smokephil/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-12-06 06:45:00 +01:00
Code Issues Projects Releases Packages Wiki Activity

Merge https://github.com/yt-dlp/yt-dlp into fix/ie/plutotv

Browse source
This commit is contained in:
DTrombett 2025-11-21 16:43:01 +01:00
commit 620240264b
No known key found for this signature in database
GPG key ID: FD8700F69650F6AA
63 changed files with 1805 additions and 559 deletions
Download patch file Download diff file Expand all files Collapse all files

6
.github/actionlint.yml vendored
View file

@ -1,9 +1,3 @@
self-hosted-runner:
labels:
# Workaround for the outdated runner list in actionlint v1.7.7
# Ref: https://github.com/rhysd/actionlint/issues/533
- windows-11-arm
config-variables:
- KEEP_CACHE_WARM
- PUSH_VERSION_COMMIT

2
.github/workflows/build.yml vendored
View file

@ -153,10 +153,12 @@ jobs:
'os': 'musllinux',
'arch': 'x86_64',
'runner': 'ubuntu-24.04',
'python_version': '3.14',
}, {
'os': 'musllinux',
'arch': 'aarch64',
'runner': 'ubuntu-24.04-arm',
'python_version': '3.14',
}],
}
INPUTS = json.loads(os.environ['INPUTS'])

23
.github/workflows/core.yml vendored
View file

@ -56,6 +56,8 @@ jobs:
python-version: pypy-3.11
steps:
- uses: actions/checkout@v5
with:
fetch-depth: 0
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v6
with:
@ -65,6 +67,25 @@ jobs:
- name: Run tests
timeout-minutes: 15
continue-on-error: False
env:
source: ${{ (github.event_name == 'push' && github.event.before) || 'origin/master' }}
target: ${{ (github.event_name == 'push' && github.event.after) || 'HEAD' }}
shell: bash
run: |
flags=()
# Check if a networking file is involved
patterns="\
^yt_dlp/networking/
^yt_dlp/utils/networking\.py$
^test/test_http_proxy\.py$
^test/test_networking\.py$
^test/test_networking_utils\.py$
^test/test_socks\.py$
^test/test_websockets\.py$
^pyproject\.toml$
"
if git diff --name-only "${source}" "${target}" | grep -Ef <(printf '%s' "${patterns}"); then
flags+=(--flaky)
fi
python3 -m yt_dlp -v || true # Print debug head
python3 ./devscripts/run_tests.py --pytest-args '--reruns 2 --reruns-delay 3.0' core
python3 -m devscripts.run_tests "${flags[@]}" --pytest-args '--reruns 2 --reruns-delay 3.0' core

4
.github/workflows/test-workflows.yml vendored
View file

@ -17,8 +17,8 @@ on:
permissions:
contents: read
env:
ACTIONLINT_VERSION: "1.7.7"
ACTIONLINT_SHA256SUM: 023070a287cd8cccd71515fedc843f1985bf96c436b7effaecce67290e7e0757
ACTIONLINT_VERSION: "1.7.8"
ACTIONLINT_SHA256SUM: be92c2652ab7b6d08425428797ceabeb16e31a781c07bc388456b4e592f3e36a
ACTIONLINT_REPO: https://github.com/rhysd/actionlint
jobs:

2
CONTRIBUTING.md
View file

@ -177,7 +177,7 @@ While it is strongly recommended to use `hatch` for yt-dlp development, if you a
```shell
# To only install development dependencies:
$ python -m devscripts.install_deps --include dev
$ python -m devscripts.install_deps --include-group dev
# Or, for an editable install plus dev dependencies:
$ python -m pip install -e ".[default,dev]"

16
CONTRIBUTORS
View file

@ -818,3 +818,19 @@ robin-mu
shssoichiro
thanhtaivtt
uoag
CaramelConnoisseur
ctengel
einstein95
evilpie
i3p9
JrM2628
krystophny
matyb08
pha1n0q
PierceLBrooks
sepro
TheQWERTYCodr
thomasmllt
w4grfw
WeidiDeng
Zer0spectrum

65
Changelog.md
View file

@ -4,6 +4,71 @@
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2025.11.12
#### Important changes
- **An external JavaScript runtime is now required for full YouTube support**
yt-dlp now requires users to have an external JavaScript runtime (e.g. Deno) installed in order to solve the JavaScript challenges presented by YouTube. [Read more](https://github.com/yt-dlp/yt-dlp/issues/15012)
#### Core changes
- **cookies**
- [Allow `--cookies-from-browser` for Safari on iOS](https://github.com/yt-dlp/yt-dlp/commit/e6414d64e73d86d65bb357e5ad59d0ca080d5812) ([#14950](https://github.com/yt-dlp/yt-dlp/issues/14950)) by [pha1n0q](https://github.com/pha1n0q)
- [Support Firefox cookies database v17](https://github.com/yt-dlp/yt-dlp/commit/bf7e04e9d8bd3c4a4614b67ce617b7ae5d17d62a) ([#15010](https://github.com/yt-dlp/yt-dlp/issues/15010)) by [Grub4K](https://github.com/Grub4K)
- **sponsorblock**: [Add `hook` category](https://github.com/yt-dlp/yt-dlp/commit/52f3c56e83bbb25eec2496b0499768753732a093) ([#14845](https://github.com/yt-dlp/yt-dlp/issues/14845)) by [seproDev](https://github.com/seproDev)
- **update**: [Fix PyInstaller onedir variant detection](https://github.com/yt-dlp/yt-dlp/commit/1c2ad94353d1c9e03615d20b6bbfc293286c7a32) ([#14800](https://github.com/yt-dlp/yt-dlp/issues/14800)) by [bashonly](https://github.com/bashonly)
#### Extractor changes
- **1tv**: live: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/19c5d7c53013440ec4f3f56ebbb067531b272f3f) ([#14299](https://github.com/yt-dlp/yt-dlp/issues/14299)) by [swayll](https://github.com/swayll)
- **ardaudiothek**: [Add extractors](https://github.com/yt-dlp/yt-dlp/commit/0046fbcbfceee32fa2f68a8ea00cca02765470b6) ([#14309](https://github.com/yt-dlp/yt-dlp/issues/14309)) by [evilpie](https://github.com/evilpie), [marieell](https://github.com/marieell)
- **bunnycdn**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/228ae9f0f2b441fa1296db2ed2b7afbd4a9a62a1) ([#14954](https://github.com/yt-dlp/yt-dlp/issues/14954)) by [seproDev](https://github.com/seproDev)
- [Support player subdomain URLs](https://github.com/yt-dlp/yt-dlp/commit/3ef867451cd9604b4195dfee00db768619629b2d) ([#14979](https://github.com/yt-dlp/yt-dlp/issues/14979)) by [einstein95](https://github.com/einstein95)
- **discoverynetworksde**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/10dea209d2460daf924c93835ddc2f0301cf2cd4) ([#14818](https://github.com/yt-dlp/yt-dlp/issues/14818)) by [dirkf](https://github.com/dirkf), [w4grfw](https://github.com/w4grfw) (With fixes in [f3c255b](https://github.com/yt-dlp/yt-dlp/commit/f3c255b63bd26069151fc3d3ba6dc626bb62ad6e) by [bashonly](https://github.com/bashonly))
- **floatplane**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/1ac7e6005cd3be9fff0b28be189c3a68ecd4c593) ([#14984](https://github.com/yt-dlp/yt-dlp/issues/14984)) by [i3p9](https://github.com/i3p9)
- **googledrive**
- [Fix subtitles extraction](https://github.com/yt-dlp/yt-dlp/commit/6d05cee4df30774ddce5c5c751fd2118f40c24fe) ([#14809](https://github.com/yt-dlp/yt-dlp/issues/14809)) by [seproDev](https://github.com/seproDev)
- [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/70f1098312fe53bc85358f7bd624370878b2fa28) ([#14746](https://github.com/yt-dlp/yt-dlp/issues/14746)) by [seproDev](https://github.com/seproDev)
- **kika**: [Do not extract non-existent subtitles](https://github.com/yt-dlp/yt-dlp/commit/79f9232ffbd57dde91c372b673b42801edaa9e53) ([#14813](https://github.com/yt-dlp/yt-dlp/issues/14813)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
- **mux**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/a0bda3b78609593ce1127215fc035c1a308a89b6) ([#14914](https://github.com/yt-dlp/yt-dlp/issues/14914)) by [PierceLBrooks](https://github.com/PierceLBrooks), [seproDev](https://github.com/seproDev)
- **nascarclassics**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/e8a6b1ca92f2a0ce2c187668165be23dc5506aab) ([#14866](https://github.com/yt-dlp/yt-dlp/issues/14866)) by [JrM2628](https://github.com/JrM2628)
- **nbc**: [Detect and discard DRM formats](https://github.com/yt-dlp/yt-dlp/commit/ee3a106f34124f0e2d28f062f5302863fd7639be) ([#14844](https://github.com/yt-dlp/yt-dlp/issues/14844)) by [bashonly](https://github.com/bashonly)
- **ntv.ru**: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/5dde0d0c9fcef2ce57e486b2e563e0dff9b2845a) ([#14934](https://github.com/yt-dlp/yt-dlp/issues/14934)) by [anlar](https://github.com/anlar), [seproDev](https://github.com/seproDev) (With fixes in [a86eeaa](https://github.com/yt-dlp/yt-dlp/commit/a86eeaadf236ceaf6bb232eb410cf21572538aa6) by [seproDev](https://github.com/seproDev))
- **play.tv**: [Update extractor for new domain](https://github.com/yt-dlp/yt-dlp/commit/73fd850d170e01c47c31aaa6aa8fe90856d9ad18) ([#14905](https://github.com/yt-dlp/yt-dlp/issues/14905)) by [thomasmllt](https://github.com/thomasmllt)
- **tubetugraz**: [Support alternate URL format](https://github.com/yt-dlp/yt-dlp/commit/f3597cfafcab4d7d4c6d41bff3647681301f1e6b) ([#14718](https://github.com/yt-dlp/yt-dlp/issues/14718)) by [krystophny](https://github.com/krystophny)
- **twitch**
- [Fix playlist extraction](https://github.com/yt-dlp/yt-dlp/commit/cb78440e468608fd55546280b537387d375335f2) ([#15008](https://github.com/yt-dlp/yt-dlp/issues/15008)) by [bashonly](https://github.com/bashonly), [ctengel](https://github.com/ctengel)
- stream: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/7eff676183518175ce495ae63291c89f9b39f02a) ([#14988](https://github.com/yt-dlp/yt-dlp/issues/14988)) by [seproDev](https://github.com/seproDev)
- vod: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b46c572b26be15683584102c5fb7e7bfde0c9821) ([#14999](https://github.com/yt-dlp/yt-dlp/issues/14999)) by [Zer0spectrum](https://github.com/Zer0spectrum)
- **urplay**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/808b1fed76fbd07840cc23a346c11334e3d34f43) ([#14785](https://github.com/yt-dlp/yt-dlp/issues/14785)) by [seproDev](https://github.com/seproDev)
- **web.archive**: youtube: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/d9e3011fd1c3a75871a50e78533afe78ad427ce3) ([#14753](https://github.com/yt-dlp/yt-dlp/issues/14753)) by [seproDev](https://github.com/seproDev)
- **xhamster**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a1d6351c3fc82c07fa0ee70811ed84807f6bbb58) ([#14948](https://github.com/yt-dlp/yt-dlp/issues/14948)) by [CaramelConnoisseur](https://github.com/CaramelConnoisseur), [dhwz](https://github.com/dhwz)
- **youtube**
- [Add `tv_downgraded` client](https://github.com/yt-dlp/yt-dlp/commit/61cf34f5447177a73ba25ea9a47d7df516ca3b3b) ([#14887](https://github.com/yt-dlp/yt-dlp/issues/14887)) by [seproDev](https://github.com/seproDev) (With fixes in [fa35eb2](https://github.com/yt-dlp/yt-dlp/commit/fa35eb27eaf27df7b5854f527a89fc828c9e0ec0))
- [Fix `web_embedded` client extraction](https://github.com/yt-dlp/yt-dlp/commit/d6ee67725397807bbb5edcd0b2c94f5bca62d3f4) ([#14843](https://github.com/yt-dlp/yt-dlp/issues/14843)) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- [Fix auto-generated metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/a56217f9f6c594f6c419ce8dce9134198a9d90d0) ([#13896](https://github.com/yt-dlp/yt-dlp/issues/13896)) by [TheQWERTYCodr](https://github.com/TheQWERTYCodr)
- [Fix original language detection](https://github.com/yt-dlp/yt-dlp/commit/afc44022d0b736b2b3e87b52490bd35c53c53632) ([#14919](https://github.com/yt-dlp/yt-dlp/issues/14919)) by [bashonly](https://github.com/bashonly)
- [Implement external n/sig solver](https://github.com/yt-dlp/yt-dlp/commit/6224a3898821965a7d6a2cb9cc2de40a0fd6e6bc) ([#14157](https://github.com/yt-dlp/yt-dlp/issues/14157)) by [bashonly](https://github.com/bashonly), [coletdjnz](https://github.com/coletdjnz), [Grub4K](https://github.com/Grub4K), [seproDev](https://github.com/seproDev) (With fixes in [4b4223b](https://github.com/yt-dlp/yt-dlp/commit/4b4223b436fb03a12628679daed32ae4fc15ae4b), [ee98be4](https://github.com/yt-dlp/yt-dlp/commit/ee98be4ad767b77e4d8dd9bfd3c7d10f2e8397ff), [c0c9f30](https://github.com/yt-dlp/yt-dlp/commit/c0c9f30695db314df084e8701a7c376eb54f283c), [cacd163](https://github.com/yt-dlp/yt-dlp/commit/cacd1630a1a59e92f857d0d175c8730cffbf9801), [8636a9b](https://github.com/yt-dlp/yt-dlp/commit/8636a9bac3bed99984c1e297453660468ecf504b))
- [Support collaborators](https://github.com/yt-dlp/yt-dlp/commit/f87cfadb5c3cba8e9dc4231c9554548e9edb3882) ([#14677](https://github.com/yt-dlp/yt-dlp/issues/14677)) by [seproDev](https://github.com/seproDev)
- tab: [Fix duration extraction for feeds](https://github.com/yt-dlp/yt-dlp/commit/1d2f0edaf978a5541cfb8f7e83fec433c65c1011) ([#14668](https://github.com/yt-dlp/yt-dlp/issues/14668)) by [WeidiDeng](https://github.com/WeidiDeng)
#### Downloader changes
- **ffmpeg**
- [Apply `ffmpeg_args` for each format](https://github.com/yt-dlp/yt-dlp/commit/ffb7b7f446b6c67a28c66598ae91f4f2263e0d75) ([#14886](https://github.com/yt-dlp/yt-dlp/issues/14886)) by [bashonly](https://github.com/bashonly)
- [Limit read rate for DASH livestreams](https://github.com/yt-dlp/yt-dlp/commit/7af6d81f35aea8832023daa30ada10e6673a0529) ([#14918](https://github.com/yt-dlp/yt-dlp/issues/14918)) by [bashonly](https://github.com/bashonly)
#### Networking changes
- [Ensure underlying file object is closed when fully read](https://github.com/yt-dlp/yt-dlp/commit/5767fb4ab108dddb07fc839a3b0f4d323a7c4bea) ([#14935](https://github.com/yt-dlp/yt-dlp/issues/14935)) by [coletdjnz](https://github.com/coletdjnz)
#### Misc. changes
- [Fix zsh path argument completion](https://github.com/yt-dlp/yt-dlp/commit/c96e9291ab7bd6e7da66d33424982c8b0b4431c7) ([#14953](https://github.com/yt-dlp/yt-dlp/issues/14953)) by [matyb08](https://github.com/matyb08)
- **build**: [Bump musllinux Python version to 3.14](https://github.com/yt-dlp/yt-dlp/commit/646904cd3a79429ec5fdc43f904b3f57ae213f34) ([#14623](https://github.com/yt-dlp/yt-dlp/issues/14623)) by [bashonly](https://github.com/bashonly)
- **cleanup**
- Miscellaneous
- [c63b4e2](https://github.com/yt-dlp/yt-dlp/commit/c63b4e2a2b81cc78397c8709ef53ffd29bada213) by [bashonly](https://github.com/bashonly), [matyb08](https://github.com/matyb08), [sepro](https://github.com/sepro)
- [335653b](https://github.com/yt-dlp/yt-dlp/commit/335653be82d5ef999cfc2879d005397402eebec1) by [bashonly](https://github.com/bashonly), [seproDev](https://github.com/seproDev)
- **devscripts**: [Improve `install_deps` script](https://github.com/yt-dlp/yt-dlp/commit/73922e66e437fb4bb618bdc119a96375081bf508) ([#14766](https://github.com/yt-dlp/yt-dlp/issues/14766)) by [bashonly](https://github.com/bashonly)
- **test**: [Skip flaky tests if source unchanged](https://github.com/yt-dlp/yt-dlp/commit/ade8c2b36ff300edef87d48fd1ba835ac35c5b63) ([#14970](https://github.com/yt-dlp/yt-dlp/issues/14970)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
### 2025.10.22
#### Important changes

2
Maintainers.md
View file

@ -10,6 +10,8 @@ Core Maintainers are responsible for reviewing and merging contributions, publis
**You can contact the core maintainers via `maintainers@yt-dlp.org`.**
This is **NOT** a support channel. [Open an issue](https://github.com/yt-dlp/yt-dlp/issues/new/choose) if you need help or want to report a bug.
### [coletdjnz](https://github.com/coletdjnz)
[![gh-sponsor](https://img.shields.io/badge/_-Github-white.svg?logo=github&labelColor=555555&style=for-the-badge)](https://github.com/sponsors/coletdjnz)

6
Makefile
View file

@ -202,9 +202,9 @@ CONTRIBUTORS: Changelog.md
# The following EJS_-prefixed variables are auto-generated by devscripts/update_ejs.py
# DO NOT EDIT!
EJS_VERSION = 0.3.0
EJS_WHEEL_NAME = yt_dlp_ejs-0.3.0-py3-none-any.whl
EJS_WHEEL_HASH = sha256:abbf269fa1674cab7b7b266e51e89e0e60b01a11a0fdf3cd63528683190cdd07
EJS_VERSION = 0.3.1
EJS_WHEEL_NAME = yt_dlp_ejs-0.3.1-py3-none-any.whl
EJS_WHEEL_HASH = sha256:a6e3548874db7c774388931752bb46c7f4642c044b2a189e56968f3d5ecab622
EJS_PY_FOLDERS = yt_dlp_ejs yt_dlp_ejs/yt yt_dlp_ejs/yt/solver
EJS_PY_FILES = yt_dlp_ejs/__init__.py yt_dlp_ejs/_version.py yt_dlp_ejs/yt/__init__.py yt_dlp_ejs/yt/solver/__init__.py
EJS_JS_FOLDERS = yt_dlp_ejs/yt/solver

64
README.md
View file

@ -189,7 +189,7 @@ Example usage:
yt-dlp --update-to nightly
# To install nightly with pip:
python3 -m pip install -U --pre "yt-dlp[default]"
python -m pip install -U --pre "yt-dlp[default]"
```
When running a yt-dlp version that is older than 90 days, you will see a warning message suggesting to update to the latest version.
@ -265,12 +265,12 @@ To build the standalone executable, you must have Python and `pyinstaller` (plus
You can run the following commands:
```
python3 devscripts/install_deps.py --include pyinstaller
python3 devscripts/make_lazy_extractors.py
python3 -m bundle.pyinstaller
python devscripts/install_deps.py --include-group pyinstaller
python devscripts/make_lazy_extractors.py
python -m bundle.pyinstaller
```
On some systems, you may need to use `py` or `python` instead of `python3`.
On some systems, you may need to use `py` or `python3` instead of `python`.
`python -m bundle.pyinstaller` accepts any arguments that can be passed to `pyinstaller`, such as `--onefile/-F` or `--onedir/-D`, which is further [documented here](https://pyinstaller.org/en/stable/usage.html#what-to-generate).
@ -360,7 +360,7 @@ Tip: Use `CTRL`+`F` (or `Command`+`F`) to search by keywords
containing directory ("-" for stdin). Can be
used multiple times and inside other
configuration files
--plugin-dirs PATH Path to an additional directory to search
--plugin-dirs DIR Path to an additional directory to search
for plugins. This option can be used
multiple times to add multiple directories.
Use "default" to search the default plugin
@ -369,22 +369,33 @@ Tip: Use `CTRL`+`F` (or `Command`+`F`) to search by keywords
including defaults and those provided by
previous --plugin-dirs
--js-runtimes RUNTIME[:PATH] Additional JavaScript runtime to enable,
with an optional path to the runtime
location. This option can be used multiple
times to enable multiple runtimes. Supported
runtimes: deno, node, bun, quickjs. By
default, only "deno" runtime is enabled.
with an optional location for the runtime
(either the path to the binary or its
containing directory). This option can be
used multiple times to enable multiple
runtimes. Supported runtimes are (in order
of priority, from highest to lowest): deno,
node, quickjs, bun. Only "deno" is enabled
by default. The highest priority runtime
that is both enabled and available will be
used. In order to use a lower priority
runtime when "deno" is available, --no-js-
runtimes needs to be passed before enabling
other runtimes
--no-js-runtimes Clear JavaScript runtimes to enable,
including defaults and those provided by
previous --js-runtimes
--remote-components COMPONENT Remote components to allow yt-dlp to fetch
when required. You can use this option
multiple times to allow multiple components.
Supported values: ejs:npm (external
JavaScript components from npm), ejs:github
(external JavaScript components from yt-dlp-
ejs GitHub). By default, no remote
components are allowed.
when required. This option is currently not
needed if you are using an official
executable or have the requisite version of
the yt-dlp-ejs package installed. You can
use this option multiple times to allow
multiple components. Supported values:
ejs:npm (external JavaScript components from
npm), ejs:github (external JavaScript
components from yt-dlp-ejs GitHub). By
default, no remote components are allowed
--no-remote-components Disallow fetching of all remote components,
including any previously allowed by
--remote-components or defaults.
@ -1105,11 +1116,12 @@ Make chapter entries for, or remove various segments (sponsor,
for, separated by commas. Available
categories are sponsor, intro, outro,
selfpromo, preview, filler, interaction,
music_offtopic, poi_highlight, chapter, all
and default (=all). You can prefix the
category with a "-" to exclude it. See [1]
for descriptions of the categories. E.g.
--sponsorblock-mark all,-preview
music_offtopic, hook, poi_highlight,
chapter, all and default (=all). You can
prefix the category with a "-" to exclude
it. See [1] for descriptions of the
categories. E.g. --sponsorblock-mark
all,-preview
[1] https://wiki.sponsor.ajay.app/w/Segment_Categories
--sponsorblock-remove CATS SponsorBlock categories to be removed from
the video file, separated by commas. If a
@ -1174,7 +1186,7 @@ Predefined aliases for convenience and ease of use. Note that future
You can configure yt-dlp by placing any supported command line option in a configuration file. The configuration is loaded from the following locations:
1. **Main Configuration**:
* The file given to `--config-location`
* The file given to `--config-locations`
1. **Portable Configuration**: (Recommended for portable installations)
* If using a binary, `yt-dlp.conf` in the same directory as the binary
* If running from source-code, `yt-dlp.conf` in the parent directory of `yt_dlp`
@ -1256,7 +1268,7 @@ yt-dlp --netrc-cmd 'gpg --decrypt ~/.authinfo.gpg' 'https://www.youtube.com/watc
### Notes about environment variables
* Environment variables are normally specified as `${VARIABLE}`/`$VARIABLE` on UNIX and `%VARIABLE%` on Windows; but is always shown as `${VARIABLE}` in this documentation
* yt-dlp also allows using UNIX-style variables on Windows for path-like options; e.g. `--output`, `--config-location`
* yt-dlp also allows using UNIX-style variables on Windows for path-like options; e.g. `--output`, `--config-locations`
* If unset, `${XDG_CONFIG_HOME}` defaults to `~/.config` and `${XDG_CACHE_HOME}` to `~/.cache`
* On Windows, `~` points to `${HOME}` if present; or, `${USERPROFILE}` or `${HOMEDRIVE}${HOMEPATH}` otherwise
* On Windows, `${USERPROFILE}` generally points to `C:\Users\<user name>` and `${APPDATA}` to `${USERPROFILE}\AppData\Roaming`
@ -1840,7 +1852,7 @@ The following extractors use this feature:
#### 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/_base.py](https://github.com/yt-dlp/yt-dlp/blob/415b4c9f955b1a0391204bd24a7132590e7b3bdb/yt_dlp/extractor/youtube/_base.py#L402-L409) for the 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 currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_sdkless`, `android_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv,android_sdkless,web` is used. If no JavaScript runtime is available, then `android_sdkless,web_safari,web` is used. If logged-in cookies are passed to yt-dlp, then `tv,web_safari,web` is used for free accounts and `tv,web_creator,web` is used for premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
* `player_client`: Clients to extract video data from. The currently available clients are `web`, `web_safari`, `web_embedded`, `web_music`, `web_creator`, `mweb`, `ios`, `android`, `android_sdkless`, `android_vr`, `tv`, `tv_simply`, `tv_downgraded`, and `tv_embedded`. By default, `tv,android_sdkless,web` is used. If no JavaScript runtime is available, then `android_sdkless,web_safari,web` is used. If logged-in cookies are passed to yt-dlp, then `tv_downgraded,web_safari,web` is used for free accounts and `tv_downgraded,web_creator,web` is used for premium accounts. The `web_music` client is added for `music.youtube.com` URLs when logged-in cookies are used. The `web_embedded` client is added for age-restricted videos but only works if the video is embeddable. The `tv_embedded` and `web_creator` clients are added for age-restricted videos if account age-verification is required. Some clients, such as `web` and `web_music`, require a `po_token` for their formats to be downloadable. Some clients, such as `web_creator`, will only work with authentication. Not all clients support authentication via cookies. You can use `default` for the default clients, or you can use `all` for all clients (not recommended). You can prefix a client with `-` to exclude it, e.g. `youtube:player_client=default,-ios`
* `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), `initial_data` (skip initial data/next ep request). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause issues such as missing formats or metadata. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) and [#12826](https://github.com/yt-dlp/yt-dlp/issues/12826) for more details
* `webpage_skip`: Skip extraction of embedded webpage data. One or both of `player_response`, `initial_data`. These options are for testing purposes and don't skip any network requests
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.

11
devscripts/changelog_override.json
View file

@ -308,5 +308,16 @@
"action": "add",
"when": "2c9091e355a7ba5d1edb69796ecdca48199b77fb",
"short": "[priority] **A stopgap release with a *TEMPORARY partial* fix for YouTube support**\nSome formats may still be unavailable, especially if cookies are passed to yt-dlp. The ***NEXT*** release, expected very soon, **will require an external JS runtime (e.g. Deno)** in order for YouTube downloads to work properly. [Read more](https://github.com/yt-dlp/yt-dlp/issues/14404)"
},
{
"action": "change",
"when": "8636a9bac3bed99984c1e297453660468ecf504b",
"short": "Fix 6224a3898821965a7d6a2cb9cc2de40a0fd6e6bc",
"authors": ["Grub4K"]
},
{
"action": "add",
"when": "6224a3898821965a7d6a2cb9cc2de40a0fd6e6bc",
"short": "[priority] **An external JavaScript runtime is now required for full YouTube support**\nyt-dlp now requires users to have an external JavaScript runtime (e.g. Deno) installed in order to solve the JavaScript challenges presented by YouTube. [Read more](https://github.com/yt-dlp/yt-dlp/issues/15012)"
}
]

7
devscripts/make_changelog.py
View file

@ -353,6 +353,13 @@ class CommitRange:
continue
commit = Commit(override_hash, override['short'], override.get('authors') or [])
logger.info(f'CHANGE {self._commits[commit.hash]} -> {commit}')
if match := self.FIXES_RE.search(commit.short):
fix_commitish = match.group(1)
if fix_commitish in self._commits:
del self._commits[commit.hash]
self._fixes[fix_commitish].append(commit)
logger.info(f'Found fix for {fix_commitish[:HASH_LENGTH]}: {commit.hash[:HASH_LENGTH]}')
continue
self._commits[commit.hash] = commit
self._commits = dict(reversed(self._commits.items()))

24
devscripts/run_tests.py
View file

@ -17,6 +17,18 @@ def parse_args():
parser = argparse.ArgumentParser(description='Run selected yt-dlp tests')
parser.add_argument(
'test', help='an extractor test, test path, or one of "core" or "download"', nargs='*')
parser.add_argument(
'--flaky',
action='store_true',
default=None,
help='Allow running flaky tests. (default: run, unless in CI)',
)
parser.add_argument(
'--no-flaky',
action='store_false',
dest='flaky',
help=argparse.SUPPRESS,
)
parser.add_argument(
'-k', help='run a test matching EXPRESSION. Same as "pytest -k"', metavar='EXPRESSION')
parser.add_argument(
@ -24,10 +36,11 @@ def parse_args():
return parser.parse_args()
def run_tests(*tests, pattern=None, ci=False):
def run_tests(*tests, pattern=None, ci=False, flaky: bool | None = None):
# XXX: hatch uses `tests` if no arguments are passed
run_core = 'core' in tests or 'tests' in tests or (not pattern and not tests)
run_download = 'download' in tests
run_flaky = flaky or (flaky is None and not ci)
pytest_args = args.pytest_args or os.getenv('HATCH_TEST_ARGS', '')
arguments = ['pytest', '-Werror', '--tb=short', *shlex.split(pytest_args)]
@ -44,6 +57,8 @@ def run_tests(*tests, pattern=None, ci=False):
test if '/' in test
else f'test/test_download.py::TestDownload::test_{fix_test_name(test)}'
for test in tests)
if not run_flaky:
arguments.append('--disallow-flaky')
print(f'Running {arguments}', flush=True)
try:
@ -72,6 +87,11 @@ if __name__ == '__main__':
args = parse_args()
os.chdir(Path(__file__).parent.parent)
sys.exit(run_tests(*args.test, pattern=args.k, ci=bool(os.getenv('CI'))))
sys.exit(run_tests(
*args.test,
pattern=args.k,
ci=bool(os.getenv('CI')),
flaky=args.flaky,
))
except KeyboardInterrupt:
pass

4
devscripts/update_ejs.py Normal file → Executable file
View file

@ -66,7 +66,9 @@ def list_wheel_contents(
) -> str:
assert folders or files, 'at least one of "folders" or "files" must be True'
path_gen = (zinfo.filename for zinfo in zipfile.ZipFile(io.BytesIO(wheel_data)).infolist())
with zipfile.ZipFile(io.BytesIO(wheel_data)) as zipf:
path_gen = (zinfo.filename for zinfo in zipf.infolist())
filtered = filter(lambda path: path.startswith('yt_dlp_ejs/'), path_gen)
if suffix:
filtered = filter(lambda path: path.endswith(f'.{suffix}'), filtered)

7
devscripts/zsh-completion.py
View file

@ -18,6 +18,7 @@ def build_completion(opt_parser):
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_path = [opt for opt in opts if opt.metavar == 'PATH']
fileopts = []
for opt in opts_file:
@ -26,6 +27,12 @@ def build_completion(opt_parser):
if opt._long_opts:
fileopts.extend(opt._long_opts)
for opt in opts_path:
if opt._short_opts:
fileopts.extend(opt._short_opts)
if opt._long_opts:
fileopts.extend(opt._long_opts)
diropts = []
for opt in opts_dir:
if opt._short_opts:

2
pyproject.toml
View file

@ -56,7 +56,7 @@ default = [
"requests>=2.32.2,<3",
"urllib3>=2.0.2,<3",
"websockets>=13.0",
"yt-dlp-ejs==0.3.0",
"yt-dlp-ejs==0.3.1",
]
curl-cffi = [
"curl-cffi>=0.5.10,!=0.6.*,!=0.7.*,!=0.8.*,!=0.9.*,<0.14; implementation_name=='cpython'",

15
supportedsites.md
View file

@ -12,6 +12,7 @@ The only reliable way to check if a site is supported is to try it.
- **17live:vod**
- **1News**: 1news.co.nz article videos
- **1tv**: Первый канал
- **1tv:live**: Первый канал (прямой эфир)
- **20min**: (**Currently broken**)
- **23video**
- **247sports**: (**Currently broken**)
@ -93,6 +94,8 @@ The only reliable way to check if a site is supported is to try it.
- **archive.org**: archive.org video and audio
- **ArcPublishing**
- **ARD**
- **ARDAudiothek**
- **ARDAudiothekPlaylist**
- **ARDMediathek**
- **ARDMediathekCollection**
- **Art19**
@ -533,7 +536,6 @@ The only reliable way to check if a site is supported is to try it.
- **google:​podcasts:feed**
- **GoogleDrive**
- **GoogleDrive:Folder**
- **GoPlay**: [*goplay*](## "netrc machine")
- **GoPro**
- **Goshgay**
- **GoToStage**
@ -844,6 +846,7 @@ The only reliable way to check if a site is supported is to try it.
- **MusicdexArtist**
- **MusicdexPlaylist**
- **MusicdexSong**
- **Mux**
- **Mx3**
- **Mx3Neo**
- **Mx3Volksmusik**
@ -858,6 +861,7 @@ The only reliable way to check if a site is supported is to try it.
- **n-tv.de**
- **N1Info:article**
- **N1InfoAsset**
- **NascarClassics**
- **Nate**
- **NateProgram**
- **natgeo:video**
@ -1071,6 +1075,7 @@ The only reliable way to check if a site is supported is to try it.
- **PlanetMarathi**
- **Platzi**: [*platzi*](## "netrc machine")
- **PlatziCourse**: [*platzi*](## "netrc machine")
- **play.tv**: [*goplay*](## "netrc machine") PLAY (formerly goplay.be)
- **player.sky.it**
- **PlayerFm**
- **playeur**
@ -1559,12 +1564,12 @@ The only reliable way to check if a site is supported is to try it.
- **TwitCastingLive**
- **TwitCastingUser**
- **twitch:clips**: [*twitch*](## "netrc machine")
- **twitch:collection**: [*twitch*](## "netrc machine")
- **twitch:stream**: [*twitch*](## "netrc machine")
- **twitch:videos**: [*twitch*](## "netrc machine")
- **twitch:​videos:clips**: [*twitch*](## "netrc machine")
- **twitch:​videos:collections**: [*twitch*](## "netrc machine")
- **twitch:vod**: [*twitch*](## "netrc machine")
- **TwitchCollection**: [*twitch*](## "netrc machine")
- **TwitchVideos**: [*twitch*](## "netrc machine")
- **TwitchVideosClips**: [*twitch*](## "netrc machine")
- **TwitchVideosCollections**: [*twitch*](## "netrc machine")
- **twitter**: [*twitter*](## "netrc machine")
- **twitter:amplify**: [*twitter*](## "netrc machine")
- **twitter:broadcast**: [*twitter*](## "netrc machine")

30
test/conftest.py
View file

@ -52,6 +52,33 @@ def skip_handlers_if(request, handler):
pytest.skip(marker.args[1] if len(marker.args) > 1 else '')
@pytest.fixture(autouse=True)
def handler_flaky(request, handler):
"""Mark a certain handler as being flaky.
This will skip the test if pytest does not get run using `--allow-flaky`
usage:
pytest.mark.handler_flaky('my_handler', os.name != 'nt', reason='reason')
"""
for marker in request.node.iter_markers(handler_flaky.__name__):
if (
marker.args[0] == handler.RH_KEY
and (not marker.args[1:] or any(marker.args[1:]))
and request.config.getoption('disallow_flaky')
):
reason = marker.kwargs.get('reason')
pytest.skip(f'flaky: {reason}' if reason else 'flaky')
def pytest_addoption(parser, pluginmanager):
parser.addoption(
'--disallow-flaky',
action='store_true',
help='disallow flaky tests from running.',
)
def pytest_configure(config):
config.addinivalue_line(
'markers', 'skip_handler(handler): skip test for the given handler',
@ -62,3 +89,6 @@ def pytest_configure(config):
config.addinivalue_line(
'markers', 'skip_handlers_if(handler): skip test for handlers when the condition is true',
)
config.addinivalue_line(
'markers', 'handler_flaky(handler): mark handler as flaky if condition is true',
)

2
test/test_http_proxy.py
View file

@ -247,6 +247,7 @@ def ctx(request):
@pytest.mark.parametrize(
'handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', reason='segfaults')
@pytest.mark.parametrize('ctx', ['http'], indirect=True) # pure http proxy can only support http
class TestHTTPProxy:
def test_http_no_auth(self, handler, ctx):
@ -315,6 +316,7 @@ class TestHTTPProxy:
('Requests', 'https'),
('CurlCFFI', 'https'),
], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', reason='segfaults')
class TestHTTPConnectProxy:
def test_http_connect_no_auth(self, handler, ctx):
with ctx.http_server(HTTPConnectProxyHandler) as server_address:

120
test/test_networking.py
View file

@ -3,6 +3,7 @@
# Allow direct execution
import os
import sys
from unittest.mock import MagicMock
import pytest
@ -311,6 +312,7 @@ class TestRequestHandlerBase:
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', os.name == 'nt', reason='segfaults')
class TestHTTPRequestHandler(TestRequestHandlerBase):
def test_verify_cert(self, handler):
@ -614,8 +616,11 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
@pytest.mark.skip_handler('CurlCFFI', 'not supported by curl-cffi')
def test_gzip_trailing_garbage(self, handler):
with handler() as rh:
data = validate_and_send(rh, Request(f'http://localhost:{self.http_port}/trailing_garbage')).read().decode()
res = validate_and_send(rh, Request(f'http://localhost:{self.http_port}/trailing_garbage'))
data = res.read().decode()
assert data == '<html><video src="/vid.mp4" /></html>'
# Should auto-close and mark the response adaptor as closed
assert res.closed
@pytest.mark.skip_handler('CurlCFFI', 'not applicable to curl-cffi')
@pytest.mark.skipif(not brotli, reason='brotli support is not installed')
@ -627,6 +632,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
headers={'ytdl-encoding': 'br'}))
assert res.headers.get('Content-Encoding') == 'br'
assert res.read() == b'<html><video src="/vid.mp4" /></html>'
# Should auto-close and mark the response adaptor as closed
assert res.closed
def test_deflate(self, handler):
with handler() as rh:
@ -636,6 +643,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
headers={'ytdl-encoding': 'deflate'}))
assert res.headers.get('Content-Encoding') == 'deflate'
assert res.read() == b'<html><video src="/vid.mp4" /></html>'
# Should auto-close and mark the response adaptor as closed
assert res.closed
def test_gzip(self, handler):
with handler() as rh:
@ -645,6 +654,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
headers={'ytdl-encoding': 'gzip'}))
assert res.headers.get('Content-Encoding') == 'gzip'
assert res.read() == b'<html><video src="/vid.mp4" /></html>'
# Should auto-close and mark the response adaptor as closed
assert res.closed
def test_multiple_encodings(self, handler):
with handler() as rh:
@ -655,6 +666,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
headers={'ytdl-encoding': pair}))
assert res.headers.get('Content-Encoding') == pair
assert res.read() == b'<html><video src="/vid.mp4" /></html>'
# Should auto-close and mark the response adaptor as closed
assert res.closed
@pytest.mark.skip_handler('CurlCFFI', 'not supported by curl-cffi')
def test_unsupported_encoding(self, handler):
@ -665,6 +678,8 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
headers={'ytdl-encoding': 'unsupported', 'Accept-Encoding': '*'}))
assert res.headers.get('Content-Encoding') == 'unsupported'
assert res.read() == b'raw'
# Should auto-close and mark the response adaptor as closed
assert res.closed
def test_read(self, handler):
with handler() as rh:
@ -672,9 +687,13 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
rh, Request(f'http://127.0.0.1:{self.http_port}/headers'))
assert res.readable()
assert res.read(1) == b'H'
# Ensure we don't close the adaptor yet
assert not res.closed
assert res.read(3) == b'ost'
assert res.read().decode().endswith('\n\n')
assert res.read() == b''
# Should auto-close and mark the response adaptor as closed
assert res.closed
def test_request_disable_proxy(self, handler):
for proxy_proto in handler._SUPPORTED_PROXY_SCHEMES or ['http']:
@ -736,8 +755,20 @@ class TestHTTPRequestHandler(TestRequestHandlerBase):
assert res.read(0) == b''
assert res.read() == b'<video src="/vid.mp4" /></html>'
def test_partial_read_greater_than_response_then_full_read(self, handler):
with handler() as rh:
for encoding in ('', 'gzip', 'deflate'):
res = validate_and_send(rh, Request(
f'http://127.0.0.1:{self.http_port}/content-encoding',
headers={'ytdl-encoding': encoding}))
assert res.headers.get('Content-Encoding') == encoding
assert res.read(512) == b'<html><video src="/vid.mp4" /></html>'
assert res.read(0) == b''
assert res.read() == b''
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', reason='segfaults')
class TestClientCertificate:
@classmethod
def setup_class(cls):
@ -875,11 +906,53 @@ class TestUrllibRequestHandler(TestRequestHandlerBase):
with handler(enable_file_urls=True) as rh:
res = validate_and_send(rh, req)
assert res.read() == b'foobar'
res.close()
assert res.read(1) == b'f'
assert not res.fp.closed
assert res.read() == b'oobar'
# Should automatically close the underlying file object
assert res.fp.closed
os.unlink(tf.name)
def test_data_uri_auto_close(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request('data:text/plain,hello%20world'))
assert res.read() == b'hello world'
# Should automatically close the underlying file object
assert res.fp.closed
assert res.closed
def test_http_response_auto_close(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/gen_200'))
assert res.read() == b'<html></html>'
# Should automatically close the underlying file object in the HTTP Response
assert isinstance(res.fp, http.client.HTTPResponse)
assert res.fp.fp is None
assert res.closed
def test_data_uri_partial_read_then_full_read(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request('data:text/plain,hello%20world'))
assert res.read(6) == b'hello '
assert res.read(0) == b''
assert res.read() == b'world'
# Should automatically close the underlying file object
assert res.fp.closed
assert res.closed
def test_data_uri_partial_read_greater_than_response_then_full_read(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request('data:text/plain,hello%20world'))
assert res.read(512) == b'hello world'
# Response and its underlying file object should already be closed now
assert res.fp.closed
assert res.closed
assert res.read(0) == b''
assert res.read() == b''
assert res.fp.closed
assert res.closed
def test_http_error_returns_content(self, handler):
# urllib HTTPError will try close the underlying response if reference to the HTTPError object is lost
def get_response():
@ -1012,8 +1085,17 @@ class TestRequestsRequestHandler(TestRequestHandlerBase):
rh.close()
assert called
def test_http_response_auto_close(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/gen_200'))
assert res.read() == b'<html></html>'
# Should automatically close the underlying file object in the HTTP Response
assert res.fp.closed
assert res.closed
@pytest.mark.parametrize('handler', ['CurlCFFI'], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', os.name == 'nt', reason='segfaults')
class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
@pytest.mark.parametrize('params,extensions', [
@ -1177,6 +1259,14 @@ class TestCurlCFFIRequestHandler(TestRequestHandlerBase):
assert res4.closed
assert res4._buffer == b''
def test_http_response_auto_close(self, handler):
with handler() as rh:
res = validate_and_send(rh, Request(f'http://127.0.0.1:{self.http_port}/gen_200'))
assert res.read() == b'<html></html>'
# Should automatically close the underlying file object in the HTTP Response
assert res.fp.closed
assert res.closed
def run_validation(handler, error, req, **handler_kwargs):
with handler(**handler_kwargs) as rh:
@ -2032,6 +2122,30 @@ class TestResponse:
assert res.info() is res.headers
assert res.getheader('test') == res.get_header('test')
def test_auto_close(self):
# Should mark the response as closed if the underlying file is closed
class AutoCloseBytesIO(io.BytesIO):
def read(self, size=-1, /):
data = super().read(size)
self.close()
return data
fp = AutoCloseBytesIO(b'test')
res = Response(fp, url='test://', headers={}, status=200)
assert not res.closed
res.read()
assert res.closed
def test_close(self):
# Should not call close() on the underlying file when already closed
fp = MagicMock()
fp.closed = False
res = Response(fp, url='test://', headers={}, status=200)
res.close()
fp.closed = True
res.close()
assert fp.close.call_count == 1
class TestImpersonateTarget:
@pytest.mark.parametrize('target_str,expected', [

2
test/test_socks.py
View file

@ -295,6 +295,7 @@ def ctx(request):
('Websockets', 'ws'),
('CurlCFFI', 'http'),
], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', reason='segfaults')
class TestSocks4Proxy:
def test_socks4_no_auth(self, handler, ctx):
with handler() as rh:
@ -370,6 +371,7 @@ class TestSocks4Proxy:
('Websockets', 'ws'),
('CurlCFFI', 'http'),
], indirect=True)
@pytest.mark.handler_flaky('CurlCFFI', reason='segfaults')
class TestSocks5Proxy:
def test_socks5_no_auth(self, handler, ctx):

7
test/test_websockets.py
View file

@ -38,6 +38,13 @@ from yt_dlp.utils.networking import HTTPHeaderDict
TEST_DIR = os.path.dirname(os.path.abspath(__file__))
pytestmark = pytest.mark.handler_flaky(
'Websockets',
os.name == 'nt' or sys.implementation.name == 'pypy',
reason='segfaults',
)
def websocket_handler(websocket):
for message in websocket:
if isinstance(message, bytes):

6
yt_dlp/cookies.py
View file

@ -125,7 +125,7 @@ def extract_cookies_from_browser(browser_name, profile=None, logger=YDLLogger(),
def _extract_firefox_cookies(profile, container, logger):
MAX_SUPPORTED_DB_SCHEMA_VERSION = 16
MAX_SUPPORTED_DB_SCHEMA_VERSION = 17
logger.info('Extracting cookies from firefox')
if not sqlite3:
@ -166,6 +166,8 @@ def _extract_firefox_cookies(profile, container, logger):
db_schema_version = cursor.execute('PRAGMA user_version;').fetchone()[0]
if db_schema_version > MAX_SUPPORTED_DB_SCHEMA_VERSION:
logger.warning(f'Possibly unsupported firefox cookies database version: {db_schema_version}')
else:
logger.debug(f'Firefox cookies database version: {db_schema_version}')
if isinstance(container_id, int):
logger.debug(
f'Only loading cookies from firefox container "{container}", ID {container_id}')
@ -557,7 +559,7 @@ class WindowsChromeCookieDecryptor(ChromeCookieDecryptor):
def _extract_safari_cookies(profile, logger):
if sys.platform != 'darwin':
if sys.platform not in ('darwin', 'ios'):
raise ValueError(f'unsupported platform: {sys.platform}')
if profile:

3
yt_dlp/downloader/common.py
View file

@ -461,7 +461,8 @@ class FileDownloader:
min_sleep_interval = self.params.get('sleep_interval') or 0
max_sleep_interval = self.params.get('max_sleep_interval') or 0
if available_at := info_dict.get('available_at'):
requested_formats = info_dict.get('requested_formats') or [info_dict]
if available_at := max(f.get('available_at') or 0 for f in requested_formats):
forced_sleep_interval = available_at - int(time.time())
if forced_sleep_interval > min_sleep_interval:
sleep_note = 'as required by the site'

88
yt_dlp/downloader/external.py
View file

@ -457,6 +457,8 @@ class FFmpegFD(ExternalFD):
@classmethod
def available(cls, path=None):
# TODO: Fix path for ffmpeg
# Fixme: This may be wrong when --ffmpeg-location is used
return FFmpegPostProcessor().available
def on_process_started(self, proc, stdin):
@ -488,20 +490,6 @@ class FFmpegFD(ExternalFD):
if not self.params.get('verbose'):
args += ['-hide_banner']
args += traverse_obj(info_dict, ('downloader_options', 'ffmpeg_args', ...))
# These exists only for compatibility. Extractors should use
# info_dict['downloader_options']['ffmpeg_args'] instead
args += info_dict.get('_ffmpeg_args') or []
seekable = info_dict.get('_seekable')
if seekable is not None:
# setting -seekable prevents ffmpeg from guessing if the server
# supports seeking(by adding the header `Range: bytes=0-`), which
# can cause problems in some cases
# https://github.com/ytdl-org/youtube-dl/issues/11800#issuecomment-275037127
# http://trac.ffmpeg.org/ticket/6125#comment:10
args += ['-seekable', '1' if seekable else '0']
env = None
proxy = self.params.get('proxy')
if proxy:
@ -521,39 +509,10 @@ class FFmpegFD(ExternalFD):
env['HTTP_PROXY'] = proxy
env['http_proxy'] = proxy
protocol = info_dict.get('protocol')
if protocol == 'rtmp':
player_url = info_dict.get('player_url')
page_url = info_dict.get('page_url')
app = info_dict.get('app')
play_path = info_dict.get('play_path')
tc_url = info_dict.get('tc_url')
flash_version = info_dict.get('flash_version')
live = info_dict.get('rtmp_live', False)
conn = info_dict.get('rtmp_conn')
if player_url is not None:
args += ['-rtmp_swfverify', player_url]
if page_url is not None:
args += ['-rtmp_pageurl', page_url]
if app is not None:
args += ['-rtmp_app', app]
if play_path is not None:
args += ['-rtmp_playpath', play_path]
if tc_url is not None:
args += ['-rtmp_tcurl', tc_url]
if flash_version is not None:
args += ['-rtmp_flashver', flash_version]
if live:
args += ['-rtmp_live', 'live']
if isinstance(conn, list):
for entry in conn:
args += ['-rtmp_conn', entry]
elif isinstance(conn, str):
args += ['-rtmp_conn', conn]
start_time, end_time = info_dict.get('section_start') or 0, info_dict.get('section_end')
fallback_input_args = traverse_obj(info_dict, ('downloader_options', 'ffmpeg_args', ...))
selected_formats = info_dict.get('requested_formats') or [info_dict]
for i, fmt in enumerate(selected_formats):
is_http = re.match(r'https?://', fmt['url'])
@ -572,6 +531,44 @@ class FFmpegFD(ExternalFD):
if end_time:
args += ['-t', str(end_time - start_time)]
protocol = fmt.get('protocol')
if protocol == 'rtmp':
player_url = fmt.get('player_url')
page_url = fmt.get('page_url')
app = fmt.get('app')
play_path = fmt.get('play_path')
tc_url = fmt.get('tc_url')
flash_version = fmt.get('flash_version')
live = fmt.get('rtmp_live', False)
conn = fmt.get('rtmp_conn')
if player_url is not None:
args += ['-rtmp_swfverify', player_url]
if page_url is not None:
args += ['-rtmp_pageurl', page_url]
if app is not None:
args += ['-rtmp_app', app]
if play_path is not None:
args += ['-rtmp_playpath', play_path]
if tc_url is not None:
args += ['-rtmp_tcurl', tc_url]
if flash_version is not None:
args += ['-rtmp_flashver', flash_version]
if live:
args += ['-rtmp_live', 'live']
if isinstance(conn, list):
for entry in conn:
args += ['-rtmp_conn', entry]
elif isinstance(conn, str):
args += ['-rtmp_conn', conn]
elif protocol == 'http_dash_segments' and info_dict.get('is_live'):
# ffmpeg may try to read past the latest available segments for
# live DASH streams unless we pass `-re`. In modern ffmpeg, this
# is an alias of `-readrate 1`, but `-readrate` was not added
# until ffmpeg 5.0, so we must stick to using `-re`
args += ['-re']
url = fmt['url']
if self.params.get('enable_file_urls') and url.startswith('file:'):
# The default protocol_whitelist is 'file,crypto,data' when reading local m3u8 URLs,
@ -586,6 +583,7 @@ class FFmpegFD(ExternalFD):
# https://trac.ffmpeg.org/ticket/2702
url = re.sub(r'^file://(?:localhost)?/', 'file:' if os.name == 'nt' else 'file:/', url)
args += traverse_obj(fmt, ('downloader_options', 'ffmpeg_args', ...)) or fallback_input_args
args += [*self._configuration_args((f'_i{i + 1}', '_i')), '-i', url]
if not (start_time or end_time) or not self.params.get('force_keyframes_at_cuts'):

22
yt_dlp/extractor/_extractors.py
View file

@ -268,6 +268,7 @@ from .bitchute import (
BitChuteChannelIE,
BitChuteIE,
)
from .bitmovin import BitmovinIE
from .blackboardcollaborate import (
BlackboardCollaborateIE,
BlackboardCollaborateLaunchIE,
@ -640,7 +641,10 @@ from .filmon import (
FilmOnIE,
)
from .filmweb import FilmwebIE
from .firsttv import FirstTVIE
from .firsttv import (
FirstTVIE,
FirstTVLiveIE,
)
from .fivetv import FiveTVIE
from .flextv import FlexTVIE
from .flickr import FlickrIE
@ -687,6 +691,10 @@ from .frontendmasters import (
FrontendMastersIE,
FrontendMastersLessonIE,
)
from .frontro import (
TheChosenGroupIE,
TheChosenIE,
)
from .fujitv import FujiTVFODPlus7IE
from .funk import FunkIE
from .funker530 import Funker530IE
@ -1090,7 +1098,10 @@ from .markiza import (
from .massengeschmacktv import MassengeschmackTVIE
from .masters import MastersIE
from .matchtv import MatchTVIE
from .mave import MaveIE
from .mave import (
MaveChannelIE,
MaveIE,
)
from .mbn import MBNIE
from .mdr import MDRIE
from .medaltv import MedalTVIE
@ -1197,6 +1208,7 @@ from .musicdex import (
MusicdexPlaylistIE,
MusicdexSongIE,
)
from .mux import MuxIE
from .mx3 import (
Mx3IE,
Mx3NeoIE,
@ -1272,6 +1284,10 @@ from .nest import (
NestClipIE,
NestIE,
)
from .netapp import (
NetAppCollectionIE,
NetAppVideoIE,
)
from .neteasemusic import (
NetEaseMusicAlbumIE,
NetEaseMusicDjRadioIE,
@ -1364,6 +1380,7 @@ from .nova import (
NovaIE,
)
from .novaplay import NovaPlayIE
from .nowcanal import NowCanalIE
from .nowness import (
NownessIE,
NownessPlaylistIE,
@ -2517,6 +2534,7 @@ from .yappy import (
YappyIE,
YappyProfileIE,
)
from .yfanefa import YfanefaIE
from .yle_areena import YleAreenaIE
from .youjizz import YouJizzIE
from .youku import (

2
yt_dlp/extractor/abc.py
View file

@ -321,6 +321,8 @@ class ABCIViewIE(InfoExtractor):
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
if formats:
break
else:
formats = []
subtitles = {}
src_vtt = stream.get('captions', {}).get('src-vtt')

74
yt_dlp/extractor/bitmovin.py Normal file
View file

@ -0,0 +1,74 @@
import re
from .common import InfoExtractor
from ..utils.traversal import traverse_obj
class BitmovinIE(InfoExtractor):
_VALID_URL = r'https?://streams\.bitmovin\.com/(?P<id>\w+)'
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//streams\.bitmovin\.com/(?P<id>\w+)[^"\']+)']
_TESTS = [{
'url': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/embed',
'info_dict': {
'id': 'cqkl1t5giv3lrce7pjbg',
'ext': 'mp4',
'title': 'Developing Osteopathic Residents as Faculty',
'thumbnail': 'https://streams.bitmovin.com/cqkl1t5giv3lrce7pjbg/poster',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/share',
'info_dict': {
'id': 'cgl9rh94uvs51rqc8jhg',
'ext': 'mp4',
'title': 'Big Buck Bunny (Streams Docs)',
'thumbnail': 'https://streams.bitmovin.com/cgl9rh94uvs51rqc8jhg/poster',
},
'params': {'skip_download': 'm3u8'},
}]
_WEBPAGE_TESTS = [{
# bitmovin-stream web component
'url': 'https://www.institutionalinvestor.com/article/2bsw1in1l9k68mp9kritc/video-war-stories-over-board-games/best-case-i-get-fired-war-stories',
'info_dict': {
'id': 'cuiumeil6g115lc4li3g',
'ext': 'mp4',
'title': '[media] War Stories over Board Games: “Best Case: I Get Fired” ',
'thumbnail': 'https://streams.bitmovin.com/cuiumeil6g115lc4li3g/poster',
},
'params': {'skip_download': 'm3u8'},
}, {
# iframe embed
'url': 'https://www.clearblueionizer.com/en/pool-ionizers/mineral-pool-vs-saltwater-pool/',
'info_dict': {
'id': 'cvpvfsm1pf7itg7cfvtg',
'ext': 'mp4',
'title': 'Pool Ionizer vs. Salt Chlorinator',
'thumbnail': 'https://streams.bitmovin.com/cvpvfsm1pf7itg7cfvtg/poster',
},
'params': {'skip_download': 'm3u8'},
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
yield from super()._extract_embed_urls(url, webpage)
for stream_id in re.findall(r'<bitmovin-stream\b[^>]*\bstream-id=["\'](?P<id>\w+)', webpage):
yield f'https://streams.bitmovin.com/{stream_id}'
def _real_extract(self, url):
video_id = self._match_id(url)
player_config = self._download_json(
f'https://streams.bitmovin.com/{video_id}/config', video_id)['sources']
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
player_config['hls'], video_id, 'mp4')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(player_config, {
'title': ('title', {str}),
'thumbnail': ('poster', {str}),
}),
}

23
yt_dlp/extractor/bunnycdn.py
View file

@ -16,7 +16,7 @@ from ..utils.traversal import find_element, traverse_obj
class BunnyCdnIE(InfoExtractor):
_VALID_URL = r'https?://(?:iframe\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
_VALID_URL = r'https?://(?:(?:iframe|player)\.mediadelivery\.net|video\.bunnycdn\.com)/(?:embed|play)/(?P<library_id>\d+)/(?P<id>[\da-f-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+src=[\'"](?P<url>{_VALID_URL}[^\'"]*)[\'"]']
_TESTS = [{
'url': 'https://iframe.mediadelivery.net/embed/113933/e73edec1-e381-4c8b-ae73-717a140e0924',
@ -39,7 +39,7 @@ class BunnyCdnIE(InfoExtractor):
'timestamp': 1691145748,
'thumbnail': r're:^https?://.*\.b-cdn\.net/32e34c4b-0d72-437c-9abb-05e67657da34/thumbnail_9172dc16\.jpg',
'duration': 106.0,
'description': 'md5:981a3e899a5c78352b21ed8b2f1efd81',
'description': 'md5:11452bcb31f379ee3eaf1234d3264e44',
'upload_date': '20230804',
'title': 'Sanela ist Teil der #arbeitsmarktkraft',
},
@ -58,6 +58,23 @@ class BunnyCdnIE(InfoExtractor):
'thumbnail': r're:^https?://.*\.b-cdn\.net/2e8545ec-509d-4571-b855-4cf0235ccd75/thumbnail\.jpg',
},
'params': {'skip_download': True},
}, {
# Requires any Referer
'url': 'https://iframe.mediadelivery.net/embed/289162/6372f5a3-68df-4ef7-a115-e1110186c477',
'info_dict': {
'id': '6372f5a3-68df-4ef7-a115-e1110186c477',
'ext': 'mp4',
'title': '12-Creating Small Asset Blockouts -Timelapse.mp4',
'description': '',
'duration': 263.0,
'timestamp': 1724485440,
'upload_date': '20240824',
'thumbnail': r're:^https?://.*\.b-cdn\.net/6372f5a3-68df-4ef7-a115-e1110186c477/thumbnail\.jpg',
},
'params': {'skip_download': True},
}, {
'url': 'https://player.mediadelivery.net/embed/519128/875880a9-bcc2-4038-9e05-e5024bba9b70',
'only_matching': True,
}]
_WEBPAGE_TESTS = [{
# Stream requires Referer
@ -100,7 +117,7 @@ class BunnyCdnIE(InfoExtractor):
video_id, library_id = self._match_valid_url(url).group('id', 'library_id')
webpage = self._download_webpage(
f'https://iframe.mediadelivery.net/embed/{library_id}/{video_id}', video_id,
headers=traverse_obj(smuggled_data, {'Referer': 'Referer'}),
headers={'Referer': smuggled_data.get('Referer') or 'https://iframe.mediadelivery.net/'},
query=traverse_obj(parse_qs(url), {'token': 'token', 'expires': 'expires'}))
if html_title := self._html_extract_title(webpage, default=None) == '403':

95
yt_dlp/extractor/digiteka.py
View file

@ -1,5 +1,6 @@
from .common import InfoExtractor
from ..utils import int_or_none
from ..utils import int_or_none, url_or_none
from ..utils.traversal import traverse_obj
class DigitekaIE(InfoExtractor):
@ -25,74 +26,56 @@ class DigitekaIE(InfoExtractor):
)/(?P<id>[\d+a-z]+)'''
_EMBED_REGEX = [r'<(?:iframe|script)[^>]+src=["\'](?P<url>(?:https?:)?//(?:www\.)?ultimedia\.com/deliver/(?:generic|musique)(?:/[^/]+)*/(?:src|article)/[\d+a-z]+)']
_TESTS = [{
# news
'url': 'https://www.ultimedia.com/default/index/videogeneric/id/s8uk0r',
'md5': '276a0e49de58c7e85d32b057837952a2',
'url': 'https://www.ultimedia.com/default/index/videogeneric/id/3x5x55k',
'info_dict': {
'id': 's8uk0r',
'id': '3x5x55k',
'ext': 'mp4',
'title': 'Loi sur la fin de vie: le texte prévoit un renforcement des directives anticipées',
'title': 'Il est passionné de DS',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 74,
'upload_date': '20150317',
'timestamp': 1426604939,
'uploader_id': '3fszv',
'duration': 89,
'upload_date': '20251012',
'timestamp': 1760285363,
'uploader_id': '3pz33',
},
}, {
# music
'url': 'https://www.ultimedia.com/default/index/videomusic/id/xvpfp8',
'md5': '2ea3513813cf230605c7e2ffe7eca61c',
'info_dict': {
'id': 'xvpfp8',
'ext': 'mp4',
'title': 'Two - C\'est La Vie (clip)',
'thumbnail': r're:^https?://.*\.jpg',
'duration': 233,
'upload_date': '20150224',
'timestamp': 1424760500,
'uploader_id': '3rfzk',
},
}, {
'url': 'https://www.digiteka.net/deliver/generic/iframe/mdtk/01637594/src/lqm3kl/zone/1/showtitle/1/autoplay/yes',
'only_matching': True,
'params': {'skip_download': True},
}]
_IFRAME_MD_ID = '01836272' # One static ID working for Ultimedia iframes
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
video_type = mobj.group('embed_type') or mobj.group('site_type')
if video_type == 'music':
video_type = 'musique'
video_id = self._match_id(url)
deliver_info = self._download_json(
f'http://www.ultimedia.com/deliver/video?video={video_id}&topic={video_type}',
video_id)
yt_id = deliver_info.get('yt_id')
if yt_id:
return self.url_result(yt_id, 'Youtube')
jwconf = deliver_info['jwconf']
video_info = self._download_json(
f'https://www.ultimedia.com/player/getConf/{self._IFRAME_MD_ID}/1/{video_id}', video_id,
note='Downloading player configuration')['video']
formats = []
for source in jwconf['playlist'][0]['sources']:
formats.append({
'url': source['file'],
'format_id': source.get('label'),
})
subtitles = {}
title = deliver_info['title']
thumbnail = jwconf.get('image')
duration = int_or_none(deliver_info.get('duration'))
timestamp = int_or_none(deliver_info.get('release_time'))
uploader_id = deliver_info.get('owner_id')
if hls_url := traverse_obj(video_info, ('media_sources', 'hls', 'hls_auto', {url_or_none})):
fmts, subs = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
formats.extend(fmts)
self._merge_subtitles(subs, target=subtitles)
for format_id, mp4_url in traverse_obj(video_info, ('media_sources', 'mp4', {dict.items}, ...)):
if not mp4_url:
continue
formats.append({
'url': mp4_url,
'format_id': format_id,
'height': int_or_none(format_id.partition('_')[2]),
'ext': 'mp4',
})
return {
'id': video_id,
'title': title,
'thumbnail': thumbnail,
'duration': duration,
'timestamp': timestamp,
'uploader_id': uploader_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(video_info, {
'title': ('title', {str}),
'thumbnail': ('image', {url_or_none}),
'duration': ('duration', {int_or_none}),
'timestamp': ('creationDate', {int_or_none}),
'uploader_id': ('ownerId', {str}),
}),
}

15
yt_dlp/extractor/dplay.py
View file

@ -1063,7 +1063,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
'ext': 'mp4',
'title': 'German Gold',
'description': 'md5:f3073306553a8d9b40e6ac4cdbf09fc6',
'display_id': 'german-gold',
'display_id': 'goldrausch-in-australien/german-gold',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 5',
@ -1112,7 +1112,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
'ext': 'mp4',
'title': '24 Stunden auf der Feuerwache 3',
'description': 'md5:f3084ef6170bfb79f9a6e0c030e09330',
'display_id': '24-stunden-auf-der-feuerwache-3',
'display_id': 'feuerwache-3-alarm-in-muenchen/24-stunden-auf-der-feuerwache-3',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 1',
@ -1134,7 +1134,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
'ext': 'mp4',
'title': 'Der Poltergeist im Kostümladen',
'description': 'md5:20b52b9736a0a3a7873d19a238fad7fc',
'display_id': 'der-poltergeist-im-kostumladen',
'display_id': 'ghost-adventures/der-poltergeist-im-kostumladen',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 25',
@ -1156,7 +1156,7 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
'ext': 'mp4',
'title': 'Das Geheimnis meines Bruders',
'description': 'md5:3167550bb582eb9c92875c86a0a20882',
'display_id': 'das-geheimnis-meines-bruders',
'display_id': 'evil-gesichter-des-boesen/das-geheimnis-meines-bruders',
'episode': 'Episode 1',
'episode_number': 1,
'season': 'Season 1',
@ -1175,18 +1175,19 @@ class DiscoveryNetworksDeIE(DiscoveryPlusBaseIE):
def _real_extract(self, url):
domain, programme, alternate_id = self._match_valid_url(url).groups()
display_id = f'{programme}/{alternate_id}'
meta = self._download_json(
f'https://de-api.loma-cms.com/feloma/videos/{alternate_id}/',
alternate_id, query={
display_id, query={
'environment': domain.split('.')[0],
'v': '2',
'filter[show.slug]': programme,
}, fatal=False)
video_id = traverse_obj(meta, ('uid', {str}, {lambda s: s[-7:]})) or alternate_id
video_id = traverse_obj(meta, ('uid', {str}, {lambda s: s[-7:]})) or display_id
disco_api_info = self._get_disco_api_info(
url, video_id, 'eu1-prod.disco-api.com', domain.replace('.', ''), 'DE')
disco_api_info['display_id'] = alternate_id
disco_api_info['display_id'] = display_id
disco_api_info['categories'] = traverse_obj(meta, (
'taxonomies', lambda _, v: v['category'] == 'genre', 'title', {str.strip}, filter, all, filter))

35
yt_dlp/extractor/firsttv.py
View file

@ -10,7 +10,7 @@ from ..utils import (
unified_strdate,
url_or_none,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import require, traverse_obj
class FirstTVIE(InfoExtractor):
@ -129,3 +129,36 @@ class FirstTVIE(InfoExtractor):
return self.playlist_result(
self._entries(items), display_id, self._og_search_title(webpage, default=None),
thumbnail=self._og_search_thumbnail(webpage, default=None))
class FirstTVLiveIE(InfoExtractor):
IE_NAME = '1tv:live'
IE_DESC = 'Первый канал (прямой эфир)'
_VALID_URL = r'https?://(?:www\.)?1tv\.ru/live'
_TESTS = [{
'url': 'https://www.1tv.ru/live',
'info_dict': {
'id': 'live',
'ext': 'mp4',
'title': r're:ПЕРВЫЙ КАНАЛ ПРЯМОЙ ЭФИР СМОТРЕТЬ ОНЛАЙН \d{4}-\d{2}-\d{2} \d{2}:\d{2}$',
'live_status': 'is_live',
},
'params': {'skip_download': 'livestream'},
}]
def _real_extract(self, url):
display_id = 'live'
webpage = self._download_webpage(url, display_id, fatal=False)
streams_list = self._download_json('https://stream.1tv.ru/api/playlist/1tvch-v1_as_array.json', display_id)
mpd_url = traverse_obj(streams_list, ('mpd', ..., {url_or_none}, any, {require('mpd url')}))
# FFmpeg needs to be passed -re to not seek past live window. This is handled by core
formats, _ = self._extract_mpd_formats_and_subtitles(mpd_url, display_id, mpd_id='dash')
return {
'id': display_id,
'title': self._html_extract_title(webpage),
'formats': formats,
'is_live': True,
}

66
yt_dlp/extractor/floatplane.py
View file

@ -6,15 +6,15 @@ from ..utils import (
OnDemandPagedList,
clean_html,
determine_ext,
float_or_none,
format_field,
int_or_none,
join_nonempty,
parse_codecs,
parse_iso8601,
url_or_none,
urljoin,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import require, traverse_obj
class FloatplaneBaseIE(InfoExtractor):
@ -50,37 +50,31 @@ class FloatplaneBaseIE(InfoExtractor):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
stream = self._download_json(
f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
'type': 'vod' if media_typ == 'video' else 'aod',
'guid': metadata['guid'],
}, note=f'Downloading {media_typ} stream data',
f'{self._BASE_URL}/api/v3/delivery/info', media_id,
query={'scenario': 'onDemand', 'entityId': media_id},
note=f'Downloading {media_typ} stream data',
impersonate=self._IMPERSONATE_TARGET)
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
metadata = self._download_json(
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id,
f'Downloading {media_typ} metadata', query={'id': media_id},
fatal=False, impersonate=self._IMPERSONATE_TARGET)
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
cdn_base_url = traverse_obj(stream, (
'groups', 0, 'origins', ..., 'url', {url_or_none}, any, {require('cdn base url')}))
formats = []
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
url = urljoin(stream['cdn'], format_path(traverse_obj(
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
format_id = traverse_obj(quality, ('name', {str}))
for variant in traverse_obj(stream, ('groups', 0, 'variants', lambda _, v: v['url'])):
format_url = urljoin(cdn_base_url, variant['url'])
format_id = traverse_obj(variant, ('name', {str}))
hls_aes = {}
m3u8_data = None
# If we need impersonation for the API, then we need it for HLS keys too: extract in advance
if self._IMPERSONATE_TARGET is not None:
m3u8_data = self._download_webpage(
url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
format_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
if not m3u8_data:
@ -98,18 +92,34 @@ class FloatplaneBaseIE(InfoExtractor):
hls_aes['key'] = urlh.read().hex()
formats.append({
**traverse_obj(quality, {
**traverse_obj(variant, {
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
'width': ('meta', 'video', 'width', {int_or_none}),
'height': ('meta', 'video', 'height', {int_or_none}),
'vcodec': ('meta', 'video', 'codec', {str}),
'acodec': ('meta', 'audio', 'codec', {str}),
'vbr': ('meta', 'video', 'bitrate', 'average', {int_or_none(scale=1000)}),
'abr': ('meta', 'audio', 'bitrate', 'average', {int_or_none(scale=1000)}),
'audio_channels': ('meta', 'audio', 'channelCount', {int_or_none}),
'fps': ('meta', 'video', 'fps', {float_or_none}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
'url': format_url,
'ext': determine_ext(format_url.partition('/chunk.m3u8')[0], 'mp4'),
'format_id': format_id,
'hls_media_playlist_data': m3u8_data,
'hls_aes': hls_aes or None,
})
subtitles = {}
automatic_captions = {}
for sub_data in traverse_obj(metadata, ('textTracks', lambda _, v: url_or_none(v['src']))):
sub_lang = sub_data.get('language') or 'en'
sub_entry = {'url': sub_data['src']}
if sub_data.get('generated'):
automatic_captions.setdefault(sub_lang, []).append(sub_entry)
else:
subtitles.setdefault(sub_lang, []).append(sub_entry)
items.append({
**common_info,
'id': media_id,
@ -119,6 +129,8 @@ class FloatplaneBaseIE(InfoExtractor):
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
'subtitles': subtitles,
'automatic_captions': automatic_captions,
})
post_info = {

164
yt_dlp/extractor/frontro.py Normal file
View file

@ -0,0 +1,164 @@
import json
from .common import InfoExtractor
from ..utils import int_or_none, parse_iso8601, url_or_none
from ..utils.traversal import traverse_obj
class FrontoBaseIE(InfoExtractor):
def _get_auth_headers(self, url):
return traverse_obj(self._get_cookies(url), {
'authorization': ('frAccessToken', 'value', {lambda token: f'Bearer {token}' if token else None}),
})
class FrontroVideoBaseIE(FrontoBaseIE):
_CHANNEL_ID = None
def _real_extract(self, url):
video_id = self._match_id(url)
metadata = self._download_json(
'https://api.frontrow.cc/query', video_id, data=json.dumps({
'operationName': 'Video',
'variables': {'channelID': self._CHANNEL_ID, 'videoID': video_id},
'query': '''query Video($channelID: ID!, $videoID: ID!) {
video(ChannelID: $channelID, VideoID: $videoID) {
... on Video {title description updatedAt thumbnail createdAt duration likeCount comments views url hasAccess}
}
}''',
}).encode(), headers={
'content-type': 'application/json',
**self._get_auth_headers(url),
})['data']['video']
if not traverse_obj(metadata, 'hasAccess'):
self.raise_login_required()
formats, subtitles = self._extract_m3u8_formats_and_subtitles(metadata['url'], video_id)
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
**traverse_obj(metadata, {
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('thumbnail', {url_or_none}),
'timestamp': ('createdAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
'duration': ('duration', {int_or_none}),
'like_count': ('likeCount', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'view_count': ('views', {int_or_none}),
}),
}
class FrontroGroupBaseIE(FrontoBaseIE):
_CHANNEL_ID = None
_VIDEO_EXTRACTOR = None
_VIDEO_URL_TMPL = None
def _real_extract(self, url):
group_id = self._match_id(url)
metadata = self._download_json(
'https://api.frontrow.cc/query', group_id, note='Downloading playlist metadata',
data=json.dumps({
'operationName': 'PaginatedStaticPageContainer',
'variables': {'channelID': self._CHANNEL_ID, 'first': 500, 'pageContainerID': group_id},
'query': '''query PaginatedStaticPageContainer($channelID: ID!, $pageContainerID: ID!) {
pageContainer(ChannelID: $channelID, PageContainerID: $pageContainerID) {
... on StaticPageContainer { id title updatedAt createdAt itemRefs {edges {node {
id contentItem { ... on ItemVideo { videoItem: item {
id
}}}
}}}
}
}
}''',
}).encode(), headers={
'content-type': 'application/json',
**self._get_auth_headers(url),
})['data']['pageContainer']
entries = []
for video_id in traverse_obj(metadata, (
'itemRefs', 'edges', ..., 'node', 'contentItem', 'videoItem', 'id', {str}),
):
entries.append(self.url_result(
self._VIDEO_URL_TMPL % video_id, self._VIDEO_EXTRACTOR, video_id))
return {
'_type': 'playlist',
'id': group_id,
'entries': entries,
**traverse_obj(metadata, {
'title': ('title', {str}),
'timestamp': ('createdAt', {parse_iso8601}),
'modified_timestamp': ('updatedAt', {parse_iso8601}),
}),
}
class TheChosenIE(FrontroVideoBaseIE):
_CHANNEL_ID = '12884901895'
_VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/video/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://watch.thechosen.tv/video/184683594325',
'md5': '3f878b689588c71b38ec9943c54ff5b0',
'info_dict': {
'id': '184683594325',
'ext': 'mp4',
'title': 'Season 3 Episode 2: Two by Two',
'description': 'md5:174c373756ecc8df46b403f4fcfbaf8c',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 4212,
'thumbnail': r're:https://fastly\.frontrowcdn\.com/channels/12884901895/VIDEO_THUMBNAIL/184683594325/',
'timestamp': 1698954546,
'upload_date': '20231102',
'modified_timestamp': int,
'modified_date': str,
},
}, {
'url': 'https://watch.thechosen.tv/video/184683596189',
'md5': 'd581562f9d29ce82f5b7770415334151',
'info_dict': {
'id': '184683596189',
'ext': 'mp4',
'title': 'Season 4 Episode 8: Humble',
'description': 'md5:20a57bead43da1cf77cd5b0fe29bbc76',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 5092,
'thumbnail': r're:https://fastly\.frontrowcdn\.com/channels/12884901895/VIDEO_THUMBNAIL/184683596189/',
'timestamp': 1715019474,
'upload_date': '20240506',
'modified_timestamp': int,
'modified_date': str,
},
}]
class TheChosenGroupIE(FrontroGroupBaseIE):
_CHANNEL_ID = '12884901895'
_VIDEO_EXTRACTOR = TheChosenIE
_VIDEO_URL_TMPL = 'https://watch.thechosen.tv/video/%s'
_VALID_URL = r'https?://(?:www\.)?watch\.thechosen\.tv/group/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://watch.thechosen.tv/group/309237658592',
'info_dict': {
'id': '309237658592',
'title': 'Season 3',
'timestamp': 1746203969,
'upload_date': '20250502',
'modified_timestamp': int,
'modified_date': str,
},
'playlist_count': 8,
}]

12
yt_dlp/extractor/goplay.py
View file

@ -13,12 +13,14 @@ from ..utils.traversal import get_first, traverse_obj
class GoPlayIE(InfoExtractor):
_VALID_URL = r'https?://(www\.)?goplay\.be/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
IE_NAME = 'play.tv'
IE_DESC = 'PLAY (formerly goplay.be)'
_VALID_URL = r'https?://(www\.)?play\.tv/video/([^/?#]+/[^/?#]+/|)(?P<id>[^/#]+)'
_NETRC_MACHINE = 'goplay'
_TESTS = [{
'url': 'https://www.goplay.be/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
'url': 'https://www.play.tv/video/de-slimste-mens-ter-wereld/de-slimste-mens-ter-wereld-s22/de-slimste-mens-ter-wereld-s22-aflevering-1',
'info_dict': {
'id': '2baa4560-87a0-421b-bffc-359914e3c387',
'ext': 'mp4',
@ -33,7 +35,7 @@ class GoPlayIE(InfoExtractor):
'params': {'skip_download': True},
'skip': 'This video is only available for registered users',
}, {
'url': 'https://www.goplay.be/video/1917',
'url': 'https://www.play.tv/video/1917',
'info_dict': {
'id': '40cac41d-8d29-4ef5-aa11-75047b9f0907',
'ext': 'mp4',
@ -43,7 +45,7 @@ class GoPlayIE(InfoExtractor):
'params': {'skip_download': True},
'skip': 'This video is only available for registered users',
}, {
'url': 'https://www.goplay.be/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
'url': 'https://www.play.tv/video/de-mol/de-mol-s11/de-mol-s11-aflevering-1#autoplay',
'info_dict': {
'id': 'ecb79672-92b9-4cd9-a0d7-e2f0250681ee',
'ext': 'mp4',
@ -101,7 +103,7 @@ class GoPlayIE(InfoExtractor):
break
api = self._download_json(
f'https://api.goplay.be/web/v1/videos/long-form/{video_id}',
f'https://api.play.tv/web/v1/videos/long-form/{video_id}',
video_id, headers={
'Authorization': f'Bearer {self._id_token}',
**self.geo_verification_headers(),

2
yt_dlp/extractor/jtbc.py
View file

@ -98,7 +98,7 @@ class JTBCIE(InfoExtractor):
formats = []
for stream_url in traverse_obj(playback_data, ('sources', 'HLS', ..., 'file', {url_or_none})):
stream_url = re.sub(r'/playlist(?:_pd\d+)?\.m3u8', '/index.m3u8', stream_url)
stream_url = re.sub(r'/playlist_pd\d+\.m3u8', '/playlist.m3u8', stream_url)
formats.extend(self._extract_m3u8_formats(stream_url, video_id, fatal=False))
metadata = self._download_json(

155
yt_dlp/extractor/mave.py
View file

@ -1,7 +1,9 @@
import re
import functools
import math
from .common import InfoExtractor
from ..utils import (
InAdvancePagedList,
clean_html,
int_or_none,
parse_iso8601,
@ -10,15 +12,64 @@ from ..utils import (
from ..utils.traversal import require, traverse_obj
class MaveIE(InfoExtractor):
_VALID_URL = r'https?://(?P<channel>[\w-]+)\.mave\.digital/(?P<id>ep-\d+)'
class MaveBaseIE(InfoExtractor):
_API_BASE_URL = 'https://api.mave.digital/v1/website'
_API_BASE_STORAGE_URL = 'https://store.cloud.mts.ru/mave/'
def _load_channel_meta(self, channel_id, display_id):
return traverse_obj(self._download_json(
f'{self._API_BASE_URL}/{channel_id}/', display_id,
note='Downloading channel metadata'), 'podcast')
def _load_episode_meta(self, channel_id, episode_code, display_id):
return self._download_json(
f'{self._API_BASE_URL}/{channel_id}/episodes/{episode_code}',
display_id, note='Downloading episode metadata')
def _create_entry(self, channel_id, channel_meta, episode_meta):
episode_code = traverse_obj(episode_meta, ('code', {int}, {require('episode code')}))
return {
'display_id': f'{channel_id}-{episode_code}',
'extractor_key': MaveIE.ie_key(),
'extractor': MaveIE.IE_NAME,
'webpage_url': f'https://{channel_id}.mave.digital/ep-{episode_code}',
'channel_id': channel_id,
'channel_url': f'https://{channel_id}.mave.digital/',
'vcodec': 'none',
**traverse_obj(episode_meta, {
'id': ('id', {str}),
'url': ('audio', {urljoin(self._API_BASE_STORAGE_URL)}),
'title': ('title', {str}),
'description': ('description', {clean_html}),
'thumbnail': ('image', {urljoin(self._API_BASE_STORAGE_URL)}),
'duration': ('duration', {int_or_none}),
'season_number': ('season', {int_or_none}),
'episode_number': ('number', {int_or_none}),
'view_count': ('listenings', {int_or_none}),
'like_count': ('reactions', lambda _, v: v['type'] == 'like', 'count', {int_or_none}, any),
'dislike_count': ('reactions', lambda _, v: v['type'] == 'dislike', 'count', {int_or_none}, any),
'age_limit': ('is_explicit', {bool}, {lambda x: 18 if x else None}),
'timestamp': ('publish_date', {parse_iso8601}),
}),
**traverse_obj(channel_meta, {
'series_id': ('id', {str}),
'series': ('title', {str}),
'channel': ('title', {str}),
'uploader': ('author', {str}),
}),
}
class MaveIE(MaveBaseIE):
IE_NAME = 'mave'
_VALID_URL = r'https?://(?P<channel_id>[\w-]+)\.mave\.digital/ep-(?P<episode_code>\d+)'
_TESTS = [{
'url': 'https://ochenlichnoe.mave.digital/ep-25',
'md5': 'aa3e513ef588b4366df1520657cbc10c',
'info_dict': {
'id': '4035f587-914b-44b6-aa5a-d76685ad9bc2',
'ext': 'mp3',
'display_id': 'ochenlichnoe-ep-25',
'display_id': 'ochenlichnoe-25',
'title': 'Между мной и миром: психология самооценки',
'description': 'md5:4b7463baaccb6982f326bce5c700382a',
'uploader': 'Самарский университет',
@ -45,7 +96,7 @@ class MaveIE(InfoExtractor):
'info_dict': {
'id': '41898bb5-ff57-4797-9236-37a8e537aa21',
'ext': 'mp3',
'display_id': 'budem-ep-12',
'display_id': 'budem-12',
'title': 'Екатерина Михайлова: "Горе от ума" не про женщин написана',
'description': 'md5:fa3bdd59ee829dfaf16e3efcb13f1d19',
'uploader': 'Полина Цветкова+Евгения Акопова',
@ -68,40 +119,72 @@ class MaveIE(InfoExtractor):
'upload_date': '20241230',
},
}]
_API_BASE_URL = 'https://api.mave.digital/'
def _real_extract(self, url):
channel_id, slug = self._match_valid_url(url).group('channel', 'id')
display_id = f'{channel_id}-{slug}'
webpage = self._download_webpage(url, display_id)
data = traverse_obj(
self._search_nuxt_json(webpage, display_id),
('data', lambda _, v: v['activeEpisodeData'], any, {require('podcast data')}))
channel_id, episode_code = self._match_valid_url(url).group(
'channel_id', 'episode_code')
display_id = f'{channel_id}-{episode_code}'
channel_meta = self._load_channel_meta(channel_id, display_id)
episode_meta = self._load_episode_meta(channel_id, episode_code, display_id)
return self._create_entry(channel_id, channel_meta, episode_meta)
class MaveChannelIE(MaveBaseIE):
IE_NAME = 'mave:channel'
_VALID_URL = r'https?://(?P<id>[\w-]+)\.mave\.digital/?(?:$|[?#])'
_TESTS = [{
'url': 'https://budem.mave.digital/',
'info_dict': {
'id': 'budem',
'title': 'Все там будем',
'description': 'md5:f04ae12a42be0f1d765c5e326b41987a',
},
'playlist_mincount': 15,
}, {
'url': 'https://ochenlichnoe.mave.digital/',
'info_dict': {
'id': 'ochenlichnoe',
'title': 'Очень личное',
'description': 'md5:ee36a6a52546b91b487fe08c552fdbb2',
},
'playlist_mincount': 20,
}, {
'url': 'https://geekcity.mave.digital/',
'info_dict': {
'id': 'geekcity',
'title': 'Мужчины в трико',
'description': 'md5:4164d425d60a0d97abdce9d1f6f8e049',
},
'playlist_mincount': 80,
}]
_PAGE_SIZE = 50
def _entries(self, channel_id, channel_meta, page_num):
page_data = self._download_json(
f'{self._API_BASE_URL}/{channel_id}/episodes', channel_id, query={
'view': 'all',
'page': page_num + 1,
'sort': 'newest',
'format': 'all',
}, note=f'Downloading page {page_num + 1}')
for ep in traverse_obj(page_data, ('episodes', lambda _, v: v['audio'] and v['id'])):
yield self._create_entry(channel_id, channel_meta, ep)
def _real_extract(self, url):
channel_id = self._match_id(url)
channel_meta = self._load_channel_meta(channel_id, channel_id)
return {
'display_id': display_id,
'channel_id': channel_id,
'channel_url': f'https://{channel_id}.mave.digital/',
'vcodec': 'none',
'thumbnail': re.sub(r'_\d+(?=\.(?:jpg|png))', '', self._og_search_thumbnail(webpage, default='')) or None,
**traverse_obj(data, ('activeEpisodeData', {
'url': ('audio', {urljoin(self._API_BASE_URL)}),
'id': ('id', {str}),
'_type': 'playlist',
'id': channel_id,
**traverse_obj(channel_meta, {
'title': ('title', {str}),
'description': ('description', {clean_html}),
'duration': ('duration', {int_or_none}),
'season_number': ('season', {int_or_none}),
'episode_number': ('number', {int_or_none}),
'view_count': ('listenings', {int_or_none}),
'like_count': ('reactions', lambda _, v: v['type'] == 'like', 'count', {int_or_none}, any),
'dislike_count': ('reactions', lambda _, v: v['type'] == 'dislike', 'count', {int_or_none}, any),
'age_limit': ('is_explicit', {bool}, {lambda x: 18 if x else None}),
'timestamp': ('publish_date', {parse_iso8601}),
})),
**traverse_obj(data, ('podcast', 'podcast', {
'series_id': ('id', {str}),
'series': ('title', {str}),
'channel': ('title', {str}),
'uploader': ('author', {str}),
})),
'description': ('description', {str}),
}),
'entries': InAdvancePagedList(
functools.partial(self._entries, channel_id, channel_meta),
math.ceil(channel_meta['episodes_count'] / self._PAGE_SIZE), self._PAGE_SIZE),
}

170
yt_dlp/extractor/medaltv.py
View file

@ -1,14 +1,9 @@
import re
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
format_field,
int_or_none,
str_or_none,
traverse_obj,
url_or_none,
)
from ..utils.traversal import traverse_obj
class MedalTVIE(InfoExtractor):
@ -30,25 +25,8 @@ class MedalTVIE(InfoExtractor):
'view_count': int,
'like_count': int,
'duration': 13,
},
}, {
'url': 'https://medal.tv/games/cod-cold-war/clips/2mA60jWAGQCBH',
'md5': 'fc7a3e4552ae8993c1c4006db46be447',
'info_dict': {
'id': '2mA60jWAGQCBH',
'ext': 'mp4',
'title': 'Quad Cold',
'description': 'Medal,https://medal.tv/desktop/',
'uploader': 'MowgliSB',
'timestamp': 1603165266,
'upload_date': '20201020',
'uploader_id': '10619174',
'thumbnail': 'https://cdn.medal.tv/10619174/thumbnail-34934644-720p.jpg?t=1080p&c=202042&missing',
'uploader_url': 'https://medal.tv/users/10619174',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 23,
'thumbnail': r're:https://cdn\.medal\.tv/ugcp/content-thumbnail/.*\.jpg',
'tags': ['headshot', 'valorant', '4k', 'clutch', 'mornu'],
},
}, {
'url': 'https://medal.tv/games/cod-cold-war/clips/2um24TWdty0NA',
@ -57,12 +35,12 @@ class MedalTVIE(InfoExtractor):
'id': '2um24TWdty0NA',
'ext': 'mp4',
'title': 'u tk me i tk u bigger',
'description': 'Medal,https://medal.tv/desktop/',
'uploader': 'Mimicc',
'description': '',
'uploader': 'zahl',
'timestamp': 1605580939,
'upload_date': '20201117',
'uploader_id': '5156321',
'thumbnail': 'https://cdn.medal.tv/5156321/thumbnail-36787208-360p.jpg?t=1080p&c=202046&missing',
'thumbnail': r're:https://cdn\.medal\.tv/source/.*\.png',
'uploader_url': 'https://medal.tv/users/5156321',
'comment_count': int,
'view_count': int,
@ -70,91 +48,77 @@ class MedalTVIE(InfoExtractor):
'duration': 9,
},
}, {
'url': 'https://medal.tv/games/valorant/clips/37rMeFpryCC-9',
'only_matching': True,
}, {
# API requires auth
'url': 'https://medal.tv/games/valorant/clips/2WRj40tpY_EU9',
'md5': '6c6bb6569777fd8b4ef7b33c09de8dcf',
'info_dict': {
'id': '2WRj40tpY_EU9',
'ext': 'mp4',
'title': '1v5 clutch',
'description': '',
'uploader': 'adny',
'uploader_id': '6256941',
'uploader_url': 'https://medal.tv/users/6256941',
'comment_count': int,
'view_count': int,
'like_count': int,
'duration': 25,
'thumbnail': r're:https://cdn\.medal\.tv/source/.*\.jpg',
'timestamp': 1612896680,
'upload_date': '20210209',
},
'expected_warnings': ['Video formats are not available through API'],
}, {
'url': 'https://medal.tv/games/valorant/clips/37rMeFpryCC-9',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id, query={'mobilebypass': 'true'})
hydration_data = self._search_json(
r'<script[^>]*>[^<]*\bhydrationData\s*=', webpage,
'next data', video_id, end_pattern='</script>', fatal=False)
clip = traverse_obj(hydration_data, ('clips', ...), get_all=False)
if not clip:
raise ExtractorError(
'Could not find video information.', video_id=video_id)
title = clip['contentTitle']
source_width = int_or_none(clip.get('sourceWidth'))
source_height = int_or_none(clip.get('sourceHeight'))
aspect_ratio = source_width / source_height if source_width and source_height else 16 / 9
def add_item(container, item_url, height, id_key='format_id', item_id=None):
item_id = item_id or '%dp' % height
if item_id not in item_url:
return
container.append({
'url': item_url,
id_key: item_id,
'width': round(aspect_ratio * height),
'height': height,
})
content_data = self._download_json(
f'https://medal.tv/api/content/{video_id}', video_id,
headers={'Accept': 'application/json'})
formats = []
thumbnails = []
for k, v in clip.items():
if not (v and isinstance(v, str)):
continue
mobj = re.match(r'(contentUrl|thumbnail)(?:(\d+)p)?$', k)
if not mobj:
continue
prefix = mobj.group(1)
height = int_or_none(mobj.group(2))
if prefix == 'contentUrl':
add_item(
formats, v, height or source_height,
item_id=None if height else 'source')
elif prefix == 'thumbnail':
add_item(thumbnails, v, height, 'id')
error = clip.get('error')
if not formats and error:
if error == 404:
self.raise_no_formats(
'That clip does not exist.',
expected=True, video_id=video_id)
else:
self.raise_no_formats(
f'An unknown error occurred ({error}).',
video_id=video_id)
# Necessary because the id of the author is not known in advance.
# Won't raise an issue if no profile can be found as this is optional.
author = traverse_obj(hydration_data, ('profiles', ...), get_all=False) or {}
author_id = str_or_none(author.get('userId'))
author_url = format_field(author_id, None, 'https://medal.tv/users/%s')
if m3u8_url := url_or_none(content_data.get('contentUrlHls')):
formats.extend(self._extract_m3u8_formats(m3u8_url, video_id, 'mp4', m3u8_id='hls'))
if http_url := url_or_none(content_data.get('contentUrl')):
formats.append({
'url': http_url,
'format_id': 'http-source',
'ext': 'mp4',
'quality': 1,
})
formats = [fmt for fmt in formats if 'video/privacy-protected-guest' not in fmt['url']]
if not formats:
# Fallback, does not require auth
self.report_warning('Video formats are not available through API, falling back to social video URL')
urlh = self._request_webpage(
f'https://medal.tv/api/content/{video_id}/socialVideoUrl', video_id,
note='Checking social video URL')
formats.append({
'url': urlh.url,
'format_id': 'social-video',
'ext': 'mp4',
'quality': -1,
})
return {
'id': video_id,
'title': title,
'formats': formats,
'thumbnails': thumbnails,
'description': clip.get('contentDescription'),
'uploader': author.get('displayName'),
'timestamp': float_or_none(clip.get('created'), 1000),
'uploader_id': author_id,
'uploader_url': author_url,
'duration': int_or_none(clip.get('videoLengthSeconds')),
'view_count': int_or_none(clip.get('views')),
'like_count': int_or_none(clip.get('likes')),
'comment_count': int_or_none(clip.get('comments')),
**traverse_obj(content_data, {
'title': ('contentTitle', {str}),
'description': ('contentDescription', {str}),
'timestamp': ('created', {int_or_none(scale=1000)}),
'duration': ('videoLengthSeconds', {int_or_none}),
'view_count': ('views', {int_or_none}),
'like_count': ('likes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'uploader': ('poster', 'displayName', {str}),
'uploader_id': ('poster', 'userId', {str}),
'uploader_url': ('poster', 'userId', {str}, filter, {lambda x: x and f'https://medal.tv/users/{x}'}),
'tags': ('tags', ..., {str}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
}),
}

92
yt_dlp/extractor/mux.py Normal file
View file

@ -0,0 +1,92 @@
import re
from .common import InfoExtractor
from ..utils import (
extract_attributes,
filter_dict,
parse_qs,
smuggle_url,
unsmuggle_url,
update_url_query,
)
from ..utils.traversal import traverse_obj
class MuxIE(InfoExtractor):
_VALID_URL = r'https?://(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)'
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//(?:stream\.new/v|player\.mux\.com)/(?P<id>[A-Za-z0-9-]+)[^"\']+)']
_TESTS = [{
'url': 'https://stream.new/v/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j/embed',
'info_dict': {
'ext': 'mp4',
'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
},
}, {
'url': 'https://player.mux.com/OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
'info_dict': {
'ext': 'mp4',
'id': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
'title': 'OCtRWZiZqKvLbnZ32WSEYiGNvHdAmB01j',
},
}]
_WEBPAGE_TESTS = [{
# iframe embed
'url': 'https://www.redbrickai.com/blog/2025-07-14-FAST-brush',
'info_dict': {
'ext': 'mp4',
'id': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
'title': 'cXhzAiW1AmsHY01eRbEYFcTEAn0102aGN8sbt8JprP6Dfw',
},
}, {
# mux-player embed
'url': 'https://muxvideo.2coders.com/download/',
'info_dict': {
'ext': 'mp4',
'id': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
'title': 'JBuasdg35Hw7tYmTe9k68QLPQKixL300YsWHDz5Flit8',
},
}, {
# mux-player with title metadata
'url': 'https://datastar-todomvc.cross.stream/',
'info_dict': {
'ext': 'mp4',
'id': 'KX01ZSZ8CXv5SVfVwMZKJTcuBcUQmo1ReS9U5JjoHm4k',
'title': 'TodoMVC with Datastar Tutorial',
},
}]
@classmethod
def _extract_embed_urls(cls, url, webpage):
yield from super()._extract_embed_urls(url, webpage)
for mux_player in re.findall(r'<mux-(?:player|video)\b[^>]*\bplayback-id=[^>]+>', webpage):
attrs = extract_attributes(mux_player)
playback_id = attrs.get('playback-id')
if not playback_id:
continue
token = attrs.get('playback-token') or traverse_obj(playback_id, ({parse_qs}, 'token', -1))
playback_id = playback_id.partition('?')[0]
embed_url = update_url_query(
f'https://player.mux.com/{playback_id}',
filter_dict({'playback-token': token}))
if title := attrs.get('metadata-video-title'):
embed_url = smuggle_url(embed_url, {'title': title})
yield embed_url
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
token = traverse_obj(parse_qs(url), ('playback-token', -1))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://stream.mux.com/{video_id}.m3u8', video_id, 'mp4',
query=filter_dict({'token': token}))
return {
'id': video_id,
'title': smuggled_data.get('title') or video_id,
'formats': formats,
'subtitles': subtitles,
}

79
yt_dlp/extractor/netapp.py Normal file
View file

@ -0,0 +1,79 @@
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from ..utils import parse_iso8601
from ..utils.traversal import require, traverse_obj
class NetAppBaseIE(InfoExtractor):
_BC_URL = 'https://players.brightcove.net/6255154784001/default_default/index.html?videoId={}'
@staticmethod
def _parse_metadata(item):
return traverse_obj(item, {
'title': ('name', {str}),
'description': ('description', {str}),
'timestamp': ('createdAt', {parse_iso8601}),
})
class NetAppVideoIE(NetAppBaseIE):
_VALID_URL = r'https?://media\.netapp\.com/video-detail/(?P<id>[0-9a-f-]+)'
_TESTS = [{
'url': 'https://media.netapp.com/video-detail/da25fc01-82ad-5284-95bc-26920200a222/seamless-storage-for-modern-kubernetes-deployments',
'info_dict': {
'id': '1843620950167202073',
'ext': 'mp4',
'title': 'Seamless storage for modern Kubernetes deployments',
'description': 'md5:1ee39e315243fe71fb90af2796037248',
'uploader_id': '6255154784001',
'duration': 2159.41,
'thumbnail': r're:https://house-fastly-signed-us-east-1-prod\.brightcovecdn\.com/image/.*\.jpg',
'tags': 'count:15',
'timestamp': 1758213949,
'upload_date': '20250918',
},
}, {
'url': 'https://media.netapp.com/video-detail/45593e5d-cf1c-5996-978c-c9081906e69f/unleash-ai-innovation-with-your-data-with-the-netapp-platform',
'only_matching': True,
}]
def _real_extract(self, url):
video_uuid = self._match_id(url)
metadata = self._download_json(
f'https://api.media.netapp.com/client/detail/{video_uuid}', video_uuid)
brightcove_video_id = traverse_obj(metadata, (
'sections', lambda _, v: v['type'] == 'Player', 'video', {str}, any, {require('brightcove video id')}))
video_item = traverse_obj(metadata, ('sections', lambda _, v: v['type'] == 'VideoDetail', any))
return self.url_result(
self._BC_URL.format(brightcove_video_id), BrightcoveNewIE, brightcove_video_id,
url_transparent=True, **self._parse_metadata(video_item))
class NetAppCollectionIE(NetAppBaseIE):
_VALID_URL = r'https?://media\.netapp\.com/collection/(?P<id>[0-9a-f-]+)'
_TESTS = [{
'url': 'https://media.netapp.com/collection/9820e190-f2a6-47ac-9c0a-98e5e64234a4',
'info_dict': {
'title': 'Featured sessions',
'id': '9820e190-f2a6-47ac-9c0a-98e5e64234a4',
},
'playlist_count': 4,
}]
def _entries(self, metadata):
for item in traverse_obj(metadata, ('items', lambda _, v: v['brightcoveVideoId'])):
brightcove_video_id = item['brightcoveVideoId']
yield self.url_result(
self._BC_URL.format(brightcove_video_id), BrightcoveNewIE, brightcove_video_id,
url_transparent=True, **self._parse_metadata(item))
def _real_extract(self, url):
collection_uuid = self._match_id(url)
metadata = self._download_json(
f'https://api.media.netapp.com/client/collection/{collection_uuid}', collection_uuid)
return self.playlist_result(self._entries(metadata), collection_uuid, playlist_title=metadata.get('name'))

37
yt_dlp/extractor/nowcanal.py Normal file
View file

@ -0,0 +1,37 @@
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
class NowCanalIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?nowcanal\.pt(?:/[\w-]+)+/detalhe/(?P<id>[\w-]+)'
_TESTS = [{
'url': 'https://www.nowcanal.pt/ultimas/detalhe/pedro-sousa-hjulmand-pode-ter-uma-saida-limpa-do-sporting-daqui-a-um-ano',
'md5': '047f17cb783e66e467d703e704bbc95d',
'info_dict': {
'id': '6376598467112',
'ext': 'mp4',
'title': 'Pedro Sousa «Hjulmand pode ter uma saída limpa do Sporting daqui a um ano»',
'description': '',
'uploader_id': '6108484330001',
'duration': 65.237,
'thumbnail': r're:^https://.+\.jpg',
'timestamp': 1754440620,
'upload_date': '20250806',
'tags': ['now'],
},
}, {
'url': 'https://www.nowcanal.pt/programas/frente-a-frente/detalhe/frente-a-frente-eva-cruzeiro-ps-e-rita-matias-chega',
'only_matching': True,
}]
_BC_URL_TMPL = 'https://players.brightcove.net/6108484330001/chhIqzukMq_default/index.html?videoId={}'
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
video_id = self._search_json(
r'videoHandler\.addBrightcoveVideoWithJson\(\[',
webpage, 'video data', display_id)['brightcoveVideoId']
return self.url_result(self._BC_URL_TMPL.format(video_id), BrightcoveNewIE)

151
yt_dlp/extractor/ntvru.py
View file

@ -1,17 +1,40 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
strip_or_none,
parse_iso8601,
unescapeHTML,
url_or_none,
xpath_text,
)
from ..utils.traversal import traverse_obj
class NTVRuIE(InfoExtractor):
IE_NAME = 'ntv.ru'
_VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/]+/)*(?P<id>[^/?#&]+)'
_VALID_URL = r'https?://(?:www\.)?ntv\.ru/(?:[^/#?]+/)*(?P<id>[^/?#&]+)'
_TESTS = [{
# JSON Api is geo restricted
'url': 'https://www.ntv.ru/peredacha/svoya_igra/m58980/o818800',
'md5': '818962a1b52747d446db7cd5be43e142',
'info_dict': {
'id': '2520563',
'ext': 'mp4',
'title': 'Участники: Ирина Петрова, Сергей Коновалов, Кристина Кораблина',
'description': 'md5:fcbd21cd45238a940b95550f9e178e3e',
'thumbnail': r're:^http://.*\.jpg',
'duration': 2462,
'view_count': int,
'comment_count': int,
'tags': ['игры и игрушки'],
'timestamp': 1761821096,
'upload_date': '20251030',
'release_timestamp': 1761821096,
'release_date': '20251030',
'modified_timestamp': 1761821096,
'modified_date': '20251030',
},
}, {
'url': 'http://www.ntv.ru/novosti/863142/',
'md5': 'ba7ea172a91cb83eb734cad18c10e723',
'info_dict': {
@ -22,31 +45,35 @@ class NTVRuIE(InfoExtractor):
'thumbnail': r're:^http://.*\.jpg',
'duration': 136,
'view_count': int,
'comment_count': int,
'tags': ['ВМС', 'захват', 'митинги', 'Севастополь', 'Украина'],
'timestamp': 1395222013,
'upload_date': '20140319',
'release_timestamp': 1395222013,
'release_date': '20140319',
'modified_timestamp': 1395222013,
'modified_date': '20140319',
},
}, {
'url': 'http://www.ntv.ru/video/novosti/750370/',
'md5': 'adecff79691b4d71e25220a191477124',
'info_dict': {
'id': '750370',
'ext': 'mp4',
'title': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'description': 'Родные пассажиров пропавшего Boeing не верят в трагический исход',
'thumbnail': r're:^http://.*\.jpg',
'duration': 172,
'view_count': int,
},
'skip': '404 Not Found',
}, {
# Requires unescapeHTML
'url': 'http://www.ntv.ru/peredacha/segodnya/m23700/o232416',
'md5': '82dbd49b38e3af1d00df16acbeab260c',
'info_dict': {
'id': '747480',
'ext': 'mp4',
'title': '«Сегодня». 21 марта 2014 года. 16:00',
'description': '«Сегодня». 21 марта 2014 года. 16:00',
'title': '"Сегодня". 21 марта 2014 года. 16:00 ',
'description': 'md5:bed80745ca72af557433195f51a02785',
'thumbnail': r're:^http://.*\.jpg',
'duration': 1496,
'view_count': int,
'comment_count': int,
'tags': ['Брюссель', 'гражданство', 'ЕС', 'Крым', 'ОСАГО', 'саммит', 'санкции', 'события', 'чиновники', 'рейтинг'],
'timestamp': 1395406951,
'upload_date': '20140321',
'release_timestamp': 1395406951,
'release_date': '20140321',
'modified_timestamp': 1395406951,
'modified_date': '20140321',
},
}, {
'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/',
@ -54,11 +81,19 @@ class NTVRuIE(InfoExtractor):
'info_dict': {
'id': '1126480',
'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»',
'title': 'Остросюжетный фильм "Кома"',
'description': 'md5:e79ffd0887425a0f05a58885c408d7d8',
'thumbnail': r're:^http://.*\.jpg',
'duration': 5592,
'duration': 5608,
'view_count': int,
'comment_count': int,
'tags': ['кино'],
'timestamp': 1432868572,
'upload_date': '20150529',
'release_timestamp': 1432868572,
'release_date': '20150529',
'modified_timestamp': 1432868572,
'modified_date': '20150529',
},
}, {
'url': 'http://www.ntv.ru/serial/Delo_vrachey/m31760/o233916/',
@ -66,11 +101,19 @@ class NTVRuIE(InfoExtractor):
'info_dict': {
'id': '751482',
'ext': 'mp4',
'title': '«Дело врачей»: «Деревце жизни»',
'description': '«Дело врачей»: «Деревце жизни»',
'title': '"Дело врачей": "Деревце жизни"',
'description': 'md5:d6fbf9193f880f50d9cbfbcc954161c1',
'thumbnail': r're:^http://.*\.jpg',
'duration': 2590,
'view_count': int,
'comment_count': int,
'tags': ['врачи', 'больницы'],
'timestamp': 1395882300,
'upload_date': '20140327',
'release_timestamp': 1395882300,
'release_date': '20140327',
'modified_timestamp': 1395882300,
'modified_date': '20140327',
},
}, {
# Schemeless file URL
@ -78,48 +121,26 @@ class NTVRuIE(InfoExtractor):
'only_matching': True,
}]
_VIDEO_ID_REGEXES = [
r'<meta property="og:url" content="https?://www\.ntv\.ru/video/(\d+)',
r'<meta property="og:video:(?:url|iframe)" content="https?://www\.ntv\.ru/embed/(\d+)',
r'<video embed=[^>]+><id>(\d+)</id>',
r'<video restriction[^>]+><key>(\d+)</key>',
]
def _real_extract(self, url):
video_id = self._match_id(url)
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage = self._download_webpage(url, video_id)
video_url = self._og_search_property(
('video', 'video:iframe'), webpage, default=None)
if video_url:
video_id = self._search_regex(
r'https?://(?:www\.)?ntv\.ru/video/(?:embed/)?(\d+)',
video_url, 'video id', default=None)
if not video_id:
video_id = self._html_search_regex(
self._VIDEO_ID_REGEXES, webpage, 'video id')
video_id = self._html_search_regex(
r'<meta property="ya:ovs:feed_url" content="https?://www\.ntv\.ru/(?:exp/)?video/(\d+)', webpage, 'video id')
player = self._download_xml(
f'http://www.ntv.ru/vi{video_id}/',
video_id, 'Downloading video XML')
title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True)))
video = player.find('./data/video')
formats = []
for format_id in ['', 'hi', 'webm']:
file_ = xpath_text(video, f'./{format_id}file')
if not file_:
video_url = url_or_none(xpath_text(video, f'./{format_id}file'))
if not video_url:
continue
if file_.startswith('//'):
file_ = self._proto_relative_url(file_)
elif not file_.startswith('http'):
file_ = 'http://media.ntv.ru/vod/' + file_
formats.append({
'url': file_,
'url': video_url,
'filesize': int_or_none(xpath_text(video, f'./{format_id}size')),
})
hls_manifest = xpath_text(video, './playback/hls')
@ -131,12 +152,28 @@ class NTVRuIE(InfoExtractor):
formats.extend(self._extract_mpd_formats(
dash_manifest, video_id, mpd_id='dash', fatal=False))
metadata = self._download_xml(
f'https://www.ntv.ru/exp/video/{video_id}', video_id, 'Downloading XML metadata', fatal=False)
return {
'id': xpath_text(video, './id'),
'title': title,
'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))),
'thumbnail': xpath_text(video, './splash'),
'duration': int_or_none(xpath_text(video, './totaltime')),
'view_count': int_or_none(xpath_text(video, './views')),
'id': video_id,
'formats': formats,
**traverse_obj(player, {
'title': ('data/title/text()', ..., {str}, {unescapeHTML}, any),
'description': ('data/description/text()', ..., {str}, {unescapeHTML}, any),
'duration': ('data/video/totaltime/text()', ..., {int_or_none}, any),
'view_count': ('data/video/views/text()', ..., {int_or_none}, any),
'thumbnail': ('data/video/splash/text()', ..., {url_or_none}, any),
}),
**traverse_obj(metadata, {
'title': ('{*}title/text()', ..., {str}, {unescapeHTML}, any),
'description': ('{*}description/text()', ..., {str}, {unescapeHTML}, any),
'duration': ('{*}duration/text()', ..., {int_or_none}, any),
'timestamp': ('{*}create_date/text()', ..., {parse_iso8601}, any),
'release_timestamp': ('{*}upload_date/text()', ..., {parse_iso8601}, any),
'modified_timestamp': ('{*}modify_date/text()', ..., {parse_iso8601}, any),
'tags': ('{*}tag/text()', ..., {str}, {lambda x: x.split(',')}, ..., {str.strip}, filter),
'view_count': ('{*}stats/views_total/text()', ..., {int_or_none}, any),
'comment_count': ('{*}stats/comments/text()', ..., {int_or_none}, any),
}),
}

39
yt_dlp/extractor/rinsefm.py
View file

@ -3,12 +3,14 @@ from ..utils import (
MEDIA_EXTENSIONS,
determine_ext,
parse_iso8601,
traverse_obj,
url_or_none,
)
from ..utils.traversal import traverse_obj
class RinseFMBaseIE(InfoExtractor):
_API_BASE = 'https://rinse.fm/api/query/v1'
@staticmethod
def _parse_entry(entry):
return {
@ -45,8 +47,10 @@ class RinseFMIE(RinseFMBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
entry = self._search_nextjs_data(webpage, display_id)['props']['pageProps']['entry']
entry = self._download_json(
f'{self._API_BASE}/episodes/{display_id}', display_id,
note='Downloading episode data from API')['entry']
return self._parse_entry(entry)
@ -58,32 +62,35 @@ class RinseFMArtistPlaylistIE(RinseFMBaseIE):
'info_dict': {
'id': 'resources',
'title': '[re]sources',
'description': '[re]sources est un label parisien piloté par le DJ et producteur Tommy Kid.',
'description': 'md5:fd6a7254e8273510e6d49fbf50edf392',
},
'playlist_mincount': 40,
}, {
'url': 'https://rinse.fm/shows/ivy/',
'url': 'https://www.rinse.fm/shows/esk',
'info_dict': {
'id': 'ivy',
'title': '[IVY]',
'description': 'A dedicated space for DNB/Turbo House and 4x4.',
'id': 'esk',
'title': 'Esk',
'description': 'md5:5893d7c1d411ae8dea7fba12f109aa98',
},
'playlist_mincount': 7,
'playlist_mincount': 139,
}]
def _entries(self, data):
for episode in traverse_obj(data, (
'props', 'pageProps', 'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
'episodes', lambda _, v: determine_ext(v['fileUrl']) in MEDIA_EXTENSIONS.audio),
):
yield self._parse_entry(episode)
def _real_extract(self, url):
playlist_id = self._match_id(url)
webpage = self._download_webpage(url, playlist_id)
title = self._og_search_title(webpage) or self._html_search_meta('title', webpage)
description = self._og_search_description(webpage) or self._html_search_meta(
'description', webpage)
data = self._search_nextjs_data(webpage, playlist_id)
api_data = self._download_json(
f'{self._API_BASE}/shows/{playlist_id}', playlist_id,
note='Downloading show data from API')
return self.playlist_result(
self._entries(data), playlist_id, title, description=description)
self._entries(api_data), playlist_id,
**traverse_obj(api_data, ('entry', {
'title': ('title', {str}),
'description': ('description', {str}),
})))

8
yt_dlp/extractor/soundcloud.py
View file

@ -1064,7 +1064,7 @@ class SoundcloudRelatedIE(SoundcloudPagedPlaylistBaseIE):
class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
_VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
_VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?:soundcloud(?:%3A|:)playlists(?:%3A|:))?(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
IE_NAME = 'soundcloud:playlist'
_TESTS = [{
'url': 'https://api.soundcloud.com/playlists/4110309',
@ -1079,6 +1079,12 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
'album': 'TILT Brass - Bowery Poetry Club, August \'03 [Non-Site SCR 02]',
},
'playlist_count': 6,
}, {
'url': 'https://api.soundcloud.com/playlists/soundcloud%3Aplaylists%3A1759227795',
'only_matching': True,
}, {
'url': 'https://api.soundcloud.com/playlists/soundcloud:playlists:2104769627?secret_token=s-wmpCLuExeYX',
'only_matching': True,
}]
def _real_extract(self, url):

4
yt_dlp/extractor/sproutvideo.py
View file

@ -101,8 +101,8 @@ class SproutVideoIE(InfoExtractor):
webpage = self._download_webpage(
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
data = self._search_json(
r'(?:var|const|let)\s+(?:dat|(?:player|video)Info|)\s*=\s*["\']', webpage, 'player info',
video_id, contains_pattern=r'[A-Za-z0-9+/=]+', end_pattern=r'["\'];',
r'(?:window\.|(?:var|const|let)\s+)(?:dat|(?:player|video)Info|)\s*=\s*["\']', webpage,
'player info', video_id, contains_pattern=r'[A-Za-z0-9+/=]+', end_pattern=r'["\'];',
transform_source=lambda x: base64.b64decode(x).decode())
# SproutVideo may send player info for 'SMPTE Color Monitor Test' [a791d7b71b12ecc52e]

70
yt_dlp/extractor/thisoldhouse.py
View file

@ -1,18 +1,17 @@
import json
import urllib.parse
from .brightcove import BrightcoveNewIE
from .common import InfoExtractor
from .zype import ZypeIE
from ..networking import HEADRequest
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
filter_dict,
parse_qs,
smuggle_url,
try_call,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class ThisOldHouseIE(InfoExtractor):
@ -77,46 +76,43 @@ class ThisOldHouseIE(InfoExtractor):
'only_matching': True,
}]
_LOGIN_URL = 'https://login.thisoldhouse.com/usernamepassword/login'
def _perform_login(self, username, password):
self._request_webpage(
HEADRequest('https://www.thisoldhouse.com/insider'), None, 'Requesting session cookies')
urlh = self._request_webpage(
'https://www.thisoldhouse.com/wp-login.php', None, 'Requesting login info',
errnote='Unable to login', query={'redirect_to': 'https://www.thisoldhouse.com/insider'})
login_page = self._download_webpage(
'https://www.thisoldhouse.com/insider-login', None, 'Downloading login page')
hidden_inputs = self._hidden_inputs(login_page)
response = self._download_json(
'https://www.thisoldhouse.com/wp-admin/admin-ajax.php', None, 'Logging in',
headers={
'Accept': 'application/json',
'X-Requested-With': 'XMLHttpRequest',
}, data=urlencode_postdata(filter_dict({
'action': 'onebill_subscriber_login',
'email': username,
'password': password,
'pricingPlanTerm': hidden_inputs['pricing_plan_term'],
'utm_parameters': hidden_inputs.get('utm_parameters'),
'nonce': hidden_inputs['mdcr_onebill_login_nonce'],
})))
try:
auth_form = self._download_webpage(
self._LOGIN_URL, None, 'Submitting credentials', headers={
'Content-Type': 'application/json',
'Referer': urlh.url,
}, data=json.dumps(filter_dict({
**{('client_id' if k == 'client' else k): v[0] for k, v in parse_qs(urlh.url).items()},
'tenant': 'thisoldhouse',
'username': username,
'password': password,
'popup_options': {},
'sso': True,
'_csrf': try_call(lambda: self._get_cookies(self._LOGIN_URL)['_csrf'].value),
'_intstate': 'deprecated',
}), separators=(',', ':')).encode())
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
message = traverse_obj(response, ('data', 'message', {str}))
if not response['success']:
if message and 'Something went wrong' in message:
raise ExtractorError('Invalid username or password', expected=True)
raise
self._request_webpage(
'https://login.thisoldhouse.com/login/callback', None, 'Completing login',
data=urlencode_postdata(self._hidden_inputs(auth_form)))
raise ExtractorError(message or 'Login was unsuccessful')
if message and 'Your subscription is not active' in message:
self.report_warning(
f'{self.IE_NAME} said your subscription is not active. '
f'If your subscription is active, this could be caused by too many sign-ins, '
f'and you should instead try using {self._login_hint(method="cookies")[4:]}')
else:
self.write_debug(f'{self.IE_NAME} said: {message}')
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
if 'To Unlock This content' in webpage:
self.raise_login_required(
'This video is only available for subscribers. '
'Note that --cookies-from-browser may not work due to this site using session cookies')
webpage, urlh = self._download_webpage_handle(url, display_id)
# If login response says inactive subscription, site redirects to frontpage for Insider content
if 'To Unlock This content' in webpage or urllib.parse.urlparse(urlh.url).path in ('', '/'):
self.raise_login_required('This video is only available for subscribers')
video_url, video_id = self._search_regex(
r'<iframe[^>]+src=[\'"]((?:https?:)?//(?:www\.)?thisoldhouse\.(?:chorus\.build|com)/videos/zype/([0-9a-f]{24})[^\'"]*)[\'"]',

12
yt_dlp/extractor/tubetugraz.py
View file

@ -136,8 +136,10 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
IE_DESC = 'tube.tugraz.at'
_VALID_URL = r'''(?x)
https?://tube\.tugraz\.at/paella/ui/watch.html\?id=
(?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
https?://tube\.tugraz\.at/(?:
paella/ui/watch\.html\?(?:[^#]*&)?id=|
portal/watch/
)(?P<id>[0-9a-fA-F]{8}-(?:[0-9a-fA-F]{4}-){3}[0-9a-fA-F]{12})
'''
_TESTS = [
{
@ -149,9 +151,9 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
'title': '#6 (23.11.2017)',
'episode': '#6 (23.11.2017)',
'series': '[INB03001UF] Einführung in die strukturierte Programmierung',
'creator': 'Safran C',
'duration': 3295818,
'series_id': 'b1192fff-2aa7-4bf0-a5cf-7b15c3bd3b34',
'creators': ['Safran C'],
},
}, {
'url': 'https://tube.tugraz.at/paella/ui/watch.html?id=2df6d787-e56a-428d-8ef4-d57f07eef238',
@ -162,6 +164,10 @@ class TubeTuGrazIE(TubeTuGrazBaseIE):
'ext': 'mp4',
},
'expected_warnings': ['Extractor failed to obtain "title"'],
}, {
# Portal URL format
'url': 'https://tube.tugraz.at/portal/watch/ab28ec60-8cbe-4f1a-9b96-a95add56c612',
'only_matching': True,
},
]

48
yt_dlp/extractor/twitch.py
View file

@ -41,16 +41,16 @@ class TwitchBaseIE(InfoExtractor):
_NETRC_MACHINE = 'twitch'
_OPERATION_HASHES = {
'CollectionSideBar': '27111f1b382effad0b6def325caef1909c733fe6a4fbabf54f8d491ef2cf2f14',
'FilterableVideoTower_Videos': 'a937f1d22e269e39a03b509f65a7490f9fc247d7f83d6ac1421523e3b68042cb',
'ClipsCards__User': 'b73ad2bfaecfd30a9e6c28fada15bd97032c83ec77a0440766a56fe0bd632777',
'ShareClipRenderStatus': 'e0a46b287d760c6890a39d1ccd736af5ec9479a267d02c710e9ac33326b651d2',
'ChannelCollectionsContent': '447aec6a0cc1e8d0a8d7732d47eb0762c336a2294fdb009e9c9d854e49d484b9',
'StreamMetadata': 'a647c2a13599e5991e175155f798ca7f1ecddde73f7f341f39009c14dbf59962',
'CollectionSideBar': '016e1e4ccee0eb4698eb3bf1a04dc1c077fb746c78c82bac9a8f0289658fbd1a',
'FilterableVideoTower_Videos': '67004f7881e65c297936f32c75246470629557a393788fb5a69d6d9a25a8fd5f',
'ClipsCards__User': '90c33f5e6465122fba8f9371e2a97076f9ed06c6fed3788d002ab9eba8f91d88',
'ShareClipRenderStatus': '1844261bb449fa51e6167040311da4a7a5f1c34fe71c71a3e0c4f551bc30c698',
'ChannelCollectionsContent': '5247910a19b1cd2b760939bf4cba4dcbd3d13bdf8c266decd16956f6ef814077',
'StreamMetadata': 'b57f9b910f8cd1a4659d894fe7550ccc81ec9052c01e438b290fd66a040b9b93',
'ComscoreStreamingQuery': 'e1edae8122517d013405f237ffcc124515dc6ded82480a88daef69c83b53ac01',
'VideoPreviewOverlay': '3006e77e51b128d838fa4e835723ca4dc9a05c5efd4466c1085215c6e437e65c',
'VideoMetadata': '49b5b8f268cdeb259d75b58dcb0c1a748e3b575003448a2333dc5cdafd49adad',
'VideoPlayer_ChapterSelectButtonVideo': '8d2793384aac3773beab5e59bd5d6f585aedb923d292800119e03d40cd0f9b41',
'VideoPreviewOverlay': '9515480dee68a77e667cb19de634739d33f243572b007e98e67184b1a5d8369f',
'VideoMetadata': '45111672eea2e507f8ba44d101a61862f9c56b11dee09a15634cb75cb9b9084d',
'VideoPlayer_ChapterSelectButtonVideo': '71835d5ef425e154bf282453a926d99b328cdc5e32f36d3a209d0f4778b41203',
'VideoPlayer_VODSeekbarPreviewVideo': '07e99e4d56c5a7c67117a154777b0baf85a5ffefa393b213f4bc712ccaf85dd6',
}
@ -621,15 +621,15 @@ def _make_video_result(node):
class TwitchCollectionIE(TwitchBaseIE):
IE_NAME = 'twitch:collection'
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/collections/(?P<id>[^/]+)'
_TESTS = [{
'url': 'https://www.twitch.tv/collections/wlDCoH0zEBZZbQ',
'url': 'https://www.twitch.tv/collections/o9zZer3IQBhTJw',
'info_dict': {
'id': 'wlDCoH0zEBZZbQ',
'title': 'Overthrow Nook, capitalism for children',
'id': 'o9zZer3IQBhTJw',
'title': 'Playthrough Archives',
},
'playlist_mincount': 13,
'playlist_mincount': 21,
}]
_OPERATION_NAME = 'CollectionSideBar'
@ -720,8 +720,8 @@ class TwitchVideosBaseIE(TwitchPlaylistBaseIE):
class TwitchVideosIE(TwitchVideosBaseIE):
IE_NAME = 'twitch:videos'
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:videos|profile)'
_TESTS = [{
# All Videos sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=all',
@ -729,7 +729,7 @@ class TwitchVideosIE(TwitchVideosBaseIE):
'id': 'spamfish',
'title': 'spamfish - All Videos sorted by Date',
},
'playlist_mincount': 924,
'playlist_mincount': 751,
}, {
# All Videos sorted by Popular
'url': 'https://www.twitch.tv/spamfish/videos?filter=all&sort=views',
@ -737,8 +737,9 @@ class TwitchVideosIE(TwitchVideosBaseIE):
'id': 'spamfish',
'title': 'spamfish - All Videos sorted by Popular',
},
'playlist_mincount': 931,
'playlist_mincount': 754,
}, {
# TODO: Investigate why we get 0 entries
# Past Broadcasts sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=archives',
'info_dict': {
@ -753,8 +754,9 @@ class TwitchVideosIE(TwitchVideosBaseIE):
'id': 'spamfish',
'title': 'spamfish - Highlights sorted by Date',
},
'playlist_mincount': 901,
'playlist_mincount': 751,
}, {
# TODO: Investigate why we get 0 entries
# Uploads sorted by Date
'url': 'https://www.twitch.tv/esl_csgo/videos?filter=uploads&sort=time',
'info_dict': {
@ -763,6 +765,7 @@ class TwitchVideosIE(TwitchVideosBaseIE):
},
'playlist_mincount': 5,
}, {
# TODO: Investigate why we get 0 entries
# Past Premieres sorted by Date
'url': 'https://www.twitch.tv/spamfish/videos?filter=past_premieres',
'info_dict': {
@ -825,8 +828,8 @@ class TwitchVideosIE(TwitchVideosBaseIE):
class TwitchVideosClipsIE(TwitchPlaylistBaseIE):
IE_NAME = 'twitch:videos:clips'
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/(?:clips|videos/*?\?.*?\bfilter=clips)'
_TESTS = [{
# Clips
'url': 'https://www.twitch.tv/vanillatv/clips?filter=clips&range=all',
@ -898,8 +901,8 @@ class TwitchVideosClipsIE(TwitchPlaylistBaseIE):
class TwitchVideosCollectionsIE(TwitchPlaylistBaseIE):
IE_NAME = 'twitch:videos:collections'
_VALID_URL = r'https?://(?:(?:www|go|m)\.)?twitch\.tv/(?P<id>[^/]+)/videos/*?\?.*?\bfilter=collections'
_TESTS = [{
# Collections
'url': 'https://www.twitch.tv/spamfish/videos?filter=collections',
@ -1050,7 +1053,10 @@ class TwitchStreamIE(TwitchVideosBaseIE):
gql = self._download_gql(
channel_name, [{
'operationName': 'StreamMetadata',
'variables': {'channelLogin': channel_name},
'variables': {
'channelLogin': channel_name,
'includeIsDJ': True,
},
}, {
'operationName': 'ComscoreStreamingQuery',
'variables': {

48
yt_dlp/extractor/urplay.py
View file

@ -7,15 +7,15 @@ from ..utils import (
parse_age_limit,
try_get,
unified_timestamp,
url_or_none,
)
from ..utils.traversal import traverse_obj
from ..utils.traversal import require, traverse_obj
class URPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?ur(?:play|skola)\.se/(?:program|Produkter)/(?P<id>[0-9]+)'
_TESTS = [{
'url': 'https://urplay.se/program/203704-ur-samtiden-livet-universum-och-rymdens-markliga-musik-om-vetenskap-kritiskt-tankande-och-motstand',
'md5': '5ba36643c77cc3d34ffeadad89937d1e',
'info_dict': {
'id': '203704',
'ext': 'mp4',
@ -31,6 +31,7 @@ class URPlayIE(InfoExtractor):
'episode': 'Om vetenskap, kritiskt tänkande och motstånd',
'age_limit': 15,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://urplay.se/program/222967-en-foralders-dagbok-mitt-barn-skadar-sig-sjalv',
'info_dict': {
@ -49,6 +50,7 @@ class URPlayIE(InfoExtractor):
'tags': 'count:7',
'episode': 'Mitt barn skadar sig själv',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://urskola.se/Produkter/190031-Tripp-Trapp-Trad-Sovkudde',
'info_dict': {
@ -68,6 +70,27 @@ class URPlayIE(InfoExtractor):
'episode': 'Sovkudde',
'season': 'Säsong 1',
},
'params': {'skip_download': 'm3u8'},
}, {
# Only accessible through new media api
'url': 'https://urplay.se/program/242932-vulkanernas-krafter-fran-kraftfull-till-forgorande',
'info_dict': {
'id': '242932',
'ext': 'mp4',
'title': 'Vulkanernas krafter : Från kraftfull till förgörande',
'description': 'md5:742bb87048e7d5a7f209d28f9bb70ab1',
'age_limit': 15,
'duration': 2613,
'thumbnail': 'https://assets.ur.se/id/242932/images/1_hd.jpg',
'categories': ['Vetenskap & teknik'],
'tags': ['Geofysik', 'Naturvetenskap', 'Vulkaner', 'Vulkanutbrott'],
'series': 'Vulkanernas krafter',
'episode': 'Från kraftfull till förgörande',
'episode_number': 2,
'timestamp': 1763514000,
'upload_date': '20251119',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://urskola.se/Produkter/155794-Smasagor-meankieli-Grodan-i-vida-varlden',
'only_matching': True,
@ -88,21 +111,12 @@ class URPlayIE(InfoExtractor):
webpage, 'urplayer data'), video_id)['accessibleEpisodes']
urplayer_data = next(e for e in accessible_episodes if e.get('id') == int_or_none(video_id))
episode = urplayer_data['title']
host = self._download_json('http://streaming-loadbalancer.ur.se/loadbalancer.json', video_id)['redirect']
formats = []
urplayer_streams = urplayer_data.get('streamingInfo', {})
for k, v in urplayer_streams.get('raw', {}).items():
if not (k in ('sd', 'hd', 'mp3', 'm4a') and isinstance(v, dict)):
continue
file_http = v.get('location')
if file_http:
formats.extend(self._extract_wowza_formats(
f'http://{host}/{file_http}playlist.m3u8',
video_id, skip_protocols=['f4m', 'rtmp', 'rtsp']))
subtitles = {}
sources = self._download_json(
f'https://media-api.urplay.se/config-streaming/v1/urplay/sources/{video_id}', video_id,
note='Downloading streaming information')
hls_url = traverse_obj(sources, ('sources', 'hls', {url_or_none}, {require('HLS URL')}))
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
hls_url, video_id, 'mp4', m3u8_id='hls')
def parse_lang_code(code):
"3-character language code or None (utils candidate)"

31
yt_dlp/extractor/xhamster.py
View file

@ -60,6 +60,37 @@ class _ByteGenerator:
s = to_signed_32(s * to_signed_32(0xc2b2ae3d))
return to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 16))
def _algo4(self, s):
# Custom scrambling function involving a left rotation (ROL)
s = self._s = to_signed_32(s + 0x6d2b79f5)
s = to_signed_32((s << 7) | ((s & 0xFFFFFFFF) >> 25)) # ROL 7
s = to_signed_32(s + 0x9e3779b9)
s = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 11))
return to_signed_32(s * 0x27d4eb2d)
def _algo5(self, s):
# xorshift variant with a final addition
s = to_signed_32(s ^ (s << 7))
s = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 9))
s = to_signed_32(s ^ (s << 8))
s = self._s = to_signed_32(s + 0xa5a5a5a5)
return s
def _algo6(self, s):
# LCG (a=0x2c9277b5, c=0xac564b05) with a variable right shift scrambler
s = self._s = to_signed_32(s * to_signed_32(0x2c9277b5) + to_signed_32(0xac564b05))
s2 = to_signed_32(s ^ ((s & 0xFFFFFFFF) >> 18))
shift = (s & 0xFFFFFFFF) >> 27 & 31
return to_signed_32((s2 & 0xFFFFFFFF) >> shift)
def _algo7(self, s):
# Weyl Sequence (k=0x9e3779b9) + custom multiply-xor-shift mixing function
s = self._s = to_signed_32(s + to_signed_32(0x9e3779b9))
e = to_signed_32(s ^ (s << 5))
e = to_signed_32(e * to_signed_32(0x7feb352d))
e = to_signed_32(e ^ ((e & 0xFFFFFFFF) >> 15))
return to_signed_32(e * to_signed_32(0x846ca68b))
def __next__(self):
return self._algorithm(self._s) & 0xFF

67
yt_dlp/extractor/yfanefa.py Normal file
View file

@ -0,0 +1,67 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
int_or_none,
join_nonempty,
remove_end,
url_or_none,
)
from ..utils.traversal import traverse_obj
class YfanefaIE(InfoExtractor):
IE_NAME = 'yfanefa'
_VALID_URL = r'https?://(?:www\.)?yfanefa\.com/(?P<id>[^?#]+)'
_TESTS = [{
'url': 'https://www.yfanefa.com/record/2717',
'info_dict': {
'id': 'record-2717',
'ext': 'mp4',
'title': 'THE HALLAMSHIRE RIFLES LEAVING SHEFFIELD, 1914',
'duration': 5239,
'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
},
}, {
'url': 'https://www.yfanefa.com/news/53',
'info_dict': {
'id': 'news-53',
'ext': 'mp4',
'title': 'Memory Bank: Bradford Launch',
'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
},
}, {
'url': 'https://www.yfanefa.com/evaluating_nature_matters',
'info_dict': {
'id': 'evaluating_nature_matters',
'ext': 'mp4',
'title': 'Evaluating Nature Matters',
'thumbnail': r're:https://media\.yfanefa\.com/storage/v1/file/',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player_data = self._search_json(
r'iwPlayer\.options\["[\w.]+"\]\s*=', webpage, 'player options', video_id)
formats = []
video_url = join_nonempty(player_data['url'], player_data.get('signature'), delim='')
if determine_ext(video_url) == 'm3u8':
formats = self._extract_m3u8_formats(
video_url, video_id, 'mp4', m3u8_id='hls')
else:
formats = [{'url': video_url, 'ext': 'mp4'}]
return {
'id': video_id.strip('/').replace('/', '-'),
'title':
self._og_search_title(webpage, default=None)
or remove_end(self._html_extract_title(webpage), ' | Yorkshire Film Archive'),
'formats': formats,
**traverse_obj(player_data, {
'thumbnail': ('preview', {url_or_none}),
'duration': ('duration', {int_or_none}),
}),
}

11
yt_dlp/extractor/youtube/_base.py
View file

@ -327,6 +327,17 @@ INNERTUBE_CLIENTS = {
# See: https://github.com/youtube/cobalt/blob/main/cobalt/browser/user_agent/user_agent_platform_info.cc#L506
'AUTHENTICATED_USER_AGENT': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/25.lts.30.1034943-gold (unlike Gecko), Unknown_TV_Unknown_0/Unknown (Unknown, Unknown)',
},
'tv_downgraded': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5',
'clientVersion': '5.20251105',
'userAgent': 'Mozilla/5.0 (ChromiumStylePlatform) Cobalt/Version',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
'SUPPORTS_COOKIES': True,
},
'tv_simply': {
'INNERTUBE_CONTEXT': {
'client': {

5
yt_dlp/extractor/youtube/_tab.py
View file

@ -340,8 +340,9 @@ class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
thumbnails=self._extract_thumbnails(view_model, (
'contentImage', *thumb_keys, 'thumbnailViewModel', 'image'), final_key='sources'),
duration=traverse_obj(view_model, (
'contentImage', 'thumbnailViewModel', 'overlays', ..., 'thumbnailOverlayBadgeViewModel',
'thumbnailBadges', ..., 'thumbnailBadgeViewModel', 'text', {parse_duration}, any)),
'contentImage', 'thumbnailViewModel', 'overlays', ...,
(('thumbnailBottomOverlayViewModel', 'badges'), ('thumbnailOverlayBadgeViewModel', 'thumbnailBadges')),
..., 'thumbnailBadgeViewModel', 'text', {parse_duration}, any)),
timestamp=(traverse_obj(view_model, (
'metadata', 'lockupMetadataViewModel', 'metadata', 'contentMetadataViewModel', 'metadataRows',
..., 'metadataParts', ..., 'text', 'content', {lambda t: self._parse_time_text(t, report_failure=False)}, any))

204
yt_dlp/extractor/youtube/_video.py
View file

@ -147,9 +147,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
_DEFAULT_CLIENTS = ('tv', 'android_sdkless', 'web')
_DEFAULT_JSLESS_CLIENTS = ('android_sdkless', 'web_safari', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv', 'web_safari', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv_downgraded', 'web_safari', 'web')
# Premium does not require POT (except for subtitles)
_DEFAULT_PREMIUM_CLIENTS = ('tv', 'web_creator', 'web')
_DEFAULT_PREMIUM_CLIENTS = ('tv_downgraded', 'web_creator', 'web')
_GEO_BYPASS = False
@ -1556,6 +1556,110 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'view_count': int,
},
'params': {'skip_download': True},
}, {
# Youtube Music Auto-generated description with dot in artist name
'url': 'https://music.youtube.com/watch?v=DbCvuSGfR3Y',
'info_dict': {
'id': 'DbCvuSGfR3Y',
'ext': 'mp4',
'title': 'Back Around',
'artists': ['half·alive'],
'track': 'Back Around',
'album': 'Conditions Of A Punk',
'release_date': '20221202',
'release_year': 2021,
'alt_title': 'Back Around',
'description': 'md5:bfc0e2b3cc903a608d8a85a13cb50f95',
'media_type': 'video',
'uploader': 'half•alive',
'channel': 'half•alive',
'channel_id': 'UCYQrYophdVI3nVDPOnXyIng',
'channel_url': 'https://www.youtube.com/channel/UCYQrYophdVI3nVDPOnXyIng',
'channel_is_verified': True,
'channel_follower_count': int,
'comment_count': int,
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 223,
'thumbnail': 'https://i.ytimg.com/vi_webp/DbCvuSGfR3Y/maxresdefault.webp',
'heatmap': 'count:100',
'categories': ['Music'],
'tags': ['half·alive', 'Conditions Of A Punk', 'Back Around'],
'creators': ['half·alive'],
'timestamp': 1669889281,
'upload_date': '20221201',
'playable_in_embed': True,
'availability': 'public',
'live_status': 'not_live',
},
'params': {
'skip_download': True,
},
}, {
# Video with two collaborators
'url': 'https://www.youtube.com/watch?v=brhfDfLdDZ8',
'info_dict': {
'id': 'brhfDfLdDZ8',
'ext': 'mp4',
'title': 'This is the WORST Movie Science We\'ve Ever Seen',
'description': 'md5:8afd0a3cd69ec63438fc573580436f92',
'media_type': 'video',
'uploader': 'Open Sauce',
'uploader_id': '@opensaucelive',
'uploader_url': 'https://www.youtube.com/@opensaucelive',
'channel': 'Open Sauce',
'channel_id': 'UC2EiGVmCeD79l_vZ204DUSw',
'channel_url': 'https://www.youtube.com/channel/UC2EiGVmCeD79l_vZ204DUSw',
'comment_count': int,
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 1664,
'thumbnail': 'https://i.ytimg.com/vi/brhfDfLdDZ8/hqdefault.jpg',
'categories': ['Entertainment'],
'tags': ['Moonfall', 'Bad Science', 'Open Sauce', 'Sauce+', 'The Backyard Scientist', 'William Osman', 'Allen Pan'],
'creators': ['Open Sauce', 'William Osman 2'],
'timestamp': 1759452918,
'upload_date': '20251003',
'playable_in_embed': True,
'availability': 'public',
'live_status': 'not_live',
},
'params': {'skip_download': True},
}, {
# Video with five collaborators
'url': 'https://www.youtube.com/watch?v=_A9KsMbWh4E',
'info_dict': {
'id': '_A9KsMbWh4E',
'ext': 'mp4',
'title': '【MV】薫習 - LIVE UNION【RK Music】',
'description': 'md5:9b3dc2b91103f303fcc0dac8617e7938',
'media_type': 'video',
'uploader': 'RK Music',
'uploader_id': '@RKMusic_inc',
'uploader_url': 'https://www.youtube.com/@RKMusic_inc',
'channel': 'RK Music',
'channel_id': 'UCiLhMk-gmE2zgF7KGVyqvFw',
'channel_url': 'https://www.youtube.com/channel/UCiLhMk-gmE2zgF7KGVyqvFw',
'comment_count': int,
'view_count': int,
'like_count': int,
'age_limit': 0,
'duration': 193,
'thumbnail': 'https://i.ytimg.com/vi_webp/_A9KsMbWh4E/maxresdefault.webp',
'categories': ['Music'],
'tags': [],
'creators': ['RK Music', 'HACHI', '焔魔るり CH. / Ruri Enma', '瀬戸乃とと', '水瀬 凪/MINASE Nagi'],
'timestamp': 1761908406,
'upload_date': '20251031',
'release_timestamp': 1761908406,
'release_date': '20251031',
'playable_in_embed': True,
'availability': 'public',
'live_status': 'not_live',
},
'params': {'skip_download': True},
}]
_WEBPAGE_TESTS = [{
# <object>
@ -3023,8 +3127,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_formats_and_subtitles(self, video_id, player_responses, player_url, live_status, duration):
CHUNK_SIZE = 10 << 20
PREFERRED_LANG_VALUE = 10
original_language = None
ORIGINAL_LANG_VALUE = 10
DEFAULT_LANG_VALUE = 5
language_map = {
ORIGINAL_LANG_VALUE: None,
DEFAULT_LANG_VALUE: None,
}
itags, stream_ids = collections.defaultdict(set), []
itag_qualities, res_qualities = {}, {0: None}
subtitles = {}
@ -3042,6 +3150,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self._downloader.deprecated_feature('[youtube] include_duplicate_formats extractor argument is deprecated. '
'Use formats=duplicate extractor argument instead')
def is_super_resolution(f_url):
return '1' in traverse_obj(f_url, ({parse_qs}, 'xtags', ..., {urllib.parse.parse_qs}, 'sr', ...))
def solve_sig(s, spec):
return ''.join(s[i] for i in spec)
@ -3064,6 +3175,22 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# For handling potential pre-playback required waiting period
playback_wait = int_or_none(self._configuration_arg('playback_wait', [None])[0], default=6)
def get_language_code_and_preference(fmt_stream):
audio_track = fmt_stream.get('audioTrack') or {}
display_name = audio_track.get('displayName') or ''
language_code = audio_track.get('id', '').split('.')[0] or None
if 'descriptive' in display_name.lower():
return join_nonempty(language_code, 'desc'), -10
if 'original' in display_name.lower():
if language_code and not language_map.get(ORIGINAL_LANG_VALUE):
language_map[ORIGINAL_LANG_VALUE] = language_code
return language_code, ORIGINAL_LANG_VALUE
if audio_track.get('audioIsDefault'):
if language_code and not language_map.get(DEFAULT_LANG_VALUE):
language_map[DEFAULT_LANG_VALUE] = language_code
return language_code, DEFAULT_LANG_VALUE
return language_code, -1
for pr in player_responses:
streaming_data = traverse_obj(pr, 'streamingData')
if not streaming_data:
@ -3078,8 +3205,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def get_stream_id(fmt_stream):
return str_or_none(fmt_stream.get('itag')), traverse_obj(fmt_stream, 'audioTrack', 'id'), fmt_stream.get('isDrc')
def process_format_stream(fmt_stream, proto, missing_pot):
nonlocal original_language
def process_format_stream(fmt_stream, proto, missing_pot, super_resolution=False):
itag = str_or_none(fmt_stream.get('itag'))
audio_track = fmt_stream.get('audioTrack') or {}
quality = fmt_stream.get('quality')
@ -3096,13 +3222,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
if height:
res_qualities[height] = quality
display_name = audio_track.get('displayName') or ''
is_original = 'original' in display_name.lower()
is_descriptive = 'descriptive' in display_name.lower()
is_default = audio_track.get('audioIsDefault')
language_code = audio_track.get('id', '').split('.')[0]
if language_code and (is_original or (is_default and not original_language)):
original_language = language_code
language_code, language_preference = get_language_code_and_preference(fmt_stream)
has_drm = bool(fmt_stream.get('drmFamilies'))
@ -3136,10 +3256,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
dct = {
'asr': int_or_none(fmt_stream.get('audioSampleRate')),
'filesize': int_or_none(fmt_stream.get('contentLength')),
'format_id': f'{itag}{"-drc" if fmt_stream.get("isDrc") else ""}',
'format_id': join_nonempty(itag, (
'drc' if fmt_stream.get('isDrc')
else 'sr' if super_resolution
else None)),
'format_note': join_nonempty(
join_nonempty(display_name, is_default and ' (default)', delim=''),
name, fmt_stream.get('isDrc') and 'DRC',
join_nonempty(audio_track.get('displayName'), audio_track.get('audioIsDefault') and '(default)', delim=' '),
name, fmt_stream.get('isDrc') and 'DRC', super_resolution and 'AI-upscaled',
try_get(fmt_stream, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
try_get(fmt_stream, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
is_damaged and 'DAMAGED', missing_pot and 'MISSING POT',
@ -3155,8 +3278,8 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'tbr': tbr,
'filesize_approx': filesize_from_tbr(tbr, format_duration),
'width': int_or_none(fmt_stream.get('width')),
'language': join_nonempty(language_code, 'desc' if is_descriptive else '') or None,
'language_preference': PREFERRED_LANG_VALUE if is_original else 5 if is_default else -10 if is_descriptive else -1,
'language': language_code,
'language_preference': language_preference,
# Strictly de-prioritize damaged and 3gp formats
'preference': -10 if is_damaged else -2 if itag == '17' else None,
}
@ -3206,6 +3329,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
fmt_url = fmt_stream.get('url')
encrypted_sig, sc = None, None
if not fmt_url:
# We still need to register original/default language information
# See: https://github.com/yt-dlp/yt-dlp/issues/14883
get_language_code_and_preference(fmt_stream)
sc = urllib.parse.parse_qs(fmt_stream.get('signatureCipher'))
fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
encrypted_sig = try_get(sc, lambda x: x['s'][0])
@ -3222,7 +3348,9 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
self.report_warning(msg, video_id, only_once=True)
continue
fmt = process_format_stream(fmt_stream, proto, missing_pot=require_po_token and not po_token)
fmt = process_format_stream(
fmt_stream, proto, missing_pot=require_po_token and not po_token,
super_resolution=is_super_resolution(fmt_url))
if not fmt:
continue
@ -3391,9 +3519,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
elif itag:
f['format_id'] = itag
if original_language and f.get('language') == original_language:
lang_code = f.get('language')
if lang_code and lang_code == language_map[ORIGINAL_LANG_VALUE]:
f['format_note'] = join_nonempty(f.get('format_note'), '(original)', delim=' ')
f['language_preference'] = ORIGINAL_LANG_VALUE
elif lang_code and lang_code == language_map[DEFAULT_LANG_VALUE]:
f['format_note'] = join_nonempty(f.get('format_note'), '(default)', delim=' ')
f['language_preference'] = PREFERRED_LANG_VALUE
f['language_preference'] = DEFAULT_LANG_VALUE
if itag in ('616', '235'):
f['format_note'] = join_nonempty(f.get('format_note'), 'Premium', delim=' ')
@ -3988,20 +4120,14 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Youtube Music Auto-generated description
if (video_description or '').strip().endswith('\nAuto-generated by YouTube.'):
# XXX: Causes catastrophic backtracking if description has "·"
# E.g. https://www.youtube.com/watch?v=DoPaAxMQoiI
# Simulating atomic groups: (?P<a>[^xy]+)x => (?=(?P<a>[^xy]+))(?P=a)x
# reduces it, but does not fully fix it. https://regex101.com/r/8Ssf2h/2
mobj = re.search(
r'''(?xs)
(?=(?P<track>[^\n·]+))(?P=track)·
(?=(?P<artist>[^\n]+))(?P=artist)\n+
(?=(?P<album>[^\n]+))(?P=album)\n
(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
(?:.+?Released\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(.+?\nArtist\s*:\s*
(?=(?P<clean_artist>[^\n]+))(?P=clean_artist)\n
)?.+\nAuto-generated\ by\ YouTube\.\s*$
(?:\n|^)(?P<track>[^\n·]+)\ ·\ (?P<artist>[^\n]+)\n+
(?P<album>[^\n]+)\n+
(?:℗\s*(?P<release_year>\d{4}))?
(?:.+?\nReleased\ on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
(?:.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+)\n)?
.+\nAuto-generated\ by\ YouTube\.\s*$
''', video_description)
if mobj:
release_year = mobj.group('release_year')
@ -4013,7 +4139,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
info.update({
'album': mobj.group('album'.strip()),
'artists': ([a] if (a := mobj.group('clean_artist'))
else [a.strip() for a in mobj.group('artist').split('·')]),
else [a.strip() for a in mobj.group('artist').split(' · ')]),
'track': mobj.group('track').strip(),
'release_date': release_date,
'release_year': int_or_none(release_year),
@ -4112,9 +4238,15 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
vsir = get_first(contents, 'videoSecondaryInfoRenderer')
if vsir:
vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
collaborators = traverse_obj(vor, (
'attributedTitle', 'commandRuns', ..., 'onTap', 'innertubeCommand', 'showDialogCommand',
'panelLoadingStrategy', 'inlineContent', 'dialogViewModel', 'customContent', 'listViewModel',
'listItems', ..., 'listItemViewModel', 'title', 'content', {str}))
info.update({
'channel': self._get_text(vor, 'title'),
'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
'channel': self._get_text(vor, 'title') or (collaborators[0] if collaborators else None),
'channel_follower_count': self._get_count(vor, 'subscriberCountText'),
'creators': collaborators if collaborators else None,
})
if not channel_handle:
channel_handle = self.handle_from_url(

2
yt_dlp/extractor/youtube/jsc/_builtin/vendor/_info.py vendored
View file

@ -1,6 +1,6 @@
# This file is generated by devscripts/update_ejs.py. DO NOT MODIFY!
VERSION = '0.3.0'
VERSION = '0.3.1'
HASHES = {
'yt.solver.bun.lib.js': '6ff45e94de9f0ea936a183c48173cfa9ce526ee4b7544cd556428427c1dd53c8073ef0174e79b320252bf0e7c64b0032cc1cf9c4358f3fda59033b7caa01c241',
'yt.solver.core.js': '0cd96b2d3f319dfa62cae689efa7d930ef1706e95f5921794db5089b2262957ec0a17d73938d8975ea35d0309cbfb4c8e4418d5e219837215eee242890c8b64d',

5
yt_dlp/networking/_curlcffi.py
View file

@ -96,7 +96,10 @@ class CurlCFFIResponseAdapter(Response):
def read(self, amt=None):
try:
return self.fp.read(amt)
res = self.fp.read(amt)
if self.fp.closed:
self.close()
return res
except curl_cffi.requests.errors.RequestsError as e:
if e.code == CurlECode.PARTIAL_FILE:
content_length = e.response and int_or_none(e.response.headers.get('Content-Length'))

23
yt_dlp/networking/_requests.py
View file

@ -119,17 +119,22 @@ class RequestsResponseAdapter(Response):
self._requests_response = res
def _real_read(self, amt: int | None = None) -> bytes:
# Work around issue with `.read(amt)` then `.read()`
# See: https://github.com/urllib3/urllib3/issues/3636
if amt is None:
# compat: py3.9: Python 3.9 preallocates the whole read buffer, read in chunks
read_chunk = functools.partial(self.fp.read, 1 << 20, decode_content=True)
return b''.join(iter(read_chunk, b''))
# Interact with urllib3 response directly.
return self.fp.read(amt, decode_content=True)
def read(self, amt: int | None = None):
try:
# Work around issue with `.read(amt)` then `.read()`
# See: https://github.com/urllib3/urllib3/issues/3636
if amt is None:
# compat: py3.9: Python 3.9 preallocates the whole read buffer, read in chunks
read_chunk = functools.partial(self.fp.read, 1 << 20, decode_content=True)
return b''.join(iter(read_chunk, b''))
# Interact with urllib3 response directly.
return self.fp.read(amt, decode_content=True)
data = self._real_read(amt)
if self.fp.closed:
self.close()
return data
# See urllib3.response.HTTPResponse.read() for exceptions raised on read
except urllib3.exceptions.SSLError as e:
raise SSLError(cause=e) from e

22
yt_dlp/networking/_urllib.py
View file

@ -305,8 +305,28 @@ class UrllibResponseAdapter(Response):
status=getattr(res, 'status', None) or res.getcode(), reason=getattr(res, 'reason', None))
def read(self, amt=None):
if self.closed:
return b''
try:
return self.fp.read(amt)
data = self.fp.read(amt)
underlying = getattr(self.fp, 'fp', None)
if isinstance(self.fp, http.client.HTTPResponse) and underlying is None:
# http.client.HTTPResponse automatically closes itself when fully read
self.close()
elif isinstance(self.fp, urllib.response.addinfourl) and underlying is not None:
# urllib's addinfourl does not close the underlying fp automatically when fully read
if isinstance(underlying, io.BytesIO):
# data URLs or in-memory responses (e.g. gzip/deflate/brotli decoded)
if underlying.tell() >= len(underlying.getbuffer()):
self.close()
elif isinstance(underlying, io.BufferedReader) and amt is None:
# file URLs.
# XXX: this will not mark the response as closed if it was fully read with amt.
self.close()
elif underlying is not None and underlying.closed:
# Catch-all for any cases where underlying file is closed
self.close()
return data
except Exception as e:
handle_response_read_exceptions(e)
raise e

8
yt_dlp/networking/common.py
View file

@ -554,12 +554,16 @@ class Response(io.IOBase):
# Expected errors raised here should be of type RequestError or subclasses.
# Subclasses should redefine this method with more precise error handling.
try:
return self.fp.read(amt)
res = self.fp.read(amt)
if self.fp.closed:
self.close()
return res
except Exception as e:
raise TransportError(cause=e) from e
def close(self):
self.fp.close()
if not self.fp.closed:
self.fp.close()
return super().close()
def get_header(self, name, default=None):

17
yt_dlp/options.py
View file

@ -441,7 +441,7 @@ def create_parser():
'("-" for stdin). Can be used multiple times and inside other configuration files'))
general.add_option(
'--plugin-dirs',
metavar='PATH',
metavar='DIR',
dest='plugin_dirs',
action='callback',
callback=_list_from_options_callback,
@ -466,9 +466,13 @@ def create_parser():
callback_kwargs={'delim': None},
default=['deno'],
help=(
'Additional JavaScript runtime to enable, with an optional path to the runtime location. '
'Additional JavaScript runtime to enable, with an optional location for the runtime '
'(either the path to the binary or its containing directory). '
'This option can be used multiple times to enable multiple runtimes. '
'Supported runtimes: deno, node, bun, quickjs. By default, only "deno" runtime is enabled.'))
'Supported runtimes are (in order of priority, from highest to lowest): deno, node, quickjs, bun. '
'Only "deno" is enabled by default. The highest priority runtime that is both enabled and '
'available will be used. In order to use a lower priority runtime when "deno" is available, '
'--no-js-runtimes needs to be passed before enabling other runtimes'))
general.add_option(
'--no-js-runtimes',
dest='js_runtimes', action='store_const', const=[],
@ -484,9 +488,12 @@ def create_parser():
default=[],
help=(
'Remote components to allow yt-dlp to fetch when required. '
'This option is currently not needed if you are using an official executable '
'or have the requisite version of the yt-dlp-ejs package installed. '
'You can use this option multiple times to allow multiple components. '
'Supported values: ejs:npm (external JavaScript components from npm), ejs:github (external JavaScript components from yt-dlp-ejs GitHub). '
'By default, no remote components are allowed.'))
'Supported values: ejs:npm (external JavaScript components from npm), '
'ejs:github (external JavaScript components from yt-dlp-ejs GitHub). '
'By default, no remote components are allowed'))
general.add_option(
'--no-remote-components',
dest='remote_components', action='store_const', const=[],

5
yt_dlp/postprocessor/ffmpeg.py
View file

@ -192,7 +192,10 @@ class FFmpegPostProcessor(PostProcessor):
@property
def available(self):
return bool(self._ffmpeg_location.get()) or self.basename is not None
# If we return that ffmpeg is available, then the basename property *must* be run
# (as doing so has side effects), and its value can never be None
# See: https://github.com/yt-dlp/yt-dlp/issues/12829
return self.basename is not None
@property
def executable(self):

17
yt_dlp/utils/_jsruntime.py
View file

@ -2,6 +2,7 @@ from __future__ import annotations
import abc
import dataclasses
import functools
import os.path
from ._utils import _get_exe_version_output, detect_exe_version, int_or_none
@ -12,6 +13,14 @@ def runtime_version_tuple(v):
return tuple(int_or_none(x, default=0) for x in v.split('.'))
def _determine_runtime_path(path, basename):
if not path:
return basename
if os.path.isdir(path):
return os.path.join(path, basename)
return path
@dataclasses.dataclass(frozen=True)
class JsRuntimeInfo:
name: str
@ -38,7 +47,7 @@ class DenoJsRuntime(JsRuntime):
MIN_SUPPORTED_VERSION = (2, 0, 0)
def _info(self):
path = self._path or 'deno'
path = _determine_runtime_path(self._path, 'deno')
out = _get_exe_version_output(path, ['--version'])
if not out:
return None
@ -53,7 +62,7 @@ class BunJsRuntime(JsRuntime):
MIN_SUPPORTED_VERSION = (1, 0, 31)
def _info(self):
path = self._path or 'bun'
path = _determine_runtime_path(self._path, 'bun')
out = _get_exe_version_output(path, ['--version'])
if not out:
return None
@ -68,7 +77,7 @@ class NodeJsRuntime(JsRuntime):
MIN_SUPPORTED_VERSION = (20, 0, 0)
def _info(self):
path = self._path or 'node'
path = _determine_runtime_path(self._path, 'node')
out = _get_exe_version_output(path, ['--version'])
if not out:
return None
@ -83,7 +92,7 @@ class QuickJsRuntime(JsRuntime):
MIN_SUPPORTED_VERSION = (2023, 12, 9)
def _info(self):
path = self._path or 'qjs'
path = _determine_runtime_path(self._path, 'qjs')
# quickjs does not have --version and --help returns a status code of 1
out = _get_exe_version_output(path, ['--help'], ignore_return_code=True)
if not out:

6
yt_dlp/version.py
View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2025.10.22'
__version__ = '2025.11.12'
RELEASE_GIT_HEAD = 'c9356f308dd3c5f9f494cb40ed14c5df017b4fe0'
RELEASE_GIT_HEAD = '335653be82d5ef999cfc2879d005397402eebec1'
VARIANT = None
@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2025.10.22'
_pkg_version = '2025.11.12'