE_E_COYOTE", {"version": "1", "path": "/acme"})},
{'Customer': ('WILE_E_COYOTE', {'version': '1', 'path': '/acme'})},
),
(
"Test flag only cookie attributes",
'Test flag only cookie attributes',
'Customer="WILE_E_COYOTE"; HttpOnly; Secure',
{"Customer": ("WILE_E_COYOTE", {"httponly": True, "secure": True})},
{'Customer': ('WILE_E_COYOTE', {'httponly': True, 'secure': True})},
),
(
"Test flag only attribute with values",
"eggs=scrambled; httponly=foo; secure=bar; Path=/bacon",
{"eggs": ("scrambled", {"httponly": "foo", "secure": "bar", "path": "/bacon"})},
'Test flag only attribute with values',
'eggs=scrambled; httponly=foo; secure=bar; Path=/bacon',
{'eggs': ('scrambled', {'httponly': 'foo', 'secure': 'bar', 'path': '/bacon'})},
),
(
"Test special case for 'expires' attribute, 4 digit year",
'Customer="W"; expires=Wed, 01 Jan 2010 00:00:00 GMT',
{"Customer": ("W", {"expires": "Wed, 01 Jan 2010 00:00:00 GMT"})},
{'Customer': ('W', {'expires': 'Wed, 01 Jan 2010 00:00:00 GMT'})},
),
(
"Test special case for 'expires' attribute, 2 digit year",
'Customer="W"; expires=Wed, 01 Jan 98 00:00:00 GMT',
{"Customer": ("W", {"expires": "Wed, 01 Jan 98 00:00:00 GMT"})},
{'Customer': ('W', {'expires': 'Wed, 01 Jan 98 00:00:00 GMT'})},
),
(
"Test extra spaces in keys and values",
"eggs = scrambled ; secure ; path = bar ; foo=foo ",
{"eggs": ("scrambled", {"secure": True, "path": "bar"}), "foo": "foo"},
'Test extra spaces in keys and values',
'eggs = scrambled ; secure ; path = bar ; foo=foo ',
{'eggs': ('scrambled', {'secure': True, 'path': 'bar'}), 'foo': 'foo'},
),
(
"Test quoted attributes",
'Test quoted attributes',
'Customer="WILE_E_COYOTE"; Version="1"; Path="/acme"',
{"Customer": ("WILE_E_COYOTE", {"version": "1", "path": "/acme"})}
{'Customer': ('WILE_E_COYOTE', {'version': '1', 'path': '/acme'})},
),
# Our own tests that CPython passes
(
"Allow ';' in quoted value",
'chips="a;hoy"; vienna=finger',
{"chips": "a;hoy", "vienna": "finger"},
{'chips': 'a;hoy', 'vienna': 'finger'},
),
(
"Keep only the last set value",
"a=c; a=b",
{"a": "b"},
'Keep only the last set value',
'a=c; a=b',
{'a': 'b'},
),
)
def test_lenient_parsing(self):
self._run_tests(
(
"Ignore and try to skip invalid cookies",
'Ignore and try to skip invalid cookies',
'chips={"ahoy;": 1}; vienna="finger;"',
{"vienna": "finger;"},
{'vienna': 'finger;'},
),
(
"Ignore cookies without a name",
"a=b; unnamed; c=d",
{"a": "b", "c": "d"},
'Ignore cookies without a name',
'a=b; unnamed; c=d',
{'a': 'b', 'c': 'd'},
),
(
"Ignore '\"' cookie without name",
'a=b; "; c=d',
{"a": "b", "c": "d"},
{'a': 'b', 'c': 'd'},
),
(
"Skip all space separated values",
"x a=b c=d x; e=f",
{"a": "b", "c": "d", "e": "f"},
'Skip all space separated values',
'x a=b c=d x; e=f',
{'a': 'b', 'c': 'd', 'e': 'f'},
),
(
"Skip all space separated values",
'Skip all space separated values',
'x a=b; data={"complex": "json", "with": "key=value"}; x c=d x',
{"a": "b", "c": "d"},
{'a': 'b', 'c': 'd'},
),
(
"Expect quote mending",
'Expect quote mending',
'a=b; invalid="; c=d',
{"a": "b", "c": "d"},
{'a': 'b', 'c': 'd'},
),
(
"Reset morsel after invalid to not capture attributes",
"a=b; invalid; Version=1; c=d",
{"a": "b", "c": "d"},
'Reset morsel after invalid to not capture attributes',
'a=b; invalid; Version=1; c=d',
{'a': 'b', 'c': 'd'},
),
(
"Reset morsel after invalid to not capture attributes",
"a=b; $invalid; $Version=1; c=d",
{"a": "b", "c": "d"},
'Reset morsel after invalid to not capture attributes',
'a=b; $invalid; $Version=1; c=d',
{'a': 'b', 'c': 'd'},
),
(
"Continue after non-flag attribute without value",
"a=b; path; Version=1; c=d",
{"a": "b", "c": "d"},
'Continue after non-flag attribute without value',
'a=b; path; Version=1; c=d',
{'a': 'b', 'c': 'd'},
),
(
"Allow cookie attributes with `$` prefix",
'Allow cookie attributes with `$` prefix',
'Customer="WILE_E_COYOTE"; $Version=1; $Secure; $Path=/acme',
{"Customer": ("WILE_E_COYOTE", {"version": "1", "secure": True, "path": "/acme"})},
{'Customer': ('WILE_E_COYOTE', {'version': '1', 'secure': True, 'path': '/acme'})},
),
(
"Invalid Morsel keys should not result in an error",
"Key=Value; [Invalid]=Value; Another=Value",
{"Key": "Value", "Another": "Value"},
'Invalid Morsel keys should not result in an error',
'Key=Value; [Invalid]=Value; Another=Value',
{'Key': 'Value', 'Another': 'Value'},
),
)

20
test/test_download.py
View file

@ -20,7 +20,6 @@
gettestcases,
getwebpagetestcases,
is_download_test,
report_warning,
try_rm,
)
@ -94,7 +93,7 @@ def test_template(self):
'playlist', [] if is_playlist else [test_case])
def print_skipping(reason):
print('Skipping %s: %s' % (test_case['name'], reason))
print('Skipping {}: {}'.format(test_case['name'], reason))
self.skipTest(reason)
if not ie.working():
@ -117,7 +116,7 @@ def print_skipping(reason):
for other_ie in other_ies:
if not other_ie.working():
print_skipping('test depends on %sIE, marked as not WORKING' % other_ie.ie_key())
print_skipping(f'test depends on {other_ie.ie_key()}IE, marked as not WORKING')
params = get_params(test_case.get('params', {}))
params['outtmpl'] = tname + '_' + params['outtmpl']
@ -148,10 +147,7 @@ def match_exception(err):
return False
if err.__class__.__name__ == expected_exception:
return True
for exc in err.exc_info:
if exc.__class__.__name__ == expected_exception:
return True
return False
return any(exc.__class__.__name__ == expected_exception for exc in err.exc_info)
def try_rm_tcs_files(tcs=None):
if tcs is None:
@ -181,8 +177,7 @@ def try_rm_tcs_files(tcs=None):
raise
if try_num == RETRIES:
report_warning('%s failed due to network errors, skipping...' % tname)
return
raise
print(f'Retrying: {try_num} failed tries\n\n##########\n\n')
@ -244,9 +239,8 @@ def try_rm_tcs_files(tcs=None):
got_fsize = os.path.getsize(tc_filename)
assertGreaterEqual(
self, got_fsize, expected_minsize,
'Expected %s to be at least %s, but it\'s only %s ' %
(tc_filename, format_bytes(expected_minsize),
format_bytes(got_fsize)))
f'Expected {tc_filename} to be at least {format_bytes(expected_minsize)}, '
f'but it\'s only {format_bytes(got_fsize)} ')
if 'md5' in tc:
md5_for_file = _file_md5(tc_filename)
self.assertEqual(tc['md5'], md5_for_file)
@ -255,7 +249,7 @@ def try_rm_tcs_files(tcs=None):
info_json_fn = os.path.splitext(tc_filename)[0] + '.info.json'
self.assertTrue(
os.path.exists(info_json_fn),
'Missing info file %s' % info_json_fn)
f'Missing info file {info_json_fn}')
with open(info_json_fn, encoding='utf-8') as infof:
info_dict = json.load(infof)
expect_info_dict(self, info_dict, tc.get('info_dict', {}))

6
test/test_downloader_http.py
View file

@ -38,9 +38,9 @@ def send_content_range(self, total=None):
end = int(mobj.group(2))
valid_range = start is not None and end is not None
if valid_range:
content_range = 'bytes %d-%d' % (start, end)
content_range = f'bytes {start}-{end}'
if total:
content_range += '/%d' % total
content_range += f'/{total}'
self.send_header('Content-Range', content_range)
return (end - start + 1) if valid_range else total
@ -84,7 +84,7 @@ def download(self, params, ep):
filename = 'testfile.mp4'
try_rm(encodeFilename(filename))
self.assertTrue(downloader.real_download(filename, {
'url': 'http://127.0.0.1:%d/%s' % (self.port, ep),
'url': f'http://127.0.0.1:{self.port}/{ep}',
}), ep)
self.assertEqual(os.path.getsize(encodeFilename(filename)), TEST_SIZE, ep)
try_rm(encodeFilename(filename))

4
test/test_http_proxy.py
View file

@ -105,7 +105,7 @@ def __init__(self, socket, ssl_context, server_hostname=None, suppress_ragged_eo
self.incoming,
self.outgoing,
server_hostname=server_hostname,
server_side=server_side
server_side=server_side,
)
self._ssl_io_loop(self.sslobj.do_handshake)
@ -333,7 +333,7 @@ def test_http_connect_auth(self, handler, ctx):
@pytest.mark.skip_handler(
'Requests',
'bug in urllib3 causes unclosed socket: https://github.com/urllib3/urllib3/issues/3374'
'bug in urllib3 causes unclosed socket: https://github.com/urllib3/urllib3/issues/3374',
)
def test_http_connect_bad_auth(self, handler, ctx):
with ctx.http_server(HTTPConnectProxyHandler, username='test', password='test') as server_address:

4
test/test_iqiyi_sdk_interpreter.py
View file

@ -29,11 +29,11 @@ def error(self, msg):
@is_download_test
class TestIqiyiSDKInterpreter(unittest.TestCase):
def test_iqiyi_sdk_interpreter(self):
'''
"""
Test the functionality of IqiyiSDKInterpreter by trying to log in
If `sign` is incorrect, /validate call throws an HTTP 556 error
'''
"""
logger = WarningLogger()
ie = IqiyiIE(FakeYDL({'logger': logger}))
ie._perform_login('foo', 'bar')

56
test/test_jsinterp.py
View file

@ -92,6 +92,7 @@ def test_operators(self):
self._test('function f(){return 0 && 1 || 2;}', 2)
self._test('function f(){return 0 ?? 42;}', 0)
self._test('function f(){return "life, the universe and everything" < 42;}', False)
self._test('function f(){return 0 - 7 * - 6;}', 42)
def test_array_access(self):
self._test('function f(){var x = [1,2,3]; x[0] = 4; x[0] = 5; x[2.0] = 7; return x;}', [5, 2, 7])
@ -375,6 +376,61 @@ def test_packed(self):
jsi = JSInterpreter('''function f(p,a,c,k,e,d){while(c--)if(k[c])p=p.replace(new RegExp('\\b'+c.toString(a)+'\\b','g'),k[c]);return p}''')
self.assertEqual(jsi.call_function('f', '''h 7=g("1j");7.7h({7g:[{33:"w://7f-7e-7d-7c.v.7b/7a/79/78/77/76.74?t=73&s=2s&e=72&f=2t&71=70.0.0.1&6z=6y&6x=6w"}],6v:"w://32.v.u/6u.31",16:"r%",15:"r%",6t:"6s",6r:"",6q:"l",6p:"l",6o:"6n",6m:\'6l\',6k:"6j",9:[{33:"/2u?b=6i&n=50&6h=w://32.v.u/6g.31",6f:"6e"}],1y:{6d:1,6c:\'#6b\',6a:\'#69\',68:"67",66:30,65:r,},"64":{63:"%62 2m%m%61%5z%5y%5x.u%5w%5v%5u.2y%22 2k%m%1o%22 5t%m%1o%22 5s%m%1o%22 2j%m%5r%22 16%m%5q%22 15%m%5p%22 5o%2z%5n%5m%2z",5l:"w://v.u/d/1k/5k.2y",5j:[]},\'5i\':{"5h":"5g"},5f:"5e",5d:"w://v.u",5c:{},5b:l,1x:[0.25,0.50,0.75,1,1.25,1.5,2]});h 1m,1n,5a;h 59=0,58=0;h 7=g("1j");h 2x=0,57=0,56=0;$.55({54:{\'53-52\':\'2i-51\'}});7.j(\'4z\',6(x){c(5>0&&x.1l>=5&&1n!=1){1n=1;$(\'q.4y\').4x(\'4w\')}});7.j(\'13\',6(x){2x=x.1l});7.j(\'2g\',6(x){2w(x)});7.j(\'4v\',6(){$(\'q.2v\').4u()});6 2w(x){$(\'q.2v\').4t();c(1m)19;1m=1;17=0;c(4s.4r===l){17=1}$.4q(\'/2u?b=4p&2l=1k&4o=2t-4n-4m-2s-4l&4k=&4j=&4i=&17=\'+17,6(2r){$(\'#4h\').4g(2r)});$(\'.3-8-4f-4e:4d("4c")\').2h(6(e){2q();g().4b(0);g().4a(l)});6 2q(){h $14=$("<q />").2p({1l:"49",16:"r%",15:"r%",48:0,2n:0,2o:47,46:"45(10%, 10%, 10%, 0.4)","44-43":"42"});$("<41 />").2p({16:"60%",15:"60%",2o:40,"3z-2n":"3y"}).3x({\'2m\':\'/?b=3w&2l=1k\',\'2k\':\'0\',\'2j\':\'2i\'}).2f($14);$14.2h(6(){$(3v).3u();g().2g()});$14.2f($(\'#1j\'))}g().13(0);}6 3t(){h 9=7.1b(2e);2d.2c(9);c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==2e){2d.2c(\'!!=\'+i);7.1p(i)}}}}7.j(\'3s\',6(){g().1h("/2a/3r.29","3q 10 28",6(){g().13(g().27()+10)},"2b");$("q[26=2b]").23().21(\'.3-20-1z\');g().1h("/2a/3p.29","3o 10 28",6(){h 12=g().27()-10;c(12<0)12=0;g().13(12)},"24");$("q[26=24]").23().21(\'.3-20-1z\');});6 1i(){}7.j(\'3n\',6(){1i()});7.j(\'3m\',6(){1i()});7.j("k",6(y){h 9=7.1b();c(9.n<2)19;$(\'.3-8-3l-3k\').3j(6(){$(\'#3-8-a-k\').1e(\'3-8-a-z\');$(\'.3-a-k\').p(\'o-1f\',\'11\')});7.1h("/3i/3h.3g","3f 3e",6(){$(\'.3-1w\').3d(\'3-8-1v\');$(\'.3-8-1y, .3-8-1x\').p(\'o-1g\',\'11\');c($(\'.3-1w\').3c(\'3-8-1v\')){$(\'.3-a-k\').p(\'o-1g\',\'l\');$(\'.3-a-k\').p(\'o-1f\',\'l\');$(\'.3-8-a\').1e(\'3-8-a-z\');$(\'.3-8-a:1u\').3b(\'3-8-a-z\')}3a{$(\'.3-a-k\').p(\'o-1g\',\'11\');$(\'.3-a-k\').p(\'o-1f\',\'11\');$(\'.3-8-a:1u\').1e(\'3-8-a-z\')}},"39");7.j("38",6(y){1d.37(\'1c\',y.9[y.36].1a)});c(1d.1t(\'1c\')){35("1s(1d.1t(\'1c\'));",34)}});h 18;6 1s(1q){h 9=7.1b();c(9.n>1){1r(i=0;i<9.n;i++){c(9[i].1a==1q){c(i==18){19}18=i;7.1p(i)}}}}',36,270,'|||jw|||function|player|settings|tracks|submenu||if||||jwplayer|var||on|audioTracks|true|3D|length|aria|attr|div|100|||sx|filemoon|https||event|active||false|tt|seek|dd|height|width|adb|current_audio|return|name|getAudioTracks|default_audio|localStorage|removeClass|expanded|checked|addButton|callMeMaybe|vplayer|0fxcyc2ajhp1|position|vvplay|vvad|220|setCurrentAudioTrack|audio_name|for|audio_set|getItem|last|open|controls|playbackRates|captions|rewind|icon|insertAfter||detach|ff00||button|getPosition|sec|png|player8|ff11|log|console|track_name|appendTo|play|click|no|scrolling|frameborder|file_code|src|top|zIndex|css|showCCform|data|1662367683|383371|dl|video_ad|doPlay|prevt|mp4|3E||jpg|thumbs|file|300|setTimeout|currentTrack|setItem|audioTrackChanged|dualSound|else|addClass|hasClass|toggleClass|Track|Audio|svg|dualy|images|mousedown|buttons|topbar|playAttemptFailed|beforePlay|Rewind|fr|Forward|ff|ready|set_audio_track|remove|this|upload_srt|prop|50px|margin|1000001|iframe|center|align|text|rgba|background|1000000|left|absolute|pause|setCurrentCaptions|Upload|contains|item|content|html|fviews|referer|prem|embed|3e57249ef633e0d03bf76ceb8d8a4b65|216|83|hash|view|get|TokenZir|window|hide|show|complete|slow|fadeIn|video_ad_fadein|time||cache|Cache|Content|headers|ajaxSetup|v2done|tott|vastdone2|vastdone1|vvbefore|playbackRateControls|cast|aboutlink|FileMoon|abouttext|UHD|1870|qualityLabels|sites|GNOME_POWER|link|2Fiframe|3C|allowfullscreen|22360|22640|22no|marginheight|marginwidth|2FGNOME_POWER|2F0fxcyc2ajhp1|2Fe|2Ffilemoon|2F|3A||22https|3Ciframe|code|sharing|fontOpacity|backgroundOpacity|Tahoma|fontFamily|303030|backgroundColor|FFFFFF|color|userFontScale|thumbnails|kind|0fxcyc2ajhp10000|url|get_slides|start|startparam|none|preload|html5|primary|hlshtml|androidhls|duration|uniform|stretching|0fxcyc2ajhp1_xt|image|2048|sp|6871|asn|127|srv|43200|_g3XlBcu2lmD9oDexD2NLWSmah2Nu3XcDrl93m9PwXY|m3u8||master|0fxcyc2ajhp1_x|00076|01|hls2|to|s01|delivery|storage|moon|sources|setup'''.split('|')))
def test_join(self):
test_input = list('test')
tests = [
'function f(a, b){return a.join(b)}',
'function f(a, b){return Array.prototype.join.call(a, b)}',
'function f(a, b){return Array.prototype.join.apply(a, [b])}',
]
for test in tests:
jsi = JSInterpreter(test)
self._test(jsi, 'test', args=[test_input, ''])
self._test(jsi, 't-e-s-t', args=[test_input, '-'])
self._test(jsi, '', args=[[], '-'])
def test_split(self):
test_result = list('test')
tests = [
'function f(a, b){return a.split(b)}',
'function f(a, b){return String.prototype.split.call(a, b)}',
'function f(a, b){return String.prototype.split.apply(a, [b])}',
]
for test in tests:
jsi = JSInterpreter(test)
self._test(jsi, test_result, args=['test', ''])
self._test(jsi, test_result, args=['t-e-s-t', '-'])
self._test(jsi, [''], args=['', '-'])
self._test(jsi, [], args=['', ''])
def test_slice(self):
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
self._test('function f(){return "012345678".slice()}', '012345678')
self._test('function f(){return "012345678".slice(0)}', '012345678')
self._test('function f(){return "012345678".slice(5)}', '5678')
self._test('function f(){return "012345678".slice(99)}', '')
self._test('function f(){return "012345678".slice(-2)}', '78')
self._test('function f(){return "012345678".slice(-99)}', '012345678')
self._test('function f(){return "012345678".slice(0, 0)}', '')
self._test('function f(){return "012345678".slice(1, 0)}', '')
self._test('function f(){return "012345678".slice(0, 1)}', '0')
self._test('function f(){return "012345678".slice(3, 6)}', '345')
self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
self._test('function f(){return "012345678".slice(-1, 1)}', '')
self._test('function f(){return "012345678".slice(-3, -1)}', '67')
if __name__ == '__main__':
unittest.main()

2
test/test_netrc.py
View file

@ -21,7 +21,7 @@ def test_netrc_present(self):
continue
self.assertTrue(
ie._NETRC_MACHINE,
'Extractor %s supports login, but is missing a _NETRC_MACHINE property' % ie.IE_NAME)
f'Extractor {ie.IE_NAME} supports login, but is missing a _NETRC_MACHINE property')
if __name__ == '__main__':

138
test/test_networking.py
View file

@ -265,6 +265,11 @@ def do_GET(self):
self.end_headers()
self.wfile.write(payload)
self.finish()
elif self.path == '/get_cookie':
self.send_response(200)
self.send_header('Set-Cookie', 'test=ytdlp; path=/')
self.end_headers()
self.finish()
else:
self._status(404)
@ -338,6 +343,52 @@ def test_ssl_error(self, handler):
validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
assert not issubclass(exc_info.type, CertificateVerifyError)
@pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
def test_legacy_ssl_extension(self, handler):
# HTTPS server with old ciphers
# XXX: is there a better way to test this than to create a new server?
https_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
https_port = http_server_port(https_httpd)
https_server_thread = threading.Thread(target=https_httpd.serve_forever)
https_server_thread.daemon = True
https_server_thread.start()
with handler(verify=False) as rh:
res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers', extensions={'legacy_ssl': True}))
assert res.status == 200
res.close()
# Ensure only applies to request extension
with pytest.raises(SSLError):
validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
@pytest.mark.skip_handler('CurlCFFI', 'legacy_ssl ignored by CurlCFFI')
def test_legacy_ssl_support(self, handler):
# HTTPS server with old ciphers
# XXX: is there a better way to test this than to create a new server?
https_httpd = http.server.ThreadingHTTPServer(
('127.0.0.1', 0), HTTPTestRequestHandler)
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(os.path.join(TEST_DIR, 'testcert.pem'), None)
https_httpd.socket = sslctx.wrap_socket(https_httpd.socket, server_side=True)
https_port = http_server_port(https_httpd)
https_server_thread = threading.Thread(target=https_httpd.serve_forever)
https_server_thread.daemon = True
https_server_thread.start()
with handler(verify=False, legacy_ssl_support=True) as rh:
res = validate_and_send(rh, Request(f'https://127.0.0.1:{https_port}/headers'))
assert res.status == 200
res.close()
def test_percent_encode(self, handler):
with handler() as rh:
# Unicode characters should be encoded with uppercase percent-encoding
@ -375,10 +426,10 @@ def test_raise_http_error(self, handler):
with handler() as rh:
for bad_status in (400, 500, 599, 302):
with pytest.raises(HTTPError):
validate_and_send(rh, Request('http://127.0.0.1:%d/gen_%d' % (self.http_port, bad_status)))
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/gen_{bad_status}'))
# Should not raise an error
validate_and_send(rh, Request('http://127.0.0.1:%d/gen_200' % self.http_port)).close()
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/gen_200')).close()
def test_response_url(self, handler):
with handler() as rh:
@ -472,7 +523,7 @@ def test_redirect_loop(self, handler):
def test_incompleteread(self, handler):
with handler(timeout=2) as rh:
with pytest.raises(IncompleteRead, match='13 bytes read, 234221 more expected'):
validate_and_send(rh, Request('http://127.0.0.1:%d/incompleteread' % self.http_port)).read()
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/incompleteread')).read()
def test_cookies(self, handler):
cookiejar = YoutubeDLCookieJar()
@ -490,6 +541,24 @@ def test_cookies(self, handler):
rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': cookiejar})).read()
assert b'cookie: test=ytdlp' in data.lower()
def test_cookie_sync_only_cookiejar(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
with handler() as rh:
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers', extensions={'cookiejar': YoutubeDLCookieJar()})).read()
assert b'cookie: test=ytdlp' not in data.lower()
def test_cookie_sync_delete_cookie(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
cookiejar = YoutubeDLCookieJar()
with handler(cookiejar=cookiejar) as rh:
validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/get_cookie'))
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
assert b'cookie: test=ytdlp' in data.lower()
cookiejar.clear_session_cookies()
data = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/headers')).read()
assert b'cookie: test=ytdlp' not in data.lower()
def test_headers(self, handler):
with handler(headers=HTTPHeaderDict({'test1': 'test', 'test2': 'test2'})) as rh:
@ -740,7 +809,7 @@ class TestRequestHandlerMisc:
@pytest.mark.parametrize('handler,logger_name', [
('Requests', 'urllib3'),
('Websockets', 'websockets.client'),
('Websockets', 'websockets.server')
('Websockets', 'websockets.server'),
], indirect=['handler'])
def test_remove_logging_handler(self, handler, logger_name):
# Ensure any logging handlers, which may contain a YoutubeDL instance,
@ -794,7 +863,7 @@ def test_verify_cert_error_text(self, handler):
with handler() as rh:
with pytest.raises(
CertificateVerifyError,
match=r'\[SSL: CERTIFICATE_VERIFY_FAILED\] certificate verify failed: self.signed certificate'
match=r'\[SSL: CERTIFICATE_VERIFY_FAILED\] certificate verify failed: self.signed certificate',
):
validate_and_send(rh, Request(f'https://127.0.0.1:{self.https_port}/headers'))
@ -804,14 +873,14 @@ def test_verify_cert_error_text(self, handler):
(
Request('http://127.0.0.1', method='GET\n'),
'method can\'t contain control characters',
lambda v: v < (3, 7, 9) or (3, 8, 0) <= v < (3, 8, 5)
lambda v: v < (3, 7, 9) or (3, 8, 0) <= v < (3, 8, 5),
),
# https://github.com/python/cpython/blob/987b712b4aeeece336eed24fcc87a950a756c3e2/Lib/http/client.py#L1265
# bpo-38576: Check implemented in 3.7.8+, 3.8.3+
(
Request('http://127.0.0. 1', method='GET'),
'URL can\'t contain control characters',
lambda v: v < (3, 7, 8) or (3, 8, 0) <= v < (3, 8, 3)
lambda v: v < (3, 7, 8) or (3, 8, 0) <= v < (3, 8, 3),
),
# https://github.com/python/cpython/blob/987b712b4aeeece336eed24fcc87a950a756c3e2/Lib/http/client.py#L1288C31-L1288C50
(Request('http://127.0.0.1', headers={'foo\n': 'bar'}), 'Invalid header name', None),
@ -840,7 +909,7 @@ class TestRequestsRequestHandler(TestRequestHandlerBase):
(lambda: requests.exceptions.InvalidHeader(), RequestError),
# catch-all: https://github.com/psf/requests/blob/main/src/requests/adapters.py#L535
(lambda: urllib3.exceptions.HTTPError(), TransportError),
(lambda: requests.exceptions.RequestException(), RequestError)
(lambda: requests.exceptions.RequestException(), RequestError),
# (lambda: requests.exceptions.TooManyRedirects(), HTTPError) - Needs a response object
])
def test_request_error_mapping(self, handler, monkeypatch, raised, expected):
@ -868,12 +937,12 @@ def request(self, *args, **kwargs):
(
lambda: urllib3.exceptions.ProtocolError('error', http.client.IncompleteRead(partial=b'abc', expected=4)),
IncompleteRead,
'3 bytes read, 4 more expected'
'3 bytes read, 4 more expected',
),
(
lambda: urllib3.exceptions.ProtocolError('error', urllib3.exceptions.IncompleteRead(partial=3, expected=5)),
IncompleteRead,
'3 bytes read, 5 more expected'
'3 bytes read, 5 more expected',
),
])
def test_response_error_mapping(self, handler, monkeypatch, raised, expected, match):
@ -914,7 +983,6 @@ def mock_close(*args, **kwargs):
class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
@pytest.mark.parametrize('params,extensions', [
({}, {'impersonate': ImpersonateTarget('chrome')}),
({'impersonate': ImpersonateTarget('chrome', '110')}, {}),
({'impersonate': ImpersonateTarget('chrome', '99')}, {'impersonate': ImpersonateTarget('chrome', '110')}),
])
@ -1125,7 +1193,7 @@ class HTTPSupportedRH(ValidationRH):
('https', False, {}),
]),
(NoCheckRH, [('http', False, {})]),
(ValidationRH, [('http', UnsupportedRequest, {})])
(ValidationRH, [('http', UnsupportedRequest, {})]),
]
PROXY_SCHEME_TESTS = [
@ -1200,6 +1268,9 @@ class HTTPSupportedRH(ValidationRH):
({'timeout': 1}, False),
({'timeout': 'notatimeout'}, AssertionError),
({'unsupported': 'value'}, UnsupportedRequest),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
('Requests', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),
@ -1207,6 +1278,9 @@ class HTTPSupportedRH(ValidationRH):
({'timeout': 1}, False),
({'timeout': 'notatimeout'}, AssertionError),
({'unsupported': 'value'}, UnsupportedRequest),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
('CurlCFFI', 'http', [
({'cookiejar': 'notacookiejar'}, AssertionError),
@ -1219,7 +1293,10 @@ class HTTPSupportedRH(ValidationRH):
({'impersonate': ImpersonateTarget('chrome', None, None, None)}, False),
({'impersonate': ImpersonateTarget(None, None, None, None)}, False),
({'impersonate': ImpersonateTarget()}, False),
({'impersonate': 'chrome'}, AssertionError)
({'impersonate': 'chrome'}, AssertionError),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
(NoCheckRH, 'http', [
({'cookiejar': 'notacookiejar'}, False),
@ -1228,6 +1305,9 @@ class HTTPSupportedRH(ValidationRH):
('Websockets', 'ws', [
({'cookiejar': YoutubeDLCookieJar()}, False),
({'timeout': 2}, False),
({'legacy_ssl': False}, False),
({'legacy_ssl': True}, False),
({'legacy_ssl': 'notabool'}, AssertionError),
]),
]
@ -1235,7 +1315,7 @@ class HTTPSupportedRH(ValidationRH):
('Urllib', False, 'http'),
('Requests', False, 'http'),
('CurlCFFI', False, 'http'),
('Websockets', False, 'ws')
('Websockets', False, 'ws'),
], indirect=['handler'])
def test_no_proxy(self, handler, fail, scheme):
run_validation(handler, fail, Request(f'{scheme}://', proxies={'no': '127.0.0.1,github.com'}))
@ -1246,7 +1326,7 @@ def test_no_proxy(self, handler, fail, scheme):
(HTTPSupportedRH, 'http'),
('Requests', 'http'),
('CurlCFFI', 'http'),
('Websockets', 'ws')
('Websockets', 'ws'),
], indirect=['handler'])
def test_empty_proxy(self, handler, scheme):
run_validation(handler, False, Request(f'{scheme}://', proxies={scheme: None}))
@ -1258,7 +1338,7 @@ def test_empty_proxy(self, handler, scheme):
(HTTPSupportedRH, 'http'),
('Requests', 'http'),
('CurlCFFI', 'http'),
('Websockets', 'ws')
('Websockets', 'ws'),
], indirect=['handler'])
def test_invalid_proxy_url(self, handler, scheme, proxy_url):
run_validation(handler, UnsupportedRequest, Request(f'{scheme}://', proxies={scheme: proxy_url}))
@ -1474,7 +1554,7 @@ def test_compat_opener(self):
@pytest.mark.parametrize('proxy,expected', [
('http://127.0.0.1:8080', {'all': 'http://127.0.0.1:8080'}),
('', {'all': '__noproxy__'}),
(None, {'http': 'http://127.0.0.1:8081', 'https': 'http://127.0.0.1:8081'}) # env, set https
(None, {'http': 'http://127.0.0.1:8081', 'https': 'http://127.0.0.1:8081'}), # env, set https
])
def test_proxy(self, proxy, expected, monkeypatch):
monkeypatch.setenv('HTTP_PROXY', 'http://127.0.0.1:8081')
@ -1546,7 +1626,7 @@ def _send(self, request: Request):
with FakeImpersonationRHYDL() as ydl:
with pytest.raises(
RequestError,
match=r'Impersonate target "test" is not available'
match=r'Impersonate target "test" is not available',
):
ydl.urlopen(Request('http://', extensions={'impersonate': ImpersonateTarget('test', None, None, None)}))
@ -1558,7 +1638,7 @@ def _send(self, request: Request):
pass
_SUPPORTED_URL_SCHEMES = ('http',)
_SUPPORTED_IMPERSONATE_TARGET_MAP = {ImpersonateTarget('abc',): 'test'}
_SUPPORTED_IMPERSONATE_TARGET_MAP = {ImpersonateTarget('abc'): 'test'}
_SUPPORTED_PROXY_SCHEMES = None
super().__init__(*args, **kwargs)
@ -1567,14 +1647,14 @@ def _send(self, request: Request):
with FakeHTTPRHYDL() as ydl:
with pytest.raises(
RequestError,
match=r'Impersonate target "test" is not available'
match=r'Impersonate target "test" is not available',
):
ydl.urlopen(Request('http://', extensions={'impersonate': ImpersonateTarget('test', None, None, None)}))
def test_raise_impersonate_error(self):
with pytest.raises(
YoutubeDLError,
match=r'Impersonate target "test" is not available'
match=r'Impersonate target "test" is not available',
):
FakeYDL({'impersonate': ImpersonateTarget('test', None, None, None)})
@ -1592,7 +1672,7 @@ def _send(self, request: Request):
monkeypatch.setattr(FakeYDL, 'build_request_director', lambda cls, handlers, preferences=None: brh(cls, handlers=[IRH]))
with FakeYDL({
'impersonate': ImpersonateTarget('abc', None, None, None)
'impersonate': ImpersonateTarget('abc', None, None, None),
}) as ydl:
rh = self.build_handler(ydl, IRH)
assert rh.impersonate == ImpersonateTarget('abc', None, None, None)
@ -1604,7 +1684,7 @@ class TestRH(ImpersonateRequestHandler):
def _send(self, request: Request):
pass
_SUPPORTED_URL_SCHEMES = ('http',)
_SUPPORTED_IMPERSONATE_TARGET_MAP = {ImpersonateTarget(target_client,): 'test'}
_SUPPORTED_IMPERSONATE_TARGET_MAP = {ImpersonateTarget(target_client): 'test'}
RH_KEY = target_client
RH_NAME = target_client
handlers.append(TestRH)
@ -1614,7 +1694,7 @@ def _send(self, request: Request):
assert set(ydl._get_available_impersonate_targets()) == {
(ImpersonateTarget('xyz'), 'xyz'),
(ImpersonateTarget('abc'), 'abc'),
(ImpersonateTarget('asd'), 'asd')
(ImpersonateTarget('asd'), 'asd'),
}
assert ydl._impersonate_target_available(ImpersonateTarget('abc'))
assert ydl._impersonate_target_available(ImpersonateTarget())
@ -1837,7 +1917,7 @@ def test_copy(self):
extensions={'cookiejar': CookieJar()},
headers={'Accept-Encoding': 'br'},
proxies={'http': 'http://127.0.0.1'},
data=[b'123']
data=[b'123'],
)
req_copy = req.copy()
assert req_copy is not req
@ -1863,7 +1943,7 @@ class AnotherRequest(Request):
assert isinstance(req.copy(), AnotherRequest)
def test_url(self):
req = Request(url='https://фtest.example.com/ some spaceв?ä=c',)
req = Request(url='https://фtest.example.com/ some spaceв?ä=c')
assert req.url == 'https://xn--test-z6d.example.com/%20some%20space%D0%B2?%C3%A4=c'
assert Request(url='//example.com').url == 'http://example.com'
@ -1878,7 +1958,7 @@ class TestResponse:
('custom', 200, 'custom'),
(None, 404, 'Not Found'), # fallback status
('', 403, 'Forbidden'),
(None, 999, None)
(None, 999, None),
])
def test_reason(self, reason, status, expected):
res = Response(io.BytesIO(b''), url='test://', headers={}, status=status, reason=reason)
@ -1933,7 +2013,7 @@ def test_target_from_str(self, target_str, expected):
@pytest.mark.parametrize('target_str', [
'-120', ':-12.0', '-12:-12', '-:-',
'::', 'a-c-d:', 'a-c-d:e-f-g', 'a:b:'
'::', 'a-c-d:', 'a-c-d:e-f-g', 'a:b:',
])
def test_target_from_invalid_str(self, target_str):
with pytest.raises(ValueError):
@ -1949,7 +2029,7 @@ def test_target_from_invalid_str(self, target_str):
(ImpersonateTarget('abc', '120', 'xyz', None), 'abc-120:xyz'),
(ImpersonateTarget('abc', None, 'xyz'), 'abc:xyz'),
(ImpersonateTarget(None, None, 'xyz', '6.5'), ':xyz-6.5'),
(ImpersonateTarget('abc', ), 'abc'),
(ImpersonateTarget('abc'), 'abc'),
(ImpersonateTarget(None, None, None, None), ''),
])
def test_str(self, target, expected):

12
test/test_networking_utils.py
View file

@ -39,7 +39,7 @@ def test_select_proxy(self):
proxies = {
'all': 'socks5://example.com',
'http': 'http://example.com:1080',
'no': 'bypass.example.com,yt-dl.org'
'no': 'bypass.example.com,yt-dl.org',
}
assert select_proxy('https://example.com', proxies) == proxies['all']
@ -54,7 +54,7 @@ def test_select_proxy(self):
'port': 1080,
'rdns': True,
'username': None,
'password': None
'password': None,
}),
('socks5://user:@example.com:5555', {
'proxytype': ProxyType.SOCKS5,
@ -62,7 +62,7 @@ def test_select_proxy(self):
'port': 5555,
'rdns': False,
'username': 'user',
'password': ''
'password': '',
}),
('socks4://u%40ser:pa%20ss@127.0.0.1:1080', {
'proxytype': ProxyType.SOCKS4,
@ -70,7 +70,7 @@ def test_select_proxy(self):
'port': 1080,
'rdns': False,
'username': 'u@ser',
'password': 'pa ss'
'password': 'pa ss',
}),
('socks4a://:pa%20ss@127.0.0.1', {
'proxytype': ProxyType.SOCKS4A,
@ -78,8 +78,8 @@ def test_select_proxy(self):
'port': 1080,
'rdns': True,
'username': '',
'password': 'pa ss'
})
'password': 'pa ss',
}),
])
def test_make_socks_proxy_opts(self, socks_proxy, expected):
assert make_socks_proxy_opts(socks_proxy) == expected

4
test/test_overwrites.py
View file

@ -27,7 +27,7 @@ def test_default_overwrites(self):
[
sys.executable, 'yt_dlp/__main__.py',
'-o', 'test.webm',
'https://www.youtube.com/watch?v=jNQXAC9IVRw'
'https://www.youtube.com/watch?v=jNQXAC9IVRw',
], cwd=root_dir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'has already been downloaded' in sout)
@ -39,7 +39,7 @@ def test_yes_overwrites(self):
[
sys.executable, 'yt_dlp/__main__.py', '--yes-overwrites',
'-o', 'test.webm',
'https://www.youtube.com/watch?v=jNQXAC9IVRw'
'https://www.youtube.com/watch?v=jNQXAC9IVRw',
], cwd=root_dir, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
sout, serr = outp.communicate()
self.assertTrue(b'has already been downloaded' not in sout)

2
test/test_plugins.py
View file

@ -31,7 +31,7 @@ def test_extractor_classes(self):
# don't load modules with underscore prefix
self.assertFalse(
f'{PACKAGE_NAME}.extractor._ignore' in sys.modules.keys(),
f'{PACKAGE_NAME}.extractor._ignore' in sys.modules,
'loaded module beginning with underscore')
self.assertNotIn('IgnorePluginIE', plugins_ie.keys())

2
test/test_post_hooks.py
View file

@ -59,7 +59,7 @@ def hook_two(self, filename):
def hook_three(self, filename):
self.files.append(filename)
raise Exception('Test exception for \'%s\'' % filename)
raise Exception(f'Test exception for \'{filename}\'')
def tearDown(self):
for f in self.files:

137
test/test_postprocessors.py
View file

@ -9,7 +9,7 @@
from yt_dlp import YoutubeDL
from yt_dlp.compat import compat_shlex_quote
from yt_dlp.utils import shell_quote
from yt_dlp.postprocessor import (
ExecPP,
FFmpegThumbnailsConvertorPP,
@ -65,7 +65,7 @@ class TestExec(unittest.TestCase):
def test_parse_cmd(self):
pp = ExecPP(YoutubeDL(), '')
info = {'filepath': 'file name'}
cmd = 'echo %s' % compat_shlex_quote(info['filepath'])
cmd = 'echo {}'.format(shell_quote(info['filepath']))
self.assertEqual(pp.parse_cmd('echo', info), cmd)
self.assertEqual(pp.parse_cmd('echo {}', info), cmd)
@ -125,7 +125,8 @@ def test_remove_marked_arrange_sponsors_CanGetThroughUnaltered(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, chapters, [])
def test_remove_marked_arrange_sponsors_ChapterWithSponsors(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 20, 'sponsor'),
self._sponsor_chapter(30, 40, 'preview'),
self._sponsor_chapter(50, 60, 'filler')]
@ -136,7 +137,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithSponsors(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
def test_remove_marked_arrange_sponsors_SponsorBlockChapters(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 20, 'chapter', title='sb c1'),
self._sponsor_chapter(15, 16, 'chapter', title='sb c2'),
self._sponsor_chapter(30, 40, 'preview'),
@ -149,10 +151,14 @@ def test_remove_marked_arrange_sponsors_SponsorBlockChapters(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
def test_remove_marked_arrange_sponsors_UniqueNamesForOverlappingSponsors(self):
chapters = self._chapters([120], ['c']) + [
self._sponsor_chapter(10, 45, 'sponsor'), self._sponsor_chapter(20, 40, 'selfpromo'),
self._sponsor_chapter(50, 70, 'sponsor'), self._sponsor_chapter(60, 85, 'selfpromo'),
self._sponsor_chapter(90, 120, 'selfpromo'), self._sponsor_chapter(100, 110, 'sponsor')]
chapters = [
*self._chapters([120], ['c']),
self._sponsor_chapter(10, 45, 'sponsor'),
self._sponsor_chapter(20, 40, 'selfpromo'),
self._sponsor_chapter(50, 70, 'sponsor'),
self._sponsor_chapter(60, 85, 'selfpromo'),
self._sponsor_chapter(90, 120, 'selfpromo'),
self._sponsor_chapter(100, 110, 'sponsor')]
expected = self._chapters(
[10, 20, 40, 45, 50, 60, 70, 85, 90, 100, 110, 120],
['c', '[SponsorBlock]: Sponsor', '[SponsorBlock]: Sponsor, Unpaid/Self Promotion',
@ -172,7 +178,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithCuts(self):
chapters, self._chapters([40], ['c']), cuts)
def test_remove_marked_arrange_sponsors_ChapterWithSponsorsAndCuts(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 20, 'sponsor'),
self._sponsor_chapter(30, 40, 'selfpromo', remove=True),
self._sponsor_chapter(50, 60, 'interaction')]
@ -185,24 +192,29 @@ def test_remove_marked_arrange_sponsors_ChapterWithSponsorsAndCuts(self):
def test_remove_marked_arrange_sponsors_ChapterWithSponsorCutInTheMiddle(self):
cuts = [self._sponsor_chapter(20, 30, 'selfpromo', remove=True),
self._chapter(40, 50, remove=True)]
chapters = self._chapters([70], ['c']) + [self._sponsor_chapter(10, 60, 'sponsor')] + cuts
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 60, 'sponsor'),
*cuts]
expected = self._chapters(
[10, 40, 50], ['c', '[SponsorBlock]: Sponsor', 'c'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_ChapterWithCutHidingSponsor(self):
cuts = [self._sponsor_chapter(20, 50, 'selfpromo', remove=True)]
chapters = self._chapters([60], ['c']) + [
chapters = [
*self._chapters([60], ['c']),
self._sponsor_chapter(10, 20, 'intro'),
self._sponsor_chapter(30, 40, 'sponsor'),
self._sponsor_chapter(50, 60, 'outro'),
] + cuts
*cuts]
expected = self._chapters(
[10, 20, 30], ['c', '[SponsorBlock]: Intermission/Intro Animation', '[SponsorBlock]: Endcards/Credits'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_ChapterWithAdjacentSponsors(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 20, 'sponsor'),
self._sponsor_chapter(20, 30, 'selfpromo'),
self._sponsor_chapter(30, 40, 'interaction')]
@ -213,7 +225,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithAdjacentSponsors(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
def test_remove_marked_arrange_sponsors_ChapterWithAdjacentCuts(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 20, 'sponsor'),
self._sponsor_chapter(20, 30, 'interaction', remove=True),
self._chapter(30, 40, remove=True),
@ -226,7 +239,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithAdjacentCuts(self):
chapters, expected, [self._chapter(20, 50, remove=True)])
def test_remove_marked_arrange_sponsors_ChapterWithOverlappingSponsors(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 30, 'sponsor'),
self._sponsor_chapter(20, 50, 'selfpromo'),
self._sponsor_chapter(40, 60, 'interaction')]
@ -238,7 +252,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithOverlappingSponsors(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
def test_remove_marked_arrange_sponsors_ChapterWithOverlappingCuts(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 30, 'sponsor', remove=True),
self._sponsor_chapter(20, 50, 'selfpromo', remove=True),
self._sponsor_chapter(40, 60, 'interaction', remove=True)]
@ -246,7 +261,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithOverlappingCuts(self):
chapters, self._chapters([20], ['c']), [self._chapter(10, 60, remove=True)])
def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingSponsors(self):
chapters = self._chapters([170], ['c']) + [
chapters = [
*self._chapters([170], ['c']),
self._sponsor_chapter(0, 30, 'intro'),
self._sponsor_chapter(20, 50, 'sponsor'),
self._sponsor_chapter(40, 60, 'selfpromo'),
@ -267,7 +283,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingSponsors(sel
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingCuts(self):
chapters = self._chapters([170], ['c']) + [
chapters = [
*self._chapters([170], ['c']),
self._chapter(0, 30, remove=True),
self._sponsor_chapter(20, 50, 'sponsor', remove=True),
self._chapter(40, 60, remove=True),
@ -284,7 +301,8 @@ def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingCuts(self):
chapters, self._chapters([20], ['c']), expected_cuts)
def test_remove_marked_arrange_sponsors_OverlappingSponsorsDifferentTitlesAfterCut(self):
chapters = self._chapters([60], ['c']) + [
chapters = [
*self._chapters([60], ['c']),
self._sponsor_chapter(10, 60, 'sponsor'),
self._sponsor_chapter(10, 40, 'intro'),
self._sponsor_chapter(30, 50, 'interaction'),
@ -297,7 +315,8 @@ def test_remove_marked_arrange_sponsors_OverlappingSponsorsDifferentTitlesAfterC
chapters, expected, [self._chapter(30, 50, remove=True)])
def test_remove_marked_arrange_sponsors_SponsorsNoLongerOverlapAfterCut(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 30, 'sponsor'),
self._sponsor_chapter(20, 50, 'interaction'),
self._sponsor_chapter(30, 50, 'selfpromo', remove=True),
@ -310,7 +329,8 @@ def test_remove_marked_arrange_sponsors_SponsorsNoLongerOverlapAfterCut(self):
chapters, expected, [self._chapter(30, 50, remove=True)])
def test_remove_marked_arrange_sponsors_SponsorsStillOverlapAfterCut(self):
chapters = self._chapters([70], ['c']) + [
chapters = [
*self._chapters([70], ['c']),
self._sponsor_chapter(10, 60, 'sponsor'),
self._sponsor_chapter(20, 60, 'interaction'),
self._sponsor_chapter(30, 50, 'selfpromo', remove=True)]
@ -321,7 +341,8 @@ def test_remove_marked_arrange_sponsors_SponsorsStillOverlapAfterCut(self):
chapters, expected, [self._chapter(30, 50, remove=True)])
def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingSponsorsAndCuts(self):
chapters = self._chapters([200], ['c']) + [
chapters = [
*self._chapters([200], ['c']),
self._sponsor_chapter(10, 40, 'sponsor'),
self._sponsor_chapter(10, 30, 'intro'),
self._chapter(20, 30, remove=True),
@ -347,8 +368,9 @@ def test_remove_marked_arrange_sponsors_ChapterWithRunsOfOverlappingSponsorsAndC
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, expected_cuts)
def test_remove_marked_arrange_sponsors_SponsorOverlapsMultipleChapters(self):
chapters = (self._chapters([20, 40, 60, 80, 100], ['c1', 'c2', 'c3', 'c4', 'c5'])
+ [self._sponsor_chapter(10, 90, 'sponsor')])
chapters = [
*self._chapters([20, 40, 60, 80, 100], ['c1', 'c2', 'c3', 'c4', 'c5']),
self._sponsor_chapter(10, 90, 'sponsor')]
expected = self._chapters([10, 90, 100], ['c1', '[SponsorBlock]: Sponsor', 'c5'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -359,9 +381,10 @@ def test_remove_marked_arrange_sponsors_CutOverlapsMultipleChapters(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorsWithinSomeChaptersAndOverlappingOthers(self):
chapters = (self._chapters([10, 40, 60, 80], ['c1', 'c2', 'c3', 'c4'])
+ [self._sponsor_chapter(20, 30, 'sponsor'),
self._sponsor_chapter(50, 70, 'selfpromo')])
chapters = [
*self._chapters([10, 40, 60, 80], ['c1', 'c2', 'c3', 'c4']),
self._sponsor_chapter(20, 30, 'sponsor'),
self._sponsor_chapter(50, 70, 'selfpromo')]
expected = self._chapters([10, 20, 30, 40, 50, 70, 80],
['c1', 'c2', '[SponsorBlock]: Sponsor', 'c2', 'c3',
'[SponsorBlock]: Unpaid/Self Promotion', 'c4'])
@ -374,8 +397,9 @@ def test_remove_marked_arrange_sponsors_CutsWithinSomeChaptersAndOverlappingOthe
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_ChaptersAfterLastSponsor(self):
chapters = (self._chapters([20, 40, 50, 60], ['c1', 'c2', 'c3', 'c4'])
+ [self._sponsor_chapter(10, 30, 'music_offtopic')])
chapters = [
*self._chapters([20, 40, 50, 60], ['c1', 'c2', 'c3', 'c4']),
self._sponsor_chapter(10, 30, 'music_offtopic')]
expected = self._chapters(
[10, 30, 40, 50, 60],
['c1', '[SponsorBlock]: Non-Music Section', 'c2', 'c3', 'c4'])
@ -388,8 +412,9 @@ def test_remove_marked_arrange_sponsors_ChaptersAfterLastCut(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorStartsAtChapterStart(self):
chapters = (self._chapters([10, 20, 40], ['c1', 'c2', 'c3'])
+ [self._sponsor_chapter(20, 30, 'sponsor')])
chapters = [
*self._chapters([10, 20, 40], ['c1', 'c2', 'c3']),
self._sponsor_chapter(20, 30, 'sponsor')]
expected = self._chapters([10, 20, 30, 40], ['c1', 'c2', '[SponsorBlock]: Sponsor', 'c3'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -400,8 +425,9 @@ def test_remove_marked_arrange_sponsors_CutStartsAtChapterStart(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorEndsAtChapterEnd(self):
chapters = (self._chapters([10, 30, 40], ['c1', 'c2', 'c3'])
+ [self._sponsor_chapter(20, 30, 'sponsor')])
chapters = [
*self._chapters([10, 30, 40], ['c1', 'c2', 'c3']),
self._sponsor_chapter(20, 30, 'sponsor')]
expected = self._chapters([10, 20, 30, 40], ['c1', 'c2', '[SponsorBlock]: Sponsor', 'c3'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -412,8 +438,9 @@ def test_remove_marked_arrange_sponsors_CutEndsAtChapterEnd(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorCoincidesWithChapters(self):
chapters = (self._chapters([10, 20, 30, 40], ['c1', 'c2', 'c3', 'c4'])
+ [self._sponsor_chapter(10, 30, 'sponsor')])
chapters = [
*self._chapters([10, 20, 30, 40], ['c1', 'c2', 'c3', 'c4']),
self._sponsor_chapter(10, 30, 'sponsor')]
expected = self._chapters([10, 30, 40], ['c1', '[SponsorBlock]: Sponsor', 'c4'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -424,8 +451,9 @@ def test_remove_marked_arrange_sponsors_CutCoincidesWithChapters(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorsAtVideoBoundaries(self):
chapters = (self._chapters([20, 40, 60], ['c1', 'c2', 'c3'])
+ [self._sponsor_chapter(0, 10, 'intro'), self._sponsor_chapter(50, 60, 'outro')])
chapters = [
*self._chapters([20, 40, 60], ['c1', 'c2', 'c3']),
self._sponsor_chapter(0, 10, 'intro'), self._sponsor_chapter(50, 60, 'outro')]
expected = self._chapters(
[10, 20, 40, 50, 60], ['[SponsorBlock]: Intermission/Intro Animation', 'c1', 'c2', 'c3', '[SponsorBlock]: Endcards/Credits'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -437,8 +465,10 @@ def test_remove_marked_arrange_sponsors_CutsAtVideoBoundaries(self):
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_SponsorsOverlapChaptersAtVideoBoundaries(self):
chapters = (self._chapters([10, 40, 50], ['c1', 'c2', 'c3'])
+ [self._sponsor_chapter(0, 20, 'intro'), self._sponsor_chapter(30, 50, 'outro')])
chapters = [
*self._chapters([10, 40, 50], ['c1', 'c2', 'c3']),
self._sponsor_chapter(0, 20, 'intro'),
self._sponsor_chapter(30, 50, 'outro')]
expected = self._chapters(
[20, 30, 50], ['[SponsorBlock]: Intermission/Intro Animation', 'c2', '[SponsorBlock]: Endcards/Credits'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -450,8 +480,10 @@ def test_remove_marked_arrange_sponsors_CutsOverlapChaptersAtVideoBoundaries(sel
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, cuts)
def test_remove_marked_arrange_sponsors_EverythingSponsored(self):
chapters = (self._chapters([10, 20, 30, 40], ['c1', 'c2', 'c3', 'c4'])
+ [self._sponsor_chapter(0, 20, 'intro'), self._sponsor_chapter(20, 40, 'outro')])
chapters = [
*self._chapters([10, 20, 30, 40], ['c1', 'c2', 'c3', 'c4']),
self._sponsor_chapter(0, 20, 'intro'),
self._sponsor_chapter(20, 40, 'outro')]
expected = self._chapters([20, 40], ['[SponsorBlock]: Intermission/Intro Animation', '[SponsorBlock]: Endcards/Credits'])
self._remove_marked_arrange_sponsors_test_impl(chapters, expected, [])
@ -491,38 +523,39 @@ def test_remove_marked_arrange_sponsors_TinyChapterAtTheStartPrependedToTheNext(
chapters, self._chapters([2.5], ['c2']), cuts)
def test_remove_marked_arrange_sponsors_TinyChaptersResultingFromSponsorOverlapAreIgnored(self):
chapters = self._chapters([1, 3, 4], ['c1', 'c2', 'c3']) + [
chapters = [
*self._chapters([1, 3, 4], ['c1', 'c2', 'c3']),
self._sponsor_chapter(1.5, 2.5, 'sponsor')]
self._remove_marked_arrange_sponsors_test_impl(
chapters, self._chapters([1.5, 2.5, 4], ['c1', '[SponsorBlock]: Sponsor', 'c3']), [])
def test_remove_marked_arrange_sponsors_TinySponsorsOverlapsAreIgnored(self):
chapters = self._chapters([2, 3, 5], ['c1', 'c2', 'c3']) + [
chapters = [
*self._chapters([2, 3, 5], ['c1', 'c2', 'c3']),
self._sponsor_chapter(1, 3, 'sponsor'),
self._sponsor_chapter(2.5, 4, 'selfpromo')
]
self._sponsor_chapter(2.5, 4, 'selfpromo')]
self._remove_marked_arrange_sponsors_test_impl(
chapters, self._chapters([1, 3, 4, 5], [
'c1', '[SponsorBlock]: Sponsor', '[SponsorBlock]: Unpaid/Self Promotion', 'c3']), [])
def test_remove_marked_arrange_sponsors_TinySponsorsPrependedToTheNextSponsor(self):
chapters = self._chapters([4], ['c']) + [
chapters = [
*self._chapters([4], ['c']),
self._sponsor_chapter(1.5, 2, 'sponsor'),
self._sponsor_chapter(2, 4, 'selfpromo')
]
self._sponsor_chapter(2, 4, 'selfpromo')]
self._remove_marked_arrange_sponsors_test_impl(
chapters, self._chapters([1.5, 4], ['c', '[SponsorBlock]: Unpaid/Self Promotion']), [])
def test_remove_marked_arrange_sponsors_SmallestSponsorInTheOverlapGetsNamed(self):
self._pp._sponsorblock_chapter_title = '[SponsorBlock]: %(name)s'
chapters = self._chapters([10], ['c']) + [
chapters = [
*self._chapters([10], ['c']),
self._sponsor_chapter(2, 8, 'sponsor'),
self._sponsor_chapter(4, 6, 'selfpromo')
]
self._sponsor_chapter(4, 6, 'selfpromo')]
self._remove_marked_arrange_sponsors_test_impl(
chapters, self._chapters([2, 4, 6, 8, 10], [
'c', '[SponsorBlock]: Sponsor', '[SponsorBlock]: Unpaid/Self Promotion',
'[SponsorBlock]: Sponsor', 'c'
'[SponsorBlock]: Sponsor', 'c',
]), [])
def test_make_concat_opts_CommonCase(self):

8
test/test_socks.py
View file

@ -95,7 +95,7 @@ def handle(self):
return
elif Socks5Auth.AUTH_USER_PASS in methods:
self.connection.sendall(struct.pack("!BB", SOCKS5_VERSION, Socks5Auth.AUTH_USER_PASS))
self.connection.sendall(struct.pack('!BB', SOCKS5_VERSION, Socks5Auth.AUTH_USER_PASS))
_, user_len = struct.unpack('!BB', self.connection.recv(2))
username = self.connection.recv(user_len).decode()
@ -174,7 +174,7 @@ def handle(self):
if 0x0 < dest_ip <= 0xFF:
use_remote_dns = True
else:
socks_info['ipv4_address'] = socket.inet_ntoa(struct.pack("!I", dest_ip))
socks_info['ipv4_address'] = socket.inet_ntoa(struct.pack('!I', dest_ip))
user_id = self._read_until_null().decode()
if user_id != (self.socks_kwargs.get('user_id') or ''):
@ -291,7 +291,7 @@ def ctx(request):
('Urllib', 'http'),
('Requests', 'http'),
('Websockets', 'ws'),
('CurlCFFI', 'http')
('CurlCFFI', 'http'),
], indirect=True)
class TestSocks4Proxy:
def test_socks4_no_auth(self, handler, ctx):
@ -366,7 +366,7 @@ def test_timeout(self, handler, ctx):
('Urllib', 'http'),
('Requests', 'http'),
('Websockets', 'ws'),
('CurlCFFI', 'http')
('CurlCFFI', 'http'),
], indirect=True)
class TestSocks5Proxy:

11
test/test_subtitles.py
View file

@ -40,12 +40,11 @@ def setUp(self):
self.ie = self.IE()
self.DL.add_info_extractor(self.ie)
if not self.IE.working():
print('Skipping: %s marked as not _WORKING' % self.IE.ie_key())
print(f'Skipping: {self.IE.ie_key()} marked as not _WORKING')
self.skipTest('IE marked as not _WORKING')
def getInfoDict(self):
info_dict = self.DL.extract_info(self.url, download=False)
return info_dict
return self.DL.extract_info(self.url, download=False)
def getSubtitles(self):
info_dict = self.getInfoDict()
@ -87,7 +86,7 @@ def test_youtube_allsubtitles(self):
self.assertEqual(md5(subtitles['en']), 'ae1bd34126571a77aabd4d276b28044d')
self.assertEqual(md5(subtitles['it']), '0e0b667ba68411d88fd1c5f4f4eab2f9')
for lang in ['fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, f'Subtitles for \'{lang}\' not extracted')
def _test_subtitles_format(self, fmt, md5_hash, lang='en'):
self.DL.params['writesubtitles'] = True
@ -157,7 +156,7 @@ def test_allsubtitles(self):
self.assertEqual(md5(subtitles['en']), '976553874490cba125086bbfea3ff76f')
self.assertEqual(md5(subtitles['fr']), '594564ec7d588942e384e920e5341792')
for lang in ['es', 'fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, f'Subtitles for \'{lang}\' not extracted')
def test_nosubtitles(self):
self.DL.expect_warning('video doesn\'t have subtitles')
@ -182,7 +181,7 @@ def test_allsubtitles(self):
self.assertEqual(md5(subtitles['en']), '4262c1665ff928a2dada178f62cb8d14')
self.assertEqual(md5(subtitles['fr']), '66a63f7f42c97a50f8c0e90bc7797bb5')
for lang in ['es', 'fr', 'de']:
self.assertTrue(subtitles.get(lang) is not None, 'Subtitles for \'%s\' not extracted' % lang)
self.assertTrue(subtitles.get(lang) is not None, f'Subtitles for \'{lang}\' not extracted')
@is_download_test

6
test/test_traversal.py
View file

@ -31,7 +31,7 @@ def test_traversal_base(self):
'allow tuple path'
assert traverse_obj(_TEST_DATA, ['str']) == 'str', \
'allow list path'
assert traverse_obj(_TEST_DATA, (value for value in ("str",))) == 'str', \
assert traverse_obj(_TEST_DATA, (value for value in ('str',))) == 'str', \
'allow iterable path'
assert traverse_obj(_TEST_DATA, 'str') == 'str', \
'single items should be treated as a path'
@ -70,7 +70,7 @@ def test_traversal_function(self):
def test_traversal_set(self):
# transformation/type, like `expected_type`
assert traverse_obj(_TEST_DATA, (..., {str.upper}, )) == ['STR'], \
assert traverse_obj(_TEST_DATA, (..., {str.upper})) == ['STR'], \
'Function in set should be a transformation'
assert traverse_obj(_TEST_DATA, (..., {str})) == ['str'], \
'Type in set should be a type filter'
@ -276,7 +276,7 @@ def test_traversal_traverse_string(self):
'`...` should result in string (same value) if `traverse_string`'
assert traverse_obj(_TRAVERSE_STRING_DATA, ('str', slice(0, None, 2)), traverse_string=True) == 'sr', \
'`slice` should result in string if `traverse_string`'
assert traverse_obj(_TRAVERSE_STRING_DATA, ('str', lambda i, v: i or v == "s"), traverse_string=True) == 'str', \
assert traverse_obj(_TRAVERSE_STRING_DATA, ('str', lambda i, v: i or v == 's'), traverse_string=True) == 'str', \
'function should result in string if `traverse_string`'
assert traverse_obj(_TRAVERSE_STRING_DATA, ('str', (0, 2)), traverse_string=True) == ['s', 'r'], \
'branching should result in list if `traverse_string`'

8
test/test_update.py
View file

@ -78,11 +78,11 @@
TEST_LOCKFILE_COMMENT = '# This file is used for regulating self-update'
TEST_LOCKFILE_V1 = r'''%s
TEST_LOCKFILE_V1 = rf'''{TEST_LOCKFILE_COMMENT}
lock 2022.08.18.36 .+ Python 3\.6
lock 2023.11.16 (?!win_x86_exe).+ Python 3\.7
lock 2023.11.16 win_x86_exe .+ Windows-(?:Vista|2008Server)
''' % TEST_LOCKFILE_COMMENT
'''
TEST_LOCKFILE_V2_TMPL = r'''%s
lockV2 yt-dlp/yt-dlp 2022.08.18.36 .+ Python 3\.6
@ -98,12 +98,12 @@
TEST_LOCKFILE_ACTUAL = TEST_LOCKFILE_V2_TMPL % TEST_LOCKFILE_V1.rstrip('\n')
TEST_LOCKFILE_FORK = r'''%s# Test if a fork blocks updates to non-numeric tags
TEST_LOCKFILE_FORK = rf'''{TEST_LOCKFILE_ACTUAL}# Test if a fork blocks updates to non-numeric tags
lockV2 fork/yt-dlp pr0000 .+ Python 3.6
lockV2 fork/yt-dlp pr1234 (?!win_x86_exe).+ Python 3\.7
lockV2 fork/yt-dlp pr1234 win_x86_exe .+ Windows-(?:Vista|2008Server)
lockV2 fork/yt-dlp pr9999 .+ Python 3.11
''' % TEST_LOCKFILE_ACTUAL
'''
class FakeUpdater(Updater):

102
test/test_utils.py
View file

@ -130,6 +130,7 @@
xpath_text,
xpath_with_ns,
)
from yt_dlp.utils._utils import _UnsafeExtensionError
from yt_dlp.utils.networking import (
HTTPHeaderDict,
escape_rfc3986,
@ -276,11 +277,18 @@ def env(var):
self.assertEqual(expand_path(env('HOME')), os.getenv('HOME'))
self.assertEqual(expand_path('~'), os.getenv('HOME'))
self.assertEqual(
expand_path('~/%s' % env('yt_dlp_EXPATH_PATH')),
'%s/expanded' % os.getenv('HOME'))
expand_path('~/{}'.format(env('yt_dlp_EXPATH_PATH'))),
'{}/expanded'.format(os.getenv('HOME')))
finally:
os.environ['HOME'] = old_home or ''
_uncommon_extensions = [
('exe', 'abc.exe.ext'),
('de', 'abc.de.ext'),
('../.mp4', None),
('..\\.mp4', None),
]
def test_prepend_extension(self):
self.assertEqual(prepend_extension('abc.ext', 'temp'), 'abc.temp.ext')
self.assertEqual(prepend_extension('abc.ext', 'temp', 'ext'), 'abc.temp.ext')
@ -289,6 +297,19 @@ def test_prepend_extension(self):
self.assertEqual(prepend_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(prepend_extension('.abc.ext', 'temp'), '.abc.temp.ext')
# Test uncommon extensions
self.assertEqual(prepend_extension('abc.ext', 'bin'), 'abc.bin.ext')
for ext, result in self._uncommon_extensions:
with self.assertRaises(_UnsafeExtensionError):
prepend_extension('abc', ext)
if result:
self.assertEqual(prepend_extension('abc.ext', ext, 'ext'), result)
else:
with self.assertRaises(_UnsafeExtensionError):
prepend_extension('abc.ext', ext, 'ext')
with self.assertRaises(_UnsafeExtensionError):
prepend_extension('abc.unexpected_ext', ext, 'ext')
def test_replace_extension(self):
self.assertEqual(replace_extension('abc.ext', 'temp'), 'abc.temp')
self.assertEqual(replace_extension('abc.ext', 'temp', 'ext'), 'abc.temp')
@ -297,6 +318,16 @@ def test_replace_extension(self):
self.assertEqual(replace_extension('.abc', 'temp'), '.abc.temp')
self.assertEqual(replace_extension('.abc.ext', 'temp'), '.abc.temp')
# Test uncommon extensions
self.assertEqual(replace_extension('abc.ext', 'bin'), 'abc.unknown_video')
for ext, _ in self._uncommon_extensions:
with self.assertRaises(_UnsafeExtensionError):
replace_extension('abc', ext)
with self.assertRaises(_UnsafeExtensionError):
replace_extension('abc.ext', ext, 'ext')
with self.assertRaises(_UnsafeExtensionError):
replace_extension('abc.unexpected_ext', ext, 'ext')
def test_subtitles_filename(self):
self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt'), 'abc.en.vtt')
self.assertEqual(subtitles_filename('abc.ext', 'en', 'vtt', 'ext'), 'abc.en.vtt')
@ -356,12 +387,12 @@ def test_datetime_from_str(self):
self.assertEqual(datetime_from_str('now+23hours', precision='hour'), datetime_from_str('now+23hours', precision='auto'))
def test_daterange(self):
_20century = DateRange("19000101", "20000101")
self.assertFalse("17890714" in _20century)
_ac = DateRange("00010101")
self.assertTrue("19690721" in _ac)
_firstmilenium = DateRange(end="10000101")
self.assertTrue("07110427" in _firstmilenium)
_20century = DateRange('19000101', '20000101')
self.assertFalse('17890714' in _20century)
_ac = DateRange('00010101')
self.assertTrue('19690721' in _ac)
_firstmilenium = DateRange(end='10000101')
self.assertTrue('07110427' in _firstmilenium)
def test_unified_dates(self):
self.assertEqual(unified_strdate('December 21, 2010'), '20101221')
@ -413,6 +444,8 @@ def test_unified_timestamps(self):
self.assertEqual(unified_timestamp('Sep 11, 2013 | 5:49 AM'), 1378878540)
self.assertEqual(unified_timestamp('December 15, 2017 at 7:49 am'), 1513324140)
self.assertEqual(unified_timestamp('2018-03-14T08:32:43.1493874+00:00'), 1521016363)
self.assertEqual(unified_timestamp('Sunday, 26 Nov 2006, 19:00'), 1164567600)
self.assertEqual(unified_timestamp('wed, aug 16, 2008, 12:00pm'), 1218931200)
self.assertEqual(unified_timestamp('December 31 1969 20:00:01 EDT'), 1)
self.assertEqual(unified_timestamp('Wednesday 31 December 1969 18:01:26 MDT'), 86)
@ -506,7 +539,7 @@ def test_xpath_attr(self):
self.assertRaises(ExtractorError, xpath_attr, doc, 'div/p', 'y', fatal=True)
def test_smuggle_url(self):
data = {"ö": "ö", "abc": [3]}
data = {'ö': 'ö', 'abc': [3]}
url = 'https://foo.bar/baz?x=y#a'
smug_url = smuggle_url(url, data)
unsmug_url, unsmug_data = unsmuggle_url(smug_url)
@ -784,7 +817,7 @@ def test_parse_iso8601(self):
def test_strip_jsonp(self):
stripped = strip_jsonp('cb ([ {"id":"532cb",\n\n\n"x":\n3}\n]\n);')
d = json.loads(stripped)
self.assertEqual(d, [{"id": "532cb", "x": 3}])
self.assertEqual(d, [{'id': '532cb', 'x': 3}])
stripped = strip_jsonp('parseMetadata({"STATUS":"OK"})\n\n\n//epc')
d = json.loads(stripped)
@ -898,6 +931,11 @@ def test_parse_codecs(self):
'acodec': 'none',
'dynamic_range': 'DV',
})
self.assertEqual(parse_codecs('fLaC'), {
'vcodec': 'none',
'acodec': 'flac',
'dynamic_range': None,
})
self.assertEqual(parse_codecs('theora, vorbis'), {
'vcodec': 'theora',
'acodec': 'vorbis',
@ -922,19 +960,19 @@ def test_escape_rfc3986(self):
def test_normalize_url(self):
self.assertEqual(
normalize_url('http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavré_FD.mp4'),
'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4'
'http://wowza.imust.org/srv/vod/telemb/new/UPLOAD/UPLOAD/20224_IncendieHavre%CC%81_FD.mp4',
)
self.assertEqual(
normalize_url('http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erklärt/Das-Erste/Video?documentId=22673108&bcastId=5290'),
'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290'
'http://www.ardmediathek.de/tv/Sturm-der-Liebe/Folge-2036-Zu-Mann-und-Frau-erkl%C3%A4rt/Das-Erste/Video?documentId=22673108&bcastId=5290',
)
self.assertEqual(
normalize_url('http://тест.рф/фрагмент'),
'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82'
'http://xn--e1aybc.xn--p1ai/%D1%84%D1%80%D0%B0%D0%B3%D0%BC%D0%B5%D0%BD%D1%82',
)
self.assertEqual(
normalize_url('http://тест.рф/абв?абв=абв#абв'),
'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2'
'http://xn--e1aybc.xn--p1ai/%D0%B0%D0%B1%D0%B2?%D0%B0%D0%B1%D0%B2=%D0%B0%D0%B1%D0%B2#%D0%B0%D0%B1%D0%B2',
)
self.assertEqual(normalize_url('http://vimeo.com/56015672#at=0'), 'http://vimeo.com/56015672#at=0')
@ -979,7 +1017,7 @@ def test_js_to_json_vars_strings(self):
'e': 'false',
'f': '"false"',
'g': 'var',
}
},
)),
{
'null': None,
@ -988,8 +1026,8 @@ def test_js_to_json_vars_strings(self):
'trueStr': 'true',
'false': False,
'falseStr': 'false',
'unresolvedVar': 'var'
}
'unresolvedVar': 'var',
},
)
self.assertDictEqual(
@ -1005,14 +1043,14 @@ def test_js_to_json_vars_strings(self):
'b': '"123"',
'c': '1.23',
'd': '"1.23"',
}
},
)),
{
'int': 123,
'intStr': '123',
'float': 1.23,
'floatStr': '1.23',
}
},
)
self.assertDictEqual(
@ -1028,14 +1066,14 @@ def test_js_to_json_vars_strings(self):
'b': '"{}"',
'c': '[]',
'd': '"[]"',
}
},
)),
{
'object': {},
'objectStr': '{}',
'array': [],
'arrayStr': '[]',
}
},
)
def test_js_to_json_realworld(self):
@ -1081,7 +1119,7 @@ def test_js_to_json_realworld(self):
def test_js_to_json_edgecases(self):
on = js_to_json("{abc_def:'1\\'\\\\2\\\\\\'3\"4'}")
self.assertEqual(json.loads(on), {"abc_def": "1'\\2\\'3\"4"})
self.assertEqual(json.loads(on), {'abc_def': "1'\\2\\'3\"4"})
on = js_to_json('{"abc": true}')
self.assertEqual(json.loads(on), {'abc': True})
@ -1113,9 +1151,9 @@ def test_js_to_json_edgecases(self):
'c': 0,
'd': 42.42,
'e': [],
'f': "abc",
'g': "",
'42': 42
'f': 'abc',
'g': '',
'42': 42,
})
on = js_to_json('["abc", "def",]')
@ -1209,8 +1247,8 @@ def test_js_to_json_common_constructors(self):
self.assertEqual(json.loads(js_to_json('Array(5, 10)')), [5, 10])
self.assertEqual(json.loads(js_to_json('new Array(15,5)')), [15, 5])
self.assertEqual(json.loads(js_to_json('new Map([Array(5, 10),new Array(15,5)])')), {'5': 10, '15': 5})
self.assertEqual(json.loads(js_to_json('new Date("123")')), "123")
self.assertEqual(json.loads(js_to_json('new Date(\'2023-10-19\')')), "2023-10-19")
self.assertEqual(json.loads(js_to_json('new Date("123")')), '123')
self.assertEqual(json.loads(js_to_json('new Date(\'2023-10-19\')')), '2023-10-19')
def test_extract_attributes(self):
self.assertEqual(extract_attributes('<e x="y">'), {'x': 'y'})
@ -1265,7 +1303,7 @@ def test_intlist_to_bytes(self):
def test_args_to_str(self):
self.assertEqual(
args_to_str(['foo', 'ba/r', '-baz', '2 be', '']),
'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""'
'foo ba/r -baz \'2 be\' \'\'' if compat_os_name != 'nt' else 'foo ba/r -baz "2 be" ""',
)
def test_parse_filesize(self):
@ -1348,10 +1386,10 @@ def test_is_html(self):
self.assertTrue(is_html( # UTF-8 with BOM
b'\xef\xbb\xbf<!DOCTYPE foo>\xaaa'))
self.assertTrue(is_html( # UTF-16-LE
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00'
b'\xff\xfe<\x00h\x00t\x00m\x00l\x00>\x00\xe4\x00',
))
self.assertTrue(is_html( # UTF-16-BE
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4'
b'\xfe\xff\x00<\x00h\x00t\x00m\x00l\x00>\x00\xe4',
))
self.assertTrue(is_html( # UTF-32-BE
b'\x00\x00\xFE\xFF\x00\x00\x00<\x00\x00\x00h\x00\x00\x00t\x00\x00\x00m\x00\x00\x00l\x00\x00\x00>\x00\x00\x00\xe4'))
@ -1935,7 +1973,7 @@ def test_locked_file(self):
with locked_file(FILE, test_mode, False):
pass
except (BlockingIOError, PermissionError):
if not testing_write: # FIXME
if not testing_write: # FIXME: blocked read access
print(f'Known issue: Exclusive lock ({lock_mode}) blocks read access ({test_mode})')
continue
self.assertTrue(testing_write, f'{test_mode} is blocked by {lock_mode}')
@ -2003,7 +2041,7 @@ def total(*x, **kwargs):
msg='int fn with expected_type int should give int')
self.assertEqual(try_call(lambda: 1, expected_type=dict), None,
msg='int fn with wrong expected_type should give None')
self.assertEqual(try_call(total, args=(0, 1, 0, ), expected_type=int), 1,
self.assertEqual(try_call(total, args=(0, 1, 0), expected_type=int), 1,
msg='fn should accept arglist')
self.assertEqual(try_call(total, kwargs={'a': 0, 'b': 1, 'c': 0}, expected_type=int), 1,
msg='fn should accept kwargs')

62
test/test_websockets.py
View file

@ -61,6 +61,10 @@ def process_request(self, request):
return websockets.http11.Response(
status.value, status.phrase, websockets.datastructures.Headers([('Location', '/')]), b'')
return self.protocol.reject(status.value, status.phrase)
elif request.path.startswith('/get_cookie'):
response = self.protocol.accept(request)
response.headers['Set-Cookie'] = 'test=ytdlp'
return response
return self.protocol.accept(request)
@ -102,6 +106,15 @@ def create_mtls_wss_websocket_server():
return create_websocket_server(ssl_context=sslctx)
def create_legacy_wss_websocket_server():
certfn = os.path.join(TEST_DIR, 'testcert.pem')
sslctx = ssl.SSLContext(ssl.PROTOCOL_TLS_SERVER)
sslctx.maximum_version = ssl.TLSVersion.TLSv1_2
sslctx.set_ciphers('SHA1:AESCCM:aDSS:eNULL:aNULL')
sslctx.load_cert_chain(certfn, None)
return create_websocket_server(ssl_context=sslctx)
def ws_validate_and_send(rh, req):
rh.validate(req)
max_tries = 3
@ -132,6 +145,9 @@ def setup_class(cls):
cls.mtls_wss_thread, cls.mtls_wss_port = create_mtls_wss_websocket_server()
cls.mtls_wss_base_url = f'wss://127.0.0.1:{cls.mtls_wss_port}'
cls.legacy_wss_thread, cls.legacy_wss_port = create_legacy_wss_websocket_server()
cls.legacy_wss_host = f'wss://127.0.0.1:{cls.legacy_wss_port}'
def test_basic_websockets(self, handler):
with handler() as rh:
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
@ -166,6 +182,22 @@ def test_ssl_error(self, handler):
ws_validate_and_send(rh, Request(self.bad_wss_host))
assert not issubclass(exc_info.type, CertificateVerifyError)
def test_legacy_ssl_extension(self, handler):
with handler(verify=False) as rh:
ws = ws_validate_and_send(rh, Request(self.legacy_wss_host, extensions={'legacy_ssl': True}))
assert ws.status == 101
ws.close()
# Ensure only applies to request extension
with pytest.raises(SSLError):
ws_validate_and_send(rh, Request(self.legacy_wss_host))
def test_legacy_ssl_support(self, handler):
with handler(verify=False, legacy_ssl_support=True) as rh:
ws = ws_validate_and_send(rh, Request(self.legacy_wss_host))
assert ws.status == 101
ws.close()
@pytest.mark.parametrize('path,expected', [
# Unicode characters should be encoded with uppercase percent-encoding
('/中文', '/%E4%B8%AD%E6%96%87'),
@ -248,6 +280,32 @@ def test_cookies(self, handler):
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
def test_cookie_sync_only_cookiejar(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
with handler() as rh:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie', extensions={'cookiejar': YoutubeDLCookieJar()}))
ws = ws_validate_and_send(rh, Request(self.ws_base_url, extensions={'cookiejar': YoutubeDLCookieJar()}))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
ws.close()
@pytest.mark.skip_handler('Websockets', 'Set-Cookie not supported by websockets')
def test_cookie_sync_delete_cookie(self, handler):
# Ensure that cookies are ONLY being handled by the cookiejar
cookiejar = YoutubeDLCookieJar()
with handler(verbose=True, cookiejar=cookiejar) as rh:
ws_validate_and_send(rh, Request(f'{self.ws_base_url}/get_cookie'))
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert json.loads(ws.recv())['cookie'] == 'test=ytdlp'
ws.close()
cookiejar.clear_session_cookies()
ws = ws_validate_and_send(rh, Request(self.ws_base_url))
ws.send('headers')
assert 'cookie' not in json.loads(ws.recv())
ws.close()
def test_source_address(self, handler):
source_address = f'127.0.0.{random.randint(5, 255)}'
verify_address_availability(source_address)
@ -297,14 +355,14 @@ def test_request_headers(self, handler):
'client_certificate': os.path.join(MTLS_CERT_DIR, 'client.crt'),
'client_certificate_key': os.path.join(MTLS_CERT_DIR, 'clientencrypted.key'),
'client_certificate_password': 'foobar',
}
},
))
def test_mtls(self, handler, client_cert):
with handler(
# Disable client-side validation of unacceptable self-signed testcert.pem
# The test is of a check on the server side, so unaffected
verify=False,
client_cert=client_cert
client_cert=client_cert,
) as rh:
ws_validate_and_send(rh, Request(self.mtls_wss_base_url)).close()

2
test/test_youtube_misc.py
View file

@ -13,7 +13,7 @@
class TestYoutubeMisc(unittest.TestCase):
def test_youtube_extract(self):
assertExtractId = lambda url, id: self.assertEqual(YoutubeIE.extract_id(url), id)
assertExtractId = lambda url, video_id: self.assertEqual(YoutubeIE.extract_id(url), video_id)
assertExtractId('http://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?&v=BaW_jenozKc', 'BaW_jenozKc')
assertExtractId('https://www.youtube.com/watch?feature=player_embedded&v=BaW_jenozKc', 'BaW_jenozKc')

28
test/test_youtube_signature.py
View file

@ -46,17 +46,17 @@
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflBb0OQx.js',
84,
'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>'
'123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQ0STUVWXYZ!"#$%&\'()*+,@./:;<=>',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vfl9FYC6l.js',
83,
'123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F'
'123456789abcdefghijklmnopqr0tuvwxyzABCDETGHIJKLMNOPQRS>UVWXYZ!"#$%&\'()*+,-./:;<=F',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflCGk6yw/html5player.js',
'4646B5181C6C3020DF1D9C7FCFEA.AD80ABF70C39BD369CCCAE780AFBB98FA6B6CB42766249D9488C288',
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B'
'82C8849D94266724DC6B6AF89BBFA087EACCD963.B93C07FBA084ACAEFCF7C9D1FD0203C6C1815B6B',
),
(
'https://s.ytimg.com/yts/jsbin/html5player-en_US-vflKjOTVq/html5player.js',
@ -163,6 +163,26 @@
'https://www.youtube.com/s/player/b7910ca8/player_ias.vflset/en_US/base.js',
'_hXMCwMt9qE310D', 'LoZMgkkofRMCZQ',
),
(
'https://www.youtube.com/s/player/590f65a6/player_ias.vflset/en_US/base.js',
'1tm7-g_A9zsI8_Lay_', 'xI4Vem4Put_rOg',
),
(
'https://www.youtube.com/s/player/b22ef6e7/player_ias.vflset/en_US/base.js',
'b6HcntHGkvBLk_FRf', 'kNPW6A7FyP2l8A',
),
(
'https://www.youtube.com/s/player/3400486c/player_ias.vflset/en_US/base.js',
'lL46g3XifCKUZn1Xfw', 'z767lhet6V2Skl',
),
(
'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
'-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
),
(
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
),
]
@ -207,7 +227,7 @@ def tearDown(self):
def t_factory(name, sig_func, url_pattern):
def make_tfunc(url, sig_input, expected_sig):
m = url_pattern.match(url)
assert m, '%r should follow URL format' % url
assert m, f'{url!r} should follow URL format'
test_id = m.group('id')
def test_func(self):

361
yt_dlp/YoutubeDL.py
View file

@ -4,6 +4,7 @@
import datetime as dt
import errno
import fileinput
import functools
import http.cookiejar
import io
import itertools
@ -24,7 +25,7 @@
import unicodedata
from .cache import Cache
from .compat import functools, urllib # isort: split
from .compat import urllib # isort: split
from .compat import compat_os_name, urllib_req_to_req
from .cookies import LenientSimpleCookie, load_cookies
from .downloader import FFmpegFD, get_suitable_downloader, shorten_protocol_name
@ -109,7 +110,6 @@
determine_protocol,
encode_compat_str,
encodeFilename,
error_to_compat_str,
escapeHTML,
expand_path,
extract_basic_auth,
@ -159,7 +159,7 @@
write_json_file,
write_string,
)
from .utils._utils import _YDLLogger
from .utils._utils import _UnsafeExtensionError, _YDLLogger
from .utils.networking import (
HTTPHeaderDict,
clean_headers,
@ -172,6 +172,20 @@
import ctypes
def _catch_unsafe_extension_error(func):
@functools.wraps(func)
def wrapper(self, *args, **kwargs):
try:
return func(self, *args, **kwargs)
except _UnsafeExtensionError as error:
self.report_error(
f'The extracted extension ({error.extension!r}) is unusual '
'and will be skipped for safety reasons. '
f'If you believe this is an error{bug_reports_message(",")}')
return wrapper
class YoutubeDL:
"""YoutubeDL class.
@ -438,7 +452,8 @@ class YoutubeDL:
Can also just be a single color policy,
in which case it applies to all outputs.
Valid stream names are 'stdout' and 'stderr'.
Valid color policies are one of 'always', 'auto', 'no_color' or 'never'.
Valid color policies are one of 'always', 'auto',
'no_color', 'never', 'auto-tty' or 'no_color-tty'.
geo_bypass: Bypass geographic restriction via faking X-Forwarded-For
HTTP header
geo_bypass_country:
@ -454,8 +469,9 @@ class YoutubeDL:
Set the value to 'native' to use the native downloader
compat_opts: Compatibility options. See "Differences in default behavior".
The following options do not work when used through the API:
filename, abort-on-error, multistreams, no-live-chat, format-sort
no-clean-infojson, no-playlist-metafiles, no-keep-subs, no-attach-info-json.
filename, abort-on-error, multistreams, no-live-chat,
format-sort, no-clean-infojson, no-playlist-metafiles,
no-keep-subs, no-attach-info-json, allow-unsafe-ext.
Refer __init__.py for their implementation
progress_template: Dictionary of templates for progress outputs.
Allowed keys are 'download', 'postprocess',
@ -582,8 +598,9 @@ class YoutubeDL:
'vbr', 'fps', 'vcodec', 'container', 'filesize', 'filesize_approx', 'rows', 'columns',
'player_url', 'protocol', 'fragment_base_url', 'fragments', 'is_from_start', 'is_dash_periods', 'request_data',
'preference', 'language', 'language_preference', 'quality', 'source_preference', 'cookies',
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'hls_aes', 'downloader_options',
'page_url', 'app', 'play_path', 'tc_url', 'flash_version', 'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time'
'http_headers', 'stretched_ratio', 'no_resume', 'has_drm', 'extra_param_to_segment_url', 'extra_param_to_key_url',
'hls_aes', 'downloader_options', 'page_url', 'app', 'play_path', 'tc_url', 'flash_version',
'rtmp_live', 'rtmp_conn', 'rtmp_protocol', 'rtmp_real_time',
}
_deprecated_multivalue_fields = {
'album_artist': 'album_artists',
@ -594,7 +611,7 @@ class YoutubeDL:
}
_format_selection_exts = {
'audio': set(MEDIA_EXTENSIONS.common_audio),
'video': set(MEDIA_EXTENSIONS.common_video + ('3gp', )),
'video': {*MEDIA_EXTENSIONS.common_video, '3gp'},
'storyboards': set(MEDIA_EXTENSIONS.storyboards),
}
@ -628,7 +645,7 @@ def __init__(self, params=None, auto_init=True):
error=sys.stderr,
screen=sys.stderr if self.params.get('quiet') else stdout,
console=None if compat_os_name == 'nt' else next(
filter(supports_terminal_sequences, (sys.stderr, sys.stdout)), None)
filter(supports_terminal_sequences, (sys.stderr, sys.stdout)), None),
)
try:
@ -643,12 +660,15 @@ def __init__(self, params=None, auto_init=True):
self.params['color'] = 'no_color'
term_allow_color = os.getenv('TERM', '').lower() != 'dumb'
no_color = bool(os.getenv('NO_COLOR'))
base_no_color = bool(os.getenv('NO_COLOR'))
def process_color_policy(stream):
stream_name = {sys.stdout: 'stdout', sys.stderr: 'stderr'}[stream]
policy = traverse_obj(self.params, ('color', (stream_name, None), {str}), get_all=False)
if policy in ('auto', None):
policy = traverse_obj(self.params, ('color', (stream_name, None), {str}, any)) or 'auto'
if policy in ('auto', 'auto-tty', 'no_color-tty'):
no_color = base_no_color
if policy.endswith('tty'):
no_color = policy.startswith('no_color')
if term_allow_color and supports_terminal_sequences(stream):
return 'no_color' if no_color else True
return False
@ -679,9 +699,9 @@ def process_color_policy(stream):
width_args = [] if width is None else ['-w', str(width)]
sp_kwargs = {'stdin': subprocess.PIPE, 'stdout': slave, 'stderr': self._out_files.error}
try:
self._output_process = Popen(['bidiv'] + width_args, **sp_kwargs)
self._output_process = Popen(['bidiv', *width_args], **sp_kwargs)
except OSError:
self._output_process = Popen(['fribidi', '-c', 'UTF-8'] + width_args, **sp_kwargs)
self._output_process = Popen(['fribidi', '-c', 'UTF-8', *width_args], **sp_kwargs)
self._output_channel = os.fdopen(master, 'rb')
except OSError as ose:
if ose.errno == errno.ENOENT:
@ -822,8 +842,7 @@ def warn_if_short_id(self, argv):
)
self.report_warning(
'Long argument string detected. '
'Use -- to separate parameters and URLs, like this:\n%s' %
shell_quote(correct_argv))
f'Use -- to separate parameters and URLs, like this:\n{shell_quote(correct_argv)}')
def add_info_extractor(self, ie):
"""Add an InfoExtractor object to the end of the list."""
@ -922,7 +941,7 @@ def to_screen(self, message, skip_eol=False, quiet=None, only_once=False):
if (self.params.get('quiet') if quiet is None else quiet) and not self.params.get('verbose'):
return
self._write_string(
'%s%s' % (self._bidi_workaround(message), ('' if skip_eol else '\n')),
'{}{}'.format(self._bidi_workaround(message), ('' if skip_eol else '\n')),
self._out_files.screen, only_once=only_once)
def to_stderr(self, message, only_once=False):
@ -1045,10 +1064,10 @@ def _format_err(self, *args, **kwargs):
return self._format_text(self._out_files.error, self._allow_colors.error, *args, **kwargs)
def report_warning(self, message, only_once=False):
'''
"""
Print the message to stderr, it will be prefixed with 'WARNING:'
If stderr is a tty file the 'WARNING:' will be colored
'''
"""
if self.params.get('logger') is not None:
self.params['logger'].warning(message)
else:
@ -1066,14 +1085,14 @@ def deprecated_feature(self, message):
self.to_stderr(f'{self._format_err("Deprecated Feature:", self.Styles.ERROR)} {message}', True)
def report_error(self, message, *args, **kwargs):
'''
"""
Do the same as trouble, but prefixes the message with 'ERROR:', colored
in red if stderr is a tty file.
'''
"""
self.trouble(f'{self._format_err("ERROR:", self.Styles.ERROR)} {message}', *args, **kwargs)
def write_debug(self, message, only_once=False):
'''Log debug message or Print message to stderr'''
"""Log debug message or Print message to stderr"""
if not self.params.get('verbose', False):
return
message = f'[debug] {message}'
@ -1085,14 +1104,14 @@ def write_debug(self, message, only_once=False):
def report_file_already_downloaded(self, file_name):
"""Report file has already been fully downloaded."""
try:
self.to_screen('[download] %s has already been downloaded' % file_name)
self.to_screen(f'[download] {file_name} has already been downloaded')
except UnicodeEncodeError:
self.to_screen('[download] The file has already been downloaded')
def report_file_delete(self, file_name):
"""Report that existing file will be deleted."""
try:
self.to_screen('Deleting existing file %s' % file_name)
self.to_screen(f'Deleting existing file {file_name}')
except UnicodeEncodeError:
self.to_screen('Deleting existing file')
@ -1147,7 +1166,7 @@ def _outtmpl_expandpath(outtmpl):
@staticmethod
def escape_outtmpl(outtmpl):
''' Escape any remaining strings like %s, %abc% etc. '''
""" Escape any remaining strings like %s, %abc% etc. """
return re.sub(
STR_FORMAT_RE_TMPL.format('', '(?![%(\0])'),
lambda mobj: ('' if mobj.group('has_key') else '%') + mobj.group(0),
@ -1155,7 +1174,7 @@ def escape_outtmpl(outtmpl):
@classmethod
def validate_outtmpl(cls, outtmpl):
''' @return None or Exception object '''
""" @return None or Exception object """
outtmpl = re.sub(
STR_FORMAT_RE_TMPL.format('[^)]*', '[ljhqBUDS]'),
lambda mobj: f'{mobj.group(0)[:-1]}s',
@ -1208,13 +1227,13 @@ def prepare_outtmpl(self, outtmpl, info_dict, sanitize=False):
}
# Field is of the form key1.key2...
# where keys (except first) can be string, int, slice or "{field, ...}"
FIELD_INNER_RE = r'(?:\w+|%(num)s|%(num)s?(?::%(num)s?){1,2})' % {'num': r'(?:-?\d+)'}
FIELD_RE = r'\w*(?:\.(?:%(inner)s|{%(field)s(?:,%(field)s)*}))*' % {
FIELD_INNER_RE = r'(?:\w+|%(num)s|%(num)s?(?::%(num)s?){1,2})' % {'num': r'(?:-?\d+)'} # noqa: UP031
FIELD_RE = r'\w*(?:\.(?:%(inner)s|{%(field)s(?:,%(field)s)*}))*' % { # noqa: UP031
'inner': FIELD_INNER_RE,
'field': rf'\w*(?:\.{FIELD_INNER_RE})*'
'field': rf'\w*(?:\.{FIELD_INNER_RE})*',
}
MATH_FIELD_RE = rf'(?:{FIELD_RE}|-?{NUMBER_RE})'
MATH_OPERATORS_RE = r'(?:%s)' % '|'.join(map(re.escape, MATH_FUNCTIONS.keys()))
MATH_OPERATORS_RE = r'(?:{})'.format('|'.join(map(re.escape, MATH_FUNCTIONS.keys())))
INTERNAL_FORMAT_RE = re.compile(rf'''(?xs)
(?P<negate>-)?
(?P<fields>{FIELD_RE})
@ -1337,7 +1356,7 @@ def create_key(outer_mobj):
value, default = None, na
fmt = outer_mobj.group('format')
if fmt == 's' and last_field in field_size_compat_map.keys() and isinstance(value, int):
if fmt == 's' and last_field in field_size_compat_map and isinstance(value, int):
fmt = f'0{field_size_compat_map[last_field]:d}d'
flags = outer_mobj.group('conversion') or ''
@ -1362,7 +1381,7 @@ def create_key(outer_mobj):
elif fmt[-1] == 'U': # unicode normalized
value, fmt = unicodedata.normalize(
# "+" = compatibility equivalence, "#" = NFD
'NF%s%s' % ('K' if '+' in flags else '', 'D' if '#' in flags else 'C'),
'NF{}{}'.format('K' if '+' in flags else '', 'D' if '#' in flags else 'C'),
value), str_fmt
elif fmt[-1] == 'D': # decimal suffix
num_fmt, fmt = fmt[:-1].replace('#', ''), 's'
@ -1390,7 +1409,7 @@ def create_key(outer_mobj):
if fmt[-1] in 'csra':
value = sanitizer(last_field, value)
key = '%s\0%s' % (key.replace('%', '%\0'), outer_mobj.group('format'))
key = '{}\0{}'.format(key.replace('%', '%\0'), outer_mobj.group('format'))
TMPL_DICT[key] = value
return '{prefix}%({key}){fmt}'.format(key=key, fmt=fmt, prefix=outer_mobj.group('prefix'))
@ -1400,6 +1419,7 @@ def evaluate_outtmpl(self, outtmpl, info_dict, *args, **kwargs):
outtmpl, info_dict = self.prepare_outtmpl(outtmpl, info_dict, *args, **kwargs)
return self.escape_outtmpl(outtmpl) % info_dict
@_catch_unsafe_extension_error
def _prepare_filename(self, info_dict, *, outtmpl=None, tmpl_type=None):
assert None in (outtmpl, tmpl_type), 'outtmpl and tmpl_type are mutually exclusive'
if outtmpl is None:
@ -1479,9 +1499,9 @@ def check_filter():
date = info_dict.get('upload_date')
if date is not None:
dateRange = self.params.get('daterange', DateRange())
if date not in dateRange:
return f'{date_from_str(date).isoformat()} upload date is not in range {dateRange}'
date_range = self.params.get('daterange', DateRange())
if date not in date_range:
return f'{date_from_str(date).isoformat()} upload date is not in range {date_range}'
view_count = info_dict.get('view_count')
if view_count is not None:
min_views = self.params.get('min_views')
@ -1491,7 +1511,7 @@ def check_filter():
if max_views is not None and view_count > max_views:
return 'Skipping %s, because it has exceeded the maximum view count (%d/%d)' % (video_title, view_count, max_views)
if age_restricted(info_dict.get('age_limit'), self.params.get('age_limit')):
return 'Skipping "%s" because it is age restricted' % video_title
return f'Skipping "{video_title}" because it is age restricted'
match_filter = self.params.get('match_filter')
if match_filter is None:
@ -1544,7 +1564,7 @@ def check_filter():
@staticmethod
def add_extra_info(info_dict, extra_info):
'''Set the keys from extra_info in info dict if they are missing'''
"""Set the keys from extra_info in info dict if they are missing"""
for key, value in extra_info.items():
info_dict.setdefault(key, value)
@ -1590,7 +1610,7 @@ def extract_info(self, url, download=True, ie_key=None, extra_info=None,
self.to_screen(f'[download] {self._format_screen(temp_id, self.Styles.ID)}: '
'has already been recorded in the archive')
if self.params.get('break_on_existing', False):
raise ExistingVideoReached()
raise ExistingVideoReached
break
return self.__extract_info(url, self.get_info_extractor(key), download, extra_info, process)
else:
@ -1616,8 +1636,8 @@ def wrapper(self, *args, **kwargs):
except GeoRestrictedError as e:
msg = e.msg
if e.countries:
msg += '\nThis video is available in %s.' % ', '.join(
map(ISO3166Utils.short2full, e.countries))
msg += '\nThis video is available in {}.'.format(', '.join(
map(ISO3166Utils.short2full, e.countries)))
msg += '\nYou might want to use a VPN or a proxy server (with --proxy) to workaround.'
self.report_error(msg)
except ExtractorError as e: # An error we somewhat expected
@ -1826,8 +1846,8 @@ def process_ie_result(self, ie_result, download=True, extra_info=None):
if isinstance(additional_urls, str):
additional_urls = [additional_urls]
self.to_screen(
'[info] %s: %d additional URL(s) requested' % (ie_result['id'], len(additional_urls)))
self.write_debug('Additional URLs: "%s"' % '", "'.join(additional_urls))
'[info] {}: {} additional URL(s) requested'.format(ie_result['id'], len(additional_urls)))
self.write_debug('Additional URLs: "{}"'.format('", "'.join(additional_urls)))
ie_result['additional_entries'] = [
self.extract_info(
url, download, extra_info=extra_info,
@ -1879,8 +1899,8 @@ def process_ie_result(self, ie_result, download=True, extra_info=None):
webpage_url = ie_result.get('webpage_url') # Playlists maynot have webpage_url
if webpage_url and webpage_url in self._playlist_urls:
self.to_screen(
'[download] Skipping already downloaded playlist: %s'
% ie_result.get('title') or ie_result.get('id'))
'[download] Skipping already downloaded playlist: {}'.format(
ie_result.get('title')) or ie_result.get('id'))
return
self._playlist_level += 1
@ -1895,8 +1915,8 @@ def process_ie_result(self, ie_result, download=True, extra_info=None):
self._playlist_urls.clear()
elif result_type == 'compat_list':
self.report_warning(
'Extractor %s returned a compat_list result. '
'It needs to be updated.' % ie_result.get('extractor'))
'Extractor {} returned a compat_list result. '
'It needs to be updated.'.format(ie_result.get('extractor')))
def _fixup(r):
self.add_extra_info(r, {
@ -1913,7 +1933,7 @@ def _fixup(r):
]
return ie_result
else:
raise Exception('Invalid result type: %s' % result_type)
raise Exception(f'Invalid result type: {result_type}')
def _ensure_dir_exists(self, path):
return make_dir(path, self.report_error)
@ -1927,6 +1947,8 @@ def _playlist_infodict(ie_result, strict=False, **kwargs):
'playlist_title': ie_result.get('title'),
'playlist_uploader': ie_result.get('uploader'),
'playlist_uploader_id': ie_result.get('uploader_id'),
'playlist_channel': ie_result.get('channel'),
'playlist_channel_id': ie_result.get('channel_id'),
**kwargs,
}
if strict:
@ -2029,8 +2051,9 @@ def __process_playlist(self, ie_result, download):
resolved_entries[i] = (playlist_index, NO_DEFAULT)
continue
self.to_screen('[download] Downloading item %s of %s' % (
self._format_screen(i + 1, self.Styles.ID), self._format_screen(n_entries, self.Styles.EMPHASIS)))
self.to_screen(
f'[download] Downloading item {self._format_screen(i + 1, self.Styles.ID)} '
f'of {self._format_screen(n_entries, self.Styles.EMPHASIS)}')
entry_result = self.__process_iterable_entry(entry, download, collections.ChainMap({
'playlist_index': playlist_index,
@ -2080,9 +2103,9 @@ def _build_format_filter(self, filter_spec):
}
operator_rex = re.compile(r'''(?x)\s*
(?P<key>[\w.-]+)\s*
(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?P<op>{})(?P<none_inclusive>\s*\?)?\s*
(?P<value>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)\s*
''' % '|'.join(map(re.escape, OPERATORS.keys())))
'''.format('|'.join(map(re.escape, OPERATORS.keys()))))
m = operator_rex.fullmatch(filter_spec)
if m:
try:
@ -2093,7 +2116,7 @@ def _build_format_filter(self, filter_spec):
comparison_value = parse_filesize(m.group('value') + 'B')
if comparison_value is None:
raise ValueError(
'Invalid value %r in format specification %r' % (
'Invalid value {!r} in format specification {!r}'.format(
m.group('value'), filter_spec))
op = OPERATORS[m.group('op')]
@ -2103,15 +2126,15 @@ def _build_format_filter(self, filter_spec):
'^=': lambda attr, value: attr.startswith(value),
'$=': lambda attr, value: attr.endswith(value),
'*=': lambda attr, value: value in attr,
'~=': lambda attr, value: value.search(attr) is not None
'~=': lambda attr, value: value.search(attr) is not None,
}
str_operator_rex = re.compile(r'''(?x)\s*
(?P<key>[a-zA-Z0-9._-]+)\s*
(?P<negation>!\s*)?(?P<op>%s)\s*(?P<none_inclusive>\?\s*)?
(?P<negation>!\s*)?(?P<op>{})\s*(?P<none_inclusive>\?\s*)?
(?P<quote>["'])?
(?P<value>(?(quote)(?:(?!(?P=quote))[^\\]|\\.)+|[\w.-]+))
(?(quote)(?P=quote))\s*
''' % '|'.join(map(re.escape, STR_OPERATORS.keys())))
'''.format('|'.join(map(re.escape, STR_OPERATORS.keys()))))
m = str_operator_rex.fullmatch(filter_spec)
if m:
if m.group('op') == '~=':
@ -2125,7 +2148,7 @@ def _build_format_filter(self, filter_spec):
op = str_op
if not m:
raise SyntaxError('Invalid filter specification %r' % filter_spec)
raise SyntaxError(f'Invalid filter specification {filter_spec!r}')
def _filter(f):
actual_value = f.get(m.group('key'))
@ -2141,7 +2164,7 @@ def _check_formats(self, formats):
if working:
yield f
continue
self.to_screen('[info] Testing format %s' % f['format_id'])
self.to_screen('[info] Testing format {}'.format(f['format_id']))
path = self.get_output_path('temp')
if not self._ensure_dir_exists(f'{path}/'):
continue
@ -2149,19 +2172,19 @@ def _check_formats(self, formats):
temp_file.close()
try:
success, _ = self.dl(temp_file.name, f, test=True)
except (DownloadError, OSError, ValueError) + network_exceptions:
except (DownloadError, OSError, ValueError, *network_exceptions):
success = False
finally:
if os.path.exists(temp_file.name):
try:
os.remove(temp_file.name)
except OSError:
self.report_warning('Unable to delete temporary file "%s"' % temp_file.name)
self.report_warning(f'Unable to delete temporary file "{temp_file.name}"')
f['__working'] = success
if success:
yield f
else:
self.to_screen('[info] Unable to download format %s. Skipping...' % f['format_id'])
self.to_screen('[info] Unable to download format {}. Skipping...'.format(f['format_id']))
def _select_formats(self, formats, selector):
return list(selector({
@ -2171,9 +2194,8 @@ def _select_formats(self, formats, selector):
or all(f.get('acodec') == 'none' for f in formats)), # OR, No formats with audio
}))
def _default_format_spec(self, info_dict, download=True):
download = download and not self.params.get('simulate')
prefer_best = download and (
def _default_format_spec(self, info_dict):
prefer_best = (
self.params['outtmpl']['default'] == '-'
or info_dict.get('is_live') and not self.params.get('live_from_start'))
@ -2181,7 +2203,7 @@ def can_merge():
merger = FFmpegMergerPP(self)
return merger.available and merger.can_merge()
if not prefer_best and download and not can_merge():
if not prefer_best and not can_merge():
prefer_best = True
formats = self._get_formats(info_dict)
evaluate_formats = lambda spec: self._select_formats(formats, self.build_format_selector(spec))
@ -2214,8 +2236,8 @@ def syntax_error(note, start):
def _parse_filter(tokens):
filter_parts = []
for type, string_, start, _, _ in tokens:
if type == tokenize.OP and string_ == ']':
for type_, string_, _start, _, _ in tokens:
if type_ == tokenize.OP and string_ == ']':
return ''.join(filter_parts)
else:
filter_parts.append(string_)
@ -2225,23 +2247,23 @@ def _remove_unused_ops(tokens):
# E.g. 'mp4' '-' 'baseline' '-' '16x9' is converted to 'mp4-baseline-16x9'
ALLOWED_OPS = ('/', '+', ',', '(', ')')
last_string, last_start, last_end, last_line = None, None, None, None
for type, string_, start, end, line in tokens:
if type == tokenize.OP and string_ == '[':
for type_, string_, start, end, line in tokens:
if type_ == tokenize.OP and string_ == '[':
if last_string:
yield tokenize.NAME, last_string, last_start, last_end, last_line
last_string = None
yield type, string_, start, end, line
yield type_, string_, start, end, line
# everything inside brackets will be handled by _parse_filter
for type, string_, start, end, line in tokens:
yield type, string_, start, end, line
if type == tokenize.OP and string_ == ']':
for type_, string_, start, end, line in tokens:
yield type_, string_, start, end, line
if type_ == tokenize.OP and string_ == ']':
break
elif type == tokenize.OP and string_ in ALLOWED_OPS:
elif type_ == tokenize.OP and string_ in ALLOWED_OPS:
if last_string:
yield tokenize.NAME, last_string, last_start, last_end, last_line
last_string = None
yield type, string_, start, end, line
elif type in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
yield type_, string_, start, end, line
elif type_ in [tokenize.NAME, tokenize.NUMBER, tokenize.OP]:
if not last_string:
last_string = string_
last_start = start
@ -2254,13 +2276,13 @@ def _remove_unused_ops(tokens):
def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, inside_group=False):
selectors = []
current_selector = None
for type, string_, start, _, _ in tokens:
for type_, string_, start, _, _ in tokens:
# ENCODING is only defined in Python 3.x
if type == getattr(tokenize, 'ENCODING', None):
if type_ == getattr(tokenize, 'ENCODING', None):
continue
elif type in [tokenize.NAME, tokenize.NUMBER]:
elif type_ in [tokenize.NAME, tokenize.NUMBER]:
current_selector = FormatSelector(SINGLE, string_, [])
elif type == tokenize.OP:
elif type_ == tokenize.OP:
if string_ == ')':
if not inside_group:
# ')' will be handled by the parentheses group
@ -2303,7 +2325,7 @@ def _parse_format_selection(tokens, inside_merge=False, inside_choice=False, ins
current_selector = FormatSelector(MERGE, (selector_1, selector_2), [])
else:
raise syntax_error(f'Operator not recognized: "{string_}"', start)
elif type == tokenize.ENDMARKER:
elif type_ == tokenize.ENDMARKER:
break
if current_selector:
selectors.append(current_selector)
@ -2378,7 +2400,7 @@ def _merge(formats_pair):
'acodec': the_only_audio.get('acodec'),
'abr': the_only_audio.get('abr'),
'asr': the_only_audio.get('asr'),
'audio_channels': the_only_audio.get('audio_channels')
'audio_channels': the_only_audio.get('audio_channels'),
})
return new_dict
@ -2459,9 +2481,9 @@ def selector_function(ctx):
format_fallback = not format_type and not format_modified # for b, w
_filter_f = (
(lambda f: f.get('%scodec' % format_type) != 'none')
(lambda f: f.get(f'{format_type}codec') != 'none')
if format_type and format_modified # bv*, ba*, wv*, wa*
else (lambda f: f.get('%scodec' % not_format_type) == 'none')
else (lambda f: f.get(f'{not_format_type}codec') == 'none')
if format_type # bv, ba, wv, wa
else (lambda f: f.get('vcodec') != 'none' and f.get('acodec') != 'none')
if not format_modified # b, w
@ -2529,7 +2551,7 @@ def __iter__(self):
def __next__(self):
if self.counter >= len(self.tokens):
raise StopIteration()
raise StopIteration
value = self.tokens[self.counter]
self.counter += 1
return value
@ -2612,7 +2634,7 @@ def check_thumbnails(thumbnails):
self._sort_thumbnails(thumbnails)
for i, t in enumerate(thumbnails):
if t.get('id') is None:
t['id'] = '%d' % i
t['id'] = str(i)
if t.get('width') and t.get('height'):
t['resolution'] = '%dx%d' % (t['width'], t['height'])
t['url'] = sanitize_url(t['url'])
@ -2673,8 +2695,8 @@ def _fill_common_fields(self, info_dict, final=True):
# Auto generate title fields corresponding to the *_number fields when missing
# in order to always have clean titles. This is very common for TV series.
for field in ('chapter', 'season', 'episode'):
if final and info_dict.get('%s_number' % field) is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict['%s_number' % field])
if final and info_dict.get(f'{field}_number') is not None and not info_dict.get(field):
info_dict[field] = '%s %d' % (field.capitalize(), info_dict[f'{field}_number'])
for old_key, new_key in self._deprecated_multivalue_fields.items():
if new_key in info_dict and old_key in info_dict:
@ -2706,8 +2728,8 @@ def process_video_result(self, info_dict, download=True):
def report_force_conversion(field, field_not, conversion):
self.report_warning(
'"%s" field is not %s - forcing %s conversion, there is an error in extractor'
% (field, field_not, conversion))
f'"{field}" field is not {field_not} - forcing {conversion} conversion, '
'there is an error in extractor')
def sanitize_string_field(info, string_field):
field = info.get(string_field)
@ -2824,28 +2846,28 @@ def is_wellformed(f):
if not formats:
self.raise_no_formats(info_dict)
for format in formats:
sanitize_string_field(format, 'format_id')
sanitize_numeric_fields(format)
format['url'] = sanitize_url(format['url'])
if format.get('ext') is None:
format['ext'] = determine_ext(format['url']).lower()
if format['ext'] in ('aac', 'opus', 'mp3', 'flac', 'vorbis'):
if format.get('acodec') is None:
format['acodec'] = format['ext']
if format.get('protocol') is None:
format['protocol'] = determine_protocol(format)
if format.get('resolution') is None:
format['resolution'] = self.format_resolution(format, default=None)
if format.get('dynamic_range') is None and format.get('vcodec') != 'none':
format['dynamic_range'] = 'SDR'
if format.get('aspect_ratio') is None:
format['aspect_ratio'] = try_call(lambda: round(format['width'] / format['height'], 2))
for fmt in formats:
sanitize_string_field(fmt, 'format_id')
sanitize_numeric_fields(fmt)
fmt['url'] = sanitize_url(fmt['url'])
if fmt.get('ext') is None:
fmt['ext'] = determine_ext(fmt['url']).lower()
if fmt['ext'] in ('aac', 'opus', 'mp3', 'flac', 'vorbis'):
if fmt.get('acodec') is None:
fmt['acodec'] = fmt['ext']
if fmt.get('protocol') is None:
fmt['protocol'] = determine_protocol(fmt)
if fmt.get('resolution') is None:
fmt['resolution'] = self.format_resolution(fmt, default=None)
if fmt.get('dynamic_range') is None and fmt.get('vcodec') != 'none':
fmt['dynamic_range'] = 'SDR'
if fmt.get('aspect_ratio') is None:
fmt['aspect_ratio'] = try_call(lambda: round(fmt['width'] / fmt['height'], 2))
# For fragmented formats, "tbr" is often max bitrate and not average
if (('manifest-filesize-approx' in self.params['compat_opts'] or not format.get('manifest_url'))
and not format.get('filesize') and not format.get('filesize_approx')):
format['filesize_approx'] = filesize_from_tbr(format.get('tbr'), info_dict.get('duration'))
format['http_headers'] = self._calc_headers(collections.ChainMap(format, info_dict), load_cookies=True)
if (('manifest-filesize-approx' in self.params['compat_opts'] or not fmt.get('manifest_url'))
and not fmt.get('filesize') and not fmt.get('filesize_approx')):
fmt['filesize_approx'] = filesize_from_tbr(fmt.get('tbr'), info_dict.get('duration'))
fmt['http_headers'] = self._calc_headers(collections.ChainMap(fmt, info_dict), load_cookies=True)
# Safeguard against old/insecure infojson when using --load-info-json
if info_dict.get('http_headers'):
@ -2858,36 +2880,36 @@ def is_wellformed(f):
self.sort_formats({
'formats': formats,
'_format_sort_fields': info_dict.get('_format_sort_fields')
'_format_sort_fields': info_dict.get('_format_sort_fields'),
})
# Sanitize and group by format_id
formats_dict = {}
for i, format in enumerate(formats):
if not format.get('format_id'):
format['format_id'] = str(i)
for i, fmt in enumerate(formats):
if not fmt.get('format_id'):
fmt['format_id'] = str(i)
else:
# Sanitize format_id from characters used in format selector expression
format['format_id'] = re.sub(r'[\s,/+\[\]()]', '_', format['format_id'])
formats_dict.setdefault(format['format_id'], []).append(format)
fmt['format_id'] = re.sub(r'[\s,/+\[\]()]', '_', fmt['format_id'])
formats_dict.setdefault(fmt['format_id'], []).append(fmt)
# Make sure all formats have unique format_id
common_exts = set(itertools.chain(*self._format_selection_exts.values()))
for format_id, ambiguous_formats in formats_dict.items():
ambigious_id = len(ambiguous_formats) > 1
for i, format in enumerate(ambiguous_formats):
for i, fmt in enumerate(ambiguous_formats):
if ambigious_id:
format['format_id'] = '%s-%d' % (format_id, i)
fmt['format_id'] = f'{format_id}-{i}'
# Ensure there is no conflict between id and ext in format selection
# See https://github.com/yt-dlp/yt-dlp/issues/1282
if format['format_id'] != format['ext'] and format['format_id'] in common_exts:
format['format_id'] = 'f%s' % format['format_id']
if fmt['format_id'] != fmt['ext'] and fmt['format_id'] in common_exts:
fmt['format_id'] = 'f{}'.format(fmt['format_id'])
if format.get('format') is None:
format['format'] = '{id} - {res}{note}'.format(
id=format['format_id'],
res=self.format_resolution(format),
note=format_field(format, 'format_note', ' (%s)'),
if fmt.get('format') is None:
fmt['format'] = '{id} - {res}{note}'.format(
id=fmt['format_id'],
res=self.format_resolution(fmt),
note=format_field(fmt, 'format_note', ' (%s)'),
)
if self.params.get('check_formats') is True:
@ -2940,7 +2962,7 @@ def is_wellformed(f):
continue
if format_selector is None:
req_format = self._default_format_spec(info_dict, download=download)
req_format = self._default_format_spec(info_dict)
self.write_debug(f'Default format spec: {req_format}')
format_selector = self.build_format_selector(req_format)
@ -3009,7 +3031,7 @@ def to_screen(*msg):
info_dict['requested_downloads'] = downloaded_formats
info_dict = self.run_all_pps('after_video', info_dict)
if max_downloads_reached:
raise MaxDownloadsReached()
raise MaxDownloadsReached
# We update the info dict with the selected best quality format (backwards compatibility)
info_dict.update(best_format)
@ -3070,8 +3092,8 @@ def process_subtitles(self, video_id, normal_subtitles, automatic_captions):
else:
f = formats[-1]
self.report_warning(
'No subtitle format found matching "%s" for language %s, '
'using %s. Use --list-subs for a list of available subtitles' % (formats_query, lang, f['ext']))
'No subtitle format found matching "{}" for language {}, '
'using {}. Use --list-subs for a list of available subtitles'.format(formats_query, lang, f['ext']))
subs[lang] = f
return subs
@ -3150,11 +3172,12 @@ def dl(self, name, info, subtitle=False, test=False):
if test:
verbose = self.params.get('verbose')
quiet = self.params.get('quiet') or not verbose
params = {
'test': True,
'quiet': self.params.get('quiet') or not verbose,
'quiet': quiet,
'verbose': verbose,
'noprogress': not verbose,
'noprogress': quiet,
'nopart': True,
'skip_unavailable_fragments': False,
'keep_fragments': False,
@ -3189,6 +3212,7 @@ def existing_file(self, filepaths, *, default_overwrite=True):
os.remove(file)
return None
@_catch_unsafe_extension_error
def process_info(self, info_dict):
"""Process a single resolved IE result. (Modifies it in-place)"""
@ -3226,7 +3250,7 @@ def replace_info_dict(new_info):
def check_max_downloads():
if self._num_downloads >= float(self.params.get('max_downloads') or 'inf'):
raise MaxDownloadsReached()
raise MaxDownloadsReached
if self.params.get('simulate'):
info_dict['__write_download_archive'] = self.params.get('force_write_download_archive')
@ -3400,7 +3424,7 @@ def correct_ext(filename, ext=new_ext):
for f in info_dict['requested_formats'] if fd != FFmpegFD else []:
f['filepath'] = fname = prepend_extension(
correct_ext(temp_filename, info_dict['ext']),
'f%s' % f['format_id'], info_dict['ext'])
'f{}'.format(f['format_id']), info_dict['ext'])
downloaded.append(fname)
info_dict['url'] = '\n'.join(f['url'] for f in info_dict['requested_formats'])
success, real_download = self.dl(temp_filename, info_dict)
@ -3433,7 +3457,7 @@ def correct_ext(filename, ext=new_ext):
if temp_filename != '-':
fname = prepend_extension(
correct_ext(temp_filename, new_info['ext']),
'f%s' % f['format_id'], new_info['ext'])
'f{}'.format(f['format_id']), new_info['ext'])
if not self._ensure_dir_exists(fname):
return
f['filepath'] = fname
@ -3465,11 +3489,11 @@ def correct_ext(filename, ext=new_ext):
info_dict['__finaldir'] = os.path.dirname(os.path.abspath(encodeFilename(full_filename)))
except network_exceptions as err:
self.report_error('unable to download video data: %s' % error_to_compat_str(err))
self.report_error(f'unable to download video data: {err}')
return
except OSError as err:
raise UnavailableVideoError(err)
except (ContentTooShortError, ) as err:
except ContentTooShortError as err:
self.report_error(f'content too short (expected {err.expected} bytes and served {err.downloaded})')
return
@ -3536,13 +3560,13 @@ def ffmpeg_fixup(cndn, msg, cls):
try:
replace_info_dict(self.post_process(dl_filename, info_dict, files_to_move))
except PostProcessingError as err:
self.report_error('Postprocessing: %s' % str(err))
self.report_error(f'Postprocessing: {err}')
return
try:
for ph in self._post_hooks:
ph(info_dict['filepath'])
except Exception as err:
self.report_error('post hooks: %s' % str(err))
self.report_error(f'post hooks: {err}')
return
info_dict['__write_download_archive'] = True
@ -3609,7 +3633,7 @@ def download_with_info_file(self, info_filename):
@staticmethod
def sanitize_info(info_dict, remove_private_keys=False):
''' Sanitize the infodict for converting to json '''
""" Sanitize the infodict for converting to json """
if info_dict is None:
return info_dict
info_dict.setdefault('epoch', int(time.time()))
@ -3644,7 +3668,7 @@ def filter_fn(obj):
@staticmethod
def filter_requested_info(info_dict, actually_filter=True):
''' Alias of sanitize_info for backward compatibility '''
""" Alias of sanitize_info for backward compatibility """
return YoutubeDL.sanitize_info(info_dict, actually_filter)
def _delete_downloaded_files(self, *files_to_delete, info={}, msg=None):
@ -3666,7 +3690,7 @@ def actual_post_extract(info_dict):
actual_post_extract(video_dict or {})
return
post_extractor = info_dict.pop('__post_extractor', None) or (lambda: {})
post_extractor = info_dict.pop('__post_extractor', None) or dict
info_dict.update(post_extractor())
actual_post_extract(info_dict or {})
@ -3771,7 +3795,7 @@ def format_resolution(format, default='unknown'):
if format.get('width') and format.get('height'):
return '%dx%d' % (format['width'], format['height'])
elif format.get('height'):
return '%sp' % format['height']
return '{}p'.format(format['height'])
elif format.get('width'):
return '%dx?' % format['width']
return default
@ -3788,7 +3812,7 @@ def _format_note(self, fdict):
if fdict.get('language'):
if res:
res += ' '
res += '[%s]' % fdict['language']
res += '[{}]'.format(fdict['language'])
if fdict.get('format_note') is not None:
if res:
res += ' '
@ -3800,7 +3824,7 @@ def _format_note(self, fdict):
if fdict.get('container') is not None:
if res:
res += ', '
res += '%s container' % fdict['container']
res += '{} container'.format(fdict['container'])
if (fdict.get('vcodec') is not None
and fdict.get('vcodec') != 'none'):
if res:
@ -3815,7 +3839,7 @@ def _format_note(self, fdict):
if fdict.get('fps') is not None:
if res:
res += ', '
res += '%sfps' % fdict['fps']
res += '{}fps'.format(fdict['fps'])
if fdict.get('acodec') is not None:
if res:
res += ', '
@ -3858,7 +3882,7 @@ def render_formats_table(self, info_dict):
format_field(f, 'format_id'),
format_field(f, 'ext'),
self.format_resolution(f),
self._format_note(f)
self._format_note(f),
] for f in formats if (f.get('preference') or 0) >= -1000]
return render_table(['format code', 'extension', 'resolution', 'note'], table, extra_gap=1)
@ -3964,11 +3988,11 @@ def print_debug_header(self):
from .extractor.extractors import _LAZY_LOADER
from .extractor.extractors import (
_PLUGIN_CLASSES as plugin_ies,
_PLUGIN_OVERRIDES as plugin_ie_overrides
_PLUGIN_OVERRIDES as plugin_ie_overrides,
)
def get_encoding(stream):
ret = str(getattr(stream, 'encoding', 'missing (%s)' % type(stream).__name__))
ret = str(getattr(stream, 'encoding', f'missing ({type(stream).__name__})'))
additional_info = []
if os.environ.get('TERM', '').lower() == 'dumb':
additional_info.append('dumb')
@ -3979,13 +4003,13 @@ def get_encoding(stream):
ret = f'{ret} ({",".join(additional_info)})'
return ret
encoding_str = 'Encodings: locale %s, fs %s, pref %s, %s' % (
encoding_str = 'Encodings: locale {}, fs {}, pref {}, {}'.format(
locale.getpreferredencoding(),
sys.getfilesystemencoding(),
self.get_encoding(),
', '.join(
f'{key} {get_encoding(stream)}' for key, stream in self._out_files.items_
if stream is not None and key != 'console')
if stream is not None and key != 'console'),
)
logger = self.params.get('logger')
@ -4017,7 +4041,7 @@ def get_encoding(stream):
else:
write_debug('Lazy loading extractors is disabled')
if self.params['compat_opts']:
write_debug('Compatibility options: %s' % ', '.join(self.params['compat_opts']))
write_debug('Compatibility options: {}'.format(', '.join(self.params['compat_opts'])))
if current_git_head():
write_debug(f'Git HEAD: {current_git_head()}')
@ -4026,14 +4050,14 @@ def get_encoding(stream):
exe_versions, ffmpeg_features = FFmpegPostProcessor.get_versions_and_features(self)
ffmpeg_features = {key for key, val in ffmpeg_features.items() if val}
if ffmpeg_features:
exe_versions['ffmpeg'] += ' (%s)' % ','.join(sorted(ffmpeg_features))
exe_versions['ffmpeg'] += ' ({})'.format(','.join(sorted(ffmpeg_features)))
exe_versions['rtmpdump'] = rtmpdump_version()
exe_versions['phantomjs'] = PhantomJSwrapper._version()
exe_str = ', '.join(
f'{exe} {v}' for exe, v in sorted(exe_versions.items()) if v
) or 'none'
write_debug('exe versions: %s' % exe_str)
write_debug(f'exe versions: {exe_str}')
from .compat.compat_utils import get_package_info
from .dependencies import available_dependencies
@ -4045,7 +4069,7 @@ def get_encoding(stream):
write_debug(f'Proxy map: {self.proxies}')
write_debug(f'Request Handlers: {", ".join(rh.RH_NAME for rh in self._request_director.handlers.values())}')
for plugin_type, plugins in {'Extractor': plugin_ies, 'Post-Processor': plugin_pps}.items():
display_list = ['%s%s' % (
display_list = ['{}{}'.format(
klass.__name__, '' if klass.__name__ == name else f' as {name}')
for name, klass in plugins.items()]
if plugin_type == 'Extractor':
@ -4062,14 +4086,13 @@ def get_encoding(stream):
# Not implemented
if False and self.params.get('call_home'):
ipaddr = self.urlopen('https://yt-dl.org/ip').read().decode()
write_debug('Public IP address: %s' % ipaddr)
write_debug(f'Public IP address: {ipaddr}')
latest_version = self.urlopen(
'https://yt-dl.org/latest/version').read().decode()
if version_tuple(latest_version) > version_tuple(__version__):
self.report_warning(
'You are using an outdated version (newest version: %s)! '
'See https://yt-dl.org/update if you need help updating.' %
latest_version)
f'You are using an outdated version (newest version: {latest_version})! '
'See https://yt-dl.org/update if you need help updating.')
@functools.cached_property
def proxies(self):
@ -4103,7 +4126,7 @@ def _opener(self):
return handler._get_instance(cookiejar=self.cookiejar, proxies=self.proxies)
def _get_available_impersonate_targets(self):
# todo(future): make available as public API
# TODO(future): make available as public API
return [
(target, rh.RH_NAME)
for rh in self._request_director.handlers.values()
@ -4112,7 +4135,7 @@ def _get_available_impersonate_targets(self):
]
def _impersonate_target_available(self, target):
# todo(future): make available as public API
# TODO(future): make available as public API
return any(
rh.is_supported_target(target)
for rh in self._request_director.handlers.values()
@ -4238,7 +4261,7 @@ def get_encoding(self):
return encoding
def _write_info_json(self, label, ie_result, infofn, overwrite=None):
''' Write infojson and returns True = written, 'exists' = Already exists, False = skip, None = error '''
""" Write infojson and returns True = written, 'exists' = Already exists, False = skip, None = error """
if overwrite is None:
overwrite = self.params.get('overwrites', True)
if not self.params.get('writeinfojson'):
@ -4261,7 +4284,7 @@ def _write_info_json(self, label, ie_result, infofn, overwrite=None):
return None
def _write_description(self, label, ie_result, descfn):
''' Write description and returns True = written, False = skip, None = error '''
""" Write description and returns True = written, False = skip, None = error """
if not self.params.get('writedescription'):
return False
elif not descfn:
@ -4285,7 +4308,7 @@ def _write_description(self, label, ie_result, descfn):
return True
def _write_subtitles(self, info_dict, filename):
''' Write subtitles to file and return list of (sub_filename, final_sub_filename); or None if error'''
""" Write subtitles to file and return list of (sub_filename, final_sub_filename); or None if error"""
ret = []
subtitles = info_dict.get('requested_subtitles')
if not (self.params.get('writesubtitles') or self.params.get('writeautomaticsub')):
@ -4331,7 +4354,7 @@ def _write_subtitles(self, info_dict, filename):
self.dl(sub_filename, sub_copy, subtitle=True)
sub_info['filepath'] = sub_filename
ret.append((sub_filename, sub_filename_final))
except (DownloadError, ExtractorError, IOError, OSError, ValueError) + network_exceptions as err:
except (DownloadError, ExtractorError, OSError, ValueError, *network_exceptions) as err:
msg = f'Unable to download video subtitles for {sub_lang!r}: {err}'
if self.params.get('ignoreerrors') is not True: # False or 'only_download'
if not self.params.get('ignoreerrors'):
@ -4341,7 +4364,7 @@ def _write_subtitles(self, info_dict, filename):
return ret
def _write_thumbnails(self, label, info_dict, filename, thumb_filename_base=None):
''' Write thumbnails to file and return list of (thumb_filename, final_thumb_filename); or None if error '''
""" Write thumbnails to file and return list of (thumb_filename, final_thumb_filename); or None if error """
write_all = self.params.get('write_all_thumbnails', False)
thumbnails, ret = [], []
if write_all or self.params.get('writethumbnail', False):
@ -4368,8 +4391,8 @@ def _write_thumbnails(self, label, info_dict, filename, thumb_filename_base=None
existing_thumb = self.existing_file((thumb_filename_final, thumb_filename))
if existing_thumb:
self.to_screen('[info] %s is already present' % (
thumb_display_id if multiple else f'{label} thumbnail').capitalize())
self.to_screen('[info] {} is already present'.format((
thumb_display_id if multiple else f'{label} thumbnail').capitalize()))
t['filepath'] = existing_thumb
ret.append((existing_thumb, thumb_filename_final))
else:

49
yt_dlp/__init__.py
View file

@ -14,7 +14,7 @@
import re
import traceback
from .compat import compat_os_name, compat_shlex_quote
from .compat import compat_os_name
from .cookies import SUPPORTED_BROWSERS, SUPPORTED_KEYRINGS
from .downloader.external import get_external_downloader
from .extractor import list_extractor_classes
@ -58,11 +58,13 @@
read_stdin,
render_table,
setproctitle,
shell_quote,
traverse_obj,
variadic,
write_string,
)
from .utils.networking import std_headers
from .utils._utils import _UnsafeExtensionError
from .YoutubeDL import YoutubeDL
_IN_CLI = False
@ -115,9 +117,9 @@ def print_extractor_information(opts, urls):
ie.description(markdown=False, search_examples=_SEARCHES)
for ie in list_extractor_classes(opts.age_limit) if ie.working() and ie.IE_DESC is not False)
elif opts.ap_list_mso:
out = 'Supported TV Providers:\n%s\n' % render_table(
out = 'Supported TV Providers:\n{}\n'.format(render_table(
['mso', 'mso name'],
[[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()])
[[mso_id, mso_info['name']] for mso_id, mso_info in MSO_INFO.items()]))
else:
return False
write_string(out, out=sys.stdout)
@ -129,7 +131,7 @@ def _unused_compat_opt(name):
if name not in opts.compat_opts:
return False
opts.compat_opts.discard(name)
opts.compat_opts.update(['*%s' % name])
opts.compat_opts.update([f'*{name}'])
return True
def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
@ -222,7 +224,7 @@ def validate_minmax(min_val, max_val, min_name, max_name=None):
validate_minmax(opts.sleep_interval, opts.max_sleep_interval, 'sleep interval')
if opts.wait_for_video is not None:
min_wait, max_wait, *_ = map(parse_duration, opts.wait_for_video.split('-', 1) + [None])
min_wait, max_wait, *_ = map(parse_duration, [*opts.wait_for_video.split('-', 1), None])
validate(min_wait is not None and not (max_wait is None and '-' in opts.wait_for_video),
'time range to wait for video', opts.wait_for_video)
validate_minmax(min_wait, max_wait, 'time range to wait for video')
@ -264,9 +266,9 @@ def parse_retries(name, value):
# Retry sleep function
def parse_sleep_func(expr):
NUMBER_RE = r'\d+(?:\.\d+)?'
op, start, limit, step, *_ = tuple(re.fullmatch(
op, start, limit, step, *_ = (*tuple(re.fullmatch(
rf'(?:(linear|exp)=)?({NUMBER_RE})(?::({NUMBER_RE})?)?(?::({NUMBER_RE}))?',
expr.strip()).groups()) + (None, None)
expr.strip()).groups()), None, None)
if op == 'exp':
return lambda n: min(float(start) * (float(step or 2) ** n), float(limit or 'inf'))
@ -396,13 +398,13 @@ def parse_chapters(name, value, advanced=False):
# MetadataParser
def metadataparser_actions(f):
if isinstance(f, str):
cmd = '--parse-metadata %s' % compat_shlex_quote(f)
cmd = f'--parse-metadata {shell_quote(f)}'
try:
actions = [MetadataFromFieldPP.to_action(f)]
except Exception as err:
raise ValueError(f'{cmd} is invalid; {err}')
else:
cmd = '--replace-in-metadata %s' % ' '.join(map(compat_shlex_quote, f))
cmd = f'--replace-in-metadata {shell_quote(f)}'
actions = ((MetadataParserPP.Actions.REPLACE, x, *f[1:]) for x in f[0].split(','))
for action in actions:
@ -413,7 +415,7 @@ def metadataparser_actions(f):
yield action
if opts.metafromtitle is not None:
opts.parse_metadata.setdefault('pre_process', []).append('title:%s' % opts.metafromtitle)
opts.parse_metadata.setdefault('pre_process', []).append(f'title:{opts.metafromtitle}')
opts.parse_metadata = {
k: list(itertools.chain(*map(metadataparser_actions, v)))
for k, v in opts.parse_metadata.items()
@ -466,7 +468,7 @@ def metadataparser_actions(f):
default_downloader = ed.get_basename()
for policy in opts.color.values():
if policy not in ('always', 'auto', 'no_color', 'never'):
if policy not in ('always', 'auto', 'auto-tty', 'no_color', 'no_color-tty', 'never'):
raise ValueError(f'"{policy}" is not a valid color policy')
warnings, deprecation_warnings = [], []
@ -592,6 +594,13 @@ def report_deprecation(val, old, new=None):
if opts.ap_username is not None and opts.ap_password is None:
opts.ap_password = getpass.getpass('Type TV provider account password and press [Return]: ')
# compat option changes global state destructively; only allow from cli
if 'allow-unsafe-ext' in opts.compat_opts:
warnings.append(
'Using allow-unsafe-ext opens you up to potential attacks. '
'Use with great care!')
_UnsafeExtensionError.sanitize_extension = lambda x, prepend=False: x
return warnings, deprecation_warnings
@ -602,7 +611,7 @@ def get_postprocessors(opts):
yield {
'key': 'MetadataParser',
'actions': actions,
'when': when
'when': when,
}
sponsorblock_query = opts.sponsorblock_mark | opts.sponsorblock_remove
if sponsorblock_query:
@ -610,19 +619,19 @@ def get_postprocessors(opts):
'key': 'SponsorBlock',
'categories': sponsorblock_query,
'api': opts.sponsorblock_api,
'when': 'after_filter'
'when': 'after_filter',
}
if opts.convertsubtitles:
yield {
'key': 'FFmpegSubtitlesConvertor',
'format': opts.convertsubtitles,
'when': 'before_dl'
'when': 'before_dl',
}
if opts.convertthumbnails:
yield {
'key': 'FFmpegThumbnailsConvertor',
'format': opts.convertthumbnails,
'when': 'before_dl'
'when': 'before_dl',
}
if opts.extractaudio:
yield {
@ -647,7 +656,7 @@ def get_postprocessors(opts):
yield {
'key': 'FFmpegEmbedSubtitle',
# already_have_subtitle = True prevents the file from being deleted after embedding
'already_have_subtitle': opts.writesubtitles and keep_subs
'already_have_subtitle': opts.writesubtitles and keep_subs,
}
if not opts.writeautomaticsub and keep_subs:
opts.writesubtitles = True
@ -660,7 +669,7 @@ def get_postprocessors(opts):
'remove_sponsor_segments': opts.sponsorblock_remove,
'remove_ranges': opts.remove_ranges,
'sponsorblock_chapter_title': opts.sponsorblock_chapter_title,
'force_keyframes': opts.force_keyframes_at_cuts
'force_keyframes': opts.force_keyframes_at_cuts,
}
# FFmpegMetadataPP should be run after FFmpegVideoConvertorPP and
# FFmpegExtractAudioPP as containers before conversion may not support
@ -694,7 +703,7 @@ def get_postprocessors(opts):
yield {
'key': 'EmbedThumbnail',
# already_have_thumbnail = True prevents the file from being deleted after embedding
'already_have_thumbnail': opts.writethumbnail
'already_have_thumbnail': opts.writethumbnail,
}
if not opts.writethumbnail:
opts.writethumbnail = True
@ -741,7 +750,7 @@ def parse_options(argv=None):
print_only = bool(opts.forceprint) and all(k not in opts.forceprint for k in POSTPROCESS_WHEN[3:])
any_getting = any(getattr(opts, k) for k in (
'dumpjson', 'dump_single_json', 'getdescription', 'getduration', 'getfilename',
'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl'
'getformat', 'getid', 'getthumbnail', 'gettitle', 'geturl',
))
if opts.quiet is None:
opts.quiet = any_getting or opts.print_json or bool(opts.forceprint)
@ -1002,7 +1011,7 @@ def _real_main(argv=None):
def make_row(target, handler):
return [
join_nonempty(target.client.title(), target.version, delim='-') or '-',
join_nonempty((target.os or "").title(), target.os_version, delim='-') or '-',
join_nonempty((target.os or '').title(), target.os_version, delim='-') or '-',
handler,
]

36
yt_dlp/aes.py
View file

@ -68,7 +68,7 @@ def pad_block(block, padding_mode):
raise NotImplementedError(f'Padding mode {padding_mode} is not implemented')
if padding_mode == 'iso7816' and padding_size:
block = block + [0x80] # NB: += mutates list
block = [*block, 0x80] # NB: += mutates list
padding_size -= 1
return block + [PADDING_BYTE[padding_mode]] * padding_size
@ -110,9 +110,7 @@ def aes_ecb_decrypt(data, key, iv=None):
for i in range(block_count):
block = data[i * BLOCK_SIZE_BYTES: (i + 1) * BLOCK_SIZE_BYTES]
encrypted_data += aes_decrypt(block, expanded_key)
encrypted_data = encrypted_data[:len(data)]
return encrypted_data
return encrypted_data[:len(data)]
def aes_ctr_decrypt(data, key, iv):
@ -148,9 +146,7 @@ def aes_ctr_encrypt(data, key, iv):
cipher_counter_block = aes_encrypt(counter_block, expanded_key)
encrypted_data += xor(block, cipher_counter_block)
encrypted_data = encrypted_data[:len(data)]
return encrypted_data
return encrypted_data[:len(data)]
def aes_cbc_decrypt(data, key, iv):
@ -174,9 +170,7 @@ def aes_cbc_decrypt(data, key, iv):
decrypted_block = aes_decrypt(block, expanded_key)
decrypted_data += xor(decrypted_block, previous_cipher_block)
previous_cipher_block = block
decrypted_data = decrypted_data[:len(data)]
return decrypted_data
return decrypted_data[:len(data)]
def aes_cbc_encrypt(data, key, iv, *, padding_mode='pkcs7'):
@ -224,7 +218,7 @@ def aes_gcm_decrypt_and_verify(data, key, tag, nonce):
hash_subkey = aes_encrypt([0] * BLOCK_SIZE_BYTES, key_expansion(key))
if len(nonce) == 12:
j0 = nonce + [0, 0, 0, 1]
j0 = [*nonce, 0, 0, 0, 1]
else:
fill = (BLOCK_SIZE_BYTES - (len(nonce) % BLOCK_SIZE_BYTES)) % BLOCK_SIZE_BYTES + 8
ghash_in = nonce + [0] * fill + bytes_to_intlist((8 * len(nonce)).to_bytes(8, 'big'))
@ -242,11 +236,11 @@ def aes_gcm_decrypt_and_verify(data, key, tag, nonce):
data
+ [0] * (BLOCK_SIZE_BYTES - len(data) + pad_len) # pad
+ bytes_to_intlist((0 * 8).to_bytes(8, 'big') # length of associated data
+ ((len(data) * 8).to_bytes(8, 'big'))) # length of data
+ ((len(data) * 8).to_bytes(8, 'big'))), # length of data
)
if tag != aes_ctr_encrypt(s_tag, key, j0):
raise ValueError("Mismatching authentication tag")
raise ValueError('Mismatching authentication tag')
return decrypted_data
@ -288,9 +282,7 @@ def aes_decrypt(data, expanded_key):
data = list(iter_mix_columns(data, MIX_COLUMN_MATRIX_INV))
data = shift_rows_inv(data)
data = sub_bytes_inv(data)
data = xor(data, expanded_key[:BLOCK_SIZE_BYTES])
return data
return xor(data, expanded_key[:BLOCK_SIZE_BYTES])
def aes_decrypt_text(data, password, key_size_bytes):
@ -318,9 +310,7 @@ def aes_decrypt_text(data, password, key_size_bytes):
cipher = data[NONCE_LENGTH_BYTES:]
decrypted_data = aes_ctr_decrypt(cipher, key, nonce + [0] * (BLOCK_SIZE_BYTES - NONCE_LENGTH_BYTES))
plaintext = intlist_to_bytes(decrypted_data)
return plaintext
return intlist_to_bytes(decrypted_data)
RCON = (0x8d, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x1b, 0x36)
@ -428,9 +418,7 @@ def key_expansion(data):
for _ in range(3 if key_size_bytes == 32 else 2 if key_size_bytes == 24 else 0):
temp = data[-4:]
data += xor(temp, data[-key_size_bytes: 4 - key_size_bytes])
data = data[:expanded_key_size_bytes]
return data
return data[:expanded_key_size_bytes]
def iter_vector(iv):
@ -511,7 +499,7 @@ def block_product(block_x, block_y):
# NIST SP 800-38D, Algorithm 1
if len(block_x) != BLOCK_SIZE_BYTES or len(block_y) != BLOCK_SIZE_BYTES:
raise ValueError("Length of blocks need to be %d bytes" % BLOCK_SIZE_BYTES)
raise ValueError(f'Length of blocks need to be {BLOCK_SIZE_BYTES} bytes')
block_r = [0xE1] + [0] * (BLOCK_SIZE_BYTES - 1)
block_v = block_y[:]
@ -534,7 +522,7 @@ def ghash(subkey, data):
# NIST SP 800-38D, Algorithm 2
if len(data) % BLOCK_SIZE_BYTES:
raise ValueError("Length of data should be %d bytes" % BLOCK_SIZE_BYTES)
raise ValueError(f'Length of data should be {BLOCK_SIZE_BYTES} bytes')
last_y = [0] * BLOCK_SIZE_BYTES
for i in range(0, len(data), BLOCK_SIZE_BYTES):

4
yt_dlp/cache.py
View file

@ -81,10 +81,10 @@ def remove(self):
cachedir = self._get_root_dir()
if not any((term in cachedir) for term in ('cache', 'tmp')):
raise Exception('Not removing directory %s - this does not look like a cache dir' % cachedir)
raise Exception(f'Not removing directory {cachedir} - this does not look like a cache dir')
self._ydl.to_screen(
'Removing cache dir %s .' % cachedir, skip_eol=True)
f'Removing cache dir {cachedir} .', skip_eol=True)
if os.path.exists(cachedir):
self._ydl.to_screen('.', skip_eol=True)
shutil.rmtree(cachedir)

2
yt_dlp/compat/_legacy.py
View file

@ -35,7 +35,7 @@
from ..dependencies import brotli as compat_brotli # noqa: F401
from ..dependencies import websockets as compat_websockets # noqa: F401
from ..dependencies.Cryptodome import AES as compat_pycrypto_AES # noqa: F401
from ..networking.exceptions import HTTPError as compat_HTTPError # noqa: F401
from ..networking.exceptions import HTTPError as compat_HTTPError
passthrough_module(__name__, '...utils', ('WINDOWS_VT_MODE', 'windows_enable_vt_mode'))

2
yt_dlp/compat/functools.py
View file

@ -7,6 +7,6 @@
del passthrough_module
try:
cache # >= 3.9
_ = cache # >= 3.9
except NameError:
cache = lru_cache(maxsize=None)

26
yt_dlp/compat/imghdr.py
View file

@ -1,16 +1,22 @@
tests = {
'webp': lambda h: h[0:4] == b'RIFF' and h[8:] == b'WEBP',
'png': lambda h: h[:8] == b'\211PNG\r\n\032\n',
'jpeg': lambda h: h[6:10] in (b'JFIF', b'Exif'),
'gif': lambda h: h[:6] in (b'GIF87a', b'GIF89a'),
}
def what(file=None, h=None):
"""Detect format of image (Currently supports jpeg, png, webp, gif only)
Ref: https://github.com/python/cpython/blob/3.10/Lib/imghdr.py
Ref: https://github.com/python/cpython/blob/3.11/Lib/imghdr.py
Ref: https://www.w3.org/Graphics/JPEG/itu-t81.pdf
"""
if h is None:
with open(file, 'rb') as f:
h = f.read(12)
return next((type_ for type_, test in tests.items() if test(h)), None)
if h.startswith(b'RIFF') and h.startswith(b'WEBP', 8):
return 'webp'
if h.startswith(b'\x89PNG'):
return 'png'
if h.startswith(b'\xFF\xD8\xFF'):
return 'jpeg'
if h.startswith(b'GIF'):
return 'gif'
return None

125
yt_dlp/cookies.py
View file

@ -2,7 +2,9 @@
import collections
import contextlib
import datetime as dt
import functools
import glob
import hashlib
import http.cookiejar
import http.cookies
import io
@ -17,14 +19,12 @@
import time
import urllib.request
from enum import Enum, auto
from hashlib import pbkdf2_hmac
from .aes import (
aes_cbc_decrypt_bytes,
aes_gcm_decrypt_and_verify_bytes,
unpad_pkcs7,
)
from .compat import functools # isort: split
from .compat import compat_os_name
from .dependencies import (
_SECRETSTORAGE_UNAVAILABLE_REASON,
@ -146,7 +146,7 @@ def _extract_firefox_cookies(profile, container, logger):
identities = json.load(containers).get('identities', [])
container_id = next((context.get('userContextId') for context in identities if container in (
context.get('name'),
try_call(lambda: re.fullmatch(r'userContext([^\.]+)\.label', context['l10nID']).group())
try_call(lambda: re.fullmatch(r'userContext([^\.]+)\.label', context['l10nID']).group()),
)), None)
if not isinstance(container_id, int):
raise ValueError(f'could not find firefox container "{container}" in containers.json')
@ -263,7 +263,7 @@ def _get_chromium_based_browser_settings(browser_name):
return {
'browser_dir': browser_dir,
'keyring_name': keyring_name,
'supports_profiles': browser_name not in browsers_without_profiles
'supports_profiles': browser_name not in browsers_without_profiles,
}
@ -740,40 +740,38 @@ def _get_linux_desktop_environment(env, logger):
xdg_current_desktop = env.get('XDG_CURRENT_DESKTOP', None)
desktop_session = env.get('DESKTOP_SESSION', None)
if xdg_current_desktop is not None:
xdg_current_desktop = xdg_current_desktop.split(':')[0].strip()
if xdg_current_desktop == 'Unity':
if desktop_session is not None and 'gnome-fallback' in desktop_session:
for part in map(str.strip, xdg_current_desktop.split(':')):
if part == 'Unity':
if desktop_session is not None and 'gnome-fallback' in desktop_session:
return _LinuxDesktopEnvironment.GNOME
else:
return _LinuxDesktopEnvironment.UNITY
elif part == 'Deepin':
return _LinuxDesktopEnvironment.DEEPIN
elif part == 'GNOME':
return _LinuxDesktopEnvironment.GNOME
else:
return _LinuxDesktopEnvironment.UNITY
elif xdg_current_desktop == 'Deepin':
return _LinuxDesktopEnvironment.DEEPIN
elif xdg_current_desktop == 'GNOME':
return _LinuxDesktopEnvironment.GNOME
elif xdg_current_desktop == 'X-Cinnamon':
return _LinuxDesktopEnvironment.CINNAMON
elif xdg_current_desktop == 'KDE':
kde_version = env.get('KDE_SESSION_VERSION', None)
if kde_version == '5':
return _LinuxDesktopEnvironment.KDE5
elif kde_version == '6':
return _LinuxDesktopEnvironment.KDE6
elif kde_version == '4':
return _LinuxDesktopEnvironment.KDE4
else:
logger.info(f'unknown KDE version: "{kde_version}". Assuming KDE4')
return _LinuxDesktopEnvironment.KDE4
elif xdg_current_desktop == 'Pantheon':
return _LinuxDesktopEnvironment.PANTHEON
elif xdg_current_desktop == 'XFCE':
return _LinuxDesktopEnvironment.XFCE
elif xdg_current_desktop == 'UKUI':
return _LinuxDesktopEnvironment.UKUI
elif xdg_current_desktop == 'LXQt':
return _LinuxDesktopEnvironment.LXQT
else:
logger.info(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
elif part == 'X-Cinnamon':
return _LinuxDesktopEnvironment.CINNAMON
elif part == 'KDE':
kde_version = env.get('KDE_SESSION_VERSION', None)
if kde_version == '5':
return _LinuxDesktopEnvironment.KDE5
elif kde_version == '6':
return _LinuxDesktopEnvironment.KDE6
elif kde_version == '4':
return _LinuxDesktopEnvironment.KDE4
else:
logger.info(f'unknown KDE version: "{kde_version}". Assuming KDE4')
return _LinuxDesktopEnvironment.KDE4
elif part == 'Pantheon':
return _LinuxDesktopEnvironment.PANTHEON
elif part == 'XFCE':
return _LinuxDesktopEnvironment.XFCE
elif part == 'UKUI':
return _LinuxDesktopEnvironment.UKUI
elif part == 'LXQt':
return _LinuxDesktopEnvironment.LXQT
logger.info(f'XDG_CURRENT_DESKTOP is set to an unknown value: "{xdg_current_desktop}"')
elif desktop_session is not None:
if desktop_session == 'deepin':
@ -826,7 +824,7 @@ def _choose_linux_keyring(logger):
elif desktop_environment == _LinuxDesktopEnvironment.KDE6:
linux_keyring = _LinuxKeyring.KWALLET6
elif desktop_environment in (
_LinuxDesktopEnvironment.KDE3, _LinuxDesktopEnvironment.LXQT, _LinuxDesktopEnvironment.OTHER
_LinuxDesktopEnvironment.KDE3, _LinuxDesktopEnvironment.LXQT, _LinuxDesktopEnvironment.OTHER,
):
linux_keyring = _LinuxKeyring.BASICTEXT
else:
@ -861,7 +859,7 @@ def _get_kwallet_network_wallet(keyring, logger):
'dbus-send', '--session', '--print-reply=literal',
f'--dest={service_name}',
wallet_path,
'org.kde.KWallet.networkWallet'
'org.kde.KWallet.networkWallet',
], text=True, stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
if returncode:
@ -891,7 +889,7 @@ def _get_kwallet_password(browser_keyring_name, keyring, logger):
'kwallet-query',
'--read-password', f'{browser_keyring_name} Safe Storage',
'--folder', f'{browser_keyring_name} Keys',
network_wallet
network_wallet,
], stdout=subprocess.PIPE, stderr=subprocess.DEVNULL)
if returncode:
@ -931,9 +929,8 @@ def _get_gnome_keyring_password(browser_keyring_name, logger):
for item in col.get_all_items():
if item.get_label() == f'{browser_keyring_name} Safe Storage':
return item.get_secret()
else:
logger.error('failed to read from keyring')
return b''
logger.error('failed to read from keyring')
return b''
def _get_linux_keyring_password(browser_keyring_name, keyring, logger):
@ -1002,7 +999,7 @@ def _get_windows_v10_key(browser_root, logger):
def pbkdf2_sha1(password, salt, iterations, key_length):
return pbkdf2_hmac('sha1', password, salt, iterations, key_length)
return hashlib.pbkdf2_hmac('sha1', password, salt, iterations, key_length)
def _decrypt_aes_cbc_multi(ciphertext, keys, logger, initialization_vector=b' ' * 16):
@ -1053,7 +1050,7 @@ class DATA_BLOB(ctypes.Structure):
None, # pvReserved: must be NULL
None, # pPromptStruct: information about prompts to display
0, # dwFlags
ctypes.byref(blob_out) # pDataOut
ctypes.byref(blob_out), # pDataOut
)
if not ret:
logger.warning('failed to decrypt with DPAPI', only_once=True)
@ -1129,24 +1126,24 @@ class LenientSimpleCookie(http.cookies.SimpleCookie):
_LEGAL_VALUE_CHARS = _LEGAL_KEY_CHARS + re.escape('(),/<=>?@[]{}')
_RESERVED = {
"expires",
"path",
"comment",
"domain",
"max-age",
"secure",
"httponly",
"version",
"samesite",
'expires',
'path',
'comment',
'domain',
'max-age',
'secure',
'httponly',
'version',
'samesite',
}
_FLAGS = {"secure", "httponly"}
_FLAGS = {'secure', 'httponly'}
# Added 'bad' group to catch the remaining value
_COOKIE_PATTERN = re.compile(r"""
_COOKIE_PATTERN = re.compile(r'''
\s* # Optional whitespace at start of cookie
(?P<key> # Start of group 'key'
[""" + _LEGAL_KEY_CHARS + r"""]+?# Any word of at least one letter
[''' + _LEGAL_KEY_CHARS + r''']+?# Any word of at least one letter
) # End of group 'key'
( # Optional group: there may not be a value.
\s*=\s* # Equal Sign
@ -1156,7 +1153,7 @@ class LenientSimpleCookie(http.cookies.SimpleCookie):
| # or
\w{3},\s[\w\d\s-]{9,11}\s[\d:]{8}\sGMT # Special case for "expires" attr
| # or
[""" + _LEGAL_VALUE_CHARS + r"""]* # Any word or empty string
[''' + _LEGAL_VALUE_CHARS + r''']* # Any word or empty string
) # End of group 'val'
| # or
(?P<bad>(?:\\;|[^;])*?) # 'bad' group fallback for invalid values
@ -1164,7 +1161,7 @@ class LenientSimpleCookie(http.cookies.SimpleCookie):
)? # End of optional value group
\s* # Any number of spaces.
(\s+|;|$) # Ending either at space, semicolon, or EOS.
""", re.ASCII | re.VERBOSE)
''', re.ASCII | re.VERBOSE)
def load(self, data):
# Workaround for https://github.com/yt-dlp/yt-dlp/issues/4776
@ -1260,14 +1257,14 @@ def _really_save(self, f, ignore_discard, ignore_expires):
# with no name, whereas http.cookiejar regards it as a
# cookie with no value.
name, value = '', name
f.write('%s\n' % '\t'.join((
f.write('{}\n'.format('\t'.join((
cookie.domain,
self._true_or_false(cookie.domain.startswith('.')),
cookie.path,
self._true_or_false(cookie.secure),
str_or_none(cookie.expires, default=''),
name, value
)))
name, value,
))))
def save(self, filename=None, ignore_discard=True, ignore_expires=True):
"""
@ -1306,10 +1303,10 @@ def prepare_line(line):
return line
cookie_list = line.split('\t')
if len(cookie_list) != self._ENTRY_LEN:
raise http.cookiejar.LoadError('invalid length %d' % len(cookie_list))
raise http.cookiejar.LoadError(f'invalid length {len(cookie_list)}')
cookie = self._CookieFileEntry(*cookie_list)
if cookie.expires_at and not cookie.expires_at.isdigit():
raise http.cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
raise http.cookiejar.LoadError(f'invalid expires at {cookie.expires_at}')
return line
cf = io.StringIO()

2
yt_dlp/downloader/common.py
View file

@ -404,7 +404,7 @@ def with_fields(*tups, default=''):
def report_resuming_byte(self, resume_len):
"""Report attempt to resume at given byte."""
self.to_screen('[download] Resuming download at byte %s' % resume_len)
self.to_screen(f'[download] Resuming download at byte {resume_len}')
def report_retry(self, err, count, retries, frag_index=NO_DEFAULT, fatal=True):
"""Report retry"""

28
yt_dlp/downloader/external.py
View file

@ -1,4 +1,5 @@
import enum
import functools
import json
import os
import re
@ -9,7 +10,6 @@
import uuid
from .fragment import FragmentFD
from ..compat import functools
from ..networking import Request
from ..postprocessor.ffmpeg import EXT_TO_OUT_FORMATS, FFmpegPostProcessor
from ..utils import (
@ -55,7 +55,7 @@ def real_download(self, filename, info_dict):
# correct and expected termination thus all postprocessing
# should take place
retval = 0
self.to_screen('[%s] Interrupted by user' % self.get_basename())
self.to_screen(f'[{self.get_basename()}] Interrupted by user')
finally:
if self._cookies_tempfile:
self.try_remove(self._cookies_tempfile)
@ -108,7 +108,7 @@ def supports(cls, info_dict):
return all((
not info_dict.get('to_stdout') or Features.TO_STDOUT in cls.SUPPORTED_FEATURES,
'+' not in info_dict['protocol'] or Features.MULTIPLE_FORMATS in cls.SUPPORTED_FEATURES,
not traverse_obj(info_dict, ('hls_aes', ...), 'extra_param_to_segment_url'),
not traverse_obj(info_dict, ('hls_aes', ...), 'extra_param_to_segment_url', 'extra_param_to_key_url'),
all(proto in cls.SUPPORTED_PROTOCOLS for proto in info_dict['protocol'].split('+')),
))
@ -172,7 +172,7 @@ def _call_downloader(self, tmpfilename, info_dict):
decrypt_fragment = self.decrypter(info_dict)
dest, _ = self.sanitize_open(tmpfilename, 'wb')
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (tmpfilename, frag_index)
fragment_filename = f'{tmpfilename}-Frag{frag_index}'
try:
src, _ = self.sanitize_open(fragment_filename, 'rb')
except OSError as err:
@ -186,7 +186,7 @@ def _call_downloader(self, tmpfilename, info_dict):
if not self.params.get('keep_fragments', False):
self.try_remove(encodeFilename(fragment_filename))
dest.close()
self.try_remove(encodeFilename('%s.frag.urls' % tmpfilename))
self.try_remove(encodeFilename(f'{tmpfilename}.frag.urls'))
return 0
def _call_process(self, cmd, info_dict):
@ -336,11 +336,11 @@ def _make_cmd(self, tmpfilename, info_dict):
if 'fragments' in info_dict:
cmd += ['--uri-selector=inorder']
url_list_file = '%s.frag.urls' % tmpfilename
url_list_file = f'{tmpfilename}.frag.urls'
url_list = []
for frag_index, fragment in enumerate(info_dict['fragments']):
fragment_filename = '%s-Frag%d' % (os.path.basename(tmpfilename), frag_index)
url_list.append('%s\n\tout=%s' % (fragment['url'], self._aria2c_filename(fragment_filename)))
fragment_filename = f'{os.path.basename(tmpfilename)}-Frag{frag_index}'
url_list.append('{}\n\tout={}'.format(fragment['url'], self._aria2c_filename(fragment_filename)))
stream, _ = self.sanitize_open(url_list_file, 'wb')
stream.write('\n'.join(url_list).encode())
stream.close()
@ -357,7 +357,7 @@ def aria2c_rpc(self, rpc_port, rpc_secret, method, params=()):
'id': sanitycheck,
'method': method,
'params': [f'token:{rpc_secret}', *params],
}).encode('utf-8')
}).encode()
request = Request(
f'http://localhost:{rpc_port}/jsonrpc',
data=d, headers={
@ -416,7 +416,7 @@ def get_stat(key, *obj, average=False):
'total_bytes_estimate': total,
'eta': (total - downloaded) / (speed or 1),
'fragment_index': min(frag_count, len(completed) + 1) if fragmented else None,
'elapsed': time.time() - started
'elapsed': time.time() - started,
})
self._hook_progress(status, info_dict)
@ -509,12 +509,12 @@ def _call_downloader(self, tmpfilename, info_dict):
proxy = self.params.get('proxy')
if proxy:
if not re.match(r'^[\da-zA-Z]+://', proxy):
proxy = 'http://%s' % proxy
proxy = f'http://{proxy}'
if proxy.startswith('socks'):
self.report_warning(
'%s does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.' % self.get_basename())
f'{self.get_basename()} does not support SOCKS proxies. Downloading is likely to fail. '
'Consider adding --hls-prefer-native to your command.')
# Since December 2015 ffmpeg supports -http_proxy option (see
# http://git.videolan.org/?p=ffmpeg.git;a=commit;h=b4eb1f29ebddd60c41a2eb39f5af701e38e0d3fd)
@ -575,7 +575,7 @@ def _call_downloader(self, tmpfilename, info_dict):
if end_time:
args += ['-t', str(end_time - start_time)]
args += self._configuration_args((f'_i{i + 1}', '_i')) + ['-i', fmt['url']]
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', fmt['url']]
if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):
args += ['-c', 'copy']

22
yt_dlp/downloader/f4m.py
View file

@ -67,12 +67,12 @@ def read_asrt(self):
self.read_bytes(3)
quality_entry_count = self.read_unsigned_char()
# QualityEntryCount
for i in range(quality_entry_count):
for _ in range(quality_entry_count):
self.read_string()
segment_run_count = self.read_unsigned_int()
segments = []
for i in range(segment_run_count):
for _ in range(segment_run_count):
first_segment = self.read_unsigned_int()
fragments_per_segment = self.read_unsigned_int()
segments.append((first_segment, fragments_per_segment))
@ -91,12 +91,12 @@ def read_afrt(self):
quality_entry_count = self.read_unsigned_char()
# QualitySegmentUrlModifiers
for i in range(quality_entry_count):
for _ in range(quality_entry_count):
self.read_string()
fragments_count = self.read_unsigned_int()
fragments = []
for i in range(fragments_count):
for _ in range(fragments_count):
first = self.read_unsigned_int()
first_ts = self.read_unsigned_long_long()
duration = self.read_unsigned_int()
@ -135,11 +135,11 @@ def read_abst(self):
self.read_string() # MovieIdentifier
server_count = self.read_unsigned_char()
# ServerEntryTable
for i in range(server_count):
for _ in range(server_count):
self.read_string()
quality_count = self.read_unsigned_char()
# QualityEntryTable
for i in range(quality_count):
for _ in range(quality_count):
self.read_string()
# DrmData
self.read_string()
@ -148,14 +148,14 @@ def read_abst(self):
segments_count = self.read_unsigned_char()
segments = []
for i in range(segments_count):
for _ in range(segments_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'asrt'
segment = FlvReader(box_data).read_asrt()
segments.append(segment)
fragments_run_count = self.read_unsigned_char()
fragments = []
for i in range(fragments_run_count):
for _ in range(fragments_run_count):
box_size, box_type, box_data = self.read_box_info()
assert box_type == b'afrt'
fragments.append(FlvReader(box_data).read_afrt())
@ -309,7 +309,7 @@ def _parse_bootstrap_node(self, node, base_url):
def real_download(self, filename, info_dict):
man_url = info_dict['url']
requested_bitrate = info_dict.get('tbr')
self.to_screen('[%s] Downloading f4m manifest' % self.FD_NAME)
self.to_screen(f'[{self.FD_NAME}] Downloading f4m manifest')
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.url
@ -326,8 +326,8 @@ def real_download(self, filename, info_dict):
formats = sorted(formats, key=lambda f: f[0])
rate, media = formats[-1]
else:
rate, media = list(filter(
lambda f: int(f[0]) == requested_bitrate, formats))[0]
rate, media = next(filter(
lambda f: int(f[0]) == requested_bitrate, formats))
# Prefer baseURL for relative URLs as per 11.2 of F4M 3.0 spec.
man_base_url = get_base_url(doc) or man_url

8
yt_dlp/downloader/fragment.py
View file

@ -199,7 +199,7 @@ def _prepare_frag_download(self, ctx):
'.ytdl file is corrupt' if is_corrupt else
'Inconsistent state of incomplete fragment download')
self.report_warning(
'%s. Restarting from the beginning ...' % message)
f'{message}. Restarting from the beginning ...')
ctx['fragment_index'] = resume_len = 0
if 'ytdl_corrupt' in ctx:
del ctx['ytdl_corrupt']
@ -366,10 +366,10 @@ def decrypt_fragment(fragment, frag_content):
return decrypt_fragment
def download_and_append_fragments_multiple(self, *args, **kwargs):
'''
"""
@params (ctx1, fragments1, info_dict1), (ctx2, fragments2, info_dict2), ...
all args must be either tuple or list
'''
"""
interrupt_trigger = [True]
max_progress = len(args)
if max_progress == 1:
@ -424,7 +424,7 @@ def interrupt_trigger_iter(fg):
finally:
tpe.shutdown(wait=True)
if not interrupt_trigger[0] and not is_live:
raise KeyboardInterrupt()
raise KeyboardInterrupt
# we expect the user wants to stop and DO WANT the preceding postprocessors to run;
# so returning a intermediate result here instead of KeyboardInterrupt on live
return result

33
yt_dlp/downloader/hls.py
View file

@ -72,7 +72,7 @@ def check_results():
def real_download(self, filename, info_dict):
man_url = info_dict['url']
self.to_screen('[%s] Downloading m3u8 manifest' % self.FD_NAME)
self.to_screen(f'[{self.FD_NAME}] Downloading m3u8 manifest')
urlh = self.ydl.urlopen(self._prepare_url(info_dict, man_url))
man_url = urlh.url
@ -160,10 +160,12 @@ def is_ad_fragment_end(s):
extra_state = ctx.setdefault('extra_state', {})
format_index = info_dict.get('format_index')
extra_query = None
extra_param_to_segment_url = info_dict.get('extra_param_to_segment_url')
if extra_param_to_segment_url:
extra_query = urllib.parse.parse_qs(extra_param_to_segment_url)
extra_segment_query = None
if extra_param_to_segment_url := info_dict.get('extra_param_to_segment_url'):
extra_segment_query = urllib.parse.parse_qs(extra_param_to_segment_url)
extra_key_query = None
if extra_param_to_key_url := info_dict.get('extra_param_to_key_url'):
extra_key_query = urllib.parse.parse_qs(extra_param_to_key_url)
i = 0
media_sequence = 0
decrypt_info = {'METHOD': 'NONE'}
@ -190,8 +192,8 @@ def is_ad_fragment_end(s):
if frag_index <= ctx['fragment_index']:
continue
frag_url = urljoin(man_url, line)
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
if extra_segment_query:
frag_url = update_url_query(frag_url, extra_segment_query)
fragments.append({
'frag_index': frag_index,
@ -212,8 +214,8 @@ def is_ad_fragment_end(s):
frag_index += 1
map_info = parse_m3u8_attributes(line[11:])
frag_url = urljoin(man_url, map_info.get('URI'))
if extra_query:
frag_url = update_url_query(frag_url, extra_query)
if extra_segment_query:
frag_url = update_url_query(frag_url, extra_segment_query)
if map_info.get('BYTERANGE'):
splitted_byte_range = map_info.get('BYTERANGE').split('@')
@ -228,7 +230,7 @@ def is_ad_fragment_end(s):
'url': frag_url,
'decrypt_info': decrypt_info,
'byte_range': byte_range,
'media_sequence': media_sequence
'media_sequence': media_sequence,
})
media_sequence += 1
@ -244,8 +246,10 @@ def is_ad_fragment_end(s):
decrypt_info['KEY'] = external_aes_key
else:
decrypt_info['URI'] = urljoin(man_url, decrypt_info['URI'])
if extra_query:
decrypt_info['URI'] = update_url_query(decrypt_info['URI'], extra_query)
if extra_key_query or extra_segment_query:
# Fall back to extra_segment_query to key for backwards compat
decrypt_info['URI'] = update_url_query(
decrypt_info['URI'], extra_key_query or extra_segment_query)
if decrypt_url != decrypt_info['URI']:
decrypt_info['KEY'] = None
@ -350,9 +354,8 @@ def pack_fragment(frag_content, frag_index):
# XXX: this should probably be silent as well
# or verify that all segments contain the same data
self.report_warning(bug_reports_message(
'Discarding a %s block found in the middle of the stream; '
'if the subtitles display incorrectly,'
% (type(block).__name__)))
f'Discarding a {type(block).__name__} block found in the middle of the stream; '
'if the subtitles display incorrectly,'))
continue
block.write_into(output)

14
yt_dlp/downloader/http.py
View file

@ -176,7 +176,7 @@ def establish_connection():
'downloaded_bytes': ctx.resume_len,
'total_bytes': ctx.resume_len,
}, info_dict)
raise SucceedDownload()
raise SucceedDownload
else:
# The length does not match, we start the download over
self.report_unable_to_resume()
@ -194,7 +194,7 @@ def establish_connection():
def close_stream():
if ctx.stream is not None:
if not ctx.tmpfilename == '-':
if ctx.tmpfilename != '-':
ctx.stream.close()
ctx.stream = None
@ -268,20 +268,20 @@ def retry(e):
ctx.filename = self.undo_temp_name(ctx.tmpfilename)
self.report_destination(ctx.filename)
except OSError as err:
self.report_error('unable to open for writing: %s' % str(err))
self.report_error(f'unable to open for writing: {err}')
return False
if self.params.get('xattr_set_filesize', False) and data_len is not None:
try:
write_xattr(ctx.tmpfilename, 'user.ytdl.filesize', str(data_len).encode())
except (XAttrUnavailableError, XAttrMetadataError) as err:
self.report_error('unable to set filesize xattr: %s' % str(err))
self.report_error(f'unable to set filesize xattr: {err}')
try:
ctx.stream.write(data_block)
except OSError as err:
self.to_stderr('\n')
self.report_error('unable to write data: %s' % str(err))
self.report_error(f'unable to write data: {err}')
return False
# Apply rate limit
@ -327,7 +327,7 @@ def retry(e):
elif now - ctx.throttle_start > 3:
if ctx.stream is not None and ctx.tmpfilename != '-':
ctx.stream.close()
raise ThrottledDownload()
raise ThrottledDownload
elif speed:
ctx.throttle_start = None
@ -338,7 +338,7 @@ def retry(e):
if not is_test and ctx.chunk_size and ctx.content_len is not None and byte_counter < ctx.content_len:
ctx.resume_len = byte_counter
raise NextFragment()
raise NextFragment
if ctx.tmpfilename != '-':
ctx.stream.close()

2
yt_dlp/downloader/ism.py
View file

@ -251,7 +251,7 @@ def real_download(self, filename, info_dict):
skip_unavailable_fragments = self.params.get('skip_unavailable_fragments', True)
frag_index = 0
for i, segment in enumerate(segments):
for segment in segments:
frag_index += 1
if frag_index <= ctx['fragment_index']:
continue

53
yt_dlp/downloader/mhtml.py
View file

@ -10,7 +10,7 @@
class MhtmlFD(FragmentFD):
_STYLESHEET = """\
_STYLESHEET = '''\
html, body {
margin: 0;
padding: 0;
@ -45,7 +45,7 @@ class MhtmlFD(FragmentFD):
max-width: 100%;
max-height: calc(100vh - 5em);
}
"""
'''
_STYLESHEET = re.sub(r'\s+', ' ', _STYLESHEET)
_STYLESHEET = re.sub(r'\B \B|(?<=[\w\-]) (?=[^\w\-])|(?<=[^\w\-]) (?=[\w\-])', '', _STYLESHEET)
@ -57,24 +57,19 @@ def _escape_mime(s):
)).decode('us-ascii') + '?='
def _gen_cid(self, i, fragment, frag_boundary):
return '%u.%s@yt-dlp.github.io.invalid' % (i, frag_boundary)
return f'{i}.{frag_boundary}@yt-dlp.github.io.invalid'
def _gen_stub(self, *, fragments, frag_boundary, title):
output = io.StringIO()
output.write((
output.write(
'<!DOCTYPE html>'
'<html>'
'<head>'
'' '<meta name="generator" content="yt-dlp {version}">'
'' '<title>{title}</title>'
'' '<style>{styles}</style>'
'<body>'
).format(
version=escapeHTML(YT_DLP_VERSION),
styles=self._STYLESHEET,
title=escapeHTML(title)
))
f'<meta name="generator" content="yt-dlp {escapeHTML(YT_DLP_VERSION)}">'
f'<title>{escapeHTML(title)}</title>'
f'<style>{self._STYLESHEET}</style>'
'<body>')
t0 = 0
for i, frag in enumerate(fragments):
@ -87,15 +82,12 @@ def _gen_stub(self, *, fragments, frag_boundary, title):
num=i + 1,
t0=srt_subtitles_timecode(t0),
t1=srt_subtitles_timecode(t1),
duration=formatSeconds(frag['duration'], msec=True)
duration=formatSeconds(frag['duration'], msec=True),
))
except (KeyError, ValueError, TypeError):
t1 = None
output.write((
'<figcaption>Slide #{num}</figcaption>'
).format(num=i + 1))
output.write('<img src="cid:{cid}">'.format(
cid=self._gen_cid(i, frag, frag_boundary)))
output.write(f'<figcaption>Slide #{i + 1}</figcaption>')
output.write(f'<img src="cid:{self._gen_cid(i, frag, frag_boundary)}">')
output.write('</figure>')
t0 = t1
@ -126,31 +118,24 @@ def real_download(self, filename, info_dict):
stub = self._gen_stub(
fragments=fragments,
frag_boundary=frag_boundary,
title=title
title=title,
)
ctx['dest_stream'].write((
'MIME-Version: 1.0\r\n'
'From: <nowhere@yt-dlp.github.io.invalid>\r\n'
'To: <nowhere@yt-dlp.github.io.invalid>\r\n'
'Subject: {title}\r\n'
f'Subject: {self._escape_mime(title)}\r\n'
'Content-type: multipart/related; '
'' 'boundary="{boundary}"; '
'' 'type="text/html"\r\n'
'X.yt-dlp.Origin: {origin}\r\n'
f'boundary="{frag_boundary}"; '
'type="text/html"\r\n'
f'X.yt-dlp.Origin: {origin}\r\n'
'\r\n'
'--{boundary}\r\n'
f'--{frag_boundary}\r\n'
'Content-Type: text/html; charset=utf-8\r\n'
'Content-Length: {length}\r\n'
f'Content-Length: {len(stub)}\r\n'
'\r\n'
'{stub}\r\n'
).format(
origin=origin,
boundary=frag_boundary,
length=len(stub),
title=self._escape_mime(title),
stub=stub
).encode())
f'{stub}\r\n').encode())
extra_state['header_written'] = True
for i, fragment in enumerate(fragments):

14
yt_dlp/downloader/niconico.py
View file

@ -15,7 +15,7 @@ class NiconicoDmcFD(FileDownloader):
def real_download(self, filename, info_dict):
from ..extractor.niconico import NiconicoIE
self.to_screen('[%s] Downloading from DMC' % self.FD_NAME)
self.to_screen(f'[{self.FD_NAME}] Downloading from DMC')
ie = NiconicoIE(self.ydl)
info_dict, heartbeat_info_dict = ie._get_heartbeat_info(info_dict)
@ -34,7 +34,7 @@ def heartbeat():
try:
self.ydl.urlopen(request).read()
except Exception:
self.to_screen('[%s] Heartbeat failed' % self.FD_NAME)
self.to_screen(f'[{self.FD_NAME}] Heartbeat failed')
with heartbeat_lock:
if not download_complete:
@ -85,14 +85,14 @@ def communicate_ws(reconnect):
'quality': live_quality,
'protocol': 'hls+fmp4',
'latency': live_latency,
'chasePlay': False
'chasePlay': False,
},
'room': {
'protocol': 'webSocket',
'commentable': True
'commentable': True,
},
'reconnect': True,
}
},
}))
else:
ws = ws_extractor
@ -118,7 +118,7 @@ def communicate_ws(reconnect):
elif self.ydl.params.get('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.to_screen('[debug] Server said: %s' % recv)
self.to_screen(f'[debug] Server said: {recv}')
def ws_main():
reconnect = False
@ -128,7 +128,7 @@ def ws_main():
if ret is True:
return
except BaseException as e:
self.to_screen('[%s] %s: Connection error occured, reconnecting after 10 seconds: %s' % ('niconico:live', video_id, str_or_none(e)))
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
time.sleep(10)
continue
finally:

6
yt_dlp/downloader/rtmp.py
View file

@ -180,9 +180,9 @@ def run_rtmpdump(args):
while retval in (RD_INCOMPLETE, RD_FAILED) and not test and not live:
prevsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] Downloaded %s bytes' % prevsize)
self.to_screen(f'[rtmpdump] Downloaded {prevsize} bytes')
time.sleep(5.0) # This seems to be needed
args = basic_args + ['--resume']
args = [*basic_args, '--resume']
if retval == RD_FAILED:
args += ['--skip', '1']
args = [encodeArgument(a) for a in args]
@ -197,7 +197,7 @@ def run_rtmpdump(args):
break
if retval == RD_SUCCESS or (test and retval == RD_INCOMPLETE):
fsize = os.path.getsize(encodeFilename(tmpfilename))
self.to_screen('[rtmpdump] Downloaded %s bytes' % fsize)
self.to_screen(f'[rtmpdump] Downloaded {fsize} bytes')
self.try_rename(tmpfilename, filename)
self._hook_progress({
'downloaded_bytes': fsize,

2
yt_dlp/downloader/youtube_live_chat.py
View file

@ -18,7 +18,7 @@ class YoutubeLiveChatFD(FragmentFD):
def real_download(self, filename, info_dict):
video_id = info_dict['video_id']
self.to_screen('[%s] Downloading live chat' % self.FD_NAME)
self.to_screen(f'[{self.FD_NAME}] Downloading live chat')
if not self.params.get('skip_download') and info_dict['protocol'] == 'youtube_live_chat':
self.report_warning('Live chat download runs until the livestream ends. '
'If you wish to download the video simultaneously, run a separate yt-dlp instance')

46
yt_dlp/extractor/_extractors.py
View file

@ -76,6 +76,7 @@
)
from .aeonco import AeonCoIE
from .afreecatv import (
AfreecaTVCatchStoryIE,
AfreecaTVIE,
AfreecaTVLiveIE,
AfreecaTVUserIE,
@ -503,7 +504,6 @@
from .digitalconcerthall import DigitalConcertHallIE
from .digiteka import DigitekaIE
from .discogs import DiscogsReleasePlaylistIE
from .discovery import DiscoveryIE
from .disney import DisneyIE
from .dispeak import DigitallySpeakingIE
from .dlf import (
@ -531,16 +531,12 @@
DiscoveryPlusIndiaShowIE,
DiscoveryPlusItalyIE,
DiscoveryPlusItalyShowIE,
DIYNetworkIE,
DPlayIE,
FoodNetworkIE,
GlobalCyclingNetworkPlusIE,
GoDiscoveryIE,
HGTVDeIE,
HGTVUsaIE,
InvestigationDiscoveryIE,
MotorTrendIE,
MotorTrendOnDemandIE,
ScienceChannelIE,
TravelChannelIE,
)
@ -779,6 +775,7 @@
from .goshgay import GoshgayIE
from .gotostage import GoToStageIE
from .gputechconf import GPUTechConfIE
from .graspop import GraspopIE
from .gronkh import (
GronkhFeedIE,
GronkhIE,
@ -942,6 +939,7 @@
KhanAcademyUnitIE,
)
from .kick import (
KickClipIE,
KickIE,
KickVODIE,
)
@ -969,6 +967,10 @@
LA7PodcastEpisodeIE,
LA7PodcastIE,
)
from .laracasts import (
LaracastsIE,
LaracastsPlaylistIE,
)
from .lastfm import (
LastFMIE,
LastFMPlaylistIE,
@ -985,6 +987,7 @@
LcpIE,
LcpPlayIE,
)
from .learningonscreen import LearningOnScreenIE
from .lecture2go import Lecture2GoIE
from .lecturio import (
LecturioCourseIE,
@ -1114,12 +1117,15 @@
from .mercadolibre import MercadoLibreIE
from .metacritic import MetacriticIE
from .mgtv import MGTVIE
from .microsoftembed import MicrosoftEmbedIE
from .microsoftstream import MicrosoftStreamIE
from .microsoftvirtualacademy import (
MicrosoftVirtualAcademyCourseIE,
MicrosoftVirtualAcademyIE,
from .microsoftembed import (
MicrosoftBuildIE,
MicrosoftEmbedIE,
MicrosoftLearnEpisodeIE,
MicrosoftLearnPlaylistIE,
MicrosoftLearnSessionIE,
MicrosoftMediusIE,
)
from .microsoftstream import MicrosoftStreamIE
from .mildom import (
MildomClipIE,
MildomIE,
@ -1604,6 +1610,7 @@
QQMusicPlaylistIE,
QQMusicSingerIE,
QQMusicToplistIE,
QQMusicVideoIE,
)
from .r7 import (
R7IE,
@ -1756,7 +1763,10 @@
RTVETelevisionIE,
)
from .rtvs import RTVSIE
from .rtvslo import RTVSLOIE
from .rtvslo import (
RTVSLOIE,
RTVSLOShowIE,
)
from .rudovideo import RudoVideoIE
from .rule34video import Rule34VideoIE
from .rumble import (
@ -1926,6 +1936,10 @@
)
from .springboardplatform import SpringboardPlatformIE
from .sprout import SproutIE
from .sproutvideo import (
SproutVideoIE,
VidsIoIE,
)
from .srgssr import (
SRGSSRIE,
SRGSSRPlayIE,
@ -2158,10 +2172,7 @@
TV5UnisVideoIE,
)
from .tv24ua import TV24UAVideoIE
from .tva import (
TVAIE,
QubIE,
)
from .tva import TVAIE
from .tvanouvelles import (
TVANouvellesArticleIE,
TVANouvellesIE,
@ -2308,6 +2319,7 @@
)
from .vidlii import VidLiiIE
from .vidly import VidlyIE
from .vidyard import VidyardIE
from .viewlift import (
ViewLiftEmbedIE,
ViewLiftIE,
@ -2373,6 +2385,10 @@
VrtNUIE,
)
from .vtm import VTMIE
from .vtv import (
VTVIE,
VTVGoIE,
)
from .vuclip import VuClipIE
from .vvvvid import (
VVVVIDIE,

28
yt_dlp/extractor/abc.py
View file

@ -4,7 +4,6 @@
import time
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
dict_get,
@ -67,7 +66,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'title': 'WWI Centenary',
'description': 'md5:c2379ec0ca84072e86b446e536954546',
}
},
}, {
'url': 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074',
'info_dict': {
@ -75,7 +74,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'title': 'Black Lives Matter protests spawn support for Papuans in Indonesia',
'description': 'md5:2961a17dc53abc558589ccd0fb8edd6f',
}
},
}, {
'url': 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476',
'info_dict': {
@ -86,7 +85,7 @@ class ABCIE(InfoExtractor):
'upload_date': '20200813',
'uploader': 'Behind the News',
'uploader_id': 'behindthenews',
}
},
}, {
'url': 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540',
'info_dict': {
@ -95,7 +94,7 @@ class ABCIE(InfoExtractor):
'ext': 'mp4',
'description': 'Wagner troops leave Rostov-on-Don and\xa0Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.',
'thumbnail': 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485',
}
},
}]
def _real_extract(self, url):
@ -126,7 +125,7 @@ def _real_extract(self, url):
if mobj is None:
expired = self._html_search_regex(r'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>', webpage, 'expired', None)
if expired:
raise ExtractorError('%s said: %s' % (self.IE_NAME, expired), expected=True)
raise ExtractorError(f'{self.IE_NAME} said: {expired}', expected=True)
raise ExtractorError('Unable to extract video urls')
urls_info = self._parse_json(
@ -164,7 +163,7 @@ def _real_extract(self, url):
'height': height,
'tbr': bitrate,
'filesize': int_or_none(url_info.get('filesize')),
'format_id': format_id
'format_id': format_id,
})
return {
@ -288,13 +287,12 @@ def _real_extract(self, url):
stream = next(s for s in video_params['playlist'] if s.get('type') in ('program', 'livestream'))
house_number = video_params.get('episodeHouseNumber') or video_id
path = '/auth/hls/sign?ts={0}&hn={1}&d=android-tablet'.format(
int(time.time()), house_number)
path = f'/auth/hls/sign?ts={int(time.time())}&hn={house_number}&d=android-tablet'
sig = hmac.new(
b'android.content.res.Resources',
path.encode('utf-8'), hashlib.sha256).hexdigest()
path.encode(), hashlib.sha256).hexdigest()
token = self._download_webpage(
'http://iview.abc.net.au{0}&sig={1}'.format(path, sig), video_id)
f'http://iview.abc.net.au{path}&sig={sig}', video_id)
def tokenize_url(url, token):
return update_url_query(url, {
@ -303,7 +301,7 @@ def tokenize_url(url, token):
for sd in ('1080', '720', 'sd', 'sd-low'):
sd_url = try_get(
stream, lambda x: x['streams']['hls'][sd], compat_str)
stream, lambda x: x['streams']['hls'][sd], str)
if not sd_url:
continue
formats = self._extract_m3u8_formats(
@ -358,7 +356,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'description': 'md5:93119346c24a7c322d446d8eece430ff',
'series': 'Upper Middle Bogan',
'season': 'Series 1',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 8,
}, {
@ -386,7 +384,7 @@ class ABCIViewShowSeriesIE(InfoExtractor):
'description': 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.',
'series': '7.30 Mark Humphries Satire',
'season': 'Episodes',
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
'thumbnail': r're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$',
},
'playlist_count': 15,
}]
@ -398,7 +396,7 @@ def _real_extract(self, url):
r'window\.__INITIAL_STATE__\s*=\s*[\'"](.+?)[\'"]\s*;',
webpage, 'initial state')
video_data = self._parse_json(
unescapeHTML(webpage_data).encode('utf-8').decode('unicode_escape'), show_id)
unescapeHTML(webpage_data).encode().decode('unicode_escape'), show_id)
video_data = video_data['route']['pageData']['_embedded']
highlight = try_get(video_data, lambda x: x['highlightVideo']['shareUrl'])

2
yt_dlp/extractor/abcnews.py
View file

@ -58,7 +58,7 @@ def _real_extract(self, url):
display_id = mobj.group('display_id')
video_id = mobj.group('id')
info_dict = self._extract_feed_info(
'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
f'http://abcnews.go.com/video/itemfeed?id={video_id}')
info_dict.update({
'id': video_id,
'display_id': display_id,

5
yt_dlp/extractor/abcotvs.py
View file

@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
dict_get,
int_or_none,
@ -57,11 +56,11 @@ def _real_extract(self, url):
data = self._download_json(
'https://api.abcotvs.com/v2/content', display_id, query={
'id': video_id,
'key': 'otv.web.%s.story' % station,
'key': f'otv.web.{station}.story',
'station': station,
})['data']
video = try_get(data, lambda x: x['featuredMedia']['video'], dict) or data
video_id = compat_str(dict_get(video, ('id', 'publishedKey'), video_id))
video_id = str(dict_get(video, ('id', 'publishedKey'), video_id))
title = video.get('title') or video['linkText']
formats = []

96
yt_dlp/extractor/abematv.py
View file

@ -9,12 +9,12 @@
import struct
import time
import urllib.parse
import urllib.request
import urllib.response
import uuid
from .common import InfoExtractor
from ..aes import aes_ecb_decrypt
from ..networking import RequestHandler, Response
from ..networking.exceptions import TransportError
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -26,37 +26,36 @@
traverse_obj,
update_url_query,
)
from ..utils.networking import clean_proxies
def add_opener(ydl, handler): # FIXME: Create proper API in .networking
"""Add a handler for opening URLs, like _download_webpage"""
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L426
# https://github.com/python/cpython/blob/main/Lib/urllib/request.py#L605
rh = ydl._request_director.handlers['Urllib']
if 'abematv-license' in rh._SUPPORTED_URL_SCHEMES:
return
headers = ydl.params['http_headers'].copy()
proxies = ydl.proxies.copy()
clean_proxies(proxies, headers)
opener = rh._get_instance(cookiejar=ydl.cookiejar, proxies=proxies)
assert isinstance(opener, urllib.request.OpenerDirector)
opener.add_handler(handler)
rh._SUPPORTED_URL_SCHEMES = (*rh._SUPPORTED_URL_SCHEMES, 'abematv-license')
class AbemaLicenseRH(RequestHandler):
_SUPPORTED_URL_SCHEMES = ('abematv-license',)
_SUPPORTED_PROXY_SCHEMES = None
_SUPPORTED_FEATURES = None
RH_NAME = 'abematv_license'
_STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
_HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
class AbemaLicenseHandler(urllib.request.BaseHandler):
handler_order = 499
STRTABLE = '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
HKEY = b'3AF0298C219469522A313570E8583005A642E73EDD58E3EA2FB7339D3DF1597E'
def __init__(self, ie: 'AbemaTVIE'):
# the protocol that this should really handle is 'abematv-license://'
# abematv_license_open is just a placeholder for development purposes
# ref. https://github.com/python/cpython/blob/f4c03484da59049eb62a9bf7777b963e2267d187/Lib/urllib/request.py#L510
setattr(self, 'abematv-license_open', getattr(self, 'abematv_license_open', None))
def __init__(self, *, ie: 'AbemaTVIE', **kwargs):
super().__init__(**kwargs)
self.ie = ie
def _send(self, request):
url = request.url
ticket = urllib.parse.urlparse(url).netloc
try:
response_data = self._get_videokey_from_ticket(ticket)
except ExtractorError as e:
raise TransportError(cause=e.cause) from e
except (IndexError, KeyError, TypeError) as e:
raise TransportError(cause=repr(e)) from e
return Response(
io.BytesIO(response_data), url,
headers={'Content-Length': str(len(response_data))})
def _get_videokey_from_ticket(self, ticket):
to_show = self.ie.get_param('verbose', False)
media_token = self.ie._get_media_token(to_show=to_show)
@ -66,31 +65,23 @@ def _get_videokey_from_ticket(self, ticket):
query={'t': media_token},
data=json.dumps({
'kv': 'a',
'lt': ticket
}).encode('utf-8'),
'lt': ticket,
}).encode(),
headers={
'Content-Type': 'application/json',
})
res = decode_base_n(license_response['k'], table=self.STRTABLE)
res = decode_base_n(license_response['k'], table=self._STRTABLE)
encvideokey = bytes_to_intlist(struct.pack('>QQ', res >> 64, res & 0xffffffffffffffff))
h = hmac.new(
binascii.unhexlify(self.HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode('utf-8'),
binascii.unhexlify(self._HKEY),
(license_response['cid'] + self.ie._DEVICE_ID).encode(),
digestmod=hashlib.sha256)
enckey = bytes_to_intlist(h.digest())
return intlist_to_bytes(aes_ecb_decrypt(encvideokey, enckey))
def abematv_license_open(self, url):
url = url.get_full_url() if isinstance(url, urllib.request.Request) else url
ticket = urllib.parse.urlparse(url).netloc
response_data = self._get_videokey_from_ticket(ticket)
return urllib.response.addinfourl(io.BytesIO(response_data), headers={
'Content-Length': str(len(response_data)),
}, url=url, code=200)
class AbemaTVBaseIE(InfoExtractor):
_NETRC_MACHINE = 'abematv'
@ -103,11 +94,11 @@ class AbemaTVBaseIE(InfoExtractor):
@classmethod
def _generate_aks(cls, deviceid):
deviceid = deviceid.encode('utf-8')
deviceid = deviceid.encode()
# add 1 hour and then drop minute and secs
ts_1hour = int((time_seconds() // 3600 + 1) * 3600)
time_struct = time.gmtime(ts_1hour)
ts_1hour_str = str(ts_1hour).encode('utf-8')
ts_1hour_str = str(ts_1hour).encode()
tmp = None
@ -119,7 +110,7 @@ def mix_once(nonce):
def mix_tmp(count):
nonlocal tmp
for i in range(count):
for _ in range(count):
mix_once(tmp)
def mix_twist(nonce):
@ -139,7 +130,7 @@ def _get_device_token(self):
if self._USERTOKEN:
return self._USERTOKEN
add_opener(self._downloader, AbemaLicenseHandler(self))
self._downloader._request_director.add_handler(AbemaLicenseRH(ie=self, logger=None))
username, _ = self._get_login_info()
auth_cache = username and self.cache.load(self._NETRC_MACHINE, username, min_ver='2024.01.19')
@ -160,7 +151,7 @@ def _get_device_token(self):
data=json.dumps({
'deviceId': self._DEVICE_ID,
'applicationKeySecret': aks,
}).encode('utf-8'),
}).encode(),
headers={
'Content-Type': 'application/json',
})
@ -180,7 +171,7 @@ def _get_media_token(self, invalidate=False, to_show=True):
'osLang': 'ja_JP',
'osTimezone': 'Asia/Tokyo',
'appId': 'tv.abema',
'appVersion': '3.27.1'
'appVersion': '3.27.1',
}, headers={
'Authorization': f'bearer {self._get_device_token()}',
})['token']
@ -202,8 +193,8 @@ def _perform_login(self, username, password):
f'https://api.abema.io/v1/auth/{ep}', None, note='Logging in',
data=json.dumps({
method: username,
'password': password
}).encode('utf-8'), headers={
'password': password,
}).encode(), headers={
'Authorization': f'bearer {self._get_device_token()}',
'Origin': 'https://abema.tv',
'Referer': 'https://abema.tv/',
@ -344,7 +335,7 @@ def _real_extract(self, url):
description = self._html_search_regex(
(r'<p\s+class="com-video-EpisodeDetailsBlock__content"><span\s+class=".+?">(.+?)</span></p><div',
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div',),
r'<span\s+class=".+?SlotSummary.+?">(.+?)</span></div><div'),
webpage, 'description', default=None, group=1)
if not description:
og_desc = self._html_search_meta(
@ -368,6 +359,7 @@ def _real_extract(self, url):
info['episode_number'] = epis if epis < 2000 else None
is_live, m3u8_url = False, None
availability = 'public'
if video_type == 'now-on-air':
is_live = True
channel_url = 'https://api.abema.io/v1/channels'
@ -385,10 +377,10 @@ def _real_extract(self, url):
f'https://api.abema.io/v1/video/programs/{video_id}', video_id,
note='Checking playability',
headers=headers)
ondemand_types = traverse_obj(api_response, ('terms', ..., 'onDemandType'))
if 3 not in ondemand_types:
if not traverse_obj(api_response, ('label', 'free', {bool})):
# cannot acquire decryption key for these streams
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
info.update(traverse_obj(api_response, {
'series': ('series', 'title'),
'season': ('season', 'name'),
@ -408,6 +400,7 @@ def _real_extract(self, url):
headers=headers)
if not traverse_obj(api_response, ('slot', 'flags', 'timeshiftFree'), default=False):
self.report_warning('This is a premium-only stream')
availability = 'premium_only'
m3u8_url = f'https://vod-abematv.akamaized.net/slot/{video_id}/playlist.m3u8'
else:
@ -425,6 +418,7 @@ def _real_extract(self, url):
'description': description,
'formats': formats,
'is_live': is_live,
'availability': availability,
})
return info

8
yt_dlp/extractor/acast.py
View file

@ -67,7 +67,7 @@ class ACastIE(ACastBaseIE):
'display_id': '2.raggarmordet-rosterurdetforflutna',
'season_number': 4,
'season': 'Season 4',
}
},
}, {
'url': 'http://embed.acast.com/adambuxton/ep.12-adam-joeschristmaspodcast2015',
'only_matching': True,
@ -93,13 +93,13 @@ class ACastIE(ACastBaseIE):
'series': 'Democracy Sausage with Mark Kenny',
'timestamp': 1684826362,
'description': 'md5:feabe1fc5004c78ee59c84a46bf4ba16',
}
},
}]
def _real_extract(self, url):
channel, display_id = self._match_valid_url(url).groups()
episode = self._call_api(
'%s/episodes/%s' % (channel, display_id),
f'{channel}/episodes/{display_id}',
display_id, {'showInfo': 'true'})
return self._extract_episode(
episode, self._extract_show_info(episode.get('show') or {}))
@ -130,7 +130,7 @@ class ACastChannelIE(ACastBaseIE):
@classmethod
def suitable(cls, url):
return False if ACastIE.suitable(url) else super(ACastChannelIE, cls).suitable(url)
return False if ACastIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
show_slug = self._match_id(url)

4
yt_dlp/extractor/acfun.py
View file

@ -25,7 +25,7 @@ def _extract_metadata(self, video_id, video_info):
'width': int_or_none(video.get('width')),
'height': int_or_none(video.get('height')),
'tbr': float_or_none(video.get('avgBitrate')),
**parse_codecs(video.get('codecs', ''))
**parse_codecs(video.get('codecs', '')),
})
return {
@ -77,7 +77,7 @@ class AcFunVideoIE(AcFunVideoBaseIE):
'comment_count': int,
'thumbnail': r're:^https?://.*\.(jpg|jpeg)',
'description': 'md5:67583aaf3a0f933bd606bc8a2d3ebb17',
}
},
}]
def _real_extract(self, url):

42
yt_dlp/extractor/adn.py
View file

@ -7,7 +7,6 @@
from .common import InfoExtractor
from ..aes import aes_cbc_decrypt_bytes, unpad_pkcs7
from ..compat import compat_b64decode
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
@ -17,6 +16,7 @@
float_or_none,
int_or_none,
intlist_to_bytes,
join_nonempty,
long_to_bytes,
parse_iso8601,
pkcs1pad,
@ -49,9 +49,9 @@ class ADNBaseIE(InfoExtractor):
class ADNIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/[^/?#]+/(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/fruits-basket/9841-episode-1-a-ce-soir',
'url': 'https://animationdigitalnetwork.com/video/fruits-basket/9841-episode-1-a-ce-soir',
'md5': '1c9ef066ceb302c86f80c2b371615261',
'info_dict': {
'id': '9841',
@ -71,10 +71,10 @@ class ADNIE(ADNBaseIE):
},
'skip': 'Only available in French and German speaking Europe',
}, {
'url': 'http://animedigitalnetwork.fr/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'url': 'http://animedigitalnetwork.com/video/blue-exorcist-kyoto-saga/7778-episode-1-debut-des-hostilites',
'only_matching': True,
}, {
'url': 'https://animationdigitalnetwork.de/video/the-eminence-in-shadow/23550-folge-1',
'url': 'https://animationdigitalnetwork.com/de/video/the-eminence-in-shadow/23550-folge-1',
'md5': '5c5651bf5791fa6fcd7906012b9d94e8',
'info_dict': {
'id': '23550',
@ -111,9 +111,9 @@ def _get_subtitles(self, sub_url, video_id):
# http://animationdigitalnetwork.fr/components/com_vodvideo/videojs/adn-vjs.min.js
dec_subtitles = unpad_pkcs7(aes_cbc_decrypt_bytes(
compat_b64decode(enc_subtitles[24:]),
base64.b64decode(enc_subtitles[24:]),
binascii.unhexlify(self._K + '7fac1178830cfe0c'),
compat_b64decode(enc_subtitles[:24])))
base64.b64decode(enc_subtitles[:24])))
subtitles_json = self._parse_json(dec_subtitles.decode(), None, fatal=False)
if not subtitles_json:
return None
@ -136,7 +136,7 @@ def _get_subtitles(self, sub_url, video_id):
if start is None or end is None or text is None:
continue
alignment = self._POS_ALIGN_MAP.get(position_align, 2) + self._LINE_ALIGN_MAP.get(line_align, 0)
ssa += os.linesep + 'Dialogue: Marked=0,%s,%s,Default,,0,0,0,,%s%s' % (
ssa += os.linesep + 'Dialogue: Marked=0,{},{},Default,,0,0,0,,{}{}'.format(
ass_subtitles_timecode(start),
ass_subtitles_timecode(end),
'{\\a%d}' % alignment if alignment != 2 else '',
@ -178,7 +178,7 @@ def _perform_login(self, username, password):
def _real_extract(self, url):
lang, video_id = self._match_valid_url(url).group('lang', 'id')
video_base_url = self._PLAYER_BASE_URL + 'video/%s/' % video_id
video_base_url = self._PLAYER_BASE_URL + f'video/{video_id}/'
player = self._download_json(
video_base_url + 'configuration', video_id,
'Downloading player config JSON metadata',
@ -218,13 +218,13 @@ def _real_extract(self, url):
links_data = self._download_json(
links_url, video_id, 'Downloading links JSON metadata', headers={
'X-Player-Token': authorization,
'X-Target-Distribution': lang,
**self._HEADERS
'X-Target-Distribution': lang or 'fr',
**self._HEADERS,
}, query={
'freeWithAds': 'true',
'adaptive': 'false',
'withMetadata': 'true',
'source': 'Web'
'source': 'Web',
})
break
except ExtractorError as e:
@ -256,7 +256,7 @@ def _real_extract(self, url):
for quality, load_balancer_url in qualities.items():
load_balancer_data = self._download_json(
load_balancer_url, video_id,
'Downloading %s %s JSON metadata' % (format_id, quality),
f'Downloading {format_id} {quality} JSON metadata',
fatal=False) or {}
m3u8_url = load_balancer_data.get('location')
if not m3u8_url:
@ -276,7 +276,7 @@ def _real_extract(self, url):
self.raise_login_required('This video requires a subscription', method='password')
video = (self._download_json(
self._API_BASE_URL + 'video/%s' % video_id, video_id,
self._API_BASE_URL + f'video/{video_id}', video_id,
'Downloading additional video metadata', fatal=False) or {}).get('video') or {}
show = video.get('show') or {}
@ -299,9 +299,9 @@ def _real_extract(self, url):
class ADNSeasonIE(ADNBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.(?P<lang>fr|de)/video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_VALID_URL = r'https?://(?:www\.)?(?:animation|anime)digitalnetwork\.com/(?:(?P<lang>de)/)?video/(?P<id>[^/?#]+)/?(?:$|[#?])'
_TESTS = [{
'url': 'https://animationdigitalnetwork.fr/video/tokyo-mew-mew-new',
'url': 'https://animationdigitalnetwork.com/video/tokyo-mew-mew-new',
'playlist_count': 12,
'info_dict': {
'id': '911',
@ -319,8 +319,8 @@ def _real_extract(self, url):
episodes = self._download_json(
f'{self._API_BASE_URL}video/show/{show_id}', video_show_slug,
'Downloading episode list', headers={
'X-Target-Distribution': lang,
**self._HEADERS
'X-Target-Distribution': lang or 'fr',
**self._HEADERS,
}, query={
'order': 'asc',
'limit': '-1',
@ -328,8 +328,8 @@ def _real_extract(self, url):
def entries():
for episode_id in traverse_obj(episodes, ('videos', ..., 'id', {str_or_none})):
yield self.url_result(
f'https://animationdigitalnetwork.{lang}/video/{video_show_slug}/{episode_id}',
ADNIE, episode_id)
yield self.url_result(join_nonempty(
'https://animationdigitalnetwork.com', lang, 'video',
video_show_slug, episode_id, delim='/'), ADNIE, episode_id)
return self.playlist_result(entries(), show_id, show.get('title'))

10
yt_dlp/extractor/adobeconnect.py
View file

@ -1,8 +1,6 @@
import urllib.parse
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
compat_urlparse,
)
class AdobeConnectIE(InfoExtractor):
@ -12,13 +10,13 @@ def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
title = self._html_extract_title(webpage)
qs = compat_parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
qs = urllib.parse.parse_qs(self._search_regex(r"swfUrl\s*=\s*'([^']+)'", webpage, 'swf url').split('?')[1])
is_live = qs.get('isLive', ['false'])[0] == 'true'
formats = []
for con_string in qs['conStrings'][0].split(','):
formats.append({
'format_id': con_string.split('://')[0],
'app': compat_urlparse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'app': urllib.parse.quote('?' + con_string.split('?')[1] + 'flvplayerapp/' + qs['appInstance'][0]),
'ext': 'flv',
'play_path': 'mp4:' + qs['streamName'][0],
'rtmp_conn': 'S:' + qs['ticket'][0],

866
yt_dlp/extractor/adobepass.py
View file

File diff suppressed because it is too large Load diff

5
yt_dlp/extractor/adobetv.py
View file

@ -2,7 +2,6 @@
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ISO639Utils,
OnDemandPagedList,
@ -36,7 +35,7 @@ def _parse_subtitles(self, video_data, url_key):
return subtitles
def _parse_video_data(self, video_data):
video_id = compat_str(video_data['id'])
video_id = str(video_data['id'])
title = video_data['title']
s3_extracted = False
@ -151,7 +150,7 @@ def _fetch_page(self, display_id, query, page):
page += 1
query['page'] = page
for element_data in self._call_api(
self._RESOURCE, display_id, query, 'Download Page %d' % page):
self._RESOURCE, display_id, query, f'Download Page {page}'):
yield self._process_data(element_data)
def _extract_playlist_entries(self, display_id, query):

6
yt_dlp/extractor/adultswim.py
View file

@ -91,7 +91,7 @@ def _real_extract(self, url):
getShowBySlug(slug:"%s") {
%%s
}
}''' % show_path
}''' % show_path # noqa: UP031
if episode_path:
query = query % '''title
getVideoBySlug(slug:"%s") {
@ -128,7 +128,7 @@ def _real_extract(self, url):
episode_title = title = video_data['title']
series = show_data.get('title')
if series:
title = '%s - %s' % (series, title)
title = f'{series} - {title}'
info = {
'id': video_id,
'title': title,
@ -191,7 +191,7 @@ def _real_extract(self, url):
if not slug:
continue
entries.append(self.url_result(
'http://adultswim.com/videos/%s/%s' % (show_path, slug),
f'http://adultswim.com/videos/{show_path}/{slug}',
'AdultSwim', video.get('_id')))
return self.playlist_result(
entries, show_path, show_data.get('title'),

34
yt_dlp/extractor/aenetworks.py
View file

@ -73,8 +73,8 @@ def _extract_aen_smil(self, smil_url, video_id, auth=None):
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
result = self._download_json(
'https://feeds.video.aetnd.com/api/v2/%s/videos' % brand,
filter_value, query={'filter[%s]' % filter_key: filter_value})
f'https://feeds.video.aetnd.com/api/v2/{brand}/videos',
filter_value, query={f'filter[{filter_key}]': filter_value})
result = traverse_obj(
result, ('results',
lambda k, v: k == 0 and v[filter_key] == filter_value),
@ -142,7 +142,7 @@ class AENetworksIE(AENetworksBaseIE):
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'Geo-restricted - This content is not available in your location.'
'skip': 'Geo-restricted - This content is not available in your location.',
}, {
'url': 'http://www.aetv.com/shows/duck-dynasty/season-9/episode-1',
'info_dict': {
@ -171,28 +171,28 @@ class AENetworksIE(AENetworksBaseIE):
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.mylifetime.com/shows/project-runway-junior/season-1/episode-6',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.mylifetime.com/movies/center-stage-on-pointe/full-movie',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://watch.lifetimemovieclub.com/movies/10-year-reunion/full-movie',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.history.com/specials/sniper-into-the-kill-zone/full-special',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://www.aetv.com/specials/hunting-jonbenets-killer-the-untold-story/preview-hunting-jonbenets-killer-the-untold-story',
'only_matching': True
'only_matching': True,
}, {
'url': 'http://www.history.com/videos/history-of-valentines-day',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://play.aetv.com/shows/duck-dynasty/videos/best-of-duck-dynasty-getting-quack-in-shape',
'only_matching': True
'only_matching': True,
}]
def _real_extract(self, url):
@ -209,14 +209,14 @@ def _call_api(self, resource, slug, brand, fields):
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields),
}''' % (resource, slug, fields), # noqa: UP031
}))['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = 'http://watch.%s' % domain
base_url = f'http://watch.{domain}'
entries = []
for item in (playlist.get(self._ITEMS_KEY) or []):
@ -248,10 +248,10 @@ class AENetworksCollectionIE(AENetworksListBaseIE):
'playlist_mincount': 12,
}, {
'url': 'https://watch.historyvault.com/shows/america-the-story-of-us-2/season-1/list/america-the-story-of-us',
'only_matching': True
'only_matching': True,
}, {
'url': 'https://www.historyvault.com/collections/mysteryquest',
'only_matching': True
'only_matching': True,
}]
_RESOURCE = 'list'
_ITEMS_KEY = 'items'
@ -309,7 +309,7 @@ class HistoryTopicIE(AENetworksBaseIE):
'info_dict': {
'id': '40700995724',
'ext': 'mp4',
'title': "History of Valentine’s Day",
'title': 'History of Valentine’s Day',
'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
'timestamp': 1375819729,
'upload_date': '20130806',
@ -364,6 +364,6 @@ def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_url = self._search_regex(
r'<phoenix-iframe[^>]+src="(%s)' % HistoryPlayerIE._VALID_URL,
rf'<phoenix-iframe[^>]+src="({HistoryPlayerIE._VALID_URL})',
webpage, 'player URL')
return self.url_result(player_url, HistoryPlayerIE.ie_key())

8
yt_dlp/extractor/aeonco.py
View file

@ -16,8 +16,8 @@ class AeonCoIE(InfoExtractor):
'uploader': 'Semiconductor',
'uploader_id': 'semiconductor',
'uploader_url': 'https://vimeo.com/semiconductor',
'duration': 348
}
'duration': 348,
},
}, {
'url': 'https://aeon.co/videos/dazzling-timelapse-shows-how-microbes-spoil-our-food-and-sometimes-enrich-it',
'md5': '03582d795382e49f2fd0b427b55de409',
@ -29,8 +29,8 @@ class AeonCoIE(InfoExtractor):
'uploader': 'Aeon Video',
'uploader_id': 'aeonvideo',
'uploader_url': 'https://vimeo.com/aeonvideo',
'duration': 1344
}
'duration': 1344,
},
}, {
'url': 'https://aeon.co/videos/chew-over-the-prisoners-dilemma-and-see-if-you-can-find-the-rational-path-out',
'md5': '1cfda0bf3ae24df17d00f2c0cb6cc21b',

57
yt_dlp/extractor/afreecatv.py
View file

@ -1,6 +1,7 @@
import functools
from .common import InfoExtractor
from ..networking import Request
from ..utils import (
ExtractorError,
OnDemandPagedList,
@ -55,9 +56,16 @@ def _perform_login(self, username, password):
if result != 1:
error = _ERRORS.get(result, 'You have failed to log in.')
raise ExtractorError(
'Unable to login: %s said: %s' % (self.IE_NAME, error),
f'Unable to login: {self.IE_NAME} said: {error}',
expected=True)
def _call_api(self, endpoint, display_id, data=None, headers=None, query=None):
return self._download_json(Request(
f'https://api.m.afreecatv.com/{endpoint}',
data=data, headers=headers, query=query,
extensions={'legacy_ssl': True}), display_id,
'Downloading API JSON', 'Unable to download API JSON')
class AfreecaTVIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv'
@ -72,7 +80,7 @@ class AfreecaTVIE(AfreecaTVBaseIE):
)\?.*?\bnTitleNo=|
vod\.afreecatv\.com/(PLAYER/STATION|player)/
)
(?P<id>\d+)
(?P<id>\d+)/?(?:$|[?#&])
'''
_TESTS = [{
'url': 'http://live.afreecatv.com:8079/app/index.cgi?szType=read_ucc_bbs&szBjId=dailyapril&nStationNo=16711924&nBbsNo=18605867&nTitleNo=36164052&szSkin=',
@ -184,9 +192,9 @@ class AfreecaTVIE(AfreecaTVBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._download_json(
'https://api.m.afreecatv.com/station/video/a/view', video_id,
headers={'Referer': url}, data=urlencode_postdata({
data = self._call_api(
'station/video/a/view', video_id, headers={'Referer': url},
data=urlencode_postdata({
'nTitleNo': video_id,
'nApiLevel': 10,
}))['data']
@ -227,7 +235,7 @@ def _real_extract(self, url):
**traverse_obj(file_element, {
'duration': ('duration', {functools.partial(int_or_none, scale=1000)}),
'timestamp': ('file_start', {unified_timestamp}),
})
}),
})
if traverse_obj(data, ('adult_status', {str})) == 'notLogin':
@ -253,6 +261,43 @@ def _real_extract(self, url):
return self.playlist_result(entries, video_id, multi_video=True, **common_info)
class AfreecaTVCatchStoryIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:catchstory'
IE_DESC = 'afreecatv.com catch story'
_VALID_URL = r'https?://vod\.afreecatv\.com/player/(?P<id>\d+)/catchstory'
_TESTS = [{
'url': 'https://vod.afreecatv.com/player/103247/catchstory',
'info_dict': {
'id': '103247',
},
'playlist_count': 2,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
data = self._call_api(
'catchstory/a/view', video_id, headers={'Referer': url},
query={'aStoryListIdx': '', 'nStoryIdx': video_id})
return self.playlist_result(self._entries(data), video_id)
@staticmethod
def _entries(data):
# 'files' is always a list with 1 element
yield from traverse_obj(data, (
'data', lambda _, v: v['story_type'] == 'catch',
'catch_list', lambda _, v: v['files'][0]['file'], {
'id': ('files', 0, 'file_info_key', {str}),
'url': ('files', 0, 'file', {url_or_none}),
'duration': ('files', 0, 'duration', {functools.partial(int_or_none, scale=1000)}),
'title': ('title', {str}),
'uploader': ('writer_nick', {str}),
'uploader_id': ('writer_id', {str}),
'thumbnail': ('thumb', {url_or_none}),
'timestamp': ('write_timestamp', {int_or_none}),
}))
class AfreecaTVLiveIE(AfreecaTVBaseIE):
IE_NAME = 'afreecatv:live'
IE_DESC = 'afreecatv.com livestreams'

6
yt_dlp/extractor/agora.py
View file

@ -168,7 +168,7 @@ def _real_extract(self, url):
for ext in ('aac', 'mp3'):
url_data = self._download_json(
f'https://api.podcast.radioagora.pl/api4/getSongUrl?podcast_id={media_id}&device_id={uuid.uuid4()}&ppre=false&audio={ext}',
media_id, 'Downloading podcast %s URL' % ext)
media_id, f'Downloading podcast {ext} URL')
# prevents inserting the mp3 (default) multiple times
if 'link_ssl' in url_data and f'.{ext}' in url_data['link_ssl']:
formats.append({
@ -206,8 +206,8 @@ class TokFMAuditionIE(InfoExtractor):
}
@staticmethod
def _create_url(id):
return f'https://audycje.tokfm.pl/audycja/{id}'
def _create_url(video_id):
return f'https://audycje.tokfm.pl/audycja/{video_id}'
def _real_extract(self, url):
audition_id = self._match_id(url)

4
yt_dlp/extractor/airtv.py
View file

@ -26,7 +26,7 @@ class AirTVIE(InfoExtractor):
'view_count': int,
'thumbnail': 'https://cdn-sp-gcs.air.tv/videos/W/8/W87jcWleSn2hXZN47zJZsQ/b13fc56464f47d9d62a36d110b9b5a72-4096x2160_9.jpg',
'timestamp': 1664792603,
}
},
}, {
# with youtube_id
'url': 'https://www.air.tv/watch?v=sv57EC8tRXG6h8dNXFUU1Q',
@ -54,7 +54,7 @@ class AirTVIE(InfoExtractor):
'channel': 'Newsflare',
'duration': 37,
'upload_date': '20180511',
}
},
}]
def _get_formats_and_subtitle(self, json_data, video_id):

2
yt_dlp/extractor/aitube.py
View file

@ -22,7 +22,7 @@ class AitubeKZVideoIE(InfoExtractor):
'timestamp': 1667370519,
'title': 'Ангел хранитель 1 серия',
'channel_follower_count': int,
}
},
}, {
# embed url
'url': 'https://aitube.kz/embed/?id=9291d29b-c038-49a1-ad42-3da2051d353c',

3
yt_dlp/extractor/aliexpress.py
View file

@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
float_or_none,
try_get,
@ -44,7 +43,7 @@ def _real_extract(self, url):
'title': title,
'thumbnail': data.get('coverUrl'),
'uploader': try_get(
data, lambda x: x['followBar']['name'], compat_str),
data, lambda x: x['followBar']['name'], str),
'timestamp': float_or_none(data.get('startTimeLong'), scale=1000),
'formats': formats,
}

14
yt_dlp/extractor/aljazeera.py
View file

@ -18,7 +18,7 @@ class AlJazeeraIE(InfoExtractor):
'timestamp': 1636219149,
'description': 'U sarajevskim naseljima Rajlovac i Reljevo stambeni objekti, ali i industrijska postrojenja i dalje su pod vodom.',
'upload_date': '20211106',
}
},
}, {
'url': 'https://balkans.aljazeera.net/videos/2021/11/6/djokovic-usao-u-finale-mastersa-u-parizu',
'info_dict': {
@ -33,7 +33,7 @@ class AlJazeeraIE(InfoExtractor):
BRIGHTCOVE_URL_RE = r'https?://players.brightcove.net/(?P<account>\d+)/(?P<player_id>[a-zA-Z0-9]+)_(?P<embed>[^/]+)/index.html\?videoId=(?P<id>\d+)'
def _real_extract(self, url):
base, post_type, id = self._match_valid_url(url).groups()
base, post_type, display_id = self._match_valid_url(url).groups()
wp = {
'balkans.aljazeera.net': 'ajb',
'chinese.aljazeera.net': 'chinese',
@ -47,11 +47,11 @@ def _real_extract(self, url):
'news': 'news',
}[post_type.split('/')[0]]
video = self._download_json(
f'https://{base}/graphql', id, query={
f'https://{base}/graphql', display_id, query={
'wp-site': wp,
'operationName': 'ArchipelagoSingleArticleQuery',
'variables': json.dumps({
'name': id,
'name': display_id,
'postType': post_type,
}),
}, headers={
@ -64,7 +64,7 @@ def _real_extract(self, url):
embed = 'default'
if video_id is None:
webpage = self._download_webpage(url, id)
webpage = self._download_webpage(url, display_id)
account, player_id, embed, video_id = self._search_regex(self.BRIGHTCOVE_URL_RE, webpage, 'video id',
group=(1, 2, 3, 4), default=(None, None, None, None))
@ -73,11 +73,11 @@ def _real_extract(self, url):
return {
'_type': 'url_transparent',
'url': url,
'ie_key': 'Generic'
'ie_key': 'Generic',
}
return {
'_type': 'url_transparent',
'url': f'https://players.brightcove.net/{account}/{player_id}_{embed}/index.html?videoId={video_id}',
'ie_key': 'BrightcoveNew'
'ie_key': 'BrightcoveNew',
}

5
yt_dlp/extractor/allocine.py
View file

@ -1,5 +1,4 @@
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
int_or_none,
qualities,
@ -95,11 +94,11 @@ def _real_extract(self, url):
duration = int_or_none(video.get('duration'))
view_count = int_or_none(video.get('view_count'))
timestamp = unified_timestamp(try_get(
video, lambda x: x['added_at']['date'], compat_str))
video, lambda x: x['added_at']['date'], str))
else:
video_id = display_id
media_data = self._download_json(
'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media=%s' % video_id, display_id)
f'http://www.allocine.fr/ws/AcVisiondataV5.ashx?media={video_id}', display_id)
title = remove_end(strip_or_none(self._html_extract_title(webpage), ' - AlloCiné'))
for key, value in media_data['video'].items():
if not key.endswith('Path'):

26
yt_dlp/extractor/allstar.py
View file

@ -33,27 +33,27 @@
video: getClip(clipIdentifier: $id) {
%s %s
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'montage': '''query ($id: String!) {
video: getMontage(clipIdentifier: $id) {
%s
}
}''' % _FIELDS,
}''' % _FIELDS, # noqa: UP031
'Clips': '''query ($page: Int!, $user: String!, $game: Int) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: false, game: $game) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
'Montages': '''query ($page: Int!, $user: String!) {
videos: montages(search: createdDate, page: $page, user: $user) {
data { %s }
}
}''' % _FIELDS,
}''' % _FIELDS, # noqa: UP031
'Mobile Clips': '''query ($page: Int!, $user: String!) {
videos: clips(search: createdDate, page: $page, user: $user, mobile: true) {
data { %s %s }
}
}''' % (_FIELDS, _EXTRA_FIELDS),
}''' % (_FIELDS, _EXTRA_FIELDS), # noqa: UP031
}
@ -121,7 +121,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230425',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/clip?clip=8LJLY4JKB',
'info_dict': {
@ -139,7 +139,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230702',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/montage?montage=643e64089da7e9363e1fa66c',
'info_dict': {
@ -155,7 +155,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230418',
'view_count': int,
}
},
}, {
'url': 'https://allstar.gg/montage?montage=RILJMH6QOS',
'info_dict': {
@ -171,7 +171,7 @@ class AllstarIE(AllstarBaseIE):
'uploader_url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d',
'upload_date': '20230703',
'view_count': int,
}
},
}]
def _real_extract(self, url):
@ -191,28 +191,28 @@ class AllstarProfileIE(AllstarBaseIE):
'id': '62b8bdfc9021052f7905882d-clips',
'title': 'cherokee - Clips',
},
'playlist_mincount': 15
'playlist_mincount': 15,
}, {
'url': 'https://allstar.gg/u/cherokee?game=730&view=Clips',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-clips-730',
'title': 'cherokee - Clips - 730',
},
'playlist_mincount': 15
'playlist_mincount': 15,
}, {
'url': 'https://allstar.gg/u/62b8bdfc9021052f7905882d?view=Montages',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-montages',
'title': 'cherokee - Montages',
},
'playlist_mincount': 4
'playlist_mincount': 4,
}, {
'url': 'https://allstar.gg/profile?user=cherokee&view=Mobile Clips',
'info_dict': {
'id': '62b8bdfc9021052f7905882d-mobile',
'title': 'cherokee - Mobile Clips',
},
'playlist_mincount': 1
'playlist_mincount': 1,
}]
_PAGE_SIZE = 10

2
yt_dlp/extractor/alphaporno.py
View file

@ -25,7 +25,7 @@ class AlphaPornoIE(InfoExtractor):
'tbr': 1145,
'categories': list,
'age_limit': 18,
}
},
}
def _real_extract(self, url):

6
yt_dlp/extractor/alsace20tv.py
View file

@ -12,7 +12,7 @@
class Alsace20TVBaseIE(InfoExtractor):
def _extract_video(self, video_id, url=None):
info = self._download_json(
'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key=%s&habillage=0&mode=html' % (video_id, ),
f'https://www.alsace20.tv/visionneuse/visio_v9_js.php?key={video_id}&habillage=0&mode=html',
video_id) or {}
title = info.get('titre')
@ -24,9 +24,9 @@ def _extract_video(self, video_id, url=None):
else self._extract_mpd_formats(fmt_url, video_id, mpd_id=res, fatal=False))
webpage = (url and self._download_webpage(url, video_id, fatal=False)) or ''
thumbnail = url_or_none(dict_get(info, ('image', 'preview', )) or self._og_search_thumbnail(webpage))
thumbnail = url_or_none(dict_get(info, ('image', 'preview')) or self._og_search_thumbnail(webpage))
upload_date = self._search_regex(r'/(\d{6})_', thumbnail, 'upload_date', default=None)
upload_date = unified_strdate('20%s-%s-%s' % (upload_date[:2], upload_date[2:4], upload_date[4:])) if upload_date else None
upload_date = unified_strdate(f'20{upload_date[:2]}-{upload_date[2:4]}-{upload_date[4:]}') if upload_date else None
return {
'id': video_id,
'title': title,

2
yt_dlp/extractor/altcensored.py
View file

@ -34,7 +34,7 @@ class AltCensoredIE(InfoExtractor):
'thumbnail': 'https://archive.org/download/youtube-k0srjLSkga8/youtube-k0srjLSkga8.thumbs/k0srjLSkga8_000925.jpg',
'view_count': int,
'categories': ['News & Politics'],
}
},
}]
def _real_extract(self, url):

16
yt_dlp/extractor/alura.py
View file

@ -1,7 +1,7 @@
import re
import urllib.parse
from .common import InfoExtractor
from ..compat import compat_urlparse
from ..utils import (
ExtractorError,
clean_html,
@ -21,7 +21,7 @@ class AluraIE(InfoExtractor):
'info_dict': {
'id': '60095',
'ext': 'mp4',
'title': 'Referências, ref-set e alter'
'title': 'Referências, ref-set e alter',
},
'skip': 'Requires alura account credentials'},
{
@ -30,7 +30,7 @@ class AluraIE(InfoExtractor):
'only_matching': True},
{
'url': 'https://cursos.alura.com.br/course/fundamentos-market-digital/task/55219',
'only_matching': True}
'only_matching': True},
]
def _real_extract(self, url):
@ -62,7 +62,7 @@ def _real_extract(self, url):
return {
'id': video_id,
'title': video_title,
"formats": formats
'formats': formats,
}
def _perform_login(self, username, password):
@ -91,7 +91,7 @@ def is_logged(webpage):
'post url', default=self._LOGIN_URL, group='url')
if not post_url.startswith('http'):
post_url = compat_urlparse.urljoin(self._LOGIN_URL, post_url)
post_url = urllib.parse.urljoin(self._LOGIN_URL, post_url)
response = self._download_webpage(
post_url, None, 'Logging in',
@ -103,7 +103,7 @@ def is_logged(webpage):
r'(?s)<p[^>]+class="alert-message[^"]*">(.+?)</p>',
response, 'error message', default=None)
if error:
raise ExtractorError('Unable to login: %s' % error, expected=True)
raise ExtractorError(f'Unable to login: {error}', expected=True)
raise ExtractorError('Unable to log in')
@ -119,7 +119,7 @@ class AluraCourseIE(AluraIE): # XXX: Do not subclass from concrete IE
@classmethod
def suitable(cls, url):
return False if AluraIE.suitable(url) else super(AluraCourseIE, cls).suitable(url)
return False if AluraIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
@ -157,7 +157,7 @@ def _real_extract(self, url):
'url': video_url,
'id_key': self.ie_key(),
'chapter': chapter,
'chapter_number': chapter_number
'chapter_number': chapter_number,
}
entries.append(entry)
return self.playlist_result(entries, course_path, course_title)

2
yt_dlp/extractor/amadeustv.py
View file

@ -24,7 +24,7 @@ class AmadeusTVIE(InfoExtractor):
'display_id': '65091a87ff85af59d9fc54c3',
'view_count': int,
'description': 'md5:a0357b9c215489e2067cbae0b777bb95',
}
},
}]
def _real_extract(self, url):

10
yt_dlp/extractor/amara.py
View file

@ -25,7 +25,7 @@ class AmaraIE(InfoExtractor):
'uploader': 'PBS NewsHour',
'uploader_id': 'PBSNewsHour',
'timestamp': 1549639570,
}
},
}, {
# Vimeo
'url': 'https://amara.org/en/videos/kYkK1VUTWW5I/info/vimeo-at-ces-2011',
@ -40,8 +40,8 @@ class AmaraIE(InfoExtractor):
'timestamp': 1294763658,
'upload_date': '20110111',
'uploader': 'Sam Morrill',
'uploader_id': 'sammorrill'
}
'uploader_id': 'sammorrill',
},
}, {
# Direct Link
'url': 'https://amara.org/en/videos/s8KL7I3jLmh6/info/the-danger-of-a-single-story/',
@ -55,13 +55,13 @@ class AmaraIE(InfoExtractor):
'subtitles': dict,
'upload_date': '20091007',
'timestamp': 1254942511,
}
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
meta = self._download_json(
'https://amara.org/api/videos/%s/' % video_id,
f'https://amara.org/api/videos/{video_id}/',
video_id, query={'format': 'json'})
title = meta['title']
video_url = meta['all_urls'][0]

8
yt_dlp/extractor/amazon.py
View file

@ -61,13 +61,13 @@ class AmazonStoreIE(InfoExtractor):
}]
def _real_extract(self, url):
id = self._match_id(url)
playlist_id = self._match_id(url)
for retry in self.RetryManager():
webpage = self._download_webpage(url, id)
webpage = self._download_webpage(url, playlist_id)
try:
data_json = self._search_json(
r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', id,
r'var\s?obj\s?=\s?jQuery\.parseJSON\(\'', webpage, 'data', playlist_id,
transform_source=js_to_json)
except ExtractorError as e:
retry.error = e
@ -81,7 +81,7 @@ def _real_extract(self, url):
'height': int_or_none(video.get('videoHeight')),
'width': int_or_none(video.get('videoWidth')),
} for video in (data_json.get('videos') or []) if video.get('isVideo') and video.get('url')]
return self.playlist_result(entries, playlist_id=id, playlist_title=data_json.get('title'))
return self.playlist_result(entries, playlist_id=playlist_id, playlist_title=data_json.get('title'))
class AmazonReviewsIE(InfoExtractor):

Some files were not shown because too many files have changed in this diff Show more