1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-08-15 17:08:29 +00:00
This commit is contained in:
DTrombett 2025-07-04 20:07:02 +02:00
commit 09970da6da
No known key found for this signature in database
GPG Key ID: FD8700F69650F6AA
90 changed files with 3197 additions and 2091 deletions

View File

@ -256,7 +256,7 @@ jobs:
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
key: cache-reqs-${{ github.job }}-${{ github.ref }}
- name: Install Requirements
run: |
@ -331,19 +331,16 @@ jobs:
if: steps.restore-cache.outputs.cache-hit == 'true'
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
cache_key: cache-reqs-${{ github.job }}
repository: ${{ github.repository }}
branch: ${{ github.ref }}
cache_key: cache-reqs-${{ github.job }}-${{ github.ref }}
run: |
gh extension install actions/gh-actions-cache
gh actions-cache delete "${cache_key}" -R "${repository}" -B "${branch}" --confirm
gh cache delete "${cache_key}"
- name: Cache requirements
uses: actions/cache/save@v4
with:
path: |
~/yt-dlp-build-venv
key: cache-reqs-${{ github.job }}
key: cache-reqs-${{ github.job }}-${{ github.ref }}
macos_legacy:
needs: process

41
.github/workflows/signature-tests.yml vendored Normal file
View File

@ -0,0 +1,41 @@
name: Signature Tests
on:
push:
paths:
- .github/workflows/signature-tests.yml
- test/test_youtube_signature.py
- yt_dlp/jsinterp.py
pull_request:
paths:
- .github/workflows/signature-tests.yml
- test/test_youtube_signature.py
- yt_dlp/jsinterp.py
permissions:
contents: read
concurrency:
group: signature-tests-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
jobs:
tests:
name: Signature Tests
runs-on: ${{ matrix.os }}
strategy:
fail-fast: false
matrix:
os: [ubuntu-latest, windows-latest]
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', pypy-3.10, pypy-3.11]
steps:
- uses: actions/checkout@v4
- name: Set up Python ${{ matrix.python-version }}
uses: actions/setup-python@v5
with:
python-version: ${{ matrix.python-version }}
- name: Install test requirements
run: python3 ./devscripts/install_deps.py --only-optional --include test
- name: Run tests
timeout-minutes: 15
run: |
python3 -m yt_dlp -v || true # Print debug head
python3 ./devscripts/run_tests.py test/test_youtube_signature.py

2
.gitignore vendored
View File

@ -105,6 +105,8 @@ README.txt
*.zsh
*.spec
test/testdata/sigs/player-*.js
test/testdata/thumbnails/empty.webp
test/testdata/thumbnails/foo\ %d\ bar/foo_%d.*
# Binary
/youtube-dl

View File

@ -775,3 +775,12 @@ GeoffreyFrogeye
Pawka
v3DJG6GL
yozel
brian6932
iednod55
maxbin123
nullpos
anlar
eason1478
ceandreasen
chauhantirth
helpimnotdrowning

View File

@ -4,6 +4,103 @@ # Changelog
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2025.06.30
#### Core changes
- **jsinterp**: [Fix `extract_object`](https://github.com/yt-dlp/yt-dlp/commit/958153a226214c86879e36211ac191bf78289578) ([#13580](https://github.com/yt-dlp/yt-dlp/issues/13580)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **bilibilispacevideo**: [Extract hidden-mode collections as playlists](https://github.com/yt-dlp/yt-dlp/commit/99b85ac102047446e6adf5b62bfc3c8d80b53778) ([#13533](https://github.com/yt-dlp/yt-dlp/issues/13533)) by [c-basalt](https://github.com/c-basalt)
- **hotstar**
- [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/b5bd057fe86550f3aa67f2fc8790d1c6a251c57b) ([#13530](https://github.com/yt-dlp/yt-dlp/issues/13530)) by [bashonly](https://github.com/bashonly), [chauhantirth](https://github.com/chauhantirth) (With fixes in [e9f1576](https://github.com/yt-dlp/yt-dlp/commit/e9f157669e24953a88d15ce22053649db7a8e81e) by [bashonly](https://github.com/bashonly))
- [Fix metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/0a6b1044899f452cd10b6c7a6b00fa985a9a8b97) ([#13560](https://github.com/yt-dlp/yt-dlp/issues/13560)) by [bashonly](https://github.com/bashonly)
- [Raise for login required](https://github.com/yt-dlp/yt-dlp/commit/5e292baad62c749b6c340621ab2d0f904165ddfb) ([#10405](https://github.com/yt-dlp/yt-dlp/issues/10405)) by [bashonly](https://github.com/bashonly)
- series: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4bd9a7ade7e0508b9795b3e72a69eeb40788b62b) ([#13564](https://github.com/yt-dlp/yt-dlp/issues/13564)) by [bashonly](https://github.com/bashonly)
- **jiocinema**: [Remove extractors](https://github.com/yt-dlp/yt-dlp/commit/7e2504f941a11ea2b0dba00de3f0295cdc253e79) ([#13565](https://github.com/yt-dlp/yt-dlp/issues/13565)) by [bashonly](https://github.com/bashonly)
- **kick**: [Support subscriber-only content](https://github.com/yt-dlp/yt-dlp/commit/b16722ede83377f77ea8352dcd0a6ca8e83b8f0f) ([#13550](https://github.com/yt-dlp/yt-dlp/issues/13550)) by [helpimnotdrowning](https://github.com/helpimnotdrowning)
- **niconico**: live: [Fix extractor and downloader](https://github.com/yt-dlp/yt-dlp/commit/06c1a8cdffe14050206683253726875144192ef5) ([#13158](https://github.com/yt-dlp/yt-dlp/issues/13158)) by [doe1080](https://github.com/doe1080)
- **sauceplus**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/35fc33fbc51c7f5392fb2300f65abf6cf107ef90) ([#13567](https://github.com/yt-dlp/yt-dlp/issues/13567)) by [bashonly](https://github.com/bashonly), [ceandreasen](https://github.com/ceandreasen)
- **sproutvideo**: [Support browser impersonation](https://github.com/yt-dlp/yt-dlp/commit/11b9416e10cff7513167d76d6c47774fcdd3e26a) ([#13589](https://github.com/yt-dlp/yt-dlp/issues/13589)) by [bashonly](https://github.com/bashonly)
- **youtube**: [Fix premium formats extraction](https://github.com/yt-dlp/yt-dlp/commit/2ba5391cd68ed4f2415c827d2cecbcbc75ace10b) ([#13586](https://github.com/yt-dlp/yt-dlp/issues/13586)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **ci**: [Add signature tests](https://github.com/yt-dlp/yt-dlp/commit/1b883846347addeab12663fd74317fd544341a1c) ([#13582](https://github.com/yt-dlp/yt-dlp/issues/13582)) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [b018784](https://github.com/yt-dlp/yt-dlp/commit/b0187844988e557c7e1e6bb1aabd4c1176768d86) by [bashonly](https://github.com/bashonly)
### 2025.06.25
#### Extractor changes
- [Add `_search_nuxt_json` helper](https://github.com/yt-dlp/yt-dlp/commit/51887484e46ab6015c041cb1ab626a55f25a03bd) ([#13386](https://github.com/yt-dlp/yt-dlp/issues/13386)) by [bashonly](https://github.com/bashonly), [Grub4K](https://github.com/Grub4K)
- **brightcove**: new: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/e6bd4a3da295b760ab20b39c18ce8934d312c2bf) ([#13461](https://github.com/yt-dlp/yt-dlp/issues/13461)) by [doe1080](https://github.com/doe1080)
- **huya**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/2600849badb0d08c55b58dcc77a13af6ba423da6) ([#13520](https://github.com/yt-dlp/yt-dlp/issues/13520)) by [doe1080](https://github.com/doe1080)
- **hypergryph**: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/1722c55400ff30bb5aee5dd7a262f0b7e9ce2f0e) ([#13415](https://github.com/yt-dlp/yt-dlp/issues/13415)) by [doe1080](https://github.com/doe1080), [eason1478](https://github.com/eason1478)
- **lsm**: [Fix extractors](https://github.com/yt-dlp/yt-dlp/commit/c57412d1f9cf0124adc972a47858ac42b740c61d) ([#13126](https://github.com/yt-dlp/yt-dlp/issues/13126)) by [Caesim404](https://github.com/Caesim404)
- **mave**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/1838a1ce5d4ade80770ba9162eaffc9a1607dc70) ([#13380](https://github.com/yt-dlp/yt-dlp/issues/13380)) by [anlar](https://github.com/anlar)
- **sportdeutschland**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a4ce4327c9836691d3b6b00e44a90b6741601ed8) ([#13519](https://github.com/yt-dlp/yt-dlp/issues/13519)) by [DTrombett](https://github.com/DTrombett)
- **sproutvideo**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/5b559d0072b7164daf06bacdc41c6f11283452c8) ([#13544](https://github.com/yt-dlp/yt-dlp/issues/13544)) by [bashonly](https://github.com/bashonly)
- **tv8.it**: [Support slugless URLs](https://github.com/yt-dlp/yt-dlp/commit/3bd30291601c47fa4a257983473884103ecab0c7) ([#13478](https://github.com/yt-dlp/yt-dlp/issues/13478)) by [DTrombett](https://github.com/DTrombett)
- **youtube**
- [Check any `ios` m3u8 formats prior to download](https://github.com/yt-dlp/yt-dlp/commit/8f94b76cbf7bbd9dfd8762c63cdea04f90f1297f) ([#13524](https://github.com/yt-dlp/yt-dlp/issues/13524)) by [bashonly](https://github.com/bashonly)
- [Improve player context payloads](https://github.com/yt-dlp/yt-dlp/commit/ff6f94041aeee19c5559e1c1cd693960a1c1dd14) ([#13539](https://github.com/yt-dlp/yt-dlp/issues/13539)) by [bashonly](https://github.com/bashonly)
#### Misc. changes
- **test**: `traversal`: [Fix morsel tests for Python 3.14](https://github.com/yt-dlp/yt-dlp/commit/73bf10211668e4a59ccafd790e06ee82d9fea9ea) ([#13471](https://github.com/yt-dlp/yt-dlp/issues/13471)) by [Grub4K](https://github.com/Grub4K)
### 2025.06.09
#### Extractor changes
- [Improve JSON LD thumbnails extraction](https://github.com/yt-dlp/yt-dlp/commit/85c8a405e3651dc041b758f4744d4fb3c4c55e01) ([#13368](https://github.com/yt-dlp/yt-dlp/issues/13368)) by [bashonly](https://github.com/bashonly), [doe1080](https://github.com/doe1080)
- **10play**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/6d265388c6e943419ac99e9151cf75a3265f980f) ([#13349](https://github.com/yt-dlp/yt-dlp/issues/13349)) by [bashonly](https://github.com/bashonly)
- **adobepass**
- [Add Fubo MSO](https://github.com/yt-dlp/yt-dlp/commit/eee90acc47d7f8de24afaa8b0271ccaefdf6e88c) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- [Always add newer user-agent when required](https://github.com/yt-dlp/yt-dlp/commit/0ee1102268cf31b07f8a8318a47424c66b2f7378) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- [Fix Philo MSO authentication](https://github.com/yt-dlp/yt-dlp/commit/943083edcd3df45aaa597a6967bc6c95b720f54c) ([#13335](https://github.com/yt-dlp/yt-dlp/issues/13335)) by [Sipherdrakon](https://github.com/Sipherdrakon)
- [Rework to require software statement](https://github.com/yt-dlp/yt-dlp/commit/711c5d5d098fee2992a1a624b1c4b30364b91426) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly), [maxbin123](https://github.com/maxbin123)
- [Validate login URL before sending credentials](https://github.com/yt-dlp/yt-dlp/commit/89c1b349ad81318d9d3bea76c01c891696e58d38) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **aenetworks**
- [Fix playlist extractors](https://github.com/yt-dlp/yt-dlp/commit/f37d599a697e82fe68b423865897d55bae34f373) ([#13408](https://github.com/yt-dlp/yt-dlp/issues/13408)) by [Sipherdrakon](https://github.com/Sipherdrakon)
- [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/6693d6603358ae6beca834dbd822a7917498b813) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- **bilibilibangumi**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/13e55162719528d42d2133e16b65ff59a667a6e4) ([#13416](https://github.com/yt-dlp/yt-dlp/issues/13416)) by [c-basalt](https://github.com/c-basalt)
- **brightcove**: new: [Adapt to new AdobePass requirement](https://github.com/yt-dlp/yt-dlp/commit/98f8eec956e3b16cb66a3d49cc71af3807db795e) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **cu.ntv.co.jp**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/aa863ddab9b1d104678e9cf39bb76f5b14fca660) ([#13302](https://github.com/yt-dlp/yt-dlp/issues/13302)) by [doe1080](https://github.com/doe1080), [nullpos](https://github.com/nullpos)
- **go**: [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/2e5bf002dad16f5ce35aa2023d392c9e518fcd8f) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly), [maxbin123](https://github.com/maxbin123)
- **nbc**: [Rework and adapt extractors to new AdobePass flow](https://github.com/yt-dlp/yt-dlp/commit/2d7949d5642bc37d1e71bf00c9a55260e5505d58) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **nobelprize**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/97ddfefeb4faba6e61cd80996c16952b8eab16f3) ([#13205](https://github.com/yt-dlp/yt-dlp/issues/13205)) by [doe1080](https://github.com/doe1080)
- **odnoklassniki**: [Detect and raise when login is required](https://github.com/yt-dlp/yt-dlp/commit/148a1eb4c59e127965396c7a6e6acf1979de459e) ([#13361](https://github.com/yt-dlp/yt-dlp/issues/13361)) by [bashonly](https://github.com/bashonly)
- **patreon**: [Fix m3u8 formats extraction](https://github.com/yt-dlp/yt-dlp/commit/e0d6c0822930f6e63f574d46d946a58b73ecd10c) ([#13266](https://github.com/yt-dlp/yt-dlp/issues/13266)) by [bashonly](https://github.com/bashonly) (With fixes in [1a8a03e](https://github.com/yt-dlp/yt-dlp/commit/1a8a03ea8d827107319a18076ee3505090667c5a))
- **podchaser**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/538eb305673c26bff6a2b12f1c96375fe02ce41a) ([#13271](https://github.com/yt-dlp/yt-dlp/issues/13271)) by [bashonly](https://github.com/bashonly)
- **sr**: mediathek: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/e3c605a61f4cc2de9059f37434fa108c3c20f58e) ([#13294](https://github.com/yt-dlp/yt-dlp/issues/13294)) by [doe1080](https://github.com/doe1080)
- **stacommu**: [Avoid partial stream formats](https://github.com/yt-dlp/yt-dlp/commit/5d96527be80dc1ed1702d9cd548ff86de570ad70) ([#13412](https://github.com/yt-dlp/yt-dlp/issues/13412)) by [bashonly](https://github.com/bashonly)
- **startrek**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/a8bf0011bde92b3f1324a98bfbd38932fd3ebe18) ([#13188](https://github.com/yt-dlp/yt-dlp/issues/13188)) by [doe1080](https://github.com/doe1080)
- **svt**: play: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/e1b6062f8c4a3fa33c65269d48d09ec78de765a2) ([#13329](https://github.com/yt-dlp/yt-dlp/issues/13329)) by [barsnick](https://github.com/barsnick), [bashonly](https://github.com/bashonly)
- **telecinco**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/03dba2012d9bd3f402fa8c2f122afba89bbd22a4) ([#13379](https://github.com/yt-dlp/yt-dlp/issues/13379)) by [bashonly](https://github.com/bashonly)
- **theplatform**: [Improve metadata extraction](https://github.com/yt-dlp/yt-dlp/commit/ed108b3ea481c6a4b5215a9302ba92d74baa2425) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **toutiao**: [Add extractor](https://github.com/yt-dlp/yt-dlp/commit/f8051e3a61686c5db1de5f5746366ecfbc3ad20c) ([#13246](https://github.com/yt-dlp/yt-dlp/issues/13246)) by [doe1080](https://github.com/doe1080)
- **turner**: [Adapt extractors to new AdobePass flow](https://github.com/yt-dlp/yt-dlp/commit/0daddc780d3ac5bebc3a3ec5b884d9243cbc0745) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **twitcasting**: [Fix password-protected livestream support](https://github.com/yt-dlp/yt-dlp/commit/52f9729c9a92ad4656d746ff0b1acecb87b3e96d) ([#13097](https://github.com/yt-dlp/yt-dlp/issues/13097)) by [bashonly](https://github.com/bashonly)
- **twitter**: broadcast: [Support events URLs](https://github.com/yt-dlp/yt-dlp/commit/7794374de8afb20499b023107e2abfd4e6b93ee4) ([#13248](https://github.com/yt-dlp/yt-dlp/issues/13248)) by [doe1080](https://github.com/doe1080)
- **umg**: de: [Rework extractor](https://github.com/yt-dlp/yt-dlp/commit/4e7c1ea346b510280218b47e8653dbbca3a69870) ([#13373](https://github.com/yt-dlp/yt-dlp/issues/13373)) by [doe1080](https://github.com/doe1080)
- **vice**: [Mark extractors as broken](https://github.com/yt-dlp/yt-dlp/commit/6121559e027a04574690799c1776bc42bb51af31) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [bashonly](https://github.com/bashonly)
- **vimeo**: [Extract subtitles from player subdomain](https://github.com/yt-dlp/yt-dlp/commit/c723c4e5e78263df178dbe69844a3d05f3ef9e35) ([#13350](https://github.com/yt-dlp/yt-dlp/issues/13350)) by [bashonly](https://github.com/bashonly)
- **watchespn**: [Fix provider-locked content extraction](https://github.com/yt-dlp/yt-dlp/commit/b094747e93cfb0a2c53007120e37d0d84d41f030) ([#13131](https://github.com/yt-dlp/yt-dlp/issues/13131)) by [maxbin123](https://github.com/maxbin123)
- **weverse**: [Support login with oauth refresh tokens](https://github.com/yt-dlp/yt-dlp/commit/3fe72e9eea38d9a58211cde42cfaa577ce020e2c) ([#13284](https://github.com/yt-dlp/yt-dlp/issues/13284)) by [bashonly](https://github.com/bashonly)
- **youtube**
- [Add `tv_simply` player client](https://github.com/yt-dlp/yt-dlp/commit/1fd0e88b67db53ad163393d6965f68e908fa70e3) ([#13389](https://github.com/yt-dlp/yt-dlp/issues/13389)) by [gamer191](https://github.com/gamer191)
- [Extract srt subtitles](https://github.com/yt-dlp/yt-dlp/commit/231349786e8c42089c2e079ec94c0ea866c37999) ([#13411](https://github.com/yt-dlp/yt-dlp/issues/13411)) by [gamer191](https://github.com/gamer191)
- [Fix `--mark-watched` support](https://github.com/yt-dlp/yt-dlp/commit/b5be29fa58ec98226e11621fd9c58585bcff6879) ([#13222](https://github.com/yt-dlp/yt-dlp/issues/13222)) by [brian6932](https://github.com/brian6932), [iednod55](https://github.com/iednod55)
- [Fix automatic captions for some client combinations](https://github.com/yt-dlp/yt-dlp/commit/53ea743a9c158f8ca2d75a09ca44ba68606042d8) ([#13268](https://github.com/yt-dlp/yt-dlp/issues/13268)) by [bashonly](https://github.com/bashonly)
- [Improve signature extraction debug output](https://github.com/yt-dlp/yt-dlp/commit/d30a49742cfa22e61c47df4ac0e7334d648fb85d) ([#13327](https://github.com/yt-dlp/yt-dlp/issues/13327)) by [bashonly](https://github.com/bashonly)
- [Rework nsig function name extraction](https://github.com/yt-dlp/yt-dlp/commit/9e38b273b7ac942e7e9fc05a651ed810ab7d30ba) ([#13403](https://github.com/yt-dlp/yt-dlp/issues/13403)) by [Grub4K](https://github.com/Grub4K)
- [nsig code improvements and cleanup](https://github.com/yt-dlp/yt-dlp/commit/f7bbf5a617f9ab54ef51eaef99be36e175b5e9c3) ([#13280](https://github.com/yt-dlp/yt-dlp/issues/13280)) by [bashonly](https://github.com/bashonly)
- **zdf**: [Fix language extraction and format sorting](https://github.com/yt-dlp/yt-dlp/commit/db162b76f6bdece50babe2e0cacfe56888c2e125) ([#13313](https://github.com/yt-dlp/yt-dlp/issues/13313)) by [InvalidUsernameException](https://github.com/InvalidUsernameException)
#### Misc. changes
- **build**
- [Exclude `pkg_resources` from being collected](https://github.com/yt-dlp/yt-dlp/commit/cc749a8a3b8b6e5c05318868c72a403f376a1b38) ([#13320](https://github.com/yt-dlp/yt-dlp/issues/13320)) by [bashonly](https://github.com/bashonly)
- [Fix macOS requirements caching](https://github.com/yt-dlp/yt-dlp/commit/201812100f315c6727a4418698d5b4e8a79863d4) ([#13328](https://github.com/yt-dlp/yt-dlp/issues/13328)) by [bashonly](https://github.com/bashonly)
- **cleanup**: Miscellaneous: [339614a](https://github.com/yt-dlp/yt-dlp/commit/339614a173c74b42d63e858c446a9cae262a13af) by [bashonly](https://github.com/bashonly)
- **test**: postprocessors: [Remove binary thumbnail test data](https://github.com/yt-dlp/yt-dlp/commit/a9b370069838e84d44ac7ad095d657003665885a) ([#13341](https://github.com/yt-dlp/yt-dlp/issues/13341)) by [bashonly](https://github.com/bashonly)
### 2025.05.22
#### Core changes

View File

@ -18,10 +18,11 @@ pypi-files: AUTHORS Changelog.md LICENSE README.md README.txt supportedsites \
tar pypi-files lazy-extractors install uninstall
clean-test:
rm -rf test/testdata/sigs/player-*.js tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
rm -rf tmp/ *.annotations.xml *.aria2 *.description *.dump *.frag \
*.frag.aria2 *.frag.urls *.info.json *.live_chat.json *.meta *.part* *.tmp *.temp *.unknown_video *.ytdl \
*.3gp *.ape *.ass *.avi *.desktop *.f4v *.flac *.flv *.gif *.jpeg *.jpg *.lrc *.m4a *.m4v *.mhtml *.mkv *.mov *.mp3 *.mp4 \
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp
*.mpg *.mpga *.oga *.ogg *.opus *.png *.sbv *.srt *.ssa *.swf *.tt *.ttml *.url *.vtt *.wav *.webloc *.webm *.webp \
test/testdata/sigs/player-*.js test/testdata/thumbnails/empty.webp "test/testdata/thumbnails/foo %d bar/foo_%d."*
clean-dist:
rm -rf yt-dlp.1.temp.md yt-dlp.1 README.txt MANIFEST build/ dist/ .coverage cover/ yt-dlp.tar.gz completions/ \
yt_dlp/extractor/lazy_extractors.py *.spec CONTRIBUTING.md.tmp yt-dlp yt-dlp.exe yt_dlp.egg-info/ AUTHORS

View File

@ -1156,15 +1156,15 @@ # CONFIGURATION
* `/etc/yt-dlp/config`
* `/etc/yt-dlp/config.txt`
E.g. with the following configuration file, yt-dlp will always extract the audio, not copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
E.g. with the following configuration file, yt-dlp will always extract the audio, copy the mtime, use a proxy and save all videos under `YouTube` directory in your home directory:
```
# Lines starting with # are comments
# Always extract audio
-x
# Do not copy the mtime
--no-mtime
# Copy the mtime
--mtime
# Use this proxy
--proxy 127.0.0.1:3128
@ -1795,9 +1795,9 @@ # EXTRACTOR ARGUMENTS
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.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
* `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_vr`, `tv` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. 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_vr`, `tv`, `tv_simply` and `tv_embedded`. By default, `tv,ios,web` is used, or `tv,web` is used when authenticating with cookies. 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
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `player_js_variant`: The player javascript variant to use for signature and nsig deciphering. The known variants are: `main`, `tce`, `tv`, `tv_es6`, `phone`, `tablet`. Only `main` is recommended as a possible workaround; the others are for debugging purposes. The default is to use what is prescribed by the site, and can be selected with `actual`
@ -2262,6 +2262,7 @@ ### Differences in default behavior
* yt-dlp uses modern http client backends such as `requests`. Use `--compat-options prefer-legacy-http-handler` to prefer the legacy http handler (`urllib`) to be used for standard http requests.
* The sub-modules `swfinterp`, `casefold` are removed.
* Passing `--simulate` (or calling `extract_info` with `download=False`) no longer alters the default format selection. See [#9843](https://github.com/yt-dlp/yt-dlp/issues/9843) for details.
* yt-dlp no longer applies the server modified time to downloaded files by default. Use `--mtime` or `--compat-options mtime-by-default` to revert this.
For ease of use, a few more compat options are available:
@ -2271,7 +2272,7 @@ ### Differences in default behavior
* `--compat-options 2021`: Same as `--compat-options 2022,no-certifi,filename-sanitization`
* `--compat-options 2022`: Same as `--compat-options 2023,playlist-match-filter,no-external-downloader-progress,prefer-legacy-http-handler,manifest-filesize-approx`
* `--compat-options 2023`: Same as `--compat-options 2024,prefer-vp9-sort`
* `--compat-options 2024`: Currently does nothing. Use this to enable all future compat options
* `--compat-options 2024`: Same as `--compat-options mtime-by-default`. Use this to enable all future compat options
The following compat options restore vulnerable behavior from before security patches:

View File

@ -2,6 +2,7 @@
set -e
source ~/.local/share/pipx/venvs/pyinstaller/bin/activate
python -m devscripts.install_deps -o --include build
python -m devscripts.install_deps --include secretstorage --include curl-cffi
python -m devscripts.make_lazy_extractors
python devscripts/update-version.py -c "${channel}" -r "${origin}" "${version}"

View File

@ -36,6 +36,9 @@ def main():
f'--name={name}',
'--icon=devscripts/logo.ico',
'--upx-exclude=vcruntime140.dll',
# Ref: https://github.com/yt-dlp/yt-dlp/issues/13311
# https://github.com/pyinstaller/pyinstaller/issues/9149
'--exclude-module=pkg_resources',
'--noconfirm',
'--additional-hooks-dir=yt_dlp/__pyinstaller',
*opts,

View File

@ -254,5 +254,13 @@
{
"action": "remove",
"when": "d596824c2f8428362c072518856065070616e348"
},
{
"action": "remove",
"when": "7b81634fb1d15999757e7a9883daa6ef09ea785b"
},
{
"action": "remove",
"when": "500761e41acb96953a5064e951d41d190c287e46"
}
]

View File

@ -65,7 +65,7 @@ build = [
"build",
"hatchling",
"pip",
"setuptools>=71.0.2", # 71.0.0 broke pyinstaller
"setuptools>=71.0.2,<81", # See https://github.com/pyinstaller/pyinstaller/issues/9149
"wheel",
]
dev = [
@ -75,7 +75,7 @@ dev = [
]
static-analysis = [
"autopep8~=2.0",
"ruff~=0.11.0",
"ruff~=0.12.0",
]
test = [
"pytest~=8.1",
@ -210,10 +210,12 @@ ignore = [
"TD001", # invalid-todo-tag
"TD002", # missing-todo-author
"TD003", # missing-todo-link
"PLC0415", # import-outside-top-level
"PLE0604", # invalid-all-object (false positives)
"PLE0643", # potential-index-error (false positives)
"PLW0603", # global-statement
"PLW1510", # subprocess-run-without-check
"PLW1641", # eq-without-hash
"PLW2901", # redefined-loop-name
"RUF001", # ambiguous-unicode-character-string
"RUF012", # mutable-class-default

View File

@ -5,6 +5,8 @@ # Supported sites
Not all sites listed here are guaranteed to work; websites are constantly changing and sometimes this breaks yt-dlp's support for them.
The only reliable way to check if a site is supported is to try it.
- **10play**: [*10play*](## "netrc machine")
- **10play:season**
- **17live**
- **17live:clip**
- **17live:vod**
@ -295,7 +297,7 @@ # Supported sites
- **CNNIndonesia**
- **ComedyCentral**
- **ComedyCentralTV**
- **ConanClassic**
- **ConanClassic**: (**Currently broken**)
- **CondeNast**: Condé Nast media group: Allure, Architectural Digest, Ars Technica, Bon Appétit, Brides, Condé Nast, Condé Nast Traveler, Details, Epicurious, GQ, Glamour, Golf Digest, SELF, Teen Vogue, The New Yorker, Vanity Fair, Vogue, W Magazine, WIRED
- **CONtv**
- **CookingChannel**
@ -317,7 +319,7 @@ # Supported sites
- **CtsNews**: 華視新聞
- **CTV**
- **CTVNews**
- **cu.ntv.co.jp**: Nippon Television Network
- **cu.ntv.co.jp**: 日テレ無料TADA!
- **CultureUnplugged**
- **curiositystream**: [*curiositystream*](## "netrc machine")
- **curiositystream:collections**: [*curiositystream*](## "netrc machine")
@ -573,9 +575,7 @@ # Supported sites
- **HollywoodReporterPlaylist**
- **Holodex**
- **HotNewHipHop**: (**Currently broken**)
- **hotstar**
- **hotstar:playlist**
- **hotstar:season**
- **hotstar**: JioHotstar
- **hotstar:series**
- **hrfernsehen**
- **HRTi**: [*hrti*](## "netrc machine")
@ -588,7 +588,7 @@ # Supported sites
- **Hungama**
- **HungamaAlbumPlaylist**
- **HungamaSong**
- **huya:live**: huya.com
- **huya:live**: 虎牙直播
- **huya:video**: 虎牙视频
- **Hypem**
- **Hytale**
@ -645,8 +645,6 @@ # Supported sites
- **Jamendo**
- **JamendoAlbum**
- **JeuxVideo**: (**Currently broken**)
- **jiocinema**: [*jiocinema*](## "netrc machine")
- **jiocinema:series**: [*jiocinema*](## "netrc machine")
- **jiosaavn:album**
- **jiosaavn:artist**
- **jiosaavn:playlist**
@ -774,6 +772,7 @@ # Supported sites
- **massengeschmack.tv**
- **Masters**
- **MatchTV**
- **Mave**
- **MBN**: mbn.co.kr (매일방송)
- **MDR**: MDR.DE
- **MedalTV**
@ -830,7 +829,7 @@ # Supported sites
- **Mojevideo**: mojevideo.sk
- **Mojvideo**
- **Monstercat**
- **MonsterSirenHypergryphMusic**
- **monstersiren**: 塞壬唱片
- **Motherless**
- **MotherlessGallery**
- **MotherlessGroup**
@ -882,19 +881,19 @@ # Supported sites
- **Naver**
- **Naver:live**
- **navernow**
- **nba**
- **nba:channel**
- **nba:embed**
- **nba:watch**
- **nba:watch:collection**
- **nba:watch:embed**
- **nba**: (**Currently broken**)
- **nba:channel**: (**Currently broken**)
- **nba:embed**: (**Currently broken**)
- **nba:watch**: (**Currently broken**)
- **nba:watch:collection**: (**Currently broken**)
- **nba:watch:embed**: (**Currently broken**)
- **NBC**
- **NBCNews**
- **nbcolympics**
- **nbcolympics:stream**
- **NBCSports**
- **NBCSportsStream**
- **NBCSportsVPlayer**
- **nbcolympics:stream**: (**Currently broken**)
- **NBCSports**: (**Currently broken**)
- **NBCSportsStream**: (**Currently broken**)
- **NBCSportsVPlayer**: (**Currently broken**)
- **NBCStations**
- **ndr**: NDR.de - Norddeutscher Rundfunk
- **ndr:embed**
@ -970,7 +969,7 @@ # Supported sites
- **Nitter**
- **njoy**: N-JOY
- **njoy:embed**
- **NobelPrize**: (**Currently broken**)
- **NobelPrize**
- **NoicePodcast**
- **NonkTube**
- **NoodleMagazine**
@ -1296,6 +1295,7 @@ # Supported sites
- **SampleFocus**
- **Sangiin**: 参議院インターネット審議中継 (archive)
- **Sapo**: SAPO Vídeos
- **SaucePlus**: Sauce+
- **SBS**: sbs.com.au
- **sbs.co.kr**
- **sbs.co.kr:allvod_program**
@ -1393,14 +1393,14 @@ # Supported sites
- **SpreakerShow**
- **SpringboardPlatform**
- **SproutVideo**
- **sr:mediathek**: Saarländischer Rundfunk (**Currently broken**)
- **sr:mediathek**: Saarländischer Rundfunk
- **SRGSSR**
- **SRGSSRPlay**: srf.ch, rts.ch, rsi.ch, rtr.ch and swissinfo.ch play sites
- **StacommuLive**: [*stacommu*](## "netrc machine")
- **StacommuVOD**: [*stacommu*](## "netrc machine")
- **StagePlusVODConcert**: [*stageplus*](## "netrc machine")
- **stanfordoc**: Stanford Open ClassRoom
- **StarTrek**: (**Currently broken**)
- **startrek**: STAR TREK
- **startv**
- **Steam**
- **SteamCommunityBroadcast**
@ -1423,12 +1423,11 @@ # Supported sites
- **SunPorno**
- **sverigesradio:episode**
- **sverigesradio:publication**
- **SVT**
- **SVTPage**
- **SVTPlay**: SVT Play and Öppet arkiv
- **SVTSeries**
- **svt:page**
- **svt:play**: SVT Play and Öppet arkiv
- **svt:play:series**
- **SwearnetEpisode**
- **Syfy**: (**Currently broken**)
- **Syfy**
- **SYVDK**
- **SztvHu**
- **t-online.de**: (**Currently broken**)
@ -1472,8 +1471,6 @@ # Supported sites
- **Telewebion**: (**Currently broken**)
- **Tempo**
- **TennisTV**: [*tennistv*](## "netrc machine")
- **TenPlay**: [*10play*](## "netrc machine")
- **TenPlaySeason**
- **TF1**
- **TFO**
- **theatercomplextown:ppv**: [*theatercomplextown*](## "netrc machine")
@ -1511,6 +1508,7 @@ # Supported sites
- **tokfm:podcast**
- **ToonGoggles**
- **tou.tv**: [*toutv*](## "netrc machine")
- **toutiao**: 今日头条
- **Toypics**: Toypics video (**Currently broken**)
- **ToypicsUser**: Toypics user profile (**Currently broken**)
- **TrailerAddict**: (**Currently broken**)
@ -1600,7 +1598,7 @@ # Supported sites
- **UKTVPlay**
- **UlizaPlayer**
- **UlizaPortal**: ulizaportal.jp
- **umg:de**: Universal Music Deutschland (**Currently broken**)
- **umg:de**: Universal Music Deutschland
- **Unistra**
- **Unity**: (**Currently broken**)
- **uol.com.br**
@ -1623,9 +1621,9 @@ # Supported sites
- **VGTV**: VGTV, BTTV, FTV, Aftenposten and Aftonbladet
- **vh1.com**
- **vhx:embed**: [*vimeo*](## "netrc machine")
- **vice**
- **vice:article**
- **vice:show**
- **vice**: (**Currently broken**)
- **vice:article**: (**Currently broken**)
- **vice:show**: (**Currently broken**)
- **Viddler**
- **Videa**
- **video.arnes.si**: Arnes Video

View File

@ -36,6 +36,18 @@ def do_GET(self):
self.send_header('Content-Type', 'text/html; charset=utf-8')
self.end_headers()
self.wfile.write(TEAPOT_RESPONSE_BODY.encode())
elif self.path == '/fake.m3u8':
self.send_response(200)
self.send_header('Content-Length', '1024')
self.end_headers()
self.wfile.write(1024 * b'\x00')
elif self.path == '/bipbop.m3u8':
with open('test/testdata/m3u8/bipbop_16x9.m3u8', 'rb') as f:
data = f.read()
self.send_response(200)
self.send_header('Content-Length', str(len(data)))
self.end_headers()
self.wfile.write(data)
else:
assert False
@ -314,6 +326,20 @@ def test_search_json_ld_realworld(self):
},
{},
),
(
# test thumbnail_url key without URL scheme
r'''
<script type="application/ld+json">
{
"@context": "https://schema.org",
"@type": "VideoObject",
"thumbnail_url": "//www.nobelprize.org/images/12693-landscape-medium-gallery.jpg"
}</script>''',
{
'thumbnails': [{'url': 'https://www.nobelprize.org/images/12693-landscape-medium-gallery.jpg'}],
},
{},
),
]
for html, expected_dict, search_json_ld_kwargs in _TESTS:
expect_dict(
@ -1933,6 +1959,177 @@ def test_search_nextjs_data(self):
with self.assertWarns(DeprecationWarning):
self.assertEqual(self.ie._search_nextjs_data('', None, default='{}'), {})
def test_search_nuxt_json(self):
HTML_TMPL = '<script data-ssr="true" id="__NUXT_DATA__" type="application/json">[{}]</script>'
VALID_DATA = '''
["ShallowReactive",1],
{"data":2,"state":21,"once":25,"_errors":28,"_server_errors":30},
["ShallowReactive",3],
{"$abcdef123456":4},
{"podcast":5,"activeEpisodeData":7},
{"podcast":6,"seasons":14},
{"title":10,"id":11},
["Reactive",8],
{"episode":9,"creators":18,"empty_list":20},
{"title":12,"id":13,"refs":34,"empty_refs":35},
"Series Title",
"podcast-id-01",
"Episode Title",
"episode-id-99",
[15,16,17],
1,
2,
3,
[19],
"Podcast Creator",
[],
{"$ssite-config":22},
{"env":23,"name":24,"map":26,"numbers":14},
"production",
"podcast-website",
["Set"],
["Reactive",27],
["Map"],
["ShallowReactive",29],
{},
["NuxtError",31],
{"status":32,"message":33},
503,
"Service Unavailable",
[36,37],
[38,39],
["Ref",40],
["ShallowRef",41],
["EmptyRef",42],
["EmptyShallowRef",43],
"ref",
"shallow_ref",
"{\\"ref\\":1}",
"{\\"shallow_ref\\":2}"
'''
PAYLOAD = {
'data': {
'$abcdef123456': {
'podcast': {
'podcast': {
'title': 'Series Title',
'id': 'podcast-id-01',
},
'seasons': [1, 2, 3],
},
'activeEpisodeData': {
'episode': {
'title': 'Episode Title',
'id': 'episode-id-99',
'refs': ['ref', 'shallow_ref'],
'empty_refs': [{'ref': 1}, {'shallow_ref': 2}],
},
'creators': ['Podcast Creator'],
'empty_list': [],
},
},
},
'state': {
'$ssite-config': {
'env': 'production',
'name': 'podcast-website',
'map': [],
'numbers': [1, 2, 3],
},
},
'once': [],
'_errors': {},
'_server_errors': {
'status': 503,
'message': 'Service Unavailable',
},
}
PARTIALLY_INVALID = [(
'''
{"data":1},
{"invalid_raw_list":2},
[15,16,17]
''',
{'data': {'invalid_raw_list': [None, None, None]}},
), (
'''
{"data":1},
["EmptyRef",2],
"not valid JSON"
''',
{'data': None},
), (
'''
{"data":1},
["EmptyShallowRef",2],
"not valid JSON"
''',
{'data': None},
)]
INVALID = [
'''
[]
''',
'''
["unsupported",1],
{"data":2},
{}
''',
]
DEFAULT = object()
self.assertEqual(self.ie._search_nuxt_json(HTML_TMPL.format(VALID_DATA), None), PAYLOAD)
self.assertEqual(self.ie._search_nuxt_json('', None, fatal=False), {})
self.assertIs(self.ie._search_nuxt_json('', None, default=DEFAULT), DEFAULT)
for data, expected in PARTIALLY_INVALID:
self.assertEqual(
self.ie._search_nuxt_json(HTML_TMPL.format(data), None, fatal=False), expected)
for data in INVALID:
self.assertIs(
self.ie._search_nuxt_json(HTML_TMPL.format(data), None, default=DEFAULT), DEFAULT)
class TestInfoExtractorNetwork(unittest.TestCase):
def setUp(self, /):
self.httpd = http.server.HTTPServer(
('127.0.0.1', 0), InfoExtractorTestRequestHandler)
self.port = http_server_port(self.httpd)
self.server_thread = threading.Thread(target=self.httpd.serve_forever)
self.server_thread.daemon = True
self.server_thread.start()
self.called = False
def require_warning(*args, **kwargs):
self.called = True
self.ydl = FakeYDL()
self.ydl.report_warning = require_warning
self.ie = DummyIE(self.ydl)
def tearDown(self, /):
self.ydl.close()
self.httpd.shutdown()
self.httpd.server_close()
self.server_thread.join(1)
def test_extract_m3u8_formats(self):
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
f'http://127.0.0.1:{self.port}/bipbop.m3u8', None, fatal=False)
self.assertFalse(self.called)
self.assertTrue(formats)
self.assertTrue(subtitles)
def test_extract_m3u8_formats_warning(self):
formats, subtitles = self.ie._extract_m3u8_formats_and_subtitles(
f'http://127.0.0.1:{self.port}/fake.m3u8', None, fatal=False)
self.assertTrue(self.called, 'Warning was not issued for binary m3u8 file')
self.assertFalse(formats)
self.assertFalse(subtitles)
if __name__ == '__main__':
unittest.main()

235
test/test_devalue.py Normal file
View File

@ -0,0 +1,235 @@
#!/usr/bin/env python3
# Allow direct execution
import os
import sys
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import datetime as dt
import json
import math
import re
import unittest
from yt_dlp.utils.jslib import devalue
TEST_CASES_EQUALS = [{
'name': 'int',
'unparsed': [-42],
'parsed': -42,
}, {
'name': 'str',
'unparsed': ['woo!!!'],
'parsed': 'woo!!!',
}, {
'name': 'Number',
'unparsed': [['Object', 42]],
'parsed': 42,
}, {
'name': 'String',
'unparsed': [['Object', 'yar']],
'parsed': 'yar',
}, {
'name': 'Infinity',
'unparsed': -4,
'parsed': math.inf,
}, {
'name': 'negative Infinity',
'unparsed': -5,
'parsed': -math.inf,
}, {
'name': 'negative zero',
'unparsed': -6,
'parsed': -0.0,
}, {
'name': 'RegExp',
'unparsed': [['RegExp', 'regexp', 'gim']], # XXX: flags are ignored
'parsed': re.compile('regexp'),
}, {
'name': 'Date',
'unparsed': [['Date', '2001-09-09T01:46:40.000Z']],
'parsed': dt.datetime.fromtimestamp(1e9, tz=dt.timezone.utc),
}, {
'name': 'Array',
'unparsed': [[1, 2, 3], 'a', 'b', 'c'],
'parsed': ['a', 'b', 'c'],
}, {
'name': 'Array (empty)',
'unparsed': [[]],
'parsed': [],
}, {
'name': 'Array (sparse)',
'unparsed': [[-2, 1, -2], 'b'],
'parsed': [None, 'b', None],
}, {
'name': 'Object',
'unparsed': [{'foo': 1, 'x-y': 2}, 'bar', 'z'],
'parsed': {'foo': 'bar', 'x-y': 'z'},
}, {
'name': 'Set',
'unparsed': [['Set', 1, 2, 3], 1, 2, 3],
'parsed': [1, 2, 3],
}, {
'name': 'Map',
'unparsed': [['Map', 1, 2], 'a', 'b'],
'parsed': [['a', 'b']],
}, {
'name': 'BigInt',
'unparsed': [['BigInt', '1']],
'parsed': 1,
}, {
'name': 'Uint8Array',
'unparsed': [['Uint8Array', 'AQID']],
'parsed': [1, 2, 3],
}, {
'name': 'ArrayBuffer',
'unparsed': [['ArrayBuffer', 'AQID']],
'parsed': [1, 2, 3],
}, {
'name': 'str (repetition)',
'unparsed': [[1, 1], 'a string'],
'parsed': ['a string', 'a string'],
}, {
'name': 'None (repetition)',
'unparsed': [[1, 1], None],
'parsed': [None, None],
}, {
'name': 'dict (repetition)',
'unparsed': [[1, 1], {}],
'parsed': [{}, {}],
}, {
'name': 'Object without prototype',
'unparsed': [['null']],
'parsed': {},
}, {
'name': 'cross-realm POJO',
'unparsed': [{}],
'parsed': {},
}]
TEST_CASES_IS = [{
'name': 'bool',
'unparsed': [True],
'parsed': True,
}, {
'name': 'Boolean',
'unparsed': [['Object', False]],
'parsed': False,
}, {
'name': 'undefined',
'unparsed': -1,
'parsed': None,
}, {
'name': 'null',
'unparsed': [None],
'parsed': None,
}, {
'name': 'NaN',
'unparsed': -3,
'parsed': math.nan,
}]
TEST_CASES_INVALID = [{
'name': 'empty string',
'unparsed': '',
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'hole',
'unparsed': -2,
'error': ValueError,
'pattern': r'invalid integer input',
}, {
'name': 'string',
'unparsed': 'hello',
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'number',
'unparsed': 42,
'error': ValueError,
'pattern': r'invalid integer input',
}, {
'name': 'boolean',
'unparsed': True,
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'null',
'unparsed': None,
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'object',
'unparsed': {},
'error': ValueError,
'pattern': r'expected int or list as input',
}, {
'name': 'empty array',
'unparsed': [],
'error': ValueError,
'pattern': r'expected a non-empty list as input',
}, {
'name': 'Python negative indexing',
'unparsed': [[1, 2, 3, 4, 5, 6, 7, -7], 1, 2, 3, 4, 5, 6, 7],
'error': IndexError,
'pattern': r'invalid index: -7',
}]
class TestDevalue(unittest.TestCase):
def test_devalue_parse_equals(self):
for tc in TEST_CASES_EQUALS:
self.assertEqual(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
def test_devalue_parse_is(self):
for tc in TEST_CASES_IS:
self.assertIs(devalue.parse(tc['unparsed']), tc['parsed'], tc['name'])
def test_devalue_parse_invalid(self):
for tc in TEST_CASES_INVALID:
with self.assertRaisesRegex(tc['error'], tc['pattern'], msg=tc['name']):
devalue.parse(tc['unparsed'])
def test_devalue_parse_cyclical(self):
name = 'Map (cyclical)'
result = devalue.parse([['Map', 1, 0], 'self'])
self.assertEqual(result[0][0], 'self', name)
self.assertIs(result, result[0][1], name)
name = 'Set (cyclical)'
result = devalue.parse([['Set', 0, 1], 42])
self.assertEqual(result[1], 42, name)
self.assertIs(result, result[0], name)
result = devalue.parse([[0]])
self.assertIs(result, result[0], 'Array (cyclical)')
name = 'Object (cyclical)'
result = devalue.parse([{'self': 0}])
self.assertIs(result, result['self'], name)
name = 'Object with null prototype (cyclical)'
result = devalue.parse([['null', 'self', 0]])
self.assertIs(result, result['self'], name)
name = 'Objects (cyclical)'
result = devalue.parse([[1, 2], {'second': 2}, {'first': 1}])
self.assertIs(result[0], result[1]['first'], name)
self.assertIs(result[1], result[0]['second'], name)
def test_devalue_parse_revivers(self):
self.assertEqual(
devalue.parse([['indirect', 1], {'a': 2}, 'b'], revivers={'indirect': lambda x: x}),
{'a': 'b'}, 'revivers (indirect)')
self.assertEqual(
devalue.parse([['parse', 1], '{"a":0}'], revivers={'parse': lambda x: json.loads(x)}),
{'a': 0}, 'revivers (parse)')
if __name__ == '__main__':
unittest.main()

View File

@ -478,6 +478,10 @@ def test_extract_function_with_global_stack(self):
func = jsi.extract_function('c', {'e': 10}, {'f': 100, 'g': 1000})
self.assertEqual(func([1]), 1111)
def test_extract_object(self):
jsi = JSInterpreter('var a={};a.xy={};var xy;var zxy={};xy={z:function(){return "abc"}};')
self.assertTrue('z' in jsi.extract_object('xy', None))
def test_increment_decrement(self):
self._test('function f() { var x = 1; return ++x; }', 2)
self._test('function f() { var x = 1; return x++; }', 1)

View File

@ -22,7 +22,6 @@
import tempfile
import threading
import time
import urllib.error
import urllib.request
import warnings
import zlib
@ -223,10 +222,7 @@ def do_GET(self):
if encoding == 'br' and brotli:
payload = brotli.compress(payload)
elif encoding == 'gzip':
buf = io.BytesIO()
with gzip.GzipFile(fileobj=buf, mode='wb') as f:
f.write(payload)
payload = buf.getvalue()
payload = gzip.compress(payload, mtime=0)
elif encoding == 'deflate':
payload = zlib.compress(payload)
elif encoding == 'unsupported':
@ -729,6 +725,17 @@ def test_keep_header_casing(self, handler):
assert 'X-test-heaDer: test' in res
def test_partial_read_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(6) == b'<html>'
assert res.read(0) == b''
assert res.read() == b'<video src="/vid.mp4" /></html>'
@pytest.mark.parametrize('handler', ['Urllib', 'Requests', 'CurlCFFI'], indirect=True)
class TestClientCertificate:

View File

@ -8,6 +8,8 @@
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))
import subprocess
from yt_dlp import YoutubeDL
from yt_dlp.utils import shell_quote
from yt_dlp.postprocessor import (
@ -47,7 +49,18 @@ def test_escaping(self):
print('Skipping: ffmpeg not found')
return
file = 'test/testdata/thumbnails/foo %d bar/foo_%d.{}'
test_data_dir = 'test/testdata/thumbnails'
generated_file = f'{test_data_dir}/empty.webp'
subprocess.check_call([
pp.executable, '-y', '-f', 'lavfi', '-i', 'color=c=black:s=320x320',
'-c:v', 'libwebp', '-pix_fmt', 'yuv420p', '-vframes', '1', generated_file,
], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
file = test_data_dir + '/foo %d bar/foo_%d.{}'
initial_file = file.format('webp')
os.replace(generated_file, initial_file)
tests = (('webp', 'png'), ('png', 'jpg'))
for inp, out in tests:
@ -55,11 +68,13 @@ def test_escaping(self):
if os.path.exists(out_file):
os.remove(out_file)
pp.convert_thumbnail(file.format(inp), out)
assert os.path.exists(out_file)
self.assertTrue(os.path.exists(out_file))
for _, out in tests:
os.remove(file.format(out))
os.remove(initial_file)
class TestExec(unittest.TestCase):
def test_parse_cmd(self):
@ -610,3 +625,7 @@ def test_quote_for_concat_QuotesAtEnd(self):
self.assertEqual(
r"'special '\'' characters '\'' galore'\'\'\'",
self._pp._quote_for_ffmpeg("special ' characters ' galore'''"))
if __name__ == '__main__':
unittest.main()

View File

@ -11,7 +11,7 @@ class TestGetWebPoContentBinding:
@pytest.mark.parametrize('client_name, context, is_authenticated, expected', [
*[(client, context, is_authenticated, expected) for client in [
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
for context, is_authenticated, expected in [
(PoTokenContext.GVS, False, ('example-visitor-data', ContentBindingType.VISITOR_DATA)),
(PoTokenContext.PLAYER, False, ('example-video-id', ContentBindingType.VIDEO_ID)),

View File

@ -49,7 +49,7 @@ def test_not_supports(self, ie, logger, pot_request, client_name, context, is_au
@pytest.mark.parametrize('client_name, context, is_authenticated, remote_host, source_address, request_proxy, expected', [
*[(client, context, is_authenticated, remote_host, source_address, request_proxy, expected) for client in [
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER']
'WEB', 'MWEB', 'TVHTML5', 'WEB_EMBEDDED_PLAYER', 'WEB_CREATOR', 'TVHTML5_SIMPLY_EMBEDDED_PLAYER', 'TVHTML5_SIMPLY']
for context, is_authenticated, remote_host, source_address, request_proxy, expected in [
(PoTokenContext.GVS, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'visitor_id'}),
(PoTokenContext.PLAYER, False, 'example-remote-host', 'example-source-address', 'example-request-proxy', {'t': 'webpo', 'ip': 'example-remote-host', 'sa': 'example-source-address', 'px': 'example-request-proxy', 'cb': '123abcXYZ_-', 'cbt': 'video_id'}),

View File

@ -416,18 +416,8 @@ def test_traversal_unbranching(self):
'`any` should allow further branching'
def test_traversal_morsel(self):
values = {
'expires': 'a',
'path': 'b',
'comment': 'c',
'domain': 'd',
'max-age': 'e',
'secure': 'f',
'httponly': 'g',
'version': 'h',
'samesite': 'i',
}
morsel = http.cookies.Morsel()
values = dict(zip(morsel, 'abcdefghijklmnop'))
morsel.set('item_key', 'item_value', 'coded_value')
morsel.update(values)
values['key'] = 'item_key'

View File

@ -133,6 +133,11 @@
'2aq0aqSyOoJXtK73m-uME_jv7-pT15gOFC02RFkGMqWpzEICs69VdbwQ0LDp1v7j8xx92efCJlYFYb1sUkkBSPOlPmXgIARw8JQ0qOAOAA',
'IAOAOq0QJ8wRAAgXmPlOPSBkkUs1bYFYlJCfe29xx8j7v1pDL0QwbdV96sCIEzpWqMGkFR20CFOg51Tp-7vj_E2u-m37KtXJoOySqa0',
),
(
'https://www.youtube.com/s/player/e12fbea4/player_ias.vflset/en_US/base.js',
'gN7a-hudCuAuPH6fByOk1_GNXN0yNMHShjZXS2VOgsEItAJz0tipeavEOmNdYN-wUtcEqD3bCXjc0iyKfAyZxCBGgIARwsSdQfJ2CJtt',
'JC2JfQdSswRAIgGBCxZyAfKyi0cjXCb3DqEctUw-NYdNmOEvaepit0zJAtIEsgOV2SXZjhSHMNy0NXNG_1kOyBf6HPuAuCduh-a',
),
]
_NSIG_TESTS = [
@ -320,6 +325,14 @@
'https://www.youtube.com/s/player/59b252b9/player_ias.vflset/en_US/base.js',
'D3XWVpYgwhLLKNK4AGX', 'aZrQ1qWJ5yv5h',
),
(
'https://www.youtube.com/s/player/fc2a56a5/player_ias.vflset/en_US/base.js',
'qTKWg_Il804jd2kAC', 'OtUAm2W6gyzJjB9u',
),
(
'https://www.youtube.com/s/player/fc2a56a5/tv-player-ias.vflset/tv-player-ias.js',
'qTKWg_Il804jd2kAC', 'OtUAm2W6gyzJjB9u',
),
]

Binary file not shown.

Before

Width:  |  Height:  |  Size: 3.8 KiB

View File

View File

@ -482,7 +482,8 @@ class YoutubeDL:
The following options do not work when used through the API:
filename, abort-on-error, multistreams, no-live-chat,
format-sort, no-clean-infojson, no-playlist-metafiles,
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort.
no-keep-subs, no-attach-info-json, allow-unsafe-ext, prefer-vp9-sort,
mtime-by-default.
Refer __init__.py for their implementation
progress_template: Dictionary of templates for progress outputs.
Allowed keys are 'download', 'postprocess',
@ -490,7 +491,7 @@ class YoutubeDL:
The template is mapped on a dictionary with keys 'progress' and 'info'
retry_sleep_functions: Dictionary of functions that takes the number of attempts
as argument and returns the time to sleep in seconds.
Allowed keys are 'http', 'fragment', 'file_access'
Allowed keys are 'http', 'fragment', 'file_access', 'extractor'
download_ranges: A callback function that gets called for every video with
the signature (info_dict, ydl) -> Iterable[Section].
Only the returned sections will be downloaded.
@ -2219,6 +2220,7 @@ def _check_formats(self, formats):
self.report_warning(f'Unable to delete temporary file "{temp_file.name}"')
f['__working'] = success
if success:
f.pop('__needs_testing', None)
yield f
else:
self.to_screen('[info] Unable to download format {}. Skipping...'.format(f['format_id']))
@ -3963,6 +3965,7 @@ def simplified_codec(f, field):
self._format_out('UNSUPPORTED', self.Styles.BAD_FORMAT) if f.get('ext') in ('f4f', 'f4m') else None,
(self._format_out('Maybe DRM', self.Styles.WARNING) if f.get('has_drm') == 'maybe'
else self._format_out('DRM', self.Styles.BAD_FORMAT) if f.get('has_drm') else None),
self._format_out('Untested', self.Styles.WARNING) if f.get('__needs_testing') else None,
format_field(f, 'format_note'),
format_field(f, 'container', ignore=(None, f.get('ext'))),
delim=', '), delim=' '),

View File

@ -159,6 +159,12 @@ def set_default_compat(compat_name, opt_name, default=True, remove_compat=True):
elif 'prefer-vp9-sort' in opts.compat_opts:
opts.format_sort.extend(FormatSorter._prefer_vp9_sort)
if 'mtime-by-default' in opts.compat_opts:
if opts.updatetime is None:
opts.updatetime = True
else:
_unused_compat_opt('mtime-by-default')
_video_multistreams_set = set_default_compat('multistreams', 'allow_multiple_video_streams', False, remove_compat=False)
_audio_multistreams_set = set_default_compat('multistreams', 'allow_multiple_audio_streams', False, remove_compat=False)
if _video_multistreams_set is False and _audio_multistreams_set is False:

View File

@ -435,7 +435,7 @@ def sub_bytes_inv(data):
def rotate(data):
return data[1:] + [data[0]]
return [*data[1:], data[0]]
def key_schedule_core(data, rcon_iteration):

View File

@ -302,7 +302,7 @@ def _finish_frag_download(self, ctx, info_dict):
elif to_file:
self.try_rename(ctx['tmpfilename'], ctx['filename'])
filetime = ctx.get('fragment_filetime')
if self.params.get('updatetime', True) and filetime:
if self.params.get('updatetime') and filetime:
with contextlib.suppress(Exception):
os.utime(ctx['filename'], (time.time(), filetime))

View File

@ -348,7 +348,7 @@ def retry(e):
self.try_rename(ctx.tmpfilename, ctx.filename)
# Update file modification time
if self.params.get('updatetime', True):
if self.params.get('updatetime'):
info_dict['filetime'] = self.try_utime(ctx.filename, ctx.data.headers.get('last-modified', None))
self._hook_progress({

View File

@ -5,47 +5,46 @@
from .common import FileDownloader
from .external import FFmpegFD
from ..networking import Request
from ..utils import DownloadError, str_or_none, try_get
from ..networking.websocket import WebSocketResponse
from ..utils import DownloadError, str_or_none, truncate_string
from ..utils.traversal import traverse_obj
class NiconicoLiveFD(FileDownloader):
""" Downloads niconico live without being stopped """
def real_download(self, filename, info_dict):
video_id = info_dict['video_id']
ws_url = info_dict['url']
ws_extractor = info_dict['ws']
ws_origin_host = info_dict['origin']
live_quality = info_dict.get('live_quality', 'high')
live_latency = info_dict.get('live_latency', 'high')
video_id = info_dict['id']
opts = info_dict['downloader_options']
quality, ws_extractor, ws_url = opts['max_quality'], opts['ws'], opts['ws_url']
dl = FFmpegFD(self.ydl, self.params or {})
new_info_dict = info_dict.copy()
new_info_dict.update({
'protocol': 'm3u8',
})
new_info_dict['protocol'] = 'm3u8'
def communicate_ws(reconnect):
if reconnect:
ws = self.ydl.urlopen(Request(ws_url, headers={'Origin': f'https://{ws_origin_host}'}))
# Support --load-info-json as if it is a reconnect attempt
if reconnect or not isinstance(ws_extractor, WebSocketResponse):
ws = self.ydl.urlopen(Request(
ws_url, headers={'Origin': 'https://live.nicovideo.jp'}))
if self.ydl.params.get('verbose', False):
self.to_screen('[debug] Sending startWatching request')
self.write_debug('Sending startWatching request')
ws.send(json.dumps({
'type': 'startWatching',
'data': {
'reconnect': True,
'room': {
'commentable': True,
'protocol': 'webSocket',
},
'stream': {
'quality': live_quality,
'protocol': 'hls+fmp4',
'latency': live_latency,
'accessRightMethod': 'single_cookie',
'chasePlay': False,
'latency': 'high',
'protocol': 'hls',
'quality': quality,
},
'room': {
'protocol': 'webSocket',
'commentable': True,
},
'reconnect': True,
},
'type': 'startWatching',
}))
else:
ws = ws_extractor
@ -58,7 +57,6 @@ def communicate_ws(reconnect):
if not data or not isinstance(data, dict):
continue
if data.get('type') == 'ping':
# pong back
ws.send(r'{"type":"pong"}')
ws.send(r'{"type":"keepSeat"}')
elif data.get('type') == 'disconnect':
@ -66,12 +64,10 @@ def communicate_ws(reconnect):
return True
elif data.get('type') == 'error':
self.write_debug(data)
message = try_get(data, lambda x: x['body']['code'], str) or recv
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
return DownloadError(message)
elif self.ydl.params.get('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.to_screen(f'[debug] Server said: {recv}')
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
def ws_main():
reconnect = False
@ -81,7 +77,8 @@ def ws_main():
if ret is True:
return
except BaseException as e:
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
self.to_screen(
f'[niconico:live] {video_id}: Connection error occured, reconnecting after 10 seconds: {e}')
time.sleep(10)
continue
finally:

View File

@ -300,7 +300,6 @@
BrainPOPIlIE,
BrainPOPJrIE,
)
from .bravotv import BravoTVIE
from .breitbart import BreitBartIE
from .brightcove import (
BrightcoveLegacyIE,
@ -806,9 +805,7 @@
from .hotnewhiphop import HotNewHipHopIE
from .hotstar import (
HotStarIE,
HotStarPlaylistIE,
HotStarPrefixIE,
HotStarSeasonIE,
HotStarSeriesIE,
)
from .hrefli import HrefLiRedirectIE
@ -922,10 +919,6 @@
ShugiinItvVodIE,
)
from .jeuxvideo import JeuxVideoIE
from .jiocinema import (
JioCinemaIE,
JioCinemaSeriesIE,
)
from .jiosaavn import (
JioSaavnAlbumIE,
JioSaavnArtistIE,
@ -1108,6 +1101,7 @@
from .massengeschmacktv import MassengeschmackTVIE
from .masters import MastersIE
from .matchtv import MatchTVIE
from .mave import MaveIE
from .mbn import MBNIE
from .mdr import MDRIE
from .medaltv import MedalTVIE
@ -1262,6 +1256,7 @@
)
from .nbc import (
NBCIE,
BravoTVIE,
NBCNewsIE,
NBCOlympicsIE,
NBCOlympicsStreamIE,
@ -1269,6 +1264,7 @@
NBCSportsStreamIE,
NBCSportsVPlayerIE,
NBCStationsIE,
SyfyIE,
)
from .ndr import (
NDRIE,
@ -1828,6 +1824,7 @@
from .saitosan import SaitosanIE
from .samplefocus import SampleFocusIE
from .sapo import SapoIE
from .sauceplus import SaucePlusIE
from .sbs import SBSIE
from .sbscokr import (
SBSCoKrAllvodProgramIE,
@ -2016,13 +2013,11 @@
SverigesRadioPublicationIE,
)
from .svt import (
SVTIE,
SVTPageIE,
SVTPlayIE,
SVTSeriesIE,
)
from .swearnet import SwearnetEpisodeIE
from .syfy import SyfyIE
from .syvdk import SYVDKIE
from .sztvhu import SztvHuIE
from .tagesschau import TagesschauIE

View File

@ -3,6 +3,7 @@
import re
import time
import urllib.parse
import uuid
import xml.etree.ElementTree as etree
from .common import InfoExtractor
@ -10,6 +11,7 @@
from ..utils import (
NO_DEFAULT,
ExtractorError,
parse_qs,
unescapeHTML,
unified_timestamp,
urlencode_postdata,
@ -45,6 +47,8 @@
'name': 'Comcast XFINITY',
'username_field': 'user',
'password_field': 'passwd',
'login_hostname': 'login.xfinity.com',
'needs_newer_ua': True,
},
'TWC': {
'name': 'Time Warner Cable | Spectrum',
@ -74,6 +78,12 @@
'name': 'Verizon FiOS',
'username_field': 'IDToken1',
'password_field': 'IDToken2',
'login_hostname': 'ssoauth.verizon.com',
},
'Fubo': {
'name': 'Fubo',
'username_field': 'username',
'password_field': 'password',
},
'Cablevision': {
'name': 'Optimum/Cablevision',
@ -1338,6 +1348,7 @@
'name': 'Sling TV',
'username_field': 'username',
'password_field': 'password',
'login_hostname': 'identity.sling.com',
},
'Suddenlink': {
'name': 'Suddenlink',
@ -1355,7 +1366,6 @@
class AdobePassIE(InfoExtractor): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
_SERVICE_PROVIDER_TEMPLATE = 'https://sp.auth.adobe.com/adobe-services/%s'
_USER_AGENT = 'Mozilla/5.0 (X11; Linux i686; rv:47.0) Gecko/20100101 Firefox/47.0'
_MODERN_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0'
_MVPD_CACHE = 'ap-mvpd'
_DOWNLOADING_LOGIN_PAGE = 'Downloading Provider Login Page'
@ -1367,6 +1377,14 @@ def _download_webpage_handle(self, *args, **kwargs):
return super()._download_webpage_handle(
*args, **kwargs)
@staticmethod
def _get_mso_headers(mso_info):
# yt-dlp's default user-agent is usually too old for some MSO's like Comcast_SSO
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
return {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:131.0) Gecko/20100101 Firefox/131.0',
} if mso_info.get('needs_newer_ua') else {}
@staticmethod
def _get_mvpd_resource(provider_id, title, guid, rating):
channel = etree.Element('channel')
@ -1382,7 +1400,13 @@ def _get_mvpd_resource(provider_id, title, guid, rating):
resource_rating.text = rating
return '<rss version="2.0" xmlns:media="http://search.yahoo.com/mrss/">' + etree.tostring(channel).decode() + '</rss>'
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource):
def _extract_mvpd_auth(self, url, video_id, requestor_id, resource, software_statement):
mso_id = self.get_param('ap_mso')
if mso_id:
mso_info = MSO_INFO[mso_id]
else:
mso_info = {}
def xml_text(xml_str, tag):
return self._search_regex(
f'<{tag}>(.+?)</{tag}>', xml_str, tag)
@ -1391,15 +1415,27 @@ def is_expired(token, date_ele):
token_expires = unified_timestamp(re.sub(r'[_ ]GMT', '', xml_text(token, date_ele)))
return token_expires and token_expires <= int(time.time())
def post_form(form_page_res, note, data={}):
def post_form(form_page_res, note, data={}, validate_url=False):
form_page, urlh = form_page_res
post_url = self._html_search_regex(r'<form[^>]+action=(["\'])(?P<url>.+?)\1', form_page, 'post url', group='url')
if not re.match(r'https?://', post_url):
post_url = urllib.parse.urljoin(urlh.url, post_url)
if validate_url:
# This request is submitting credentials so we should validate it when possible
url_parsed = urllib.parse.urlparse(post_url)
expected_hostname = mso_info.get('login_hostname')
if expected_hostname and expected_hostname != url_parsed.hostname:
raise ExtractorError(
f'Unexpected login URL hostname; expected "{expected_hostname}" but got '
f'"{url_parsed.hostname}". Aborting before submitting credentials')
if url_parsed.scheme != 'https':
self.write_debug('Upgrading login URL scheme to https')
post_url = urllib.parse.urlunparse(url_parsed._replace(scheme='https'))
form_data = self._hidden_inputs(form_page)
form_data.update(data)
return self._download_webpage_handle(
post_url, video_id, note, data=urlencode_postdata(form_data), headers={
**self._get_mso_headers(mso_info),
'Content-Type': 'application/x-www-form-urlencoded',
})
@ -1432,19 +1468,58 @@ def extract_redirect_url(html, url=None, fatal=False):
}
guid = xml_text(resource, 'guid') if '<' in resource else resource
count = 0
while count < 2:
for _ in range(2):
requestor_info = self.cache.load(self._MVPD_CACHE, requestor_id) or {}
authn_token = requestor_info.get('authn_token')
if authn_token and is_expired(authn_token, 'simpleTokenExpires'):
authn_token = None
if not authn_token:
mso_id = self.get_param('ap_mso')
if mso_id:
if not mso_id:
raise_mvpd_required()
username, password = self._get_login_info('ap_username', 'ap_password', mso_id)
if not username or not password:
raise_mvpd_required()
mso_info = MSO_INFO[mso_id]
device_info, urlh = self._download_json_handle(
'https://sp.auth.adobe.com/indiv/devices',
video_id, 'Registering device with Adobe',
data=json.dumps({'fingerprint': uuid.uuid4().hex}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
device_id = device_info['deviceId']
mvpd_headers['pass_sfp'] = urlh.get_header('pass_sfp')
mvpd_headers['Ap_21'] = device_id
registration = self._download_json(
'https://sp.auth.adobe.com/o/client/register',
video_id, 'Registering client with Adobe',
data=json.dumps({'software_statement': software_statement}).encode(),
headers={'Content-Type': 'application/json; charset=UTF-8'})
access_token = self._download_json(
'https://sp.auth.adobe.com/o/client/token', video_id,
'Obtaining access token', data=urlencode_postdata({
'grant_type': 'client_credentials',
'client_id': registration['client_id'],
'client_secret': registration['client_secret'],
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
})['access_token']
mvpd_headers['Authorization'] = f'Bearer {access_token}'
reg_code = self._download_json(
f'https://sp.auth.adobe.com/reggie/v1/{requestor_id}/regcode',
video_id, 'Obtaining registration code',
data=urlencode_postdata({
'requestor': requestor_id,
'deviceId': device_id,
'format': 'json',
}),
headers={
'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
'Authorization': f'Bearer {access_token}',
})['code']
provider_redirect_page_res = self._download_webpage_handle(
self._SERVICE_PROVIDER_TEMPLATE % 'authenticate/saml', video_id,
@ -1455,17 +1530,10 @@ def extract_redirect_url(html, url=None, fatal=False):
'no_iframe': 'false',
'domain_name': 'adobe.com',
'redirect_url': url,
}, headers={
# yt-dlp's default user-agent is usually too old for Comcast_SSO
# See: https://github.com/yt-dlp/yt-dlp/issues/10848
'User-Agent': self._MODERN_USER_AGENT,
} if mso_id == 'Comcast_SSO' else None)
elif not self._cookies_passed:
raise_mvpd_required()
'reg_code': reg_code,
}, headers=self._get_mso_headers(mso_info))
if not mso_id:
pass
elif mso_id == 'Comcast_SSO':
if mso_id == 'Comcast_SSO':
# Comcast page flow varies by video site and whether you
# are on Comcast's network.
provider_redirect_page, urlh = provider_redirect_page_res
@ -1489,8 +1557,8 @@ def extract_redirect_url(html, url=None, fatal=False):
oauth_redirect_url = extract_redirect_url(
provider_redirect_page, fatal=True)
provider_login_page_res = self._download_webpage_handle(
oauth_redirect_url, video_id,
self._DOWNLOADING_LOGIN_PAGE)
oauth_redirect_url, video_id, self._DOWNLOADING_LOGIN_PAGE,
headers=self._get_mso_headers(mso_info))
else:
provider_login_page_res = post_form(
provider_redirect_page_res,
@ -1500,24 +1568,35 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
mvpd_confirm_page, urlh = mvpd_confirm_page_res
if '<button class="submit" value="Resume">Resume</button>' in mvpd_confirm_page:
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Philo':
# Philo has very unique authentication method
self._download_webpage(
'https://idp.philo.com/auth/init/login_code', video_id, 'Requesting auth code', data=urlencode_postdata({
self._request_webpage(
'https://idp.philo.com/auth/init/login_code', video_id,
'Requesting Philo auth code', data=json.dumps({
'ident': username,
'device': 'web',
'send_confirm_link': False,
'send_token': True,
}))
'device_ident': f'web-{uuid.uuid4().hex}',
'include_login_link': True,
}).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
philo_code = getpass.getpass('Type auth code you have received [Return]: ')
self._download_webpage(
'https://idp.philo.com/auth/update/login_code', video_id, 'Submitting token', data=urlencode_postdata({
'token': philo_code,
}))
self._request_webpage(
'https://idp.philo.com/auth/update/login_code', video_id,
'Submitting token', data=json.dumps({'token': philo_code}).encode(),
headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
})
mvpd_confirm_page_res = self._download_webpage_handle('https://idp.philo.com/idp/submit', video_id, 'Confirming Philo Login')
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Verizon':
@ -1539,7 +1618,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_redirect_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
saml_login_page, urlh = saml_login_page_res
if 'Please try again.' in saml_login_page:
raise ExtractorError(
@ -1560,7 +1639,7 @@ def extract_redirect_url(html, url=None, fatal=False):
[saml_login_page, saml_redirect_url], 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
if 'Please try again.' in saml_login_page:
raise ExtractorError(
'Failed to login, incorrect User ID or Password.')
@ -1631,7 +1710,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@ -1682,7 +1761,7 @@ def extract_redirect_url(html, url=None, fatal=False):
provider_login_page_res, 'Logging in', {
mso_info['username_field']: username,
mso_info['password_field']: password,
})
}, validate_url=True)
provider_refresh_redirect_url = extract_redirect_url(
provider_association_redirect, url=urlh.url)
@ -1699,6 +1778,27 @@ def extract_redirect_url(html, url=None, fatal=False):
query=hidden_data)
post_form(mvpd_confirm_page_res, 'Confirming Login')
elif mso_id == 'Fubo':
_, urlh = provider_redirect_page_res
fubo_response = self._download_json(
'https://api.fubo.tv/partners/tve/connect', video_id,
'Authenticating with Fubo', 'Unable to authenticate with Fubo',
query=parse_qs(urlh.url), data=json.dumps({
'username': username,
'password': password,
}).encode(), headers={
'Accept': 'application/json',
'Content-Type': 'application/json',
})
self._request_webpage(
'https://sp.auth.adobe.com/adobe-services/oauth2', video_id,
'Authenticating with Adobe', 'Failed to authenticate with Adobe',
query={
'code': fubo_response['code'],
'state': fubo_response['state'],
})
else:
# Some providers (e.g. DIRECTV NOW) have another meta refresh
# based redirect that should be followed.
@ -1717,7 +1817,8 @@ def extract_redirect_url(html, url=None, fatal=False):
}
if mso_id in ('Cablevision', 'AlticeOne'):
form_data['_eventId_proceed'] = ''
mvpd_confirm_page_res = post_form(provider_login_page_res, 'Logging in', form_data)
mvpd_confirm_page_res = post_form(
provider_login_page_res, 'Logging in', form_data, validate_url=True)
if mso_id != 'Rogers':
post_form(mvpd_confirm_page_res, 'Confirming Login')
@ -1727,6 +1828,7 @@ def extract_redirect_url(html, url=None, fatal=False):
'Retrieving Session', data=urlencode_postdata({
'_method': 'GET',
'requestor_id': requestor_id,
'reg_code': reg_code,
}), headers=mvpd_headers)
except ExtractorError as e:
if not mso_id and isinstance(e.cause, HTTPError) and e.cause.status == 401:
@ -1734,7 +1836,6 @@ def extract_redirect_url(html, url=None, fatal=False):
raise
if '<pendingLogout' in session:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
authn_token = unescapeHTML(xml_text(session, 'authnToken'))
requestor_info['authn_token'] = authn_token
@ -1755,7 +1856,6 @@ def extract_redirect_url(html, url=None, fatal=False):
}), headers=mvpd_headers)
if '<pendingLogout' in authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
if '<error' in authorize:
raise ExtractorError(xml_text(authorize, 'details'), expected=True)
@ -1778,6 +1878,5 @@ def extract_redirect_url(html, url=None, fatal=False):
}), headers=mvpd_headers)
if '<pendingLogout' in short_authorize:
self.cache.store(self._MVPD_CACHE, requestor_id, {})
count += 1
continue
return short_authorize

View File

@ -84,6 +84,8 @@ class AdultSwimIE(TurnerBaseIE):
'skip': '404 Not Found',
}]
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwNjg5ZmU2My00OTc5LTQxZmQtYWYxNC1hYjVlNmJjNWVkZWIiLCJuYmYiOjE1MzcxOTA2NzQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwNjc0fQ.Xl3AEduM0s1TxDQ6-XssdKIiLm261hhsEv1C1yo_nitIajZThSI9rXILqtIzO0aujoHhdzUnu_dUCq9ffiSBzEG632tTa1la-5tegHtce80cMhewBN4n2t8n9O5tiaPx8MPY8ALdm5wS7QzWE6DO_LTJKgE8Bl7Yv-CWJT4q4SywtNiQWLVOuhBRnDyfsRezxRwptw8qTn9dv5ZzUrVJaby5fDZ_nOncMKvegOgaKd5KEuCAGQ-mg-PSuValMjGuf6FwDguGaK7IyI5Y2oOrzXmD4Dj7q4WBg8w9QoZhtLeAU56mcsGILolku2R5FHlVLO9xhjResyt-pfmegOkpSw'
def _real_extract(self, url):
show_path, episode_path = self._match_valid_url(url).groups()
display_id = episode_path or show_path
@ -152,7 +154,7 @@ def _real_extract(self, url):
# CDN_TOKEN_APP_ID from:
# https://d2gg02c3xr550i.cloudfront.net/assets/asvp.e9c8bef24322d060ef87.bundle.js
'appId': 'eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJhcHBJZCI6ImFzLXR2ZS1kZXNrdG9wLXB0enQ2bSIsInByb2R1Y3QiOiJ0dmUiLCJuZXR3b3JrIjoiYXMiLCJwbGF0Zm9ybSI6ImRlc2t0b3AiLCJpYXQiOjE1MzI3MDIyNzl9.BzSCk-WYOZ2GMCIaeVb8zWnzhlgnXuJTCu0jGp_VaZE',
}, {
}, self._SOFTWARE_STATEMENT, {
'url': url,
'site_name': 'AdultSwim',
'auth_required': auth,

View File

@ -1,3 +1,5 @@
import json
from .theplatform import ThePlatformIE
from ..utils import (
ExtractorError,
@ -6,7 +8,6 @@
remove_start,
traverse_obj,
update_url_query,
urlencode_postdata,
)
@ -20,13 +21,13 @@ class AENetworksBaseIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_THEPLATFORM_KEY = '43jXaGRQud'
_THEPLATFORM_SECRET = 'S10BPXHMlb'
_DOMAIN_MAP = {
'history.com': ('HISTORY', 'history'),
'aetv.com': ('AETV', 'aetv'),
'mylifetime.com': ('LIFETIME', 'lifetime'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc'),
'fyi.tv': ('FYI', 'fyi'),
'historyvault.com': (None, 'historyvault'),
'biography.com': (None, 'biography'),
'history.com': ('HISTORY', 'history', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzZlMTQ3ZS0zMzFhLTQxY2YtYTMwNC01MDA2NzNlOGYwYjYiLCJuYmYiOjE1Mzg2NjMzMDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMzA5fQ.n24-FVHLGXJe2D4atIQZ700aiXKIajKh5PWFoHJ40Az4itjtwwSFHnvufnoal3T8lYkwNLxce7H-IEGxIykRkZEdwq09pMKMT-ft9ASzE4vQ8fAWbf5ZgDME86x4Jq_YaxkRc9Ne0eShGhl8fgTJHvk07sfWcol61HJ7kU7K8FzzcHR0ucFQgA5VNd8RyjoGWY7c6VxnXR214LOpXsywmit04-vGJC102b_WA2EQfqI93UzG6M6l0EeV4n0_ijP3s8_i8WMJZ_uwnTafCIY6G_731i01dKXDLSFzG1vYglAwDa8DTcdrAAuIFFDF6QNGItCCmwbhjufjmoeVb7R1Gg'),
'aetv.com': ('AETV', 'aetv', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI5Y2IwNjg2Yy03ODUxLTRiZDUtODcyMC00MjNlZTg1YTQ1NzMiLCJuYmYiOjE1Mzg2NjMyOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM4NjYzMjkwfQ.T5Elf0X4TndO4NEgqBas1gDxNHGPVk_daO2Ha5FBzVO6xi3zM7eavdAKfYMCN7gpWYJx03iADaVPtczO_t_aGZczDjpwJHgTUzDgvcLZAVsVDqtDIAMy3S846rPgT6UDbVoxurA7B2VTPm9phjrSXhejvd0LBO8MQL4AZ3sy2VmiPJ2noT1ily5PuHCYlkrT1fheO064duR__Cd9DQ5VTMnKjzY3Cx345CEwKDkUk5gwgxhXM-aY0eblehrq8VD81_aRM_O3tvh7nbTydHOnUpV-k_iKVi49gqz7Sf8zb6Zh5z2Uftn3vYCfE5NQuesitoRMnsH17nW7o_D59hkRgg'),
'mylifetime.com': ('LIFETIME', 'lifetime', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJmODg0MDM1ZC1mZGRmLTRmYjgtYmRkMC05MzRhZDdiYTAwYTciLCJuYmYiOjE1NDkzOTI2NDQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQ5MzkyNjQ0fQ.vkTIaCpheKdKQd__2-3ec4qkcpbAhyCTvwe5iTl922ItSQfVhpEJG4wseVSNmBTrpBi0hvLedcw6Hj1_UuzBMVuVcCqLprU-pI8recEwL0u7G-eVkylsxe1OTUm1o3V6OykXQ9KlA-QQLL1neUhdhR1n5B1LZ4cmtBmiEpfgf4rFwXD1ScFylIcaWKLBqHoRBNUmxyTmoXXvn_A-GGSj9eCizFzY8W5uBwUcsoiw2Cr1skx7PbB2RSP1I5DsoIJKG-8XV1KS7MWl-fNLjE-hVAsI9znqfEEFcPBiv3LhCP4Nf4OIs7xAselMn0M0c8igRUZhURWX_hdygUAxkbKFtQ'),
'fyi.tv': ('FYI', 'fyi', 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxOGZiOWM3Ny1mYmMzLTQxYTktYmE1Yi1lMzM0ZmUzNzU4NjEiLCJuYmYiOjE1ODc1ODAzNzcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NTgwMzc3fQ.AYDuipKswmIfLBfOjHRsfc5fMV5NmJUmiJnkpiep4VEw9QiXkygFj4bN06Si5tFc5Mee5TDrGzDpV6iuKbVpLT5kuqXhAn-Wozf5zKPsg_IpdEKO7gsiCq4calt72ct44KTqtKD_hVcoxQU24_HaJsRgXzu3B-6Ff6UrmsXkyvYifYVC9v2DSkdCuA02_IrlllzVT2kRuefUXgL4vQRtTFf77uYa0RKSTG7uVkiQ_AU41eXevKlO2qgtc14Hk5cZ7-ZNrDyMCXYA5ngdIHP7Gs9PWaFXT36PFHI_rC4EfxUABPzjQFxjpP75aX5qn8SH__HbM9q3hoPWgaEaf76qIQ'),
'lifetimemovieclub.com': ('LIFETIMEMOVIECLUB', 'lmc', None),
'historyvault.com': (None, 'historyvault', None),
'biography.com': (None, 'biography', None),
}
def _extract_aen_smil(self, smil_url, video_id, auth=None):
@ -71,7 +72,7 @@ def _extract_aen_smil(self, smil_url, video_id, auth=None):
}
def _extract_aetn_info(self, domain, filter_key, filter_value, url):
requestor_id, brand = self._DOMAIN_MAP[domain]
requestor_id, brand, software_statement = self._DOMAIN_MAP[domain]
result = self._download_json(
f'https://feeds.video.aetnd.com/api/v2/{brand}/videos',
filter_value, query={f'filter[{filter_key}]': filter_value})
@ -95,7 +96,7 @@ def _extract_aetn_info(self, domain, filter_key, filter_value, url):
theplatform_metadata.get('AETN$PPL_pplProgramId') or theplatform_metadata.get('AETN$PPL_pplProgramId_OLD'),
traverse_obj(theplatform_metadata, ('ratings', 0, 'rating')))
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, requestor_id, resource, software_statement)
info.update(self._extract_aen_smil(media_url, video_id, auth))
info.update({
'title': title,
@ -132,10 +133,11 @@ class AENetworksIE(AENetworksBaseIE):
'tags': 'count:14',
'categories': ['Mountain Men'],
'episode_number': 1,
'episode': 'Episode 1',
'episode': 'Winter Is Coming',
'season': 'Season 1',
'season_number': 1,
'series': 'Mountain Men',
'age_limit': 0,
},
'params': {
# m3u8 download
@ -157,18 +159,18 @@ class AENetworksIE(AENetworksBaseIE):
'thumbnail': r're:^https?://.*\.jpe?g$',
'chapters': 'count:4',
'tags': 'count:23',
'episode': 'Episode 1',
'episode': 'Inlawful Entry',
'episode_number': 1,
'season': 'Season 9',
'season_number': 9,
'series': 'Duck Dynasty',
'age_limit': 0,
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'This video is only available for users of participating TV providers.',
}, {
'url': 'http://www.fyi.tv/shows/tiny-house-nation/season-1/episode-8',
'only_matching': True,
@ -203,18 +205,19 @@ def _real_extract(self, url):
class AENetworksListBaseIE(AENetworksBaseIE):
def _call_api(self, resource, slug, brand, fields):
return self._download_json(
'https://yoga.appsvcs.aetnd.com/graphql',
slug, query={'brand': brand}, data=urlencode_postdata({
'https://yoga.appsvcs.aetnd.com/graphql', slug,
query={'brand': brand}, headers={'Content-Type': 'application/json'},
data=json.dumps({
'query': '''{
%s(slug: "%s") {
%s
}
}''' % (resource, slug, fields), # noqa: UP031
}))['data'][resource]
}).encode())['data'][resource]
def _real_extract(self, url):
domain, slug = self._match_valid_url(url).groups()
_, brand = self._DOMAIN_MAP[domain]
_, brand, _ = self._DOMAIN_MAP[domain]
playlist = self._call_api(self._RESOURCE, slug, brand, self._FIELDS)
base_url = f'http://watch.{domain}'

View File

@ -816,6 +816,26 @@ class BiliBiliBangumiIE(BilibiliBaseIE):
'upload_date': '20111104',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'note': 'new playurlSSRData scheme',
'url': 'https://www.bilibili.com/bangumi/play/ep678060',
'info_dict': {
'id': '678060',
'ext': 'mp4',
'series': '去你家吃饭好吗',
'series_id': '6198',
'season': '第二季',
'season_id': '42542',
'season_number': 2,
'episode': '吴老二:你家大公鸡养不熟,能煮熟吗…',
'episode_id': '678060',
'episode_number': 61,
'title': '一只小九九丫 吴老二:你家大公鸡养不熟,能煮熟吗…',
'duration': 266.123,
'timestamp': 1663315904,
'upload_date': '20220916',
'thumbnail': r're:^https?://.*\.(jpg|jpeg|png)$',
},
}, {
'url': 'https://www.bilibili.com/bangumi/play/ep267851',
'info_dict': {
@ -879,13 +899,27 @@ def _real_extract(self, url):
'Extracting episode', query={'fnval': 12240, 'ep_id': episode_id},
headers=headers))
geo_blocked = traverse_obj(play_info, (
'raw', 'data', 'plugins', lambda _, v: v['name'] == 'AreaLimitPanel', 'config', 'is_block', {bool}, any))
premium_only = play_info.get('code') == -10403
play_info = traverse_obj(play_info, ('result', 'video_info', {dict})) or {}
formats = self.extract_formats(play_info)
if not formats and (premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage):
video_info = traverse_obj(play_info, (('result', ('raw', 'data')), 'video_info', {dict}, any)) or {}
formats = self.extract_formats(video_info)
if not formats:
if geo_blocked:
self.raise_geo_restricted()
elif premium_only or '成为大会员抢先看' in webpage or '开通大会员观看' in webpage:
self.raise_login_required('This video is for premium members only')
if traverse_obj(play_info, ((
('result', 'play_check', 'play_detail'), # 'PLAY_PREVIEW' vs 'PLAY_WHOLE'
('raw', 'data', 'play_video_type'), # 'preview' vs 'whole'
), any, {lambda x: x in ('PLAY_PREVIEW', 'preview')})):
self.report_warning(
'Only preview format is available, '
f'you have to become a premium member to access full video. {self._login_hint()}')
bangumi_info = self._download_json(
'https://api.bilibili.com/pgc/view/web/season', episode_id, 'Get episode details',
query={'ep_id': episode_id}, headers=headers)['result']
@ -922,7 +956,7 @@ def _real_extract(self, url):
'season': str_or_none(season_title),
'season_id': str_or_none(season_id),
'season_number': season_number,
'duration': float_or_none(play_info.get('timelength'), scale=1000),
'duration': float_or_none(video_info.get('timelength'), scale=1000),
'subtitles': self.extract_subtitles(episode_id, episode_info.get('cid'), aid=aid),
'__post_extractor': self.extract_comments(aid),
'http_headers': {'Referer': url},
@ -1192,6 +1226,26 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
'id': '313580179',
},
'playlist_mincount': 92,
}, {
# Hidden-mode collection
'url': 'https://space.bilibili.com/3669403/video',
'info_dict': {
'id': '3669403',
},
'playlist': [{
'info_dict': {
'_type': 'playlist',
'id': '3669403_3958082',
'title': '合集·直播回放',
'description': '',
'uploader': '月路Yuel',
'uploader_id': '3669403',
'timestamp': int,
'upload_date': str,
'thumbnail': str,
},
}],
'params': {'playlist_items': '7'},
}]
def _real_extract(self, url):
@ -1248,7 +1302,13 @@ def get_metadata(page_data):
}
def get_entries(page_data):
for entry in traverse_obj(page_data, ('list', 'vlist')) or []:
for entry in traverse_obj(page_data, ('list', 'vlist', ..., {dict})):
if traverse_obj(entry, ('meta', 'attribute')) == 156:
# hidden-mode collection doesn't show its videos in uploads; extract as playlist instead
yield self.url_result(
f'https://space.bilibili.com/{entry["mid"]}/lists/{entry["meta"]["id"]}?type=season',
BilibiliCollectionListIE, f'{entry["mid"]}_{entry["meta"]["id"]}')
else:
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)

View File

@ -1,188 +0,0 @@
from .adobepass import AdobePassIE
from ..networking import HEADRequest
from ..utils import (
extract_attributes,
float_or_none,
get_element_html_by_class,
int_or_none,
merge_dicts,
parse_age_limit,
remove_end,
str_or_none,
traverse_obj,
unescapeHTML,
unified_timestamp,
update_url_query,
url_or_none,
)
class BravoTVIE(AdobePassIE):
_VALID_URL = r'https?://(?:www\.)?(?P<site>bravotv|oxygen)\.com/(?:[^/]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'info_dict': {
'id': '3923059',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'description': 'Find out who takes the title of Top Chef!',
'upload_date': '20190314',
'timestamp': 1552591860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'The Top Chef Season 16 Winner Is...',
'duration': 190.357,
'season': 'Season 16',
'thumbnail': r're:^https://.+\.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
'info_dict': {
'id': '9000234570',
'ext': 'mp4',
'title': 'London Calling',
'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
'upload_date': '20230310',
'timestamp': 1678410000,
'season_number': 20,
'episode_number': 1,
'series': 'Top Chef',
'episode': 'London Calling',
'duration': 3266.03,
'season': 'Season 20',
'chapters': 'count:7',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
'info_dict': {
'id': '3692045',
'ext': 'mp4',
'title': 'Closing Night',
'description': 'md5:3170065c5c2f19548d72a4cbc254af63',
'upload_date': '20180401',
'timestamp': 1522623600,
'season_number': 1,
'episode_number': 1,
'series': 'In Ice Cold Blood',
'episode': 'Closing Night',
'duration': 2629.051,
'season': 'Season 1',
'chapters': 'count:6',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'info_dict': {
'id': '3974019',
'ext': 'mp4',
'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
'upload_date': '20190617',
'timestamp': 1560790800,
'season_number': 2,
'episode_number': 16,
'series': 'In Ice Cold Blood',
'episode': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'duration': 68.235,
'season': 'Season 2',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
settings = self._search_json(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>', webpage, 'settings', display_id)
tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
query = {
'manifest': 'm3u',
'formats': 'm3u,mpeg4',
}
if tve:
account_pid = tve.get('data-mpx-media-account-pid') or 'HNK2IC'
account_id = tve['data-mpx-media-account-id']
metadata = self._parse_json(
tve.get('data-normalized-video', ''), display_id, fatal=False, transform_source=unescapeHTML)
video_id = tve.get('data-guid') or metadata['guid']
if tve.get('data-entitlement') == 'auth':
auth = traverse_obj(settings, ('tve_adobe_auth', {dict})) or {}
site = remove_end(site, 'tv')
release_pid = tve['data-release-pid']
resource = self._get_mvpd_resource(
tve.get('data-adobe-pass-resource-id') or auth.get('adobePassResourceId') or site,
tve['data-title'], release_pid, tve.get('data-rating'))
query.update({
'switch': 'HLSServiceSecure',
'auth': self._extract_mvpd_auth(
url, release_pid, auth.get('adobePassRequestorId') or site, resource),
})
else:
ls_playlist = traverse_obj(settings, ('ls_playlist', ..., {dict}), get_all=False) or {}
account_pid = ls_playlist.get('mpxMediaAccountPid') or 'PHSl-B'
account_id = ls_playlist['mpxMediaAccountId']
video_id = ls_playlist['defaultGuid']
metadata = traverse_obj(
ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, {dict}), get_all=False)
tp_url = f'https://link.theplatform.com/s/{account_pid}/media/guid/{account_id}/{video_id}'
tp_metadata = self._download_json(
update_url_query(tp_url, {'format': 'preview'}), video_id, fatal=False)
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
}))
# prune pointless single chapters that span the entire duration from short videos
if len(chapters) == 1 and not traverse_obj(chapters, (0, 'end_time')):
chapters = None
m3u8_url = self._request_webpage(HEADRequest(
update_url_query(f'{tp_url}/stream.m3u8', query)), video_id, 'Checking m3u8 URL').url
if 'mpeg_cenc' in m3u8_url:
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
return {
'id': video_id,
'formats': formats,
'subtitles': subtitles,
'chapters': chapters,
**merge_dicts(traverse_obj(tp_metadata, {
'title': 'title',
'description': 'description',
'duration': ('duration', {float_or_none(scale=1000)}),
'timestamp': ('pubDate', {float_or_none(scale=1000)}),
'season_number': (('pl1$seasonNumber', 'nbcu$seasonNumber'), {int_or_none}),
'episode_number': (('pl1$episodeNumber', 'nbcu$episodeNumber'), {int_or_none}),
'series': (('pl1$show', 'nbcu$show'), (None, ...), {str}),
'episode': (('title', 'pl1$episodeNumber', 'nbcu$episodeNumber'), {str_or_none}),
'age_limit': ('ratings', ..., 'rating', {parse_age_limit}),
}, get_all=False), traverse_obj(metadata, {
'title': 'title',
'description': 'description',
'duration': ('durationInSeconds', {int_or_none}),
'timestamp': ('airDate', {unified_timestamp}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode': 'episodeTitle',
'series': 'show',
})),
}

View File

@ -495,8 +495,6 @@ def _real_extract(self, url):
class BrightcoveNewBaseIE(AdobePassIE):
def _parse_brightcove_metadata(self, json_data, video_id, headers={}):
title = json_data['name'].strip()
formats, subtitles = [], {}
sources = json_data.get('sources') or []
for source in sources:
@ -600,16 +598,18 @@ def build_format_id(kind):
return {
'id': video_id,
'title': title,
'description': clean_html(json_data.get('description')),
'thumbnails': thumbnails,
'duration': duration,
'timestamp': parse_iso8601(json_data.get('published_at')),
'uploader_id': json_data.get('account_id'),
'formats': formats,
'subtitles': subtitles,
'tags': json_data.get('tags', []),
'is_live': is_live,
**traverse_obj(json_data, {
'title': ('name', {clean_html}),
'description': ('description', {clean_html}),
'tags': ('tags', ..., {str}, filter, all, filter),
'timestamp': ('published_at', {parse_iso8601}),
'uploader_id': ('account_id', {str}),
}),
}
@ -645,10 +645,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'uploader_id': '4036320279001',
'formats': 'mincount:39',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': '404 Not Found',
}, {
# playlist stream
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
@ -709,7 +706,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD_01-032_5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1646078943,
'uploader_id': '1569565978001',
'upload_date': '20220228',
@ -721,7 +717,6 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
'ext': 'mp4',
'title': 'TGD 01-087 (Airs 05.25.22)_Segment 5',
'thumbnail': r're:^https?://.*\.jpg$',
'tags': [],
'timestamp': 1651604591,
'uploader_id': '1569565978001',
'upload_date': '20220503',
@ -923,10 +918,18 @@ def extract_policy_key():
errors = json_data.get('errors')
if errors and errors[0].get('error_subcode') == 'TVE_AUTH':
custom_fields = json_data['custom_fields']
missing_fields = ', '.join(
key for key in ('source_url', 'software_statement') if not smuggled_data.get(key))
if missing_fields:
raise ExtractorError(
f'Missing fields in smuggled data: {missing_fields}. '
f'This video can be only extracted from the webpage where it is embedded. '
f'Pass the URL of the embedding webpage instead of the Brightcove URL', expected=True)
tve_token = self._extract_mvpd_auth(
smuggled_data['source_url'], video_id,
custom_fields['bcadobepassrequestorid'],
custom_fields['bcadobepassresourceid'])
custom_fields['bcadobepassresourceid'],
smuggled_data['software_statement'])
json_data = self._download_json(
api_url, video_id, headers={
'Accept': f'application/json;pk={policy_key}',

View File

@ -11,7 +11,7 @@
class CloudyCDNIE(InfoExtractor):
_VALID_URL = r'(?:https?:)?//embed\.cloudycdn\.services/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_VALID_URL = r'(?:https?:)?//embed\.(?P<domain>cloudycdn\.services|backscreen\.com)/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
_EMBED_REGEX = [rf'<iframe[^>]+\bsrc=[\'"](?P<url>{_VALID_URL})']
_TESTS = [{
'url': 'https://embed.cloudycdn.services/ltv/media/46k_d23-6000-105?',
@ -23,7 +23,7 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
},
}, {
'url': 'https://embed.cloudycdn.services/izm/media/26e_lv-8-5-1',
@ -33,7 +33,7 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'title': 'LV-8-5-1',
'timestamp': 1669767167,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
'duration': 1205,
'upload_date': '20221130',
},
@ -48,9 +48,21 @@ class CloudyCDNIE(InfoExtractor):
'duration': 1673,
'title': 'D24-6000-074-cetstud',
'timestamp': 1718902233,
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
},
'params': {'format': 'bv'},
}, {
'url': 'https://embed.backscreen.com/ltv/media/32j_z25-0600-127?',
'md5': '9b6fa09ac1a4de53d4f42b94affc3b42',
'info_dict': {
'id': '32j_z25-0600-127',
'ext': 'mp4',
'title': 'Z25-0600-127-DZ',
'duration': 1906,
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/977427/placeholder1746633646.jpg',
'timestamp': 1746632402,
'upload_date': '20250507',
},
}]
_WEBPAGE_TESTS = [{
'url': 'https://www.tavaklase.lv/video/es-esmu-mina-um-2/',
@ -60,17 +72,17 @@ class CloudyCDNIE(InfoExtractor):
'ext': 'mp4',
'upload_date': '20230223',
'duration': 629,
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
'timestamp': 1677181513,
'title': 'LIB-2',
},
}]
def _real_extract(self, url):
site_id, video_id = self._match_valid_url(url).group('site_id', 'id')
domain, site_id, video_id = self._match_valid_url(url).group('domain', 'site_id', 'id')
data = self._download_json(
f'https://player.cloudycdn.services/player/{site_id}/media/{video_id}/',
f'https://player.{domain}/player/{site_id}/media/{video_id}/',
video_id, data=urlencode_postdata({
'version': '6.4.0',
'referer': url,

View File

@ -1,5 +1,6 @@
import base64
import collections
import contextlib
import functools
import getpass
import http.client
@ -101,6 +102,7 @@
xpath_with_ns,
)
from ..utils._utils import _request_dump_filename
from ..utils.jslib import devalue
class InfoExtractor:
@ -262,6 +264,9 @@ class InfoExtractor:
* http_chunk_size Chunk size for HTTP downloads
* ffmpeg_args Extra arguments for ffmpeg downloader (input)
* ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
* ws (NiconicoLiveFD only) WebSocketResponse
* ws_url (NiconicoLiveFD only) Websockets URL
* max_quality (NiconicoLiveFD only) Max stream quality string
* is_dash_periods Whether the format is a result of merging
multiple DASH periods.
RTMP formats can also have the additional fields: page_url,
@ -1675,9 +1680,9 @@ def extract_video_object(e):
'ext': mimetype2ext(e.get('encodingFormat')),
'title': unescapeHTML(e.get('name')),
'description': unescapeHTML(e.get('description')),
'thumbnails': [{'url': unescapeHTML(url)}
for url in variadic(traverse_obj(e, 'thumbnailUrl', 'thumbnailURL'))
if url_or_none(url)],
'thumbnails': traverse_obj(e, (('thumbnailUrl', 'thumbnailURL', 'thumbnail_url'), (None, ...), {
'url': ({str}, {unescapeHTML}, {self._proto_relative_url}, {url_or_none}),
})),
'duration': parse_duration(e.get('duration')),
'timestamp': unified_timestamp(e.get('uploadDate')),
# author can be an instance of 'Organization' or 'Person' types.
@ -1795,6 +1800,63 @@ def _search_nuxt_data(self, webpage, video_id, context_name='__NUXT__', *, fatal
ret = self._parse_json(js, video_id, transform_source=functools.partial(js_to_json, vars=args), fatal=fatal)
return traverse_obj(ret, traverse) or {}
def _resolve_nuxt_array(self, array, video_id, *, fatal=True, default=NO_DEFAULT):
"""Resolves Nuxt rich JSON payload arrays"""
# Ref: https://github.com/nuxt/nuxt/commit/9e503be0f2a24f4df72a3ccab2db4d3e63511f57
# https://github.com/nuxt/nuxt/pull/19205
if default is not NO_DEFAULT:
fatal = False
if not isinstance(array, list) or not array:
error_msg = 'Unable to resolve Nuxt JSON data: invalid input'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id)
return {} if default is NO_DEFAULT else default
def indirect_reviver(data):
return data
def json_reviver(data):
return json.loads(data)
gen = devalue.parse_iter(array, revivers={
'NuxtError': indirect_reviver,
'EmptyShallowRef': json_reviver,
'EmptyRef': json_reviver,
'ShallowRef': indirect_reviver,
'ShallowReactive': indirect_reviver,
'Ref': indirect_reviver,
'Reactive': indirect_reviver,
})
while True:
try:
error_msg = f'Error resolving Nuxt JSON: {gen.send(None)}'
if fatal:
raise ExtractorError(error_msg, video_id=video_id)
elif default is NO_DEFAULT:
self.report_warning(error_msg, video_id=video_id, only_once=True)
else:
self.write_debug(f'{video_id}: {error_msg}', only_once=True)
except StopIteration as error:
return error.value or ({} if default is NO_DEFAULT else default)
def _search_nuxt_json(self, webpage, video_id, *, fatal=True, default=NO_DEFAULT):
"""Parses metadata from Nuxt rich JSON payloads embedded in HTML"""
passed_default = default is not NO_DEFAULT
array = self._search_json(
r'<script\b[^>]+\bid="__NUXT_DATA__"[^>]*>', webpage,
'Nuxt JSON data', video_id, contains_pattern=r'\[(?s:.+)\]',
fatal=fatal, default=NO_DEFAULT if not passed_default else None)
if not array:
return default if passed_default else {}
return self._resolve_nuxt_array(array, video_id, fatal=fatal, default=default)
@staticmethod
def _hidden_inputs(html):
html = re.sub(r'<!--(?:(?!<!--).)*-->', '', html)
@ -2068,21 +2130,33 @@ def _extract_m3u8_formats_and_subtitles(
raise ExtractorError(errnote, video_id=video_id)
self.report_warning(f'{errnote}{bug_reports_message()}')
return [], {}
res = self._download_webpage_handle(
m3u8_url, video_id,
note='Downloading m3u8 information' if note is None else note,
errnote='Failed to download m3u8 information' if errnote is None else errnote,
if note is None:
note = 'Downloading m3u8 information'
if errnote is None:
errnote = 'Failed to download m3u8 information'
response = self._request_webpage(
m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, data=data, headers=headers, query=query)
if res is False:
if response is False:
return [], {}
m3u8_doc, urlh = res
m3u8_url = urlh.url
with contextlib.closing(response):
prefix = response.read(512)
if not prefix.startswith(b'#EXTM3U'):
msg = 'Response data has no m3u header'
if fatal:
raise ExtractorError(msg, video_id=video_id)
self.report_warning(f'{msg}{bug_reports_message()}', video_id=video_id)
return [], {}
content = self._webpage_read_content(
response, m3u8_url, video_id, note=note, errnote=errnote,
fatal=fatal, prefix=prefix, data=data)
if content is False:
return [], {}
return self._parse_m3u8_formats_and_subtitles(
m3u8_doc, m3u8_url, ext=ext, entry_protocol=entry_protocol,
content, response.url, ext=ext, entry_protocol=entry_protocol,
preference=preference, quality=quality, m3u8_id=m3u8_id,
note=note, errnote=errnote, fatal=fatal, live=live, data=data,
headers=headers, query=query, video_id=video_id)

View File

@ -206,7 +206,7 @@ def _real_extract(self, url):
'is_live': True,
**traverse_obj(room, {
'display_id': ('url', {str}, {lambda i: i[1:]}),
'title': ('room_name', {unescapeHTML}),
'title': ('room_name', {str}, {unescapeHTML}),
'description': ('show_details', {str}),
'uploader': ('nickname', {str}),
'thumbnail': ('room_src', {url_or_none}),

View File

@ -64,7 +64,7 @@ class DreiSatIE(ZDFBaseIE):
'title': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'description': 'md5:bae51bfc22f15563ce3acbf97d2e8844',
'duration': 5399.0,
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1743329640903',
'thumbnail': 'https://www.3sat.de/assets/buchmesse-kerkeling-100~original?cb=1747256996338',
'chapters': 'count:24',
'episode': 'dein buch - Das Beste von der Leipziger Buchmesse 2025 - Teil 1',
'episode_id': 'POS_1ef236cc-b390-401e-acd0-4fb4b04315fb',

View File

@ -329,6 +329,7 @@ class WatchESPNIE(AdobePassIE):
}]
_API_KEY = 'ZXNwbiZicm93c2VyJjEuMC4w.ptUt7QxsteaRruuPmGZFaJByOoqKvDP2a5YkInHrc7c'
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIyZGJmZWM4My03OWE1LTQyNzEtYTVmZC04NTZjYTMxMjRjNjMiLCJuYmYiOjE1NDAyMTI3NjEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTQwMjEyNzYxfQ.yaK3r4AI2uLVvsyN1GLzqzgzRlxMPtasSaiYYBV0wIstqih5tvjTmeoLmi8Xy9Kp_U7Md-bOffwiyK3srHkpUkhhwXLH2x6RPjmS1tPmhaG7-3LBcHTf2ySPvXhVf7cN4ngldawK4tdtLtsw6rF_JoZE2yaC6XbS2F51nXSFEDDnOQWIHEQRG3aYAj-38P2CLGf7g-Yfhbp5cKXeksHHQ90u3eOO4WH0EAjc9oO47h33U8KMEXxJbvjV5J8Va2G2fQSgLDZ013NBI3kQnE313qgqQh2feQILkyCENpB7g-TVBreAjOaH1fU471htSoGGYepcAXv-UDtpgitDiLy7CQ'
def _call_bamgrid_api(self, path, video_id, payload=None, headers={}):
if 'Authorization' not in headers:
@ -405,8 +406,8 @@ def _real_extract(self, url):
# TV Provider required
else:
resource = self._get_mvpd_resource('ESPN', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource).encode()
resource = self._get_mvpd_resource('espn1', video_data['name'], video_id, None)
auth = self._extract_mvpd_auth(url, video_id, 'ESPN', resource, self._SOFTWARE_STATEMENT).encode()
asset = self._download_json(
f'https://watch.auth.api.espn.com/video/auth/media/{video_id}/asset?apikey=uiqlbgzdwuru14v627vdusswb',

View File

@ -17,8 +17,140 @@
from ..utils.traversal import traverse_obj
class FloatplaneIE(InfoExtractor):
class FloatplaneBaseIE(InfoExtractor):
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
f'{self._BASE_URL}/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data',
impersonate=self._IMPERSONATE_TARGET)
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], f'{self._BASE_URL}/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
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',
impersonate=self._IMPERSONATE_TARGET)
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
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}))
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,
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
if not m3u8_data:
continue
key_url = self._search_regex(
r'#EXT-X-KEY:METHOD=AES-128,URI="(https?://[^"]+)"',
m3u8_data, 'HLS AES key URI', default=None)
if key_url:
urlh = self._request_webpage(
key_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
note=join_nonempty('Downloading', format_id, 'HLS AES key', delim=' '),
errnote=join_nonempty('Failed to download', format_id, 'HLS AES key', delim=' '))
if urlh:
hls_aes['key'] = urlh.read().hex()
formats.append({
**traverse_obj(quality, {
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
'format_id': format_id,
'hls_media_playlist_data': m3u8_data,
'hls_aes': hls_aes or None,
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'http_headers': self._HEADERS,
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneIE(FloatplaneBaseIE):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/post/(?P<id>\w+)'
_BASE_URL = 'https://www.floatplane.com'
_IMPERSONATE_TARGET = None
_HEADERS = {
'Origin': _BASE_URL,
'Referer': f'{_BASE_URL}/',
}
_TESTS = [{
'url': 'https://www.floatplane.com/post/2Yf3UedF7C',
'info_dict': {
@ -170,105 +302,9 @@ class FloatplaneIE(InfoExtractor):
}]
def _real_initialize(self):
if not self._get_cookies('https://www.floatplane.com').get('sails.sid'):
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
self.raise_login_required()
def _real_extract(self, url):
post_id = self._match_id(url)
post_data = self._download_json(
'https://www.floatplane.com/api/v3/content/post', post_id, query={'id': post_id},
note='Downloading post data', errnote='Unable to download post data')
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
raise ExtractorError('Post does not contain a video or audio track', expected=True)
uploader_url = format_field(
post_data, [('creator', 'urlname')], 'https://www.floatplane.com/channel/%s/home') or None
common_info = {
'uploader_url': uploader_url,
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
'availability': self._availability(needs_subscription=True),
**traverse_obj(post_data, {
'uploader': ('creator', 'title', {str}),
'uploader_id': ('creator', 'id', {str}),
'channel': ('channel', 'title', {str}),
'channel_id': ('channel', 'id', {str}),
'release_timestamp': ('releaseDate', {parse_iso8601}),
}),
}
items = []
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
media_id = media['id']
media_typ = media.get('type') or 'video'
metadata = self._download_json(
f'https://www.floatplane.com/api/v3/content/{media_typ}', media_id, query={'id': media_id},
note=f'Downloading {media_typ} metadata')
stream = self._download_json(
'https://www.floatplane.com/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')
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
def format_path(params):
path = path_template
for i, val in (params or {}).items():
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
return path
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}))))
formats.append({
**traverse_obj(quality, {
'format_id': ('name', {str}),
'format_note': ('label', {str}),
'width': ('width', {int}),
'height': ('height', {int}),
}),
**parse_codecs(quality.get('codecs')),
'url': url,
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
})
items.append({
**common_info,
'id': media_id,
**traverse_obj(metadata, {
'title': ('title', {str}),
'duration': ('duration', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
'formats': formats,
})
post_info = {
**common_info,
'id': post_id,
'display_id': post_id,
**traverse_obj(post_data, {
'title': ('title', {str}),
'description': ('text', {clean_html}),
'like_count': ('likes', {int_or_none}),
'dislike_count': ('dislikes', {int_or_none}),
'comment_count': ('comments', {int_or_none}),
'thumbnail': ('thumbnail', 'path', {url_or_none}),
}),
}
if len(items) > 1:
return self.playlist_result(items, **post_info)
post_info.update(items[0])
return post_info
class FloatplaneChannelIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'

View File

@ -7,161 +7,157 @@
int_or_none,
join_nonempty,
parse_age_limit,
remove_end,
remove_start,
traverse_obj,
try_get,
unified_timestamp,
urlencode_postdata,
)
from ..utils.traversal import traverse_obj
class GoIE(AdobePassIE):
_SITE_INFO = {
'abc': {
'brand': '001',
'requestor_id': 'ABC',
'requestor_id': 'dtci',
'provider_id': 'ABC',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI4OTcwMjlkYS0yYjM1LTQyOWUtYWQ0NS02ZjZiZjVkZTdhOTUiLCJuYmYiOjE2MjAxNzM5NjksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNjIwMTczOTY5fQ.SC69DVJWSL8sIe-vVUrP6xS_kzHKqwz9PdKYexs_y-f7Vin6mM-7S-W1TE_-K55O0pyf-TL4xYgvm6LIye8CckG-nZfVwNPV4huduov0jmIcxCQFeUwkHULG2IaA44wfBVUBdaHgkhPweZ2amjycO_IXtez-gBXOLbE3B7Gx9j_5ISCFtyVUblThKfoGyQv6KT6t8Vpmc4ZSKCCQp74KWFFypydb9ucego1taW_nQD06Cdf4yByLd6NaTBceMcIKbug9b9gxFm3XBgJ5q3z7KGo1Kr6XalAV5j4m-fQ91wczlTilX8FM4AljMupyRM9mA_aEADILQ4hS79q4SM0w6w',
},
'freeform': {
'brand': '002',
'requestor_id': 'ABCFamily',
},
'watchdisneychannel': {
'brand': '004',
'resource_id': 'Disney',
},
'watchdisneyjunior': {
'brand': '008',
'resource_id': 'DisneyJunior',
},
'watchdisneyxd': {
'brand': '009',
'resource_id': 'DisneyXD',
'provider_id': 'ABCFamily',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhZWM2MGYyNC0xYzRjLTQ1NzQtYjc0Zi03ZmM4N2E5YWMzMzgiLCJuYmYiOjE1ODc2NjU5MjMsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTg3NjY1OTIzfQ.flCn3dhvmvPnWmV0JV8Fm0YFyj07yPez9-n1GFEwVIm_S2wQVWbWyJhqsAyLZVFrhOMZYTqmPS3OHxGwTwXkEYn6PD7o_vIVG3oqi-Xn1m5jRt_Gazw5qEtpat6VE7bvKGSD3ZhcidOrsCk8NcYyq75u61NHDvSl81pcedJjVRVUpsqrEwmo0aVbA0C8PX3ri0mEbGvkMKvHn8E60xp-PSE-VK8SDT0plwPu_TwUszkZ6-_I8_2xcv_WBqcXFkAVg7Q-iNJXgQvmNsrpcrYuLvi6hEH4ZLtoDcXU6MhwTQAJTiHSo8x9aHX1_qFP09CzlNOFQbC2ZEJdP9SvA53SLQ',
},
'disneynow': {
'brand': '011',
'brand': '011', # also: '004', '008', '009'
'requestor_id': 'DisneyChannels',
'provider_id': 'DisneyChannels',
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1MzAzNTRiOS04NDNiLTRkNjAtYTQ3ZS0yNzk1MzlkOTIyNTciLCJuYmYiOjE1NTg5ODc0NDksImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTU4OTg3NDQ5fQ.Jud6YS6-J2h0h6po0oMheDym0qRTJQGj4kzacrz4DFuEwhcBkkykW6pF5pKuAUJy9HCZ40oDAHe2KcTlDJjCZF5tDaUEfdihakZ9cC_rG7MU-QoRne8qaB_dPDKwGuk-ZyWD8eV3zwTJmbGo8hDxYTEU81YNCxwhyc_BPDr5TYiubbmpP3_pTnXmSpuL58isJ2peSKWlX9BacuXtBY25c_QnPFKk-_EETm7IHkTpDazde1QfHWGu4s4yJpKGk8RVVujVG6h6ELlL-ZeYLilBm7iS7h1TYG1u7fJhyZRL7isaom6NvAzsvN3ngss1fLwt8decP8wzdFHrbYTdTjW8qw',
'resource_id': 'Disney',
},
'fxnow.fxnetworks': {
'brand': '025',
'fxnetworks': {
'brand': '025', # also: '020'
'requestor_id': 'dtci',
'provider_id': 'fx', # also 'fxx', 'fxm'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIzYWRhYWZiNC02OTAxLTRlYzktOTdmNy1lYWZkZTJkODJkN2EiLCJuYmYiOjE1NjIwMjQwNzYsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDI0MDc2fQ.dhKMpZK50AObbZYrMiYPSfWtzXHUaeMP3jrIY4Cgfvh0GaEgk0Mns_zp78jypFeZgRtPVleQMQDNq2YEloRLcAGqP1aa6WVDglnK77ZWUm4IKai14Rwf3A6YBhSRoO2_lMmUGkuTf6gZY-kMIPqBYKqzTQiQl4HbniPFodIzFRiuI9QJVrkoyTGrJL4oqiX08PoFI3Z-TOti1Heu3EbFC-GveQHhlinYrzU7rbiAqLEz7FImtfBDsnXX1Y3uJDLYM3Bq4Oh0nrzTv1Fd62wNsCNErHHIbELidh1zZF0ujvt7ReuZUwAitm0UhEJ7OxNOUbEQWtae6pVNscvdvTFMpg',
},
'nationalgeographic': {
'brand': '026', # also '023'
'requestor_id': 'dtci',
'provider_id': 'ngc', # also 'ngw'
'software_statement': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIxMzE4YTM1Ni05Mjc4LTQ4NjEtYTFmNi1jMTIzMzg1ZWMzYzMiLCJuYmYiOjE1NjIwMjM4MjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTYyMDIzODI4fQ.Le-2OzF9-jrhJ7ZfWtLWk5iSHGVZoxeU1w0_fO--Heli0OwRZsRq2slSmx-oZTzxuWmAgDEiBkWSDcDK6sM25DrCLsdsJa3MBuZ-slBRtH8aq3HpNoqqLkU-vg6gRUEKMtwBUtwCu_9aKUCayYtndWv4b1DjVQeSrteOW5NNudWVYleAe0kxeNJQHo5If9SCzDudKVJktFUjhNks4QPOC_uONPkRRlL9D0fNvtOY-LRFckfcHhf5z9l1iZjeukV0YhdKnuw1wyiaWrQXBUDiBfbkCRd2DM-KnelqPxfiXCaTjGKDURRBO3pz33ebge3IFXSiU5vl4qHQ8xvunzGpFw',
},
}
_VALID_URL = r'''(?x)
https?://
(?P<sub_domain>
(?:{}\.)?go|fxnow\.fxnetworks|
(?:www\.)?(?:abc|freeform|disneynow)
)\.com/
(?:
(?:[^/]+/)*(?P<id>[Vv][Dd][Kk][Aa]\w+)|
(?:[^/]+/)*(?P<display_id>[^/?\#]+)
)
'''.format(r'\.|'.join(list(_SITE_INFO.keys())))
_URL_PATH_RE = r'(?:video|episode|movies-and-specials)/(?P<id>[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12})'
_VALID_URL = [
fr'https?://(?:www\.)?(?P<site>abc)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>freeform)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>disneynow)\.com/{_URL_PATH_RE}',
fr'https?://fxnow\.(?P<site>fxnetworks)\.com/{_URL_PATH_RE}',
fr'https?://(?:www\.)?(?P<site>nationalgeographic)\.com/tv/{_URL_PATH_RE}',
]
_TESTS = [{
'url': 'http://abc.go.com/shows/designated-survivor/video/most-recent/VDKA3807643',
'url': 'https://abc.com/episode/4192c0e6-26e5-47a8-817b-ce8272b9e440/playlist/PL551127435',
'info_dict': {
'id': 'VDKA3807643',
'id': 'VDKA10805898',
'ext': 'mp4',
'title': 'The Traitor in the White House',
'description': 'md5:05b009d2d145a1e85d25111bd37222e8',
},
'params': {
# m3u8 download
'skip_download': True,
},
'skip': 'This content is no longer available.',
}, {
'url': 'https://disneynow.com/shows/big-hero-6-the-series',
'info_dict': {
'title': 'Doraemon',
'id': 'SH55574025',
},
'playlist_mincount': 51,
}, {
'url': 'http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood',
'info_dict': {
'id': 'VDKA3609139',
'title': 'This Guilty Blood',
'description': 'md5:f18e79ad1c613798d95fdabfe96cd292',
'title': 'Switch the Flip',
'description': 'To help get Brians life in order, Stewie and Brian swap bodies using a machine that Stewie invents.',
'age_limit': 14,
'duration': 1297,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Family Guy',
'season': 'Season 16',
'season_number': 16,
'episode': 'Episode 17',
'episode_number': 17,
'timestamp': 1746082800.0,
'upload_date': '20250501',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://disneynow.com/episode/21029660-ba06-4406-adb0-a9a78f6e265e/playlist/PL553044961',
'info_dict': {
'id': 'VDKA39546942',
'ext': 'mp4',
'title': 'Zero Friends Again',
'description': 'Relationships fray under the pressures of a difficult journey.',
'age_limit': 0,
'duration': 1721,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Star Wars: Skeleton Crew',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 6',
'episode_number': 6,
'timestamp': 1746946800.0,
'upload_date': '20250511',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://fxnow.fxnetworks.com/episode/09f4fa6f-c293-469e-aebe-32c9ca5842a7/playlist/PL554408064',
'info_dict': {
'id': 'VDKA38112033',
'ext': 'mp4',
'title': 'The Return of Jerry',
'description': 'The vampires long-lost fifth roommate returns. Written by Paul Simms; directed by Kyle Newacheck.',
'age_limit': 17,
'duration': 1493,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'What We Do in the Shadows',
'season': 'Season 6',
'season_number': 6,
'episode': 'Episode 1',
'upload_date': '20170102',
'season': 'Season 2',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abcf/Shadowhunters/video/201/ae5f75608d86bf88aa4f9f4aa76ab1b7/579x325-Q100_ae5f75608d86bf88aa4f9f4aa76ab1b7.jpg',
'duration': 2544,
'season_number': 2,
'series': 'Shadowhunters',
'episode_number': 1,
'timestamp': 1483387200,
'ext': 'mp4',
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'timestamp': 1729573200.0,
'upload_date': '20241022',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://abc.com/shows/the-rookie/episode-guide/season-04/12-the-knock',
'url': 'https://www.freeform.com/episode/bda0eaf7-761a-4838-aa44-96f794000844/playlist/PL553044961',
'info_dict': {
'id': 'VDKA26050359',
'title': 'The Knock',
'description': 'md5:0c2947e3ada4c31f28296db7db14aa64',
'age_limit': 14,
'id': 'VDKA39007340',
'ext': 'mp4',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/abc/TheRookie/video/412/daf830d06e83b11eaf5c0a299d993ae3/1556x876-Q75_daf830d06e83b11eaf5c0a299d993ae3.jpg',
'episode': 'Episode 12',
'season_number': 4,
'season': 'Season 4',
'timestamp': 1642975200,
'episode_number': 12,
'upload_date': '20220123',
'series': 'The Rookie',
'duration': 2572,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Angel\'s Landing',
'description': 'md5:91bf084e785c968fab16734df7313446',
'age_limit': 14,
'duration': 2523,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'How I Escaped My Cult',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 2',
'episode_number': 2,
'timestamp': 1740038400.0,
'upload_date': '20250220',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://fxnow.fxnetworks.com/shows/better-things/video/vdka12782841',
'url': 'https://www.nationalgeographic.com/tv/episode/ca694661-1186-41ae-8089-82f64d69b16d/playlist/PL554408064',
'info_dict': {
'id': 'VDKA12782841',
'title': 'First Look: Better Things - Season 2',
'description': 'md5:fa73584a95761c605d9d54904e35b407',
'id': 'VDKA39492078',
'ext': 'mp4',
'age_limit': 14,
'upload_date': '20170825',
'duration': 161,
'series': 'Better Things',
'thumbnail': 'http://cdn1.edgedatg.com/aws/v2/fx/BetterThings/video/12782841/b6b05e58264121cc2c98811318e6d507/1556x876-Q75_b6b05e58264121cc2c98811318e6d507.jpg',
'timestamp': 1503661074,
},
'params': {
'geo_bypass_ip_block': '3.244.239.0/24',
# m3u8 download
'skip_download': True,
'title': 'Heart of the Emperors',
'description': 'md5:4fc50a2878f030bb3a7eac9124dca677',
'age_limit': 0,
'duration': 2775,
'thumbnail': r're:https?://.+/.+\.jpg',
'series': 'Secrets of the Penguins',
'season': 'Season 1',
'season_number': 1,
'episode': 'Episode 1',
'episode_number': 1,
'timestamp': 1745204400.0,
'upload_date': '20250421',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://abc.go.com/shows/the-catch/episode-guide/season-01/10-the-wedding',
'url': 'https://www.freeform.com/movies-and-specials/c38281fc-9f8f-47c7-8220-22394f9df2e1',
'only_matching': True,
}, {
'url': 'http://abc.go.com/shows/world-news-tonight/episode-guide/2017-02/17-021717-intense-stand-off-between-man-with-rifle-and-police-in-oakland',
'only_matching': True,
}, {
# brand 004
'url': 'http://disneynow.go.com/shows/big-hero-6-the-series/season-01/episode-10-mr-sparkles-loses-his-sparkle/vdka4637915',
'only_matching': True,
}, {
# brand 008
'url': 'http://disneynow.go.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://disneynow.com/shows/minnies-bow-toons/video/happy-campers/vdka4872013',
'only_matching': True,
}, {
'url': 'https://www.freeform.com/shows/cruel-summer/episode-guide/season-01/01-happy-birthday-jeanette-turner',
'url': 'https://abc.com/video/219a454a-172c-41bf-878a-d169e6bc0bdc/playlist/PL5523098420',
'only_matching': True,
}]
@ -171,58 +167,29 @@ def _extract_videos(self, brand, video_id='-1', show_id='-1'):
f'http://api.contents.watchabc.go.com/vp2/ws/contents/3000/videos/{brand}/001/-1/{show_id}/-1/{video_id}/-1/-1.json',
display_id)['video']
def _extract_global_var(self, name, webpage, video_id):
return self._search_json(
fr'window\[["\']{re.escape(name)}["\']\]\s*=',
webpage, f'{name.strip("_")} JSON', video_id)
def _real_extract(self, url):
mobj = self._match_valid_url(url)
sub_domain = remove_start(remove_end(mobj.group('sub_domain') or '', '.go'), 'www.')
video_id, display_id = mobj.group('id', 'display_id')
site_info = self._SITE_INFO.get(sub_domain, {})
brand = site_info.get('brand')
if not video_id or not site_info:
webpage = self._download_webpage(url, display_id or video_id)
data = self._parse_json(
self._search_regex(
r'["\']__abc_com__["\']\s*\]\s*=\s*({.+?})\s*;', webpage,
'data', default='{}'),
display_id or video_id, fatal=False)
# https://abc.com/shows/modern-family/episode-guide/season-01/101-pilot
layout = try_get(data, lambda x: x['page']['content']['video']['layout'], dict)
video_id = None
if layout:
video_id = try_get(
layout,
(lambda x: x['videoid'], lambda x: x['video']['id']),
str)
site, display_id = self._match_valid_url(url).group('site', 'id')
webpage = self._download_webpage(url, display_id)
config = self._extract_global_var('__CONFIG__', webpage, display_id)
data = self._extract_global_var(config['globalVar'], webpage, display_id)
video_id = traverse_obj(data, (
'page', 'content', 'video', 'layout', (('video', 'id'), 'videoid'), {str}, any))
if not video_id:
video_id = self._search_regex(
(
# There may be inner quotes, e.g. data-video-id="'VDKA3609139'"
# from http://freeform.go.com/shows/shadowhunters/episodes/season-2/1-this-guilty-blood
r'data-video-id=["\']*(VDKA\w+)',
video_id = self._search_regex([
# data-track-video_id="VDKA39492078"
# data-track-video_id_code="vdka39492078"
# data-video-id="'VDKA3609139'"
r'data-(?:track-)?video[_-]id(?:_code)?=["\']*((?:vdka|VDKA)\d+)',
# page.analytics.videoIdCode
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\w+)',
# https://abc.com/shows/the-rookie/episode-guide/season-02/03-the-bet
r'\b(?:video)?id["\']\s*:\s*["\'](VDKA\w+)',
), webpage, 'video id', default=video_id)
if not site_info:
brand = self._search_regex(
(r'data-brand=\s*["\']\s*(\d+)',
r'data-page-brand=\s*["\']\s*(\d+)'), webpage, 'brand',
default='004')
site_info = next(
si for _, si in self._SITE_INFO.items()
if si.get('brand') == brand)
if not video_id:
# show extraction works for Disney, DisneyJunior and DisneyXD
# ABC and Freeform has different layout
show_id = self._search_regex(r'data-show-id=["\']*(SH\d+)', webpage, 'show id')
videos = self._extract_videos(brand, show_id=show_id)
show_title = self._search_regex(r'data-show-title="([^"]+)"', webpage, 'show title', fatal=False)
entries = []
for video in videos:
entries.append(self.url_result(
video['url'], 'Go', video.get('id'), video.get('title')))
entries.reverse()
return self.playlist_result(entries, show_id, show_title)
r'\bvideoIdCode["\']\s*:\s*["\']((?:vdka|VDKA)\d+)'], webpage, 'video ID')
site_info = self._SITE_INFO[site]
brand = site_info['brand']
video_data = self._extract_videos(brand, video_id)[0]
video_id = video_data['id']
title = video_data['title']
@ -238,26 +205,31 @@ def _real_extract(self, url):
if ext == 'm3u8':
video_type = video_data.get('type')
data = {
'video_id': video_data['id'],
'video_id': video_id,
'video_type': video_type,
'brand': brand,
'device': '001',
'app_name': 'webplayer-abc',
}
if video_data.get('accesslevel') == '1':
requestor_id = site_info.get('requestor_id', 'DisneyChannels')
provider_id = site_info['provider_id']
software_statement = traverse_obj(data, ('app', 'config', (
('features', 'auth', 'softwareStatement'),
('tvAuth', 'SOFTWARE_STATEMENTS', 'PRODUCTION'),
), {str}, any)) or site_info['software_statement']
resource = site_info.get('resource_id') or self._get_mvpd_resource(
requestor_id, title, video_id, None)
provider_id, title, video_id, None)
auth = self._extract_mvpd_auth(
url, video_id, requestor_id, resource)
url, video_id, site_info['requestor_id'], resource, software_statement)
data.update({
'token': auth,
'token_type': 'ap',
'adobe_requestor_id': requestor_id,
'adobe_requestor_id': provider_id,
})
else:
self._initialize_geo_bypass({'countries': ['US']})
entitlement = self._download_json(
'https://api.entitlement.watchabc.go.com/vp2/ws-secure/entitlement/2020/authorize.json',
'https://prod.gatekeeper.us-abc.symphony.edgedatg.go.com/vp2/ws-secure/entitlement/2020/playmanifest_secure.json',
video_id, data=urlencode_postdata(data))
errors = entitlement.get('errors', {}).get('errors', [])
if errors:
@ -267,7 +239,7 @@ def _real_extract(self, url):
error['message'], countries=['US'])
error_message = ', '.join([error['message'] for error in errors])
raise ExtractorError(f'{self.IE_NAME} said: {error_message}', expected=True)
asset_url += '?' + entitlement['uplynkData']['sessionKey']
asset_url += '?' + entitlement['entitlement']['uplynkData']['sessionKey']
fmts, subs = self._extract_m3u8_formats_and_subtitles(
asset_url, video_id, 'mp4', m3u8_id=format_id or 'hls', fatal=False)
formats.extend(fmts)

View File

@ -1,3 +1,4 @@
import functools
import hashlib
import hmac
import json
@ -9,18 +10,20 @@
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
determine_ext,
int_or_none,
join_nonempty,
str_or_none,
traverse_obj,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class HotStarBaseIE(InfoExtractor):
_BASE_URL = 'https://www.hotstar.com'
_API_URL = 'https://api.hotstar.com'
_API_URL_V2 = 'https://apix.hotstar.com/v2'
_AKAMAI_ENCRYPTION_KEY = b'\x05\xfc\x1a\x01\xca\xc9\x4b\xc4\x12\xfc\x53\x12\x07\x75\xf9\xee'
def _call_api_v1(self, path, *args, **kwargs):
@ -29,57 +32,86 @@ def _call_api_v1(self, path, *args, **kwargs):
headers={'x-country-code': 'IN', 'x-platform-code': 'PCTV'})
def _call_api_impl(self, path, video_id, query, st=None, cookies=None):
if not cookies or not cookies.get('userUP'):
self.raise_login_required()
st = int_or_none(st) or int(time.time())
exp = st + 6000
auth = f'st={st}~exp={exp}~acl=/*'
auth += '~hmac=' + hmac.new(self._AKAMAI_ENCRYPTION_KEY, auth.encode(), hashlib.sha256).hexdigest()
if cookies and cookies.get('userUP'):
token = cookies.get('userUP').value
else:
token = self._download_json(
f'{self._API_URL}/um/v3/users',
video_id, note='Downloading token',
data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
headers={
'hotstarauth': auth,
'x-hs-platform': 'PCTV', # or 'web'
'Content-Type': 'application/json',
})['user_identity']
response = self._download_json(
f'{self._API_URL}/{path}', video_id, query=query,
f'{self._API_URL_V2}/{path}', video_id, query=query,
headers={
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
'hotstarauth': auth,
'x-hs-appversion': '6.72.2',
'x-hs-platform': 'web',
'x-hs-usertoken': token,
'x-hs-usertoken': cookies['userUP'].value,
'x-hs-device-id': traverse_obj(cookies, ('deviceId', 'value')) or str(uuid.uuid4()),
'x-hs-client': 'platform:androidtv;app_id:in.startv.hotstar.dplus.tv;app_version:23.08.14.4;os:Android;os_version:13;schema_version:0.0.970',
'x-hs-platform': 'androidtv',
'content-type': 'application/json',
})
if response['message'] != "Playback URL's fetched successfully":
raise ExtractorError(
response['message'], expected=True)
return response['data']
if not traverse_obj(response, ('success', {dict})):
raise ExtractorError('API call was unsuccessful')
return response['success']
def _call_api_v2(self, path, video_id, st=None, cookies=None):
return self._call_api_impl(
f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
'os-name': 'Windows',
'os-version': '10',
def _call_api_v2(self, path, video_id, content_type, cookies=None, st=None):
return self._call_api_impl(f'{path}', video_id, query={
'content_id': video_id,
'filters': f'content_type={content_type}',
'client_capabilities': json.dumps({
'package': ['dash', 'hls'],
'container': ['fmp4br', 'fmp4'],
'ads': ['non_ssai', 'ssai'],
'audio_channel': ['atmos', 'dolby51', 'stereo'],
'encryption': ['plain', 'widevine'], # wv only so we can raise appropriate error
'video_codec': ['h265', 'h264'],
'ladder': ['tv', 'full'],
'resolution': ['4k', 'hd'],
'true_resolution': ['4k', 'hd'],
'dynamic_range': ['hdr', 'sdr'],
}, separators=(',', ':')),
'drm_parameters': json.dumps({
'widevine_security_level': ['SW_SECURE_DECODE', 'SW_SECURE_CRYPTO'],
'hdcp_version': ['HDCP_V2_2', 'HDCP_V2_1', 'HDCP_V2', 'HDCP_V1'],
}, separators=(',', ':')),
}, st=st, cookies=cookies)
@staticmethod
def _parse_metadata_v1(video_data):
return traverse_obj(video_data, {
'id': ('contentId', {str}),
'title': ('title', {str}),
'description': ('description', {str}),
'duration': ('duration', {int_or_none}),
'timestamp': (('broadcastDate', 'startDate'), {int_or_none}, any),
'release_year': ('year', {int_or_none}),
'channel': ('channelName', {str}),
'channel_id': ('channelId', {int}, {str_or_none}),
'series': ('showName', {str}),
'season': ('seasonName', {str}),
'season_number': ('seasonNo', {int_or_none}),
'season_id': ('seasonId', {int}, {str_or_none}),
'episode': ('title', {str}),
'episode_number': ('episodeNo', {int_or_none}),
})
def _playlist_entries(self, path, item_id, root=None, **kwargs):
results = self._call_api_v1(path, item_id, **kwargs)['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', ...)):
if video.get('contentId'):
def _fetch_page(self, path, item_id, name, query, root, page):
results = self._call_api_v1(
path, item_id, note=f'Downloading {name} page {page + 1} JSON', query={
**query,
'tao': page * self._PAGE_SIZE,
'tas': self._PAGE_SIZE,
})['body']['results']
for video in traverse_obj(results, (('assets', None), 'items', lambda _, v: v['contentId'])):
yield self.url_result(
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
class HotStarIE(HotStarBaseIE):
IE_NAME = 'hotstar'
IE_DESC = 'JioHotstar'
_VALID_URL = r'''(?x)
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
(?:
@ -114,15 +146,16 @@ class HotStarIE(HotStarBaseIE):
'upload_date': '20190501',
'duration': 1219,
'channel': 'StarPlus',
'channel_id': '3',
'channel_id': '821',
'series': 'Ek Bhram - Sarvagun Sampanna',
'season': 'Chapter 1',
'season_number': 1,
'season_id': '6771',
'season_id': '1260004607',
'episode': 'Janhvi Targets Suman',
'episode_number': 8,
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
'info_dict': {
'id': '1000282843',
@ -134,14 +167,14 @@ class HotStarIE(HotStarBaseIE):
'channel': 'StarPlus',
'series': 'Anupama',
'season_number': 1,
'season_id': '7399',
'season_id': '1260022018',
'upload_date': '20230307',
'episode': 'Anupama, Anuj Share a Moment',
'episode_number': 853,
'duration': 1272,
'channel_id': '3',
'duration': 1266,
'channel_id': '821',
},
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
'info_dict': {
@ -154,14 +187,15 @@ class HotStarIE(HotStarBaseIE):
'channel': 'Hotstar Specials',
'series': 'Kana Kaanum Kaalangal',
'season_number': 1,
'season_id': '9441',
'season_id': '1260097089',
'upload_date': '20220421',
'episode': 'Back To School',
'episode_number': 1,
'duration': 1810,
'channel_id': '54',
'channel_id': '1260003991',
},
}, {
'params': {'skip_download': 'm3u8'},
}, { # Metadata call gets HTTP Error 504 with tas=10000
'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
'info_dict': {
'id': '1000262286',
@ -173,6 +207,7 @@ class HotStarIE(HotStarBaseIE):
'timestamp': 1622943900,
'duration': 5395,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
'info_dict': {
@ -180,12 +215,13 @@ class HotStarIE(HotStarBaseIE):
'ext': 'mp4',
'title': 'Premam',
'release_year': 2015,
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
'timestamp': 1462149000,
'upload_date': '20160502',
'episode': 'Premam',
'duration': 8994,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
'only_matching': True,
@ -208,6 +244,13 @@ class HotStarIE(HotStarBaseIE):
None: 'content',
}
_CONTENT_TYPE = {
'movie': 'MOVIE',
'episode': 'EPISODE',
'match': 'SPORT',
'content': 'CLIPS',
}
_IGNORE_MAP = {
'res': 'resolution',
'vcodec': 'video_codec',
@ -229,38 +272,48 @@ def _video_url(cls, video_id, video_type=None, *, slug='ignore_me', root=None):
def _real_extract(self, url):
video_id, video_type = self._match_valid_url(url).group('id', 'type')
video_type = self._TYPE.get(video_type, video_type)
video_type = self._TYPE[video_type]
cookies = self._get_cookies(url) # Cookies before any request
video_data = traverse_obj(
self._call_api_v1(
f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
('body', 'results', 'item', {dict})) or {}
if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
self._call_api_v1(f'{video_type}/detail', video_id, fatal=False, query={
'tas': 5, # See https://github.com/yt-dlp/yt-dlp/issues/7946
'contentId': video_id,
}), ('body', 'results', 'item', {dict})) or {}
if video_data.get('drmProtected'):
self.report_drm(video_id)
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
geo_restricted = False
formats, subs = [], {}
formats, subs, has_drm = [], {}, False
headers = {'Referer': f'{self._BASE_URL}/in'}
content_type = traverse_obj(video_data, ('contentType', {str})) or self._CONTENT_TYPE[video_type]
# change to v2 in the future
playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
for playback_set in playback_sets:
if not isinstance(playback_set, dict):
continue
tags = str_or_none(playback_set.get('tagsCombination')) or ''
# See https://github.com/yt-dlp/yt-dlp/issues/396
st = self._request_webpage(
f'{self._BASE_URL}/in', video_id, 'Fetching server time').get_header('x-origin-date')
watch = self._call_api_v2('pages/watch', video_id, content_type, cookies=cookies, st=st)
player_config = traverse_obj(watch, (
'page', 'spaces', 'player', 'widget_wrappers', lambda _, v: v['template'] == 'PlayerWidget',
'widget', 'data', 'player_config', {dict}, any, {require('player config')}))
for playback_set in traverse_obj(player_config, (
('media_asset', 'media_asset_v2'),
('primary', 'fallback'),
all, lambda _, v: url_or_none(v['content_url']),
)):
tags = str_or_none(playback_set.get('playback_tags')) or ''
if any(f'{prefix}:{ignore}' in tags
for key, prefix in self._IGNORE_MAP.items()
for ignore in self._configuration_arg(key)):
continue
format_url = url_or_none(playback_set.get('playbackUrl'))
if not format_url:
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
has_drm = True
continue
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
ext = determine_ext(format_url)
current_formats, current_subs = [], {}
@ -280,14 +333,12 @@ def _real_extract(self, url):
'height': int_or_none(playback_set.get('height')),
}]
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
geo_restricted = True
else:
self.write_debug(e)
continue
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
if tag_dict.get('encryption') not in ('plain', None):
for f in current_formats:
f['has_drm'] = True
for f in current_formats:
for k, v in self._TAG_FIELDS.items():
if not f.get(k):
@ -299,6 +350,11 @@ def _real_extract(self, url):
'stereo': 2,
'dolby51': 6,
}.get(tag_dict.get('audio_channel'))
if (
'Audio_Description' in f['format_id']
or 'Audio Description' in (f.get('format_note') or '')
):
f['source_preference'] = -99 + (f.get('source_preference') or -1)
f['format_note'] = join_nonempty(
tag_dict.get('ladder'),
tag_dict.get('audio_channel') if f.get('acodec') != 'none' else None,
@ -310,27 +366,17 @@ def _real_extract(self, url):
if not formats and geo_restricted:
self.raise_geo_restricted(countries=['IN'], metadata_available=True)
elif not formats and has_drm:
self.report_drm(video_id)
self._remove_duplicate_formats(formats)
for f in formats:
f.setdefault('http_headers', {}).update(headers)
return {
**self._parse_metadata_v1(video_data),
'id': video_id,
'title': video_data.get('title'),
'description': video_data.get('description'),
'duration': int_or_none(video_data.get('duration')),
'timestamp': int_or_none(traverse_obj(video_data, 'broadcastDate', 'startDate')),
'release_year': int_or_none(video_data.get('year')),
'formats': formats,
'subtitles': subs,
'channel': video_data.get('channelName'),
'channel_id': str_or_none(video_data.get('channelId')),
'series': video_data.get('showName'),
'season': video_data.get('seasonName'),
'season_number': int_or_none(video_data.get('seasonNo')),
'season_id': str_or_none(video_data.get('seasonId')),
'episode': video_data.get('title'),
'episode_number': int_or_none(video_data.get('episodeNo')),
}
@ -371,64 +417,6 @@ def _real_extract(self, url):
return self.url_result(HotStarIE._video_url(video_id, video_type), HotStarIE, video_id)
class HotStarPlaylistIE(HotStarBaseIE):
IE_NAME = 'hotstar:playlist'
_VALID_URL = r'https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)(?:/[^/]+){2}/list/[^/]+/t-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'info_dict': {
'id': '3_2_26',
},
'playlist_mincount': 20,
}, {
'url': 'https://www.hotstar.com/shows/savdhaan-india/s-26/list/popular-clips/t-3_2_26',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/tv/savdhaan-india/s-26/list/extras/t-2480',
'only_matching': True,
}, {
'url': 'https://www.hotstar.com/in/tv/karthika-deepam/15457/list/popular-clips/t-3_2_1272',
'only_matching': True,
}]
def _real_extract(self, url):
id_ = self._match_id(url)
return self.playlist_result(
self._playlist_entries('tray/find', id_, query={'tas': 10000, 'uqId': id_}), id_)
class HotStarSeasonIE(HotStarBaseIE):
IE_NAME = 'hotstar:season'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/\w+)/seasons/[^/]+/ss-(?P<id>\w+)'
_TESTS = [{
'url': 'https://www.hotstar.com/tv/radhakrishn/1260000646/seasons/season-2/ss-8028',
'info_dict': {
'id': '8028',
},
'playlist_mincount': 35,
}, {
'url': 'https://www.hotstar.com/in/tv/ishqbaaz/9567/seasons/season-2/ss-4357',
'info_dict': {
'id': '4357',
},
'playlist_mincount': 30,
}, {
'url': 'https://www.hotstar.com/in/tv/bigg-boss/14714/seasons/season-4/ss-8208/',
'info_dict': {
'id': '8208',
},
'playlist_mincount': 19,
}, {
'url': 'https://www.hotstar.com/in/shows/bigg-boss/14714/seasons/season-4/ss-8208/',
'only_matching': True,
}]
def _real_extract(self, url):
url, season_id = self._match_valid_url(url).groups()
return self.playlist_result(self._playlist_entries(
'season/asset', season_id, url, query={'tao': 0, 'tas': 0, 'size': 10000, 'id': season_id}), season_id)
class HotStarSeriesIE(HotStarBaseIE):
IE_NAME = 'hotstar:series'
_VALID_URL = r'(?P<url>https?://(?:www\.)?hotstar\.com(?:/in)?/(?:tv|shows)/[^/]+/(?P<id>\d+))/?(?:[#?]|$)'
@ -443,25 +431,29 @@ class HotStarSeriesIE(HotStarBaseIE):
'info_dict': {
'id': '1260050431',
},
'playlist_mincount': 43,
'playlist_mincount': 42,
}, {
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
'info_dict': {
'id': '435',
},
'playlist_mincount': 267,
}, {
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
'info_dict': {
'id': '1260022017',
},
'playlist_mincount': 940,
'playlist_mincount': 1601,
}]
_PAGE_SIZE = 100
def _real_extract(self, url):
url, series_id = self._match_valid_url(url).groups()
id_ = self._call_api_v1(
url, series_id = self._match_valid_url(url).group('url', 'id')
eid = self._call_api_v1(
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
return self.playlist_result(self._playlist_entries(
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
entries = OnDemandPagedList(functools.partial(
self._fetch_page, 'tray/g/1/items', series_id,
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
return self.playlist_result(entries, series_id)

View File

@ -7,12 +7,13 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
clean_html,
int_or_none,
parse_duration,
str_or_none,
try_get,
unescapeHTML,
unified_strdate,
update_url,
update_url_query,
url_or_none,
)
@ -22,8 +23,8 @@
class HuyaLiveIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
IE_NAME = 'huya:live'
IE_DESC = 'huya.com'
TESTS = [{
IE_DESC = '虎牙直播'
_TESTS = [{
'url': 'https://www.huya.com/572329',
'info_dict': {
'id': '572329',
@ -149,63 +150,94 @@ class HuyaVideoIE(InfoExtractor):
'id': '1002412640',
'ext': 'mp4',
'title': '8月3日',
'thumbnail': r're:https?://.*\.jpg',
'duration': 14,
'categories': ['主机游戏'],
'duration': 14.0,
'uploader': '虎牙-ATS欧卡车队青木',
'uploader_id': '1564376151',
'upload_date': '20240803',
'view_count': int,
'comment_count': int,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1722675433,
},
},
{
}, {
'url': 'https://www.huya.com/video/play/556054543.html',
'info_dict': {
'id': '556054543',
'ext': 'mp4',
'title': '我不挑事 也不怕事',
'thumbnail': r're:https?://.*\.jpg',
'duration': 1864,
'categories': ['英雄联盟'],
'description': 'md5:58184869687d18ce62dc7b4b2ad21201',
'duration': 1864.0,
'uploader': '卡尔',
'uploader_id': '367138632',
'upload_date': '20210811',
'view_count': int,
'comment_count': int,
'like_count': int,
'tags': 'count:4',
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1628675950,
},
}, {
# Only m3u8 available
'url': 'https://www.huya.com/video/play/1063345618.html',
'info_dict': {
'id': '1063345618',
'ext': 'mp4',
'title': '峡谷第一中黑铁上钻石顶级教学对抗elo',
'categories': ['英雄联盟'],
'comment_count': int,
'duration': 21603.0,
'like_count': int,
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1749668803,
'upload_date': '20250611',
'uploader': '北枫CC',
'uploader_id': '2183525275',
'view_count': int,
},
}]
def _real_extract(self, url: str):
video_id = self._match_id(url)
video_data = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent', video_id,
query={'videoId': video_id})['data']['moment']['videoInfo']
moment = self._download_json(
'https://liveapi.huya.com/moment/getMomentContent',
video_id, query={'videoId': video_id})['data']['moment']
formats = []
for definition in traverse_obj(video_data, ('definitions', lambda _, v: url_or_none(v['url']))):
formats.append({
'url': definition['url'],
**traverse_obj(definition, {
'format_id': ('defName', {str}),
'width': ('width', {int_or_none}),
'height': ('height', {int_or_none}),
for definition in traverse_obj(moment, (
'videoInfo', 'definitions', lambda _, v: url_or_none(v['m3u8']),
)):
fmts = self._extract_m3u8_formats(definition['m3u8'], video_id, 'mp4', fatal=False)
for fmt in fmts:
fmt.update(**traverse_obj(definition, {
'filesize': ('size', {int_or_none}),
}),
})
'format_id': ('defName', {str}),
'height': ('height', {int_or_none}),
'quality': ('definition', {int_or_none}),
'width': ('width', {int_or_none}),
}))
formats.extend(fmts)
return {
'id': video_id,
'formats': formats,
**traverse_obj(video_data, {
**traverse_obj(moment, {
'comment_count': ('commentCount', {int_or_none}),
'description': ('content', {clean_html}, filter),
'like_count': ('favorCount', {int_or_none}),
'timestamp': ('cTime', {int_or_none}),
}),
**traverse_obj(moment, ('videoInfo', {
'title': ('videoTitle', {str}),
'thumbnail': ('videoCover', {url_or_none}),
'categories': ('category', {str}, filter, all, filter),
'duration': ('videoDuration', {parse_duration}),
'tags': ('tags', ..., {str}, filter, all, filter),
'thumbnail': (('videoBigCover', 'videoCover'), {url_or_none}, {update_url(query=None)}, any),
'uploader': ('nickName', {str}),
'uploader_id': ('uid', {str_or_none}),
'upload_date': ('videoUploadTime', {unified_strdate}),
'view_count': ('videoPlayNum', {int_or_none}),
'comment_count': ('videoCommentNum', {int_or_none}),
'like_count': ('favorCount', {int_or_none}),
}),
})),
}

View File

@ -1,32 +1,66 @@
from .common import InfoExtractor
from ..utils import js_to_json, traverse_obj
from ..utils import (
ExtractorError,
clean_html,
url_or_none,
)
from ..utils.traversal import subs_list_to_dict, traverse_obj
class MonsterSirenHypergryphMusicIE(InfoExtractor):
IE_NAME = 'monstersiren'
IE_DESC = '塞壬唱片'
_API_BASE = 'https://monster-siren.hypergryph.com/api'
_VALID_URL = r'https?://monster-siren\.hypergryph\.com/music/(?P<id>\d+)'
_TESTS = [{
'url': 'https://monster-siren.hypergryph.com/music/514562',
'info_dict': {
'id': '514562',
'ext': 'wav',
'artists': ['塞壬唱片-MSR'],
'album': 'Flame Shadow',
'title': 'Flame Shadow',
'album': 'Flame Shadow',
'artists': ['塞壬唱片-MSR'],
'description': 'md5:19e2acfcd1b65b41b29e8079ab948053',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}, {
'url': 'https://monster-siren.hypergryph.com/music/514518',
'info_dict': {
'id': '514518',
'ext': 'wav',
'title': 'Heavenly Me (Instrumental)',
'album': 'Heavenly Me',
'artists': ['塞壬唱片-MSR', 'AIYUE blessed : 理名'],
'description': 'md5:ce790b41c932d1ad72eb791d1d8ae598',
'thumbnail': r're:https?://web\.hycdn\.cn/siren/pic/.+\.jpg',
},
}]
def _real_extract(self, url):
audio_id = self._match_id(url)
webpage = self._download_webpage(url, audio_id)
json_data = self._search_json(
r'window\.g_initialProps\s*=', webpage, 'data', audio_id, transform_source=js_to_json)
song = self._download_json(f'{self._API_BASE}/song/{audio_id}', audio_id)
if traverse_obj(song, 'code') != 0:
msg = traverse_obj(song, ('msg', {str}, filter))
raise ExtractorError(
msg or 'API returned an error response', expected=bool(msg))
album = None
if album_id := traverse_obj(song, ('data', 'albumCid', {str})):
album = self._download_json(
f'{self._API_BASE}/album/{album_id}/detail', album_id, fatal=False)
return {
'id': audio_id,
'title': traverse_obj(json_data, ('player', 'songDetail', 'name')),
'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')),
'ext': 'wav',
'vcodec': 'none',
'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)),
'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')),
**traverse_obj(song, ('data', {
'title': ('name', {str}),
'artists': ('artists', ..., {str}),
'subtitles': ({'url': 'lyricUrl'}, all, {subs_list_to_dict(lang='en')}),
'url': ('sourceUrl', {url_or_none}),
})),
**traverse_obj(album, ('data', {
'album': ('name', {str}),
'description': ('intro', {clean_html}),
'thumbnail': ('coverUrl', {url_or_none}),
})),
}

View File

@ -1,408 +0,0 @@
import base64
import itertools
import json
import random
import re
import string
import time
from .common import InfoExtractor
from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
jwt_decode_hs256,
parse_age_limit,
try_call,
url_or_none,
)
from ..utils.traversal import traverse_obj
class JioCinemaBaseIE(InfoExtractor):
_NETRC_MACHINE = 'jiocinema'
_GEO_BYPASS = False
_ACCESS_TOKEN = None
_REFRESH_TOKEN = None
_GUEST_TOKEN = None
_USER_ID = None
_DEVICE_ID = None
_API_HEADERS = {'Origin': 'https://www.jiocinema.com', 'Referer': 'https://www.jiocinema.com/'}
_APP_NAME = {'appName': 'RJIL_JioCinema'}
_APP_VERSION = {'appVersion': '5.0.0'}
_API_SIGNATURES = 'o668nxgzwff'
_METADATA_API_BASE = 'https://content-jiovoot.voot.com/psapi'
_ACCESS_HINT = 'the `accessToken` from your browser local storage'
_LOGIN_HINT = (
'Log in with "-u phone -p <PHONE_NUMBER>" to authenticate with OTP, '
f'or use "-u token -p <ACCESS_TOKEN>" to log in with {_ACCESS_HINT}. '
'If you have previously logged in with yt-dlp and your session '
'has been cached, you can use "-u device -p <DEVICE_ID>"')
def _cache_token(self, token_type):
assert token_type in ('access', 'refresh', 'all')
if token_type in ('access', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-access', JioCinemaBaseIE._ACCESS_TOKEN)
if token_type in ('refresh', 'all'):
self.cache.store(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh', JioCinemaBaseIE._REFRESH_TOKEN)
def _call_api(self, url, video_id, note='Downloading API JSON', headers={}, data={}):
return self._download_json(
url, video_id, note, data=json.dumps(data, separators=(',', ':')).encode(), headers={
'Content-Type': 'application/json',
'Accept': 'application/json',
**self._API_HEADERS,
**headers,
}, expected_status=(400, 403, 474))
def _call_auth_api(self, service, endpoint, note, headers={}, data={}):
return self._call_api(
f'https://auth-jiocinema.voot.com/{service}service/apis/v4/{endpoint}',
None, note=note, headers=headers, data=data)
def _refresh_token(self):
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._DEVICE_ID:
raise ExtractorError('User token has expired', expected=True)
response = self._call_auth_api(
'token', 'refreshtoken', 'Refreshing token',
headers={'accesstoken': self._ACCESS_TOKEN}, data={
**self._APP_NAME,
'deviceId': self._DEVICE_ID,
'refreshToken': self._REFRESH_TOKEN,
**self._APP_VERSION,
})
refresh_token = response.get('refreshTokenId')
if refresh_token and refresh_token != JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
self._cache_token('refresh')
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
self._cache_token('access')
def _fetch_guest_token(self):
JioCinemaBaseIE._DEVICE_ID = ''.join(random.choices(string.digits, k=10))
guest_token = self._call_auth_api(
'token', 'guest', 'Downloading guest token', data={
**self._APP_NAME,
'deviceType': 'phone',
'os': 'ios',
'deviceId': self._DEVICE_ID,
'freshLaunch': False,
'adId': self._DEVICE_ID,
**self._APP_VERSION,
})
self._GUEST_TOKEN = guest_token['authToken']
self._USER_ID = guest_token['userId']
def _call_login_api(self, endpoint, guest_token, data, note):
return self._call_auth_api(
'user', f'loginotp/{endpoint}', note, headers={
**self.geo_verification_headers(),
'accesstoken': self._GUEST_TOKEN,
**self._APP_NAME,
**traverse_obj(guest_token, 'data', {
'deviceType': ('deviceType', {str}),
'os': ('os', {str}),
})}, data=data)
def _is_token_expired(self, token):
return (try_call(lambda: jwt_decode_hs256(token)['exp']) or 0) <= int(time.time() - 180)
def _perform_login(self, username, password):
if self._ACCESS_TOKEN and not self._is_token_expired(self._ACCESS_TOKEN):
return
UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
if username.lower() == 'token':
if try_call(lambda: jwt_decode_hs256(password)):
JioCinemaBaseIE._ACCESS_TOKEN = password
refresh_hint = 'the `refreshToken` UUID from your browser local storage'
refresh_token = self._configuration_arg('refresh_token', [''], ie_key=JioCinemaIE)[0]
if not refresh_token:
self.to_screen(
'To extend the life of your login session, in addition to your access token, '
'you can pass --extractor-args "jiocinema:refresh_token=REFRESH_TOKEN" '
f'where REFRESH_TOKEN is {refresh_hint}')
elif re.fullmatch(UUID_RE, refresh_token):
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
else:
self.report_warning(f'Invalid refresh_token value. Use {refresh_hint}')
else:
raise ExtractorError(
f'The password given could not be decoded as a token; use {self._ACCESS_HINT}', expected=True)
elif username.lower() == 'device' and re.fullmatch(rf'(?:{UUID_RE}|\d+)', password):
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-refresh')
JioCinemaBaseIE._ACCESS_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-access')
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._ACCESS_TOKEN:
raise ExtractorError(f'Failed to load cached tokens for device ID "{password}"', expected=True)
elif username.lower() == 'phone' and re.fullmatch(r'\+?\d+', password):
self._fetch_guest_token()
guest_token = jwt_decode_hs256(self._GUEST_TOKEN)
initial_data = {
'number': base64.b64encode(password.encode()).decode(),
**self._APP_VERSION,
}
response = self._call_login_api('send', guest_token, initial_data, 'Requesting OTP')
if not traverse_obj(response, ('OTPInfo', {dict})):
raise ExtractorError('There was a problem with the phone number login attempt')
is_iphone = guest_token.get('os') == 'ios'
response = self._call_login_api('verify', guest_token, {
'deviceInfo': {
'consumptionDeviceName': 'iPhone' if is_iphone else 'Android',
'info': {
'platform': {'name': 'iPhone OS' if is_iphone else 'Android'},
'androidId': self._DEVICE_ID,
'type': 'iOS' if is_iphone else 'Android',
},
},
**initial_data,
'otp': self._get_tfa_info('the one-time password sent to your phone'),
}, 'Submitting OTP')
if traverse_obj(response, 'code') == 1043:
raise ExtractorError('Wrong OTP', expected=True)
JioCinemaBaseIE._REFRESH_TOKEN = response['refreshToken']
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
else:
raise ExtractorError(self._LOGIN_HINT, expected=True)
user_token = jwt_decode_hs256(JioCinemaBaseIE._ACCESS_TOKEN)['data']
JioCinemaBaseIE._USER_ID = user_token['userId']
JioCinemaBaseIE._DEVICE_ID = user_token['deviceId']
if JioCinemaBaseIE._REFRESH_TOKEN and username != 'device':
self._cache_token('all')
if self.get_param('cachedir') is not False:
self.to_screen(
f'NOTE: For subsequent logins you can use "-u device -p {JioCinemaBaseIE._DEVICE_ID}"')
elif not JioCinemaBaseIE._REFRESH_TOKEN:
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh')
if JioCinemaBaseIE._REFRESH_TOKEN:
self._cache_token('access')
self.to_screen(f'Logging in as device ID "{JioCinemaBaseIE._DEVICE_ID}"')
if self._is_token_expired(JioCinemaBaseIE._ACCESS_TOKEN):
self._refresh_token()
class JioCinemaIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/?(?:movies?/[^/?#]+/|tv-shows/(?:[^/?#]+/){3})(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/agnisakshi-ek-samjhauta/1/pradeep-to-stop-the-wedding/3759931',
'info_dict': {
'id': '3759931',
'ext': 'mp4',
'title': 'Pradeep to stop the wedding?',
'description': 'md5:75f72d1d1a66976633345a3de6d672b1',
'episode': 'Pradeep to stop the wedding?',
'episode_number': 89,
'season': 'Agnisakshi…Ek Samjhauta-S1',
'season_number': 1,
'series': 'Agnisakshi Ek Samjhauta',
'duration': 1238.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'season_id': '3698031',
'upload_date': '20230606',
'timestamp': 1686009600,
'release_date': '20230607',
'genres': ['Drama'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.jiocinema.com/movies/bhediya/3754021/watch',
'info_dict': {
'id': '3754021',
'ext': 'mp4',
'title': 'Bhediya',
'description': 'md5:a6bf2900371ac2fc3f1447401a9f7bb0',
'episode': 'Bhediya',
'duration': 8500.0,
'thumbnail': r're:https?://.+\.jpg',
'age_limit': 13,
'upload_date': '20230525',
'timestamp': 1685026200,
'release_date': '20230524',
'genres': ['Comedy'],
},
'params': {'skip_download': 'm3u8'},
}]
def _extract_formats_and_subtitles(self, playback, video_id):
m3u8_url = traverse_obj(playback, (
'data', 'playbackUrls', lambda _, v: v['streamtype'] == 'hls', 'url', {url_or_none}, any))
if not m3u8_url: # DRM-only content only serves dash urls
self.report_drm(video_id)
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls')
self._remove_duplicate_formats(formats)
return {
# '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
'formats': traverse_obj(formats, (
lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
'subtitles': subtitles,
}
def _real_extract(self, url):
video_id = self._match_id(url)
if not self._ACCESS_TOKEN and self._is_token_expired(self._GUEST_TOKEN):
self._fetch_guest_token()
elif self._ACCESS_TOKEN and self._is_token_expired(self._ACCESS_TOKEN):
self._refresh_token()
playback = self._call_api(
f'https://apis-jiovoot.voot.com/playbackjv/v3/{video_id}', video_id,
'Downloading playback JSON', headers={
**self.geo_verification_headers(),
'accesstoken': self._ACCESS_TOKEN or self._GUEST_TOKEN,
**self._APP_NAME,
'deviceid': self._DEVICE_ID,
'uniqueid': self._USER_ID,
'x-apisignatures': self._API_SIGNATURES,
'x-platform': 'androidweb',
'x-platform-token': 'web',
}, data={
'4k': False,
'ageGroup': '18+',
'appVersion': '3.4.0',
'bitrateProfile': 'xhdpi',
'capability': {
'drmCapability': {
'aesSupport': 'yes',
'fairPlayDrmSupport': 'none',
'playreadyDrmSupport': 'none',
'widevineDRMSupport': 'none',
},
'frameRateCapability': [{
'frameRateSupport': '30fps',
'videoQuality': '1440p',
}],
},
'continueWatchingRequired': False,
'dolby': False,
'downloadRequest': False,
'hevc': False,
'kidsSafe': False,
'manufacturer': 'Windows',
'model': 'Windows',
'multiAudioRequired': True,
'osVersion': '10',
'parentalPinValid': True,
'x-apisignatures': self._API_SIGNATURES,
})
status_code = traverse_obj(playback, ('code', {int}))
if status_code == 474:
self.raise_geo_restricted(countries=['IN'])
elif status_code == 1008:
error_msg = 'This content is only available for premium users'
if self._ACCESS_TOKEN:
raise ExtractorError(error_msg, expected=True)
self.raise_login_required(f'{error_msg}. {self._LOGIN_HINT}', method=None)
elif status_code == 400:
raise ExtractorError('The requested content is not available', expected=True)
elif status_code is not None and status_code != 200:
raise ExtractorError(
f'JioCinema says: {traverse_obj(playback, ("message", {str})) or status_code}')
metadata = self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/query/asset-details',
video_id, fatal=False, query={
'ids': f'include:{video_id}',
'responseType': 'common',
'devicePlatformType': 'desktop',
})
return {
'id': video_id,
'http_headers': self._API_HEADERS,
**self._extract_formats_and_subtitles(playback, video_id),
**traverse_obj(playback, ('data', {
# fallback metadata
'title': ('name', {str}),
'description': ('fullSynopsis', {str}),
'series': ('show', 'name', {str}, filter),
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
'season_number': ('episode', 'season', {int_or_none}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('totalDuration', {float_or_none}),
'thumbnail': ('images', {url_or_none}),
})),
**traverse_obj(metadata, ('result', 0, {
'title': ('fullTitle', {str}),
'description': ('fullSynopsis', {str}),
'series': ('showName', {str}, filter),
'season': ('seasonName', {str}, filter),
'season_number': ('season', {int_or_none}),
'season_id': ('seasonId', {str}, filter),
'episode': ('fullTitle', {str}),
'episode_number': ('episode', {int_or_none}),
'timestamp': ('uploadTime', {int_or_none}),
'release_date': ('telecastDate', {str}),
'age_limit': ('ageNemonic', {parse_age_limit}),
'duration': ('duration', {float_or_none}),
'genres': ('genres', ..., {str}),
'thumbnail': ('seo', 'ogImage', {url_or_none}),
})),
}
class JioCinemaSeriesIE(JioCinemaBaseIE):
IE_NAME = 'jiocinema:series'
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/tv-shows/(?P<slug>[\w-]+)/(?P<id>\d{3,})'
_TESTS = [{
'url': 'https://www.jiocinema.com/tv-shows/naagin/3499917',
'info_dict': {
'id': '3499917',
'title': 'naagin',
},
'playlist_mincount': 120,
}, {
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
'info_dict': {
'id': '3499820',
'title': 'mtv-splitsvilla-x5',
},
'playlist_mincount': 310,
}]
def _entries(self, series_id):
seasons = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
'Downloading series metadata JSON', query={'responseType': 'common'}), (
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
'trayTabs', lambda _, v: v['id']))
for season_num, season in enumerate(seasons, start=1):
season_id = season['id']
label = season.get('label') or season_num
for page_num in itertools.count(1):
episodes = traverse_obj(self._download_json(
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',
season_id, f'Downloading season {label} page {page_num} JSON', query={
'sort': 'episode:asc',
'id': season_id,
'responseType': 'common',
'page': page_num,
}), ('result', lambda _, v: v['id'] and url_or_none(v['slug'])))
if not episodes:
break
for episode in episodes:
yield self.url_result(
episode['slug'], JioCinemaIE, **traverse_obj(episode, {
'video_id': 'id',
'video_title': ('fullTitle', {str}),
'season_number': ('season', {int_or_none}),
'episode_number': ('episode', {int_or_none}),
}))
def _real_extract(self, url):
slug, series_id = self._match_valid_url(url).group('slug', 'id')
return self.playlist_result(self._entries(series_id), series_id, slug)

View File

@ -1,12 +1,12 @@
import functools
import urllib.parse
from .common import InfoExtractor
from ..networking import HEADRequest
from ..utils import (
UserNotLive,
determine_ext,
float_or_none,
int_or_none,
merge_dicts,
parse_iso8601,
str_or_none,
traverse_obj,
@ -16,21 +16,17 @@
class KickBaseIE(InfoExtractor):
def _real_initialize(self):
self._request_webpage(
HEADRequest('https://kick.com/'), None, 'Setting up session', fatal=False, impersonate=True)
xsrf_token = self._get_cookies('https://kick.com/').get('XSRF-TOKEN')
if not xsrf_token:
self.write_debug('kick.com did not set XSRF-TOKEN cookie')
KickBaseIE._API_HEADERS = {
'Authorization': f'Bearer {xsrf_token.value}',
'X-XSRF-TOKEN': xsrf_token.value,
} if xsrf_token else {}
@functools.cached_property
def _api_headers(self):
token = traverse_obj(
self._get_cookies('https://kick.com/'),
('session_token', 'value', {urllib.parse.unquote}))
return {'Authorization': f'Bearer {token}'} if token else {}
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
return self._download_json(
f'https://kick.com/api/{path}', display_id, note=note,
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
headers={**self._api_headers, **headers}, impersonate=True, **kwargs)
class KickIE(KickBaseIE):

View File

@ -167,11 +167,11 @@ class LSMLTVEmbedIE(InfoExtractor):
'duration': 1442,
'upload_date': '20231121',
'title': 'D23-6000-105_cetstud',
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
},
}, {
'url': 'https://ltv.lsm.lv/embed?enablesdkjs=1&c=eyJpdiI6IncwVzZmUFk2MU12enVWK1I3SUcwQ1E9PSIsInZhbHVlIjoid3FhV29vamc3T2sxL1RaRmJ5Rm1GTXozU0o2dVczdUtLK0cwZEZJMDQ2a3ZIRG5DK2pneGlnbktBQy9uazVleHN6VXhxdWIweWNvcHRDSnlISlNYOHlVZ1lpcTUrcWZSTUZPQW14TVdkMW9aOUtRWVNDcFF4eWpHNGcrT0VZbUNFQStKQk91cGpndW9FVjJIa0lpbkh3PT0iLCJtYWMiOiIyZGI1NDJlMWRlM2QyMGNhOGEwYTM2MmNlN2JlOGRhY2QyYjdkMmEzN2RlOTEzYTVkNzI1ODlhZDlhZjU4MjQ2IiwidGFnIjoiIn0=',
'md5': 'a1711e190fe680fdb68fd8413b378e87',
'md5': 'f236cef2fd5953612754e4e66be51e7a',
'info_dict': {
'id': 'wUnFArIPDSY',
'ext': 'mp4',
@ -198,6 +198,8 @@ class LSMLTVEmbedIE(InfoExtractor):
'uploader_url': 'https://www.youtube.com/@LTV16plus',
'like_count': int,
'description': 'md5:7ff0c42ba971e3c13e4b8a2ff03b70b5',
'media_type': 'livestream',
'timestamp': 1652550741,
},
}]
@ -208,7 +210,7 @@ def _real_extract(self, url):
r'window\.ltvEmbedPayload\s*=', webpage, 'embed json', video_id)
embed_type = traverse_obj(data, ('source', 'name', {str}))
if embed_type == 'telia':
if embed_type in ('backscreen', 'telia'): # 'telia' only for backwards compat
ie_key = 'CloudyCDN'
embed_url = traverse_obj(data, ('source', 'embed_url', {url_or_none}))
elif embed_type == 'youtube':
@ -226,9 +228,9 @@ def _real_extract(self, url):
class LSMReplayIE(InfoExtractor):
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:skaties/|klausies/)?(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
_TESTS = [{
'url': 'https://replay.lsm.lv/lv/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'url': 'https://replay.lsm.lv/lv/skaties/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'md5': '64f72a360ca530d5ed89c77646c9eee5',
'info_dict': {
'id': '46k_d23-6000-105',
@ -241,20 +243,23 @@ class LSMReplayIE(InfoExtractor):
'thumbnail': 'https://ltv.lsm.lv/storage/media/8/7/large/5/1f9604e1.jpg',
},
}, {
'url': 'https://replay.lsm.lv/lv/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
'md5': '719b33875cd1429846eeeaeec6df2830',
'url': 'https://replay.lsm.lv/lv/klausies/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
'md5': '84feb80fd7e6ec07744726a9f01cda4d',
'info_dict': {
'id': 'a342781',
'ext': 'mp3',
'id': '183522',
'ext': 'm4a',
'duration': 1823,
'title': '#138 Nepilnīgā kompensējamo zāļu sistēma pat mēnešiem dzenā pacientus pa aptiekām',
'thumbnail': 'https://pic.latvijasradio.lv/public/assets/media/9/d/large_fd4675ac.jpg',
'upload_date': '20231102',
'timestamp': 1698921060,
'timestamp': 1698913860,
'description': 'md5:7bac3b2dd41e44325032943251c357b1',
},
}, {
'url': 'https://replay.lsm.lv/ru/statja/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'url': 'https://replay.lsm.lv/ru/skaties/statja/ltv/355067/v-kengaragse-nacalas-ukladka-relsov',
'only_matching': True,
}, {
'url': 'https://replay.lsm.lv/lv/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
'only_matching': True,
}]
@ -267,12 +272,24 @@ def _real_extract(self, url):
data = self._search_nuxt_data(
self._fix_nuxt_data(webpage), video_id, context_name='__REPLAY__')
playback_type = data['playback']['type']
if playback_type == 'playable_audio_lr':
playback_data = {
'formats': self._extract_m3u8_formats(data['playback']['service']['hls_url'], video_id),
}
elif playback_type == 'embed':
playback_data = {
'_type': 'url_transparent',
'url': data['playback']['service']['url'],
}
else:
raise ExtractorError(f'Unsupported playback type "{playback_type}"')
return {
'_type': 'url_transparent',
'id': video_id,
**playback_data,
**traverse_obj(data, {
'url': ('playback', 'service', 'url', {url_or_none}),
'title': ('mediaItem', 'title'),
'description': ('mediaItem', ('lead', 'body')),
'duration': ('mediaItem', 'duration', {int_or_none}),

107
yt_dlp/extractor/mave.py Normal file
View File

@ -0,0 +1,107 @@
import re
from .common import InfoExtractor
from ..utils import (
clean_html,
int_or_none,
parse_iso8601,
urljoin,
)
from ..utils.traversal import require, traverse_obj
class MaveIE(InfoExtractor):
_VALID_URL = r'https?://(?P<channel>[\w-]+)\.mave\.digital/(?P<id>ep-\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',
'title': 'Между мной и миром: психология самооценки',
'description': 'md5:4b7463baaccb6982f326bce5c700382a',
'uploader': 'Самарский университет',
'channel': 'Очень личное',
'channel_id': 'ochenlichnoe',
'channel_url': 'https://ochenlichnoe.mave.digital/',
'view_count': int,
'like_count': int,
'dislike_count': int,
'duration': 3744,
'thumbnail': r're:https://.+/storage/podcasts/.+\.jpg',
'series': 'Очень личное',
'series_id': '2e0c3749-6df2-4946-82f4-50691419c065',
'season': 'Season 3',
'season_number': 3,
'episode': 'Episode 3',
'episode_number': 3,
'timestamp': 1747817300,
'upload_date': '20250521',
},
}, {
'url': 'https://budem.mave.digital/ep-12',
'md5': 'e1ce2780fcdb6f17821aa3ca3e8c919f',
'info_dict': {
'id': '41898bb5-ff57-4797-9236-37a8e537aa21',
'ext': 'mp3',
'display_id': 'budem-ep-12',
'title': 'Екатерина Михайлова: "Горе от ума" не про женщин написана',
'description': 'md5:fa3bdd59ee829dfaf16e3efcb13f1d19',
'uploader': 'Полина Цветкова+Евгения Акопова',
'channel': 'Все там будем',
'channel_id': 'budem',
'channel_url': 'https://budem.mave.digital/',
'view_count': int,
'like_count': int,
'dislike_count': int,
'age_limit': 18,
'duration': 3664,
'thumbnail': r're:https://.+/storage/podcasts/.+\.jpg',
'series': 'Все там будем',
'series_id': 'fe9347bf-c009-4ebd-87e8-b06f2f324746',
'season': 'Season 2',
'season_number': 2,
'episode': 'Episode 5',
'episode_number': 5,
'timestamp': 1735538400,
'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')}))
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}),
'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}),
})),
}

View File

@ -1,7 +1,5 @@
from .telecinco import TelecincoBaseIE
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
int_or_none,
parse_iso8601,
)
@ -81,17 +79,7 @@ class MiTeleIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
try: # yt-dlp's default user-agents are too old and blocked by akamai
webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient to bypass akamai
webpage = self._download_webpage(url, display_id, impersonate=True)
webpage = self._download_akamai_webpage(url, display_id)
pre_player = self._search_json(
r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=',
webpage, 'Pre Player', display_id)['prePlayer']

View File

@ -19,7 +19,8 @@
class NBACVPBaseIE(TurnerBaseIE):
def _extract_nba_cvp_info(self, path, video_id, fatal=False):
return self._extract_cvp_info(
f'http://secure.nba.com/{path}', video_id, {
# XXX: The 3rd argument (None) needs to be the AdobePass software_statement
f'http://secure.nba.com/{path}', video_id, None, {
'default': {
'media_src': 'http://nba.cdn.turner.com/nba/big',
},
@ -94,6 +95,7 @@ def _extract_video(self, filter_key, filter_value):
class NBAWatchEmbedIE(NBAWatchBaseIE):
_WORKING = False
IE_NAME = 'nba:watch:embed'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'embed\?.*?\bid=(?P<id>\d+)'
_TESTS = [{
@ -115,6 +117,7 @@ def _real_extract(self, url):
class NBAWatchIE(NBAWatchBaseIE):
_WORKING = False
IE_NAME = 'nba:watch'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'(?:nba/)?video/(?P<id>.+?(?=/index\.html)|(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
@ -167,6 +170,7 @@ def _real_extract(self, url):
class NBAWatchCollectionIE(NBAWatchBaseIE):
_WORKING = False
IE_NAME = 'nba:watch:collection'
_VALID_URL = NBAWatchBaseIE._VALID_URL_BASE + r'list/collection/(?P<id>[^/?#&]+)'
_TESTS = [{
@ -336,6 +340,7 @@ def _real_extract(self, url):
class NBAEmbedIE(NBABaseIE):
_WORKING = False
IE_NAME = 'nba:embed'
_VALID_URL = r'https?://secure\.nba\.com/assets/amp/include/video/(?:topI|i)frame\.html\?.*?\bcontentId=(?P<id>[^?#&]+)'
_TESTS = [{
@ -358,6 +363,7 @@ def _real_extract(self, url):
class NBAIE(NBABaseIE):
_WORKING = False
IE_NAME = 'nba'
_VALID_URL = NBABaseIE._VALID_URL_BASE + f'(?!{NBABaseIE._CHANNEL_PATH_REGEX})video/(?P<id>(?:[^/]+/)*[^/?#&]+)'
_TESTS = [{
@ -385,6 +391,7 @@ def _extract_url_results(self, team, content_id):
class NBAChannelIE(NBABaseIE):
_WORKING = False
IE_NAME = 'nba:channel'
_VALID_URL = NBABaseIE._VALID_URL_BASE + f'(?:{NBABaseIE._CHANNEL_PATH_REGEX})/(?P<id>[^/?#&]+)'
_TESTS = [{

View File

@ -6,7 +6,7 @@
from .adobepass import AdobePassIE
from .common import InfoExtractor
from .theplatform import ThePlatformIE, default_ns
from .theplatform import ThePlatformBaseIE, ThePlatformIE, default_ns
from ..networking import HEADRequest
from ..utils import (
ExtractorError,
@ -14,26 +14,130 @@
UserNotLive,
clean_html,
determine_ext,
extract_attributes,
float_or_none,
get_element_html_by_class,
int_or_none,
join_nonempty,
make_archive_id,
mimetype2ext,
parse_age_limit,
parse_duration,
parse_iso8601,
remove_end,
smuggle_url,
traverse_obj,
try_get,
unescapeHTML,
unified_timestamp,
update_url_query,
url_basename,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
_VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/]+/video/[^/]+/(?P<id>(?:NBCE|n)?\d+))'
class NBCUniversalBaseIE(ThePlatformBaseIE):
_GEO_COUNTRIES = ['US']
_GEO_BYPASS = False
_M3U8_RE = r'https?://[^/?#]+/prod/[\w-]+/(?P<folders>[^?#]+/)cmaf/mpeg_(?:cbcs|cenc)\w*/master_cmaf\w*\.m3u8'
def _download_nbcu_smil_and_extract_m3u8_url(self, tp_path, video_id, query):
smil = self._download_xml(
f'https://link.theplatform.com/s/{tp_path}', video_id,
'Downloading SMIL manifest', 'Failed to download SMIL manifest', query={
**query,
'format': 'SMIL', # XXX: Do not confuse "format" with "formats"
'manifest': 'm3u',
'switch': 'HLSServiceSecure', # Or else we get broken mp4 http URLs instead of HLS
}, headers=self.geo_verification_headers())
ns = f'//{{{default_ns}}}'
if url := traverse_obj(smil, (f'{ns}video/@src', lambda _, v: determine_ext(v) == 'm3u8', any)):
return url
exc = traverse_obj(smil, (f'{ns}param', lambda _, v: v.get('name') == 'exception', '@value', any))
if exc == 'GeoLocationBlocked':
self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
raise ExtractorError(traverse_obj(smil, (f'{ns}ref/@abstract', ..., any)), expected=exc == 'Expired')
def _extract_nbcu_formats_and_subtitles(self, tp_path, video_id, query):
# formats='mpeg4' will return either a working m3u8 URL or an m3u8 template for non-DRM HLS
# formats='m3u+none,mpeg4' may return DRM HLS but w/the "folders" needed for non-DRM template
query['formats'] = 'm3u+none,mpeg4'
m3u8_url = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
if mobj := re.fullmatch(self._M3U8_RE, m3u8_url):
query['formats'] = 'mpeg4'
m3u8_tmpl = self._download_nbcu_smil_and_extract_m3u8_url(tp_path, video_id, query)
# Example: https://vod-lf-oneapp-prd.akamaized.net/prod/video/{folders}master_hls.m3u8
if '{folders}' in m3u8_tmpl:
self.write_debug('Found m3u8 URL template, formatting URL path')
m3u8_url = m3u8_tmpl.format(folders=mobj.group('folders'))
if '/mpeg_cenc' in m3u8_url or '/mpeg_cbcs' in m3u8_url:
self.report_drm(video_id)
return self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, 'mp4', m3u8_id='hls')
def _extract_nbcu_video(self, url, display_id, old_ie_key=None):
webpage = self._download_webpage(url, display_id)
settings = self._search_json(
r'<script[^>]+data-drupal-selector="drupal-settings-json"[^>]*>',
webpage, 'settings', display_id)
query = {}
tve = extract_attributes(get_element_html_by_class('tve-video-deck-app', webpage) or '')
if tve:
account_pid = tve.get('data-mpx-media-account-pid') or tve['data-mpx-account-pid']
account_id = tve['data-mpx-media-account-id']
metadata = self._parse_json(
tve.get('data-normalized-video') or '', display_id, fatal=False, transform_source=unescapeHTML)
video_id = tve.get('data-guid') or metadata['guid']
if tve.get('data-entitlement') == 'auth':
auth = settings['tve_adobe_auth']
release_pid = tve['data-release-pid']
resource = self._get_mvpd_resource(
tve.get('data-adobe-pass-resource-id') or auth['adobePassResourceId'],
tve['data-title'], release_pid, tve.get('data-rating'))
query['auth'] = self._extract_mvpd_auth(
url, release_pid, auth['adobePassRequestorId'],
resource, auth['adobePassSoftwareStatement'])
else:
ls_playlist = traverse_obj(settings, (
'ls_playlist', lambda _, v: v['defaultGuid'], any, {require('LS playlist')}))
video_id = ls_playlist['defaultGuid']
account_pid = ls_playlist.get('mpxMediaAccountPid') or ls_playlist['mpxAccountPid']
account_id = ls_playlist['mpxMediaAccountId']
metadata = traverse_obj(ls_playlist, ('videos', lambda _, v: v['guid'] == video_id, any)) or {}
tp_path = f'{account_pid}/media/guid/{account_id}/{video_id}'
formats, subtitles = self._extract_nbcu_formats_and_subtitles(tp_path, video_id, query)
tp_metadata = self._download_theplatform_metadata(tp_path, video_id, fatal=False)
parsed_info = self._parse_theplatform_metadata(tp_metadata)
self._merge_subtitles(parsed_info['subtitles'], target=subtitles)
return {
**parsed_info,
**traverse_obj(metadata, {
'title': ('title', {str}),
'description': ('description', {str}),
'duration': ('durationInSeconds', {int_or_none}),
'timestamp': ('airDate', {parse_iso8601}),
'thumbnail': ('thumbnailUrl', {url_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'episode_number': ('episodeNumber', {int_or_none}),
'episode': ('episodeTitle', {str}),
'series': ('show', {str}),
}),
'id': video_id,
'display_id': display_id,
'formats': formats,
'subtitles': subtitles,
'_old_archive_ids': [make_archive_id(old_ie_key, video_id)] if old_ie_key else None,
}
class NBCIE(NBCUniversalBaseIE):
_VALID_URL = r'https?(?P<permalink>://(?:www\.)?nbc\.com/(?:classic-tv/)?[^/?#]+/video/[^/?#]+/(?P<id>\w+))'
_TESTS = [
{
'url': 'http://www.nbc.com/the-tonight-show/video/jimmy-fallon-surprises-fans-at-ben-jerrys/2848237',
@ -49,47 +153,20 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'episode_number': 86,
'season': 'Season 2',
'season_number': 2,
'series': 'Tonight Show: Jimmy Fallon',
'duration': 237.0,
'chapters': 'count:1',
'tags': 'count:4',
'series': 'Tonight',
'duration': 236.504,
'tags': 'count:2',
'thumbnail': r're:https?://.+\.jpg',
'categories': ['Series/The Tonight Show Starring Jimmy Fallon'],
'media_type': 'Full Episode',
'age_limit': 14,
'_old_archive_ids': ['theplatform 2848237'],
},
'params': {
'skip_download': 'm3u8',
},
},
{
'url': 'http://www.nbc.com/saturday-night-live/video/star-wars-teaser/2832821',
'info_dict': {
'id': '2832821',
'ext': 'mp4',
'title': 'Star Wars Teaser',
'description': 'md5:0b40f9cbde5b671a7ff62fceccc4f442',
'timestamp': 1417852800,
'upload_date': '20141206',
'uploader': 'NBCU-COM',
},
'skip': 'page not found',
},
{
# HLS streams requires the 'hdnea3' cookie
'url': 'http://www.nbc.com/Kings/video/goliath/n1806',
'info_dict': {
'id': '101528f5a9e8127b107e98c5e6ce4638',
'ext': 'mp4',
'title': 'Goliath',
'description': 'When an unknown soldier saves the life of the King\'s son in battle, he\'s thrust into the limelight and politics of the kingdom.',
'timestamp': 1237100400,
'upload_date': '20090315',
'uploader': 'NBCU-COM',
},
'skip': 'page not found',
},
{
# manifest url does not have extension
'url': 'https://www.nbc.com/the-golden-globe-awards/video/oprah-winfrey-receives-cecil-b-de-mille-award-at-the-2018-golden-globes/3646439',
'info_dict': {
'id': '3646439',
@ -99,48 +176,47 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'episode_number': 1,
'season': 'Season 75',
'season_number': 75,
'series': 'The Golden Globe Awards',
'series': 'Golden Globes',
'description': 'Oprah Winfrey receives the Cecil B. de Mille Award at the 75th Annual Golden Globe Awards.',
'uploader': 'NBCU-COM',
'upload_date': '20180107',
'timestamp': 1515312000,
'duration': 570.0,
'duration': 569.703,
'tags': 'count:8',
'thumbnail': r're:https?://.+\.jpg',
'chapters': 'count:1',
'media_type': 'Highlight',
'age_limit': 0,
'categories': ['Series/The Golden Globe Awards'],
'_old_archive_ids': ['theplatform 3646439'],
},
'params': {
'skip_download': 'm3u8',
},
},
{
# new video_id format
'url': 'https://www.nbc.com/quantum-leap/video/bens-first-leap-nbcs-quantum-leap/NBCE125189978',
# Needs to be extracted from webpage instead of GraphQL
'url': 'https://www.nbc.com/paris2024/video/ali-truwit-found-purpose-pool-after-her-life-changed/para24_sww_alitruwittodayshow_240823',
'info_dict': {
'id': 'NBCE125189978',
'id': 'para24_sww_alitruwittodayshow_240823',
'ext': 'mp4',
'title': 'Ben\'s First Leap | NBC\'s Quantum Leap',
'description': 'md5:a82762449b7ec4bb83291a7b355ebf8e',
'uploader': 'NBCU-COM',
'series': 'Quantum Leap',
'season': 'Season 1',
'season_number': 1,
'episode': 'Ben\'s First Leap | NBC\'s Quantum Leap',
'episode_number': 1,
'duration': 170.171,
'chapters': [],
'timestamp': 1663956155,
'upload_date': '20220923',
'tags': 'count:10',
'age_limit': 0,
'title': 'Ali Truwit found purpose in the pool after her life changed',
'description': 'md5:c16d7489e1516593de1cc5d3f39b9bdb',
'uploader': 'NBCU-SPORTS',
'duration': 311.077,
'thumbnail': r're:https?://.+\.jpg',
'categories': ['Series/Quantum Leap 2022'],
'media_type': 'Highlight',
'episode': 'Ali Truwit found purpose in the pool after her life changed',
'timestamp': 1724435902.0,
'upload_date': '20240823',
'_old_archive_ids': ['theplatform para24_sww_alitruwittodayshow_240823'],
},
'params': {
'skip_download': 'm3u8',
},
},
{
'url': 'https://www.nbc.com/quantum-leap/video/bens-first-leap-nbcs-quantum-leap/NBCE125189978',
'only_matching': True,
},
{
'url': 'https://www.nbc.com/classic-tv/charles-in-charge/video/charles-in-charge-pilot/n3310',
'only_matching': True,
@ -151,6 +227,7 @@ class NBCIE(ThePlatformIE): # XXX: Do not subclass from concrete IE
'only_matching': True,
},
]
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiI1Yzg2YjdkYy04NDI3LTRjNDUtOGQwZi1iNDkzYmE3MmQwYjQiLCJuYmYiOjE1Nzg3MDM2MzEsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTc4NzAzNjMxfQ.QQKIsBhAjGQTMdAqRTqhcz2Cddr4Y2hEjnSiOeKKki4nLrkDOsjQMmqeTR0hSRarraxH54wBgLvsxI7LHwKMvr7G8QpynNAxylHlQD3yhN9tFhxt4KR5wW3as02B-W2TznK9bhNWPKIyHND95Uo2Mi6rEQoq8tM9O09WPWaanE5BX_-r6Llr6dPq5F0Lpx2QOn2xYRb1T4nFxdFTNoss8GBds8OvChTiKpXMLHegLTc1OS4H_1a8tO_37jDwSdJuZ8iTyRLV4kZ2cpL6OL5JPMObD4-HQiec_dfcYgMKPiIfP9ZqdXpec2SVaCLsWEk86ZYvD97hLIQrK5rrKd1y-A'
def _real_extract(self, url):
permalink, video_id = self._match_valid_url(url).groups()
@ -196,62 +273,50 @@ def _real_extract(self, url):
'userId': '0',
}),
})['data']['bonanzaPage']['metadata']
query = {
'mbr': 'true',
'manifest': 'm3u',
'switch': 'HLSServiceSecure',
}
if not video_data:
# Some videos are not available via GraphQL API
webpage = self._download_webpage(url, video_id)
video_data = self._search_json(
r'<script>\s*PRELOAD\s*=', webpage, 'video data',
video_id)['pages'][urllib.parse.urlparse(url).path]['base']['metadata']
video_id = video_data['mpxGuid']
tp_path = 'NnzsPC/media/guid/{}/{}'.format(video_data.get('mpxAccountId') or '2410887629', video_id)
tpm = self._download_theplatform_metadata(tp_path, video_id)
title = tpm.get('title') or video_data.get('secondaryTitle')
tp_path = f'NnzsPC/media/guid/{video_data["mpxAccountId"]}/{video_id}'
tpm = self._download_theplatform_metadata(tp_path, video_id, fatal=False)
title = traverse_obj(tpm, ('title', {str})) or video_data.get('secondaryTitle')
query = {}
if video_data.get('locked'):
resource = self._get_mvpd_resource(
video_data.get('resourceId') or 'nbcentertainment',
title, video_id, video_data.get('rating'))
video_data['resourceId'], title, video_id, video_data.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'nbcentertainment', resource)
theplatform_url = smuggle_url(update_url_query(
'http://link.theplatform.com/s/NnzsPC/media/guid/{}/{}'.format(video_data.get('mpxAccountId') or '2410887629', video_id),
query), {'force_smil_url': True})
url, video_id, 'nbcentertainment', resource, self._SOFTWARE_STATEMENT)
# Empty string or 0 can be valid values for these. So the check must be `is None`
description = video_data.get('description')
if description is None:
description = tpm.get('description')
episode_number = int_or_none(video_data.get('episodeNumber'))
if episode_number is None:
episode_number = int_or_none(tpm.get('nbcu$airOrder'))
rating = video_data.get('rating')
if rating is None:
try_get(tpm, lambda x: x['ratings'][0]['rating'])
season_number = int_or_none(video_data.get('seasonNumber'))
if season_number is None:
season_number = int_or_none(tpm.get('nbcu$seasonNumber'))
series = video_data.get('seriesShortTitle')
if series is None:
series = tpm.get('nbcu$seriesShortTitle')
tags = video_data.get('keywords')
if tags is None or len(tags) == 0:
tags = tpm.get('keywords')
formats, subtitles = self._extract_nbcu_formats_and_subtitles(tp_path, video_id, query)
parsed_info = self._parse_theplatform_metadata(tpm)
self._merge_subtitles(parsed_info['subtitles'], target=subtitles)
return {
'_type': 'url_transparent',
'age_limit': parse_age_limit(rating),
'description': description,
'episode': title,
'episode_number': episode_number,
**traverse_obj(video_data, {
'description': ('description', {str}, filter),
'episode': ('secondaryTitle', {str}, filter),
'episode_number': ('episodeNumber', {int_or_none}),
'season_number': ('seasonNumber', {int_or_none}),
'age_limit': ('rating', {parse_age_limit}),
'tags': ('keywords', ..., {str}, filter, all, filter),
'series': ('seriesShortTitle', {str}),
}),
**parsed_info,
'id': video_id,
'ie_key': 'ThePlatform',
'season_number': season_number,
'series': series,
'tags': tags,
'title': title,
'url': theplatform_url,
'formats': formats,
'subtitles': subtitles,
'_old_archive_ids': [make_archive_id('ThePlatform', video_id)],
}
class NBCSportsVPlayerIE(InfoExtractor):
_WORKING = False
_VALID_URL_BASE = r'https?://(?:vplayer\.nbcsports\.com|(?:www\.)?nbcsports\.com/vplayer)/'
_VALID_URL = _VALID_URL_BASE + r'(?:[^/]+/)+(?P<id>[0-9a-zA-Z_]+)'
_EMBED_REGEX = [rf'(?:iframe[^>]+|var video|div[^>]+data-(?:mpx-)?)[sS]rc\s?=\s?"(?P<url>{_VALID_URL_BASE}[^\"]+)']
@ -286,6 +351,7 @@ def _real_extract(self, url):
class NBCSportsIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?nbcsports\.com//?(?!vplayer/)(?:[^/]+/)+(?P<id>[0-9a-z-]+)'
_TESTS = [{
@ -321,6 +387,7 @@ def _real_extract(self, url):
class NBCSportsStreamIE(AdobePassIE):
_WORKING = False
_VALID_URL = r'https?://stream\.nbcsports\.com/.+?\bpid=(?P<id>\d+)'
_TEST = {
'url': 'http://stream.nbcsports.com/nbcsn/generic?pid=206559',
@ -354,7 +421,7 @@ def _real_extract(self, url):
source_url = video_source['ottStreamUrl']
is_live = video_source.get('type') == 'live' or video_source.get('status') == 'Live'
resource = self._get_mvpd_resource('nbcsports', title, video_id, '')
token = self._extract_mvpd_auth(url, video_id, 'nbcsports', resource)
token = self._extract_mvpd_auth(url, video_id, 'nbcsports', resource, None) # XXX: None arg needs to be software_statement
tokenized_url = self._download_json(
'https://token.playmakerservices.com/cdn',
video_id, data=json.dumps({
@ -534,22 +601,26 @@ class NBCOlympicsIE(InfoExtractor):
IE_NAME = 'nbcolympics'
_VALID_URL = r'https?://www\.nbcolympics\.com/videos?/(?P<id>[0-9a-z-]+)'
_TEST = {
_TESTS = [{
# Geo-restricted to US
'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
'md5': '54fecf846d05429fbaa18af557ee523a',
'url': 'https://www.nbcolympics.com/videos/watch-final-minutes-team-usas-mens-basketball-gold',
'info_dict': {
'id': 'WjTBzDXx5AUq',
'display_id': 'justin-roses-son-leo-was-tears-after-his-dad-won-gold',
'id': 'SAwGfPlQ1q01',
'ext': 'mp4',
'title': 'Rose\'s son Leo was in tears after his dad won gold',
'description': 'Olympic gold medalist Justin Rose gets emotional talking to the impact his win in men\'s golf has already had on his children.',
'timestamp': 1471274964,
'upload_date': '20160815',
'display_id': 'watch-final-minutes-team-usas-mens-basketball-gold',
'title': 'Watch the final minutes of Team USA\'s men\'s basketball gold',
'description': 'md5:f704f591217305c9559b23b877aa8d31',
'uploader': 'NBCU-SPORTS',
'duration': 387.053,
'thumbnail': r're:https://.+/.+\.jpg',
'chapters': [],
'timestamp': 1723346984,
'upload_date': '20240811',
},
'skip': '404 Not Found',
}
}, {
'url': 'http://www.nbcolympics.com/video/justin-roses-son-leo-was-tears-after-his-dad-won-gold',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
@ -578,6 +649,7 @@ def _real_extract(self, url):
class NBCOlympicsStreamIE(AdobePassIE):
_WORKING = False
IE_NAME = 'nbcolympics:stream'
_VALID_URL = r'https?://stream\.nbcolympics\.com/(?P<id>[0-9a-z-]+)'
_TESTS = [
@ -630,7 +702,8 @@ def _real_extract(self, url):
event_config.get('resourceId', 'NBCOlympics'),
re.sub(r'[^\w\d ]+', '', event_config['eventTitle']), pid,
event_config.get('ratingId', 'NO VALUE'))
media_token = self._extract_mvpd_auth(url, pid, event_config.get('requestorId', 'NBCOlympics'), ap_resource)
# XXX: The None arg below needs to be the software_statement for this requestor
media_token = self._extract_mvpd_auth(url, pid, event_config.get('requestorId', 'NBCOlympics'), ap_resource, None)
source_url = self._download_json(
'https://tokens.playmakerservices.com/', pid, 'Retrieving tokenized URL',
@ -848,3 +921,178 @@ def _real_extract(self, url):
'is_live': is_live,
**info,
}
class BravoTVIE(NBCUniversalBaseIE):
_VALID_URL = r'https?://(?:www\.)?(?:bravotv|oxygen)\.com/(?:[^/?#]+/)+(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.bravotv.com/top-chef/season-16/episode-15/videos/the-top-chef-season-16-winner-is',
'info_dict': {
'id': '3923059',
'ext': 'mp4',
'title': 'The Top Chef Season 16 Winner Is...',
'display_id': 'the-top-chef-season-16-winner-is',
'description': 'Find out who takes the title of Top Chef!',
'upload_date': '20190315',
'timestamp': 1552618860,
'season_number': 16,
'episode_number': 15,
'series': 'Top Chef',
'episode': 'Finale',
'duration': 190,
'season': 'Season 16',
'thumbnail': r're:^https://.+\.jpg',
'uploader': 'NBCU-BRAV',
'categories': ['Series', 'Series/Top Chef'],
'tags': 'count:10',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/top-chef/season-20/episode-1/london-calling',
'info_dict': {
'id': '9000234570',
'ext': 'mp4',
'title': 'London Calling',
'display_id': 'london-calling',
'description': 'md5:5af95a8cbac1856bd10e7562f86bb759',
'upload_date': '20230310',
'timestamp': 1678418100,
'season_number': 20,
'episode_number': 1,
'series': 'Top Chef',
'episode': 'London Calling',
'duration': 3266,
'season': 'Season 20',
'chapters': 'count:7',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
'media_type': 'Full Episode',
'uploader': 'NBCU-MPAT',
'categories': ['Series/Top Chef'],
'tags': 'count:10',
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-1/closing-night',
'info_dict': {
'id': '3692045',
'ext': 'mp4',
'title': 'Closing Night',
'display_id': 'closing-night',
'description': 'md5:c8a5bb523c8ef381f3328c6d9f1e4632',
'upload_date': '20230126',
'timestamp': 1674709200,
'season_number': 1,
'episode_number': 1,
'series': 'In Ice Cold Blood',
'episode': 'Closing Night',
'duration': 2629,
'season': 'Season 1',
'chapters': 'count:6',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
'media_type': 'Full Episode',
'uploader': 'NBCU-MPAT',
'categories': ['Series/In Ice Cold Blood'],
'tags': ['ice-t', 'in ice cold blood', 'law and order', 'oxygen', 'true crime'],
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}, {
'url': 'https://www.oxygen.com/in-ice-cold-blood/season-2/episode-16/videos/handling-the-horwitz-house-after-the-murder-season-2',
'info_dict': {
'id': '3974019',
'ext': 'mp4',
'title': '\'Handling The Horwitz House After The Murder (Season 2, Episode 16)',
'display_id': 'handling-the-horwitz-house-after-the-murder-season-2',
'description': 'md5:f9d638dd6946a1c1c0533a9c6100eae5',
'upload_date': '20190618',
'timestamp': 1560819600,
'season_number': 2,
'episode_number': 16,
'series': 'In Ice Cold Blood',
'episode': 'Mother Vs Son',
'duration': 68,
'season': 'Season 2',
'thumbnail': r're:^https://.+\.jpg',
'age_limit': 14,
'uploader': 'NBCU-OXY',
'categories': ['Series/In Ice Cold Blood'],
'tags': ['in ice cold blood', 'ice-t', 'law and order', 'true crime', 'oxygen'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.bravotv.com/below-deck/season-3/ep-14-reunion-part-1',
'only_matching': True,
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self._extract_nbcu_video(url, display_id)
class SyfyIE(NBCUniversalBaseIE):
_VALID_URL = r'https?://(?:www\.)?syfy\.com/[^/?#]+/(?:season-\d+/episode-\d+/(?:videos/)?|videos/)(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://www.syfy.com/face-off/season-13/episode-10/videos/keyed-up',
'info_dict': {
'id': '3774403',
'ext': 'mp4',
'display_id': 'keyed-up',
'title': 'Keyed Up',
'description': 'md5:feafd15bee449f212dcd3065bbe9a755',
'age_limit': 14,
'duration': 169,
'thumbnail': r're:https://www\.syfy\.com/.+/.+\.jpg',
'series': 'Face Off',
'season': 'Season 13',
'season_number': 13,
'episode': 'Through the Looking Glass Part 2',
'episode_number': 10,
'timestamp': 1533711618,
'upload_date': '20180808',
'media_type': 'Excerpt',
'uploader': 'NBCU-MPAT',
'categories': ['Series/Face Off'],
'tags': 'count:15',
'_old_archive_ids': ['theplatform 3774403'],
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.syfy.com/face-off/season-13/episode-10/through-the-looking-glass-part-2',
'info_dict': {
'id': '3772391',
'ext': 'mp4',
'display_id': 'through-the-looking-glass-part-2',
'title': 'Through the Looking Glass Pt.2',
'description': 'md5:90bd5dcbf1059fe3296c263599af41d2',
'age_limit': 0,
'duration': 2599,
'thumbnail': r're:https://www\.syfy\.com/.+/.+\.jpg',
'chapters': [{'start_time': 0.0, 'end_time': 679.0, 'title': '<Untitled Chapter 1>'},
{'start_time': 679.0, 'end_time': 1040.967, 'title': '<Untitled Chapter 2>'},
{'start_time': 1040.967, 'end_time': 1403.0, 'title': '<Untitled Chapter 3>'},
{'start_time': 1403.0, 'end_time': 1870.0, 'title': '<Untitled Chapter 4>'},
{'start_time': 1870.0, 'end_time': 2496.967, 'title': '<Untitled Chapter 5>'},
{'start_time': 2496.967, 'end_time': 2599, 'title': '<Untitled Chapter 6>'}],
'series': 'Face Off',
'season': 'Season 13',
'season_number': 13,
'episode': 'Through the Looking Glass Part 2',
'episode_number': 10,
'timestamp': 1672570800,
'upload_date': '20230101',
'media_type': 'Full Episode',
'uploader': 'NBCU-MPAT',
'categories': ['Series/Face Off'],
'tags': 'count:15',
'_old_archive_ids': ['theplatform 3772391'],
},
'params': {'skip_download': 'm3u8'},
'skip': 'This video requires AdobePass MSO credentials',
}]
def _real_extract(self, url):
display_id = self._match_id(url)
return self._extract_nbcu_video(url, display_id, old_ie_key='ThePlatform')

View File

@ -495,7 +495,7 @@ def _real_extract(self, url):
chapters = None
if chapter_durations and chapter_titles and len(chapter_durations) == len(chapter_titles):
start_time = chapter_durations
end_time = chapter_durations[1:] + [duration]
end_time = [*chapter_durations[1:], duration]
chapters = [{
'start_time': s,
'end_time': e,

View File

@ -4,16 +4,15 @@
import json
import re
import time
import urllib.parse
from .common import InfoExtractor, SearchInfoExtractor
from ..networking import Request
from ..networking.exceptions import HTTPError
from ..utils import (
ExtractorError,
OnDemandPagedList,
clean_html,
determine_ext,
extract_attributes,
float_or_none,
int_or_none,
parse_bitrate,
@ -22,9 +21,8 @@
parse_qs,
parse_resolution,
qualities,
remove_start,
str_or_none,
unescapeHTML,
truncate_string,
unified_timestamp,
update_url_query,
url_basename,
@ -32,7 +30,11 @@
urlencode_postdata,
urljoin,
)
from ..utils.traversal import find_element, require, traverse_obj
from ..utils.traversal import (
find_element,
require,
traverse_obj,
)
class NiconicoBaseIE(InfoExtractor):
@ -806,41 +808,39 @@ class NiconicoLiveIE(NiconicoBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
webpage = self._download_webpage(url, video_id, expected_status=404)
if err_msg := traverse_obj(webpage, ({find_element(cls='message')}, {clean_html})):
raise ExtractorError(err_msg, expected=True)
embedded_data = self._parse_json(unescapeHTML(self._search_regex(
r'<script\s+id="embedded-data"\s*data-props="(.+?)"', webpage, 'embedded data')), video_id)
ws_url = traverse_obj(embedded_data, ('site', 'relive', 'webSocketUrl'))
if not ws_url:
raise ExtractorError('The live hasn\'t started yet or already ended.', expected=True)
ws_url = update_url_query(ws_url, {
'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9',
})
hostname = remove_start(urllib.parse.urlparse(urlh.url).hostname, 'sp.')
embedded_data = traverse_obj(webpage, (
{find_element(tag='script', id='embedded-data', html=True)},
{extract_attributes}, 'data-props', {json.loads}))
frontend_id = traverse_obj(embedded_data, ('site', 'frontendId', {str_or_none}), default='9')
ws_url = traverse_obj(embedded_data, (
'site', 'relive', 'webSocketUrl', {url_or_none}, {require('websocket URL')}))
ws_url = update_url_query(ws_url, {'frontend_id': frontend_id})
ws = self._request_webpage(
Request(ws_url, headers={'Origin': f'https://{hostname}'}),
video_id=video_id, note='Connecting to WebSocket server')
ws_url, video_id, 'Connecting to WebSocket server',
headers={'Origin': 'https://live.nicovideo.jp'})
self.write_debug('Sending HLS server request')
ws.send(json.dumps({
'type': 'startWatching',
'data': {
'reconnect': False,
'room': {
'commentable': True,
'protocol': 'webSocket',
},
'stream': {
'quality': 'abr',
'protocol': 'hls',
'latency': 'high',
'accessRightMethod': 'single_cookie',
'chasePlay': False,
'latency': 'high',
'protocol': 'hls',
'quality': 'abr',
},
'room': {
'protocol': 'webSocket',
'commentable': True,
},
'reconnect': False,
},
'type': 'startWatching',
}))
while True:
@ -860,17 +860,15 @@ def _real_extract(self, url):
raise ExtractorError('Disconnected at middle of extraction')
elif data.get('type') == 'error':
self.write_debug(recv)
message = traverse_obj(data, ('body', 'code')) or recv
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
raise ExtractorError(message)
elif self.get_param('verbose', False):
if len(recv) > 100:
recv = recv[:100] + '...'
self.write_debug(f'Server said: {recv}')
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
title = traverse_obj(embedded_data, ('program', 'title')) or self._html_search_meta(
('og:title', 'twitter:title'), webpage, 'live title', fatal=False)
raw_thumbs = traverse_obj(embedded_data, ('program', 'thumbnail')) or {}
raw_thumbs = traverse_obj(embedded_data, ('program', 'thumbnail', {dict})) or {}
thumbnails = []
for name, value in raw_thumbs.items():
if not isinstance(value, dict):
@ -897,31 +895,30 @@ def _real_extract(self, url):
cookie['domain'], cookie['name'], cookie['value'],
expire_time=unified_timestamp(cookie.get('expires')), path=cookie['path'], secure=cookie['secure'])
fmt_common = {
'live_latency': 'high',
'origin': hostname,
'protocol': 'niconico_live',
'video_id': video_id,
'ws': ws,
}
q_iter = (q for q in qualities[1:] if not q.startswith('audio_')) # ignore initial 'abr'
a_map = {96: 'audio_low', 192: 'audio_high'}
formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4', live=True)
for fmt in formats:
fmt['protocol'] = 'niconico_live'
if fmt.get('acodec') == 'none':
fmt['format_id'] = next(q_iter, fmt['format_id'])
elif fmt.get('vcodec') == 'none':
abr = parse_bitrate(fmt['url'].lower())
fmt.update({
'abr': abr,
'acodec': 'mp4a.40.2',
'format_id': a_map.get(abr, fmt['format_id']),
})
fmt.update(fmt_common)
return {
'id': video_id,
'title': title,
'downloader_options': {
'max_quality': traverse_obj(embedded_data, ('program', 'stream', 'maxQuality', {str})) or 'normal',
'ws': ws,
'ws_url': ws_url,
},
**traverse_obj(embedded_data, {
'view_count': ('program', 'statistics', 'watchCount'),
'comment_count': ('program', 'statistics', 'commentCount'),

View File

@ -1,59 +1,57 @@
from .common import InfoExtractor
from ..utils import (
determine_ext,
get_element_by_attribute,
UnsupportedError,
clean_html,
int_or_none,
js_to_json,
mimetype2ext,
update_url_query,
parse_duration,
parse_qs,
str_or_none,
update_url,
)
from ..utils.traversal import find_element, traverse_obj
class NobelPrizeIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
_TEST = {
'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
'md5': '04c81e5714bb36cc4e2232fee1d8157f',
_VALID_URL = r'https?://(?:(?:mediaplayer|www)\.)?nobelprize\.org/mediaplayer/'
_TESTS = [{
'url': 'https://www.nobelprize.org/mediaplayer/?id=2636',
'info_dict': {
'id': '2636',
'ext': 'mp4',
'title': 'Announcement of the 2016 Nobel Prize in Physics',
'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739',
'description': 'md5:1a2d8a6ca80c88fb3b9a326e0b0e8e43',
'duration': 1560.0,
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
'timestamp': 1504883793,
'upload_date': '20170908',
},
}
}, {
'url': 'https://mediaplayer.nobelprize.org/mediaplayer/?qid=12693',
'info_dict': {
'id': '12693',
'ext': 'mp4',
'title': 'Nobel Lecture by Peter Higgs',
'description': 'md5:9b12e275dbe3a8138484e70e00673a05',
'duration': 1800.0,
'thumbnail': r're:https?://www\.nobelprize\.org/images/.+\.jpg',
'timestamp': 1504883793,
'upload_date': '20170908',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
media = self._parse_json(self._search_regex(
r'(?s)var\s*config\s*=\s*({.+?});', webpage,
'config'), video_id, js_to_json)['media']
title = media['title']
formats = []
for source in media.get('source', []):
source_src = source.get('src')
if not source_src:
continue
ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
source_src, video_id, 'mp4', 'm3u8_native',
m3u8_id='hls', fatal=False))
elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
update_url_query(source_src, {'hdcore': '3.7.0'}),
video_id, f4m_id='hds', fatal=False))
else:
formats.append({
'url': source_src,
})
video_id = traverse_obj(parse_qs(url), (
('id', 'qid'), -1, {int_or_none}, {str_or_none}, any))
if not video_id:
raise UnsupportedError(url)
webpage = self._download_webpage(
update_url(url, netloc='mediaplayer.nobelprize.org'), video_id)
return {
**self._search_json_ld(webpage, video_id),
'id': video_id,
'title': title,
'description': get_element_by_attribute('itemprop', 'description', webpage),
'duration': int_or_none(media.get('duration')),
'formats': formats,
'title': self._html_search_meta('caption', webpage),
'description': traverse_obj(webpage, (
{find_element(tag='span', attr='itemprop', value='description')}, {clean_html})),
'duration': parse_duration(self._html_search_meta('duration', webpage)),
}

View File

@ -1,55 +1,82 @@
from .common import InfoExtractor
from .streaks import StreaksBaseIE
from ..utils import (
ExtractorError,
smuggle_url,
traverse_obj,
int_or_none,
parse_iso8601,
str_or_none,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class NTVCoJpCUIE(InfoExtractor):
class NTVCoJpCUIE(StreaksBaseIE):
IE_NAME = 'cu.ntv.co.jp'
IE_DESC = 'Nippon Television Network'
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program)(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://cu.ntv.co.jp/televiva-chill-gohan_181031/',
IE_DESC = '日テレ無料TADA!'
_VALID_URL = r'https?://cu\.ntv\.co\.jp/(?!program-list|search)(?P<id>[\w-]+)/?(?:[?#]|$)'
_TESTS = [{
'url': 'https://cu.ntv.co.jp/gaki_20250525/',
'info_dict': {
'id': '5978891207001',
'id': 'gaki_20250525',
'ext': 'mp4',
'title': '桜エビと炒り卵がポイント! 「中華風 エビチリおにぎり」──『美虎』五十嵐美幸',
'upload_date': '20181213',
'description': 'md5:1985b51a9abc285df0104d982a325f2a',
'uploader_id': '3855502814001',
'timestamp': 1544669941,
'title': '放送開始36年!方正ココリコが選ぶ神回&地獄回!',
'cast': 'count:2',
'description': 'md5:1e1db556224d627d4d2f74370c650927',
'display_id': 'ref:gaki_20250525',
'duration': 1450,
'episode': '放送開始36年!方正ココリコが選ぶ神回&地獄回!',
'episode_id': '000000010172808',
'episode_number': 255,
'genres': ['variety'],
'live_status': 'not_live',
'modified_date': '20250525',
'modified_timestamp': 1748145537,
'release_date': '20250525',
'release_timestamp': 1748145539,
'series': 'ダウンタウンのガキの使いやあらへんで!',
'series_id': 'gaki',
'thumbnail': r're:https?://.+\.jpg',
'timestamp': 1748145197,
'upload_date': '20250525',
'uploader': '日本テレビ放送網',
'uploader_id': '0x7FE2',
},
'params': {
# m3u8 download
'skip_download': True,
},
}
BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
player_config = self._search_nuxt_data(webpage, display_id)
video_id = traverse_obj(player_config, ('movie', 'video_id'))
if not video_id:
raise ExtractorError('Failed to extract video ID for Brightcove')
account_id = traverse_obj(player_config, ('player', 'account')) or '3855502814001'
title = traverse_obj(player_config, ('movie', 'name'))
if not title:
og_title = self._og_search_title(webpage, fatal=False) or traverse_obj(player_config, ('player', 'title'))
if og_title:
title = og_title.split('(', 1)[0].strip()
description = (traverse_obj(player_config, ('movie', 'description'))
or self._html_search_meta(['description', 'og:description'], webpage))
info = self._search_json(
r'window\.app\s*=', webpage, 'video info',
display_id)['falcorCache']['catalog']['episode'][display_id]['value']
media_id = traverse_obj(info, (
'streaks_data', 'mediaid', {str_or_none}, {require('Streaks media ID')}))
non_phonetic = (lambda _, v: v['is_phonetic'] is False, 'value', {str})
return {
'_type': 'url_transparent',
'id': video_id,
'display_id': display_id,
'title': title,
'description': description,
'url': smuggle_url(self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id), {'geo_countries': ['JP']}),
'ie_key': 'BrightcoveNew',
**self._extract_from_streaks_api('ntv-tada', media_id, headers={
'X-Streaks-Api-Key': 'df497719056b44059a0483b8faad1f4a',
}),
**traverse_obj(info, {
'id': ('content_id', {str_or_none}),
'title': ('title', *non_phonetic, any),
'age_limit': ('is_adult_only_content', {lambda x: 18 if x else None}),
'cast': ('credit', ..., 'name', *non_phonetic),
'genres': ('genre', ..., {str}),
'release_timestamp': ('pub_date', {parse_iso8601}),
'tags': ('tags', ..., {str}),
'thumbnail': ('artwork', ..., 'url', any, {url_or_none}),
}),
**traverse_obj(info, ('tv_episode_info', {
'duration': ('duration', {int_or_none}),
'episode_number': ('episode_number', {int}),
'series': ('parent_show_title', *non_phonetic, any),
'series_id': ('show_content_id', {str}),
})),
**traverse_obj(info, ('custom_data', {
'description': ('program_detail', {str}),
'episode': ('episode_title', {str}),
'episode_id': ('episode_id', {str_or_none}),
'uploader': ('network_name', {str}),
'uploader_id': ('network_id', {str}),
})),
}

View File

@ -273,6 +273,8 @@ def _extract_desktop(self, url):
return self._extract_desktop(smuggle_url(url, {'referrer': 'https://boosty.to'}))
elif error:
raise ExtractorError(error, expected=True)
elif '>Access to this video is restricted</div>' in webpage:
self.raise_login_required()
player = self._parse_json(
unescapeHTML(self._search_regex(
@ -429,7 +431,7 @@ def _extract_mobile(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
f'http://m.ok.ru/video/{video_id}', video_id,
f'https://m.ok.ru/video/{video_id}', video_id,
note='Downloading mobile webpage')
error = self._search_regex(

View File

@ -15,7 +15,6 @@
str_or_none,
strip_jsonp,
traverse_obj,
unescapeHTML,
url_or_none,
urljoin,
)
@ -425,7 +424,7 @@ def _real_extract(self, url):
return self.playlist_result(entries, list_id, **traverse_obj(list_json, ('cdlist', 0, {
'title': ('dissname', {str}),
'description': ('desc', {unescapeHTML}, {clean_html}),
'description': ('desc', {clean_html}),
})))

View File

@ -0,0 +1,41 @@
from .floatplane import FloatplaneBaseIE
class SaucePlusIE(FloatplaneBaseIE):
IE_DESC = 'Sauce+'
_VALID_URL = r'https?://(?:(?:www|beta)\.)?sauceplus\.com/post/(?P<id>\w+)'
_BASE_URL = 'https://www.sauceplus.com'
_HEADERS = {
'Origin': _BASE_URL,
'Referer': f'{_BASE_URL}/',
}
_IMPERSONATE_TARGET = True
_TESTS = [{
'url': 'https://www.sauceplus.com/post/YbBwIa2A5g',
'info_dict': {
'id': 'eit4Ugu5TL',
'ext': 'mp4',
'display_id': 'YbBwIa2A5g',
'title': 'Scare the Coyote - Episode 3',
'description': '',
'thumbnail': r're:^https?://.*\.jpe?g$',
'duration': 2975,
'comment_count': int,
'like_count': int,
'dislike_count': int,
'release_date': '20250627',
'release_timestamp': 1750993500,
'uploader': 'Scare The Coyote',
'uploader_id': '683e0a3269688656a5a49a44',
'uploader_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home',
'channel': 'Scare The Coyote',
'channel_id': '683e0a326968866ceba49a45',
'channel_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home/main',
'availability': 'subscriber_only',
},
'params': {'skip_download': 'm3u8'},
}]
def _real_initialize(self):
if not self._get_cookies(self._BASE_URL).get('__Host-sp-sess'):
self.raise_login_required()

View File

@ -213,7 +213,7 @@ class CieloTVItIE(SkyItIE): # XXX: Do not subclass from concrete IE
class TV8ItIE(SkyItVideoIE): # XXX: Do not subclass from concrete IE
IE_NAME = 'tv8.it'
_VALID_URL = r'https?://(?:www\.)?tv8\.it/(?:show)?video/[0-9a-z-]+-(?P<id>\d+)'
_VALID_URL = r'https?://(?:www\.)?tv8\.it/(?:show)?video/(?:[0-9a-z-]+-)?(?P<id>\d+)'
_TESTS = [{
'url': 'https://www.tv8.it/video/ogni-mattina-ucciso-asino-di-andrea-lo-cicero-630529',
'md5': '9ab906a3f75ea342ed928442f9dabd21',
@ -227,6 +227,19 @@ class TV8ItIE(SkyItVideoIE): # XXX: Do not subclass from concrete IE
'thumbnail': 'https://videoplatform.sky.it/still/2020/11/18/1605717753954_ogni-mattina-ucciso-asino-di-andrea-lo-cicero_videostill_1.jpg',
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'https://www.tv8.it/video/964361',
'md5': '1e58e807154658a16edc29e45be38107',
'info_dict': {
'id': '964361',
'ext': 'mp4',
'title': 'GialappaShow - S.4 Ep.2',
'description': 'md5:60bb4ff5af18bbeeaedabc1de5f9e1e2',
'duration': 8030,
'thumbnail': 'https://videoplatform.sky.it/captures/494/2024/11/06/964361/964361_1730888412914_thumb_494.jpg',
'timestamp': 1730821499,
'upload_date': '20241105',
},
}]
_DOMAIN = 'mtv8'

View File

@ -25,6 +25,7 @@ class SportDeutschlandIE(InfoExtractor):
'upload_date': '20230114',
'timestamp': 1673733618,
},
'skip': 'not found',
}, {
'url': 'https://sportdeutschland.tv/deutscherbadmintonverband/bwf-tour-1-runde-feld-1-yonex-gainward-german-open-2022-0',
'info_dict': {
@ -41,6 +42,7 @@ class SportDeutschlandIE(InfoExtractor):
'upload_date': '20220309',
'timestamp': 1646860727.0,
},
'skip': 'not found',
}, {
'url': 'https://sportdeutschland.tv/ggcbremen/formationswochenende-latein-2023',
'info_dict': {
@ -68,6 +70,7 @@ class SportDeutschlandIE(InfoExtractor):
'live_status': 'was_live',
},
}],
'skip': 'not found',
}, {
'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
'info_dict': {
@ -82,13 +85,30 @@ class SportDeutschlandIE(InfoExtractor):
'live_status': 'is_live',
},
'skip': 'live',
}, {
'url': 'https://sportdeutschland.tv/rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
'md5': '35c11a19395c938cdd076b93bda54cde',
'info_dict': {
'id': '9f27a97d-1544-4d0b-aa03-48d92d17a03a',
'ext': 'mp4',
'title': 'GFL2: Rostock Griffins vs. Elmshorn Fighting Pirates',
'display_id': 'rostock-griffins/gfl2-rostock-griffins-vs-elmshorn-fighting-pirates',
'channel': 'Rostock Griffins',
'channel_url': 'https://sportdeutschland.tv/rostock-griffins',
'live_status': 'was_live',
'description': 'md5:60cb00067e55dafa27b0933a43d72862',
'channel_id': '9635f21c-3f67-4584-9ce4-796e9a47276b',
'timestamp': 1749913117,
'upload_date': '20250614',
},
}]
def _process_video(self, asset_id, video):
is_live = video['type'] == 'mux_live'
token = self._download_json(
f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
video['id'], query={'type': video['type'], 'playback_id': video['src']})['token']
f'https://api.sportdeutschland.tv/api/web/personal/asset-token/{asset_id}',
video['id'], query={'type': video['type'], 'playback_id': video['src']},
headers={'Referer': 'https://sportdeutschland.tv/'})['token']
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
f'https://stream.mux.com/{video["src"]}.m3u8?token={token}', video['id'], live=is_live)

View File

@ -41,6 +41,7 @@ class SproutVideoIE(InfoExtractor):
'duration': 703,
'thumbnail': r're:https?://images\.sproutvideo\.com/.+\.jpg',
},
'skip': 'Account Disabled',
}, {
# http formats 'sd' and 'hd' are available
'url': 'https://videos.sproutvideo.com/embed/119cd6bc1a18e6cd98/30751a1761ae5b90',
@ -98,10 +99,17 @@ def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})
video_id = self._match_id(url)
webpage = self._download_webpage(
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}), impersonate=True)
data = self._search_json(
r'var\s+dat\s*=\s*["\']', webpage, 'data', video_id, contains_pattern=r'[A-Za-z0-9+/=]+',
end_pattern=r'["\'];', transform_source=lambda x: base64.b64decode(x).decode())
r'(?:var|const|let)\s+(?:dat|playerInfo)\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]
# e.g. if the user-agent we used with the webpage request is too old
video_uid = data['videoUid']
if video_id != video_uid:
raise ExtractorError(f'{self.IE_NAME} sent the wrong video data ({video_uid})')
formats, subtitles = [], {}
headers = {

View File

@ -1,57 +1,102 @@
from .ard import ARDMediathekBaseIE
from ..utils import (
ExtractorError,
get_element_by_attribute,
clean_html,
extract_attributes,
parse_duration,
parse_qs,
unified_strdate,
)
from ..utils.traversal import (
find_element,
require,
traverse_obj,
)
class SRMediathekIE(ARDMediathekBaseIE):
_WORKING = False
IE_NAME = 'sr:mediathek'
IE_DESC = 'Saarländischer Rundfunk'
_VALID_URL = r'https?://sr-mediathek(?:\.sr-online)?\.de/index\.php\?.*?&id=(?P<id>[0-9]+)'
_CLS_COMMON = 'teaser__image__caption__text teaser__image__caption__text--'
_VALID_URL = r'https?://(?:www\.)?sr-mediathek\.de/index\.php\?.*?&id=(?P<id>\d+)'
_TESTS = [{
'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=28455',
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=141317',
'info_dict': {
'id': '28455',
'id': '141317',
'ext': 'mp4',
'title': 'sportarena (26.10.2014)',
'description': 'Ringen: KSV Köllerbach gegen Aachen-Walheim; Frauen-Fußball: 1. FC Saarbrücken gegen Sindelfingen; Motorsport: Rallye in Losheim; dazu: Interview mit Timo Bernhard; Turnen: TG Saar; Reitsport: Deutscher Voltigier-Pokal; Badminton: Interview mit Michael Fuchs ',
'thumbnail': r're:^https?://.*\.jpg$',
},
'skip': 'no longer available',
}, {
'url': 'http://sr-mediathek.sr-online.de/index.php?seite=7&id=37682',
'info_dict': {
'id': '37682',
'ext': 'mp4',
'title': 'Love, Cakes and Rock\'n\'Roll',
'description': 'md5:18bf9763631c7d326c22603681e1123d',
},
'params': {
# m3u8 download
'skip_download': True,
'title': 'Kärnten, da will ich hin!',
'channel': 'SR Fernsehen',
'description': 'md5:7732e71e803379a499732864a572a456',
'duration': 1788.0,
'release_date': '20250525',
'series': 'da will ich hin!',
'series_id': 'DWIH',
'thumbnail': r're:https?://.+\.jpg',
},
}, {
'url': 'http://sr-mediathek.de/index.php?seite=7&id=7480',
'only_matching': True,
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=153853',
'info_dict': {
'id': '153853',
'ext': 'mp3',
'title': 'Kappes, Klöße, Kokosmilch: Bruschetta mit Nduja',
'channel': 'SR 3',
'description': 'md5:3935798de3562b10c4070b408a15e225',
'duration': 139.0,
'release_date': '20250523',
'series': 'Kappes, Klöße, Kokosmilch',
'series_id': 'SR3_KKK_A',
'thumbnail': r're:https?://.+\.jpg',
},
}, {
'url': 'https://www.sr-mediathek.de/index.php?seite=7&id=31406&pnr=&tbl=pf',
'info_dict': {
'id': '31406',
'ext': 'mp3',
'title': 'Das Leben schwer nehmen, ist einfach zu anstrengend',
'channel': 'SR 1',
'description': 'md5:3e03fd556af831ad984d0add7175fb0c',
'duration': 1769.0,
'release_date': '20230717',
'series': 'Abendrot',
'series_id': 'SR1_AB_P',
'thumbnail': r're:https?://.+\.jpg',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
description = self._og_search_description(webpage)
if '>Der gew&uuml;nschte Beitrag ist leider nicht mehr verf&uuml;gbar.<' in webpage:
if description == 'Der gewünschte Beitrag ist leider nicht mehr vorhanden.':
raise ExtractorError(f'Video {video_id} is no longer available', expected=True)
media_collection_url = self._search_regex(
r'data-mediacollection-ardplayer="([^"]+)"', webpage, 'media collection url')
info = self._extract_media_info(media_collection_url, webpage, video_id)
info.update({
player_url = traverse_obj(webpage, (
{find_element(tag='div', id=f'player{video_id}', html=True)},
{extract_attributes}, 'data-mediacollection-ardplayer',
{self._proto_relative_url}, {require('player URL')}))
article = traverse_obj(webpage, (
{find_element(cls='article__content')},
{find_element(tag='p')}, {clean_html}))
return {
**self._extract_media_info(player_url, webpage, video_id),
'id': video_id,
'title': get_element_by_attribute('class', 'ardplayer-title', webpage),
'description': self._og_search_description(webpage),
'title': traverse_obj(webpage, (
{find_element(cls='ardplayer-title')}, {clean_html})),
'channel': traverse_obj(webpage, (
{find_element(cls=f'{self._CLS_COMMON}subheadline')},
{lambda x: x.split('|')[0]}, {clean_html})),
'description': description,
'duration': parse_duration(self._search_regex(
r'(\d{2}:\d{2}:\d{2})', article, 'duration')),
'release_date': unified_strdate(self._search_regex(
r'(\d{2}\.\d{2}\.\d{4})', article, 'release_date')),
'series': traverse_obj(webpage, (
{find_element(cls=f'{self._CLS_COMMON}headline')}, {clean_html})),
'series_id': traverse_obj(webpage, (
{find_element(cls='teaser__link', html=True)},
{extract_attributes}, 'href', {parse_qs}, 'sen', ..., {str}, any)),
'thumbnail': self._og_search_thumbnail(webpage),
})
return info
}

View File

@ -4,6 +4,7 @@
from ..utils import (
int_or_none,
traverse_obj,
url_basename,
url_or_none,
)
@ -65,9 +66,19 @@ def _extract_ppv(self, url):
hls_info, decrypt = self._call_encrypted_api(
video_id, ':watchArchive', 'stream information', data={'method': 1})
formats = self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id)
for f in formats:
# bitrates are exaggerated in PPV playlists, so avoid wrong/huge filesize_approx values
if f.get('tbr'):
f['tbr'] = int(f['tbr'] / 2.5)
# prefer variants with the same basename as the master playlist to avoid partial streams
f['format_id'] = url_basename(f['url']).partition('.')[0]
if not f['format_id'].startswith(url_basename(f['manifest_url']).partition('.')[0]):
f['preference'] = -10
return {
'id': video_id,
'formats': self._get_formats(hls_info, ('hls', 'urls', ..., {url_or_none}), video_id),
'formats': formats,
'hls_aes': self._extract_hls_key(hls_info, 'hls', decrypt),
**traverse_obj(video_info, {
'title': ('displayName', {str}),

View File

@ -1,76 +1,76 @@
from .common import InfoExtractor
from ..utils import int_or_none, urljoin
from .youtube import YoutubeIE
from ..utils import (
clean_html,
parse_iso8601,
update_url,
url_or_none,
)
from ..utils.traversal import subs_list_to_dict, traverse_obj
class StarTrekIE(InfoExtractor):
_WORKING = False
_VALID_URL = r'(?P<base>https?://(?:intl|www)\.startrek\.com)/videos/(?P<id>[^/]+)'
IE_NAME = 'startrek'
IE_DESC = 'STAR TREK'
_VALID_URL = r'https?://(?:www\.)?startrek\.com(?:/en-(?:ca|un))?/videos/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'https://intl.startrek.com/videos/watch-welcoming-jess-bush-to-the-ready-room',
'md5': '491df5035c9d4dc7f63c79caaf9c839e',
'url': 'https://www.startrek.com/en-un/videos/official-trailer-star-trek-lower-decks-season-4',
'info_dict': {
'id': 'watch-welcoming-jess-bush-to-the-ready-room',
'id': 'official-trailer-star-trek-lower-decks-season-4',
'ext': 'mp4',
'title': 'WATCH: Welcoming Jess Bush to The Ready Room',
'duration': 1888,
'timestamp': 1655388000,
'upload_date': '20220616',
'description': 'md5:1ffee884e3920afbdd6dd04e926a1221',
'thumbnail': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14794_rr_thumb_107_yt_16x9\.jpg(?:\?.+)?',
'subtitles': {'en-US': [{
'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_107_v4\.vtt',
}, {
'url': 'https://media.startrek.com/2022/06/16/2043801155561/1069981_hls/trr_snw_107_v4-c4bfc25d/stream_vtt.m3u8',
}]},
'title': 'Official Trailer | Star Trek: Lower Decks - Season 4',
'alt_title': 'md5:dd7e3191aaaf9e95db16fc3abd5ef68b',
'categories': ['TRAILERS'],
'description': 'md5:563d7856ddab99bee7a5e50f45531757',
'release_date': '20230722',
'release_timestamp': 1690033200,
'series': 'Star Trek: Lower Decks',
'series_id': 'star-trek-lower-decks',
'thumbnail': r're:https?://.+\.(?:jpg|png)',
},
}, {
'url': 'https://www.startrek.com/videos/watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
'md5': 'f5ad74fbb86e91e0882fc0a333178d1d',
'url': 'https://www.startrek.com/en-ca/videos/my-first-contact-senator-cory-booker',
'info_dict': {
'id': 'watch-ethan-peck-and-gia-sandhu-beam-down-to-the-ready-room',
'id': 'my-first-contact-senator-cory-booker',
'ext': 'mp4',
'title': 'WATCH: Ethan Peck and Gia Sandhu Beam Down to The Ready Room',
'duration': 1986,
'timestamp': 1654221600,
'upload_date': '20220603',
'description': 'md5:b3aa0edacfe119386567362dec8ed51b',
'thumbnail': r're:https://www\.startrek\.com/sites/default/files/styles/video_1920x1080/public/images/2022-06/pp_14792_rr_thumb_105_yt_16x9_1.jpg(?:\?.+)?',
'subtitles': {'en-US': [{
'url': r're:https://(?:intl|www)\.startrek\.com/sites/default/files/video/captions/2022-06/TRR_SNW_105_v5\.vtt',
}]},
'title': 'My First Contact: Senator Cory Booker',
'alt_title': 'md5:fe74a8bdb0afab421c6e159a7680db4d',
'categories': ['MY FIRST CONTACT'],
'description': 'md5:a3992ab3b3e0395925d71156bbc018ce',
'release_date': '20250401',
'release_timestamp': 1743512400,
'series': 'Star Trek: The Original Series',
'series_id': 'star-trek-the-original-series',
'thumbnail': r're:https?://.+\.(?:jpg|png)',
},
}]
def _real_extract(self, url):
urlbase, video_id = self._match_valid_url(url).group('base', 'id')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
player = self._search_regex(
r'(<\s*div\s+id\s*=\s*"cvp-player-[^<]+<\s*/div\s*>)', webpage, 'player')
page_props = self._search_nextjs_data(webpage, video_id)['props']['pageProps']
video_data = page_props['video']['data']
if youtube_id := video_data.get('youtube_video_id'):
return self.url_result(youtube_id, YoutubeIE)
hls = self._html_search_regex(r'\bdata-hls\s*=\s*"([^"]+)"', player, 'HLS URL')
formats, subtitles = self._extract_m3u8_formats_and_subtitles(hls, video_id, 'mp4')
captions = self._html_search_regex(
r'\bdata-captions-url\s*=\s*"([^"]+)"', player, 'captions URL', fatal=False)
if captions:
subtitles.setdefault('en-US', [])[:0] = [{'url': urljoin(urlbase, captions)}]
# NB: Most of the data in the json_ld is undesirable
json_ld = self._search_json_ld(webpage, video_id, fatal=False)
series_id = traverse_obj(video_data, (
'series_and_movies', ..., 'series_or_movie', 'slug', {str}, any))
return {
'id': video_id,
'title': self._html_search_regex(
r'\bdata-title\s*=\s*"([^"]+)"', player, 'title', json_ld.get('title')),
'description': self._html_search_regex(
r'(?s)<\s*div\s+class\s*=\s*"header-body"\s*>(.+?)<\s*/div\s*>',
webpage, 'description', fatal=False),
'duration': int_or_none(self._html_search_regex(
r'\bdata-duration\s*=\s*"(\d+)"', player, 'duration', fatal=False)),
'formats': formats,
'subtitles': subtitles,
'thumbnail': urljoin(urlbase, self._html_search_regex(
r'\bdata-poster-url\s*=\s*"([^"]+)"', player, 'thumbnail', fatal=False)),
'timestamp': json_ld.get('timestamp'),
'series': traverse_obj(page_props, (
'queried', 'header', 'tab3', 'slices', ..., 'items',
lambda _, v: v['link']['slug'] == series_id, 'link_copy', {str}, any)),
'series_id': series_id,
**traverse_obj(video_data, {
'title': ('title', ..., 'text', {clean_html}, any),
'alt_title': ('subhead', ..., 'text', {clean_html}, any),
'categories': ('category', 'data', 'category_name', {str.upper}, filter, all),
'description': ('slices', ..., 'primary', 'content', ..., 'text', {clean_html}, any),
'release_timestamp': ('published', {parse_iso8601}),
'subtitles': ({'url': 'legacy_subtitle_file'}, all, {subs_list_to_dict(lang='en')}),
'thumbnail': ('poster_frame', 'url', {url_or_none}, {update_url(query=None)}),
'url': ('legacy_video_url', {url_or_none}),
}),
}

View File

@ -6,10 +6,13 @@
determine_ext,
dict_get,
int_or_none,
traverse_obj,
try_get,
unified_timestamp,
)
from ..utils.traversal import (
require,
traverse_obj,
)
class SVTBaseIE(InfoExtractor):
@ -97,40 +100,8 @@ def _extract_video(self, video_info, video_id):
}
class SVTIE(SVTBaseIE):
_VALID_URL = r'https?://(?:www\.)?svt\.se/wd\?(?:.*?&)?widgetId=(?P<widget_id>\d+)&.*?\barticleId=(?P<id>\d+)'
_EMBED_REGEX = [rf'(?:<iframe src|href)="(?P<url>{_VALID_URL}[^"]*)"']
_TEST = {
'url': 'http://www.svt.se/wd?widgetId=23991&sectionId=541&articleId=2900353&type=embed&contextSectionId=123&autostart=false',
'md5': '33e9a5d8f646523ce0868ecfb0eed77d',
'info_dict': {
'id': '2900353',
'ext': 'mp4',
'title': 'Stjärnorna skojar till det - under SVT-intervjun',
'duration': 27,
'age_limit': 0,
},
}
def _real_extract(self, url):
mobj = self._match_valid_url(url)
widget_id = mobj.group('widget_id')
article_id = mobj.group('id')
info = self._download_json(
f'http://www.svt.se/wd?widgetId={widget_id}&articleId={article_id}&format=json&type=embed&output=json',
article_id)
info_dict = self._extract_video(info['video'], article_id)
info_dict['title'] = info['context']['title']
return info_dict
class SVTPlayBaseIE(SVTBaseIE):
_SVTPLAY_RE = r'root\s*\[\s*(["\'])_*svtplay\1\s*\]\s*=\s*(?P<json>{.+?})\s*;\s*\n'
class SVTPlayIE(SVTPlayBaseIE):
class SVTPlayIE(SVTBaseIE):
IE_NAME = 'svt:play'
IE_DESC = 'SVT Play and Öppet arkiv'
_VALID_URL = r'''(?x)
(?:
@ -173,6 +144,7 @@ class SVTPlayIE(SVTPlayBaseIE):
'ext': 'mp4',
'title': '1. Farlig kryssning',
'timestamp': 1491019200,
'description': 'md5:8f350bc605677a5ead36a19a62fd9a34',
'upload_date': '20170401',
'duration': 2566,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
@ -186,19 +158,21 @@ class SVTPlayIE(SVTPlayBaseIE):
'params': {
'skip_download': 'm3u8',
},
'expected_warnings': [r'Failed to download (?:MPD|m3u8)'],
}, {
'url': 'https://www.svtplay.se/video/jz2rYz7/anders-hansen-moter/james-fallon?info=visa',
'info_dict': {
'id': 'jvXAGVb',
'ext': 'mp4',
'title': 'James Fallon',
'timestamp': 1673917200,
'upload_date': '20230117',
'description': r're:James Fallon är hjärnforskaren .{532} att upptäcka psykopati tidigt\?$',
'timestamp': 1743379200,
'upload_date': '20250331',
'duration': 1081,
'thumbnail': r're:^https?://(?:.*[\.-]jpg|www.svtstatic.se/image/.*)$',
'age_limit': 0,
'episode': 'James Fallon',
'series': 'Anders Hansen möter...',
'series': 'Anders Hansen möter',
},
'params': {
'skip_download': 'dash',
@ -233,96 +207,75 @@ class SVTPlayIE(SVTPlayBaseIE):
'only_matching': True,
}]
def _extract_by_video_id(self, video_id, webpage=None):
def _extract_by_video_id(self, video_id):
data = self._download_json(
f'https://api.svt.se/videoplayer-api/video/{video_id}',
video_id, headers=self.geo_verification_headers())
info_dict = self._extract_video(data, video_id)
if not info_dict.get('title'):
title = dict_get(info_dict, ('episode', 'series'))
if not title and webpage:
title = re.sub(
r'\s*\|\s*.+?$', '', self._og_search_title(webpage))
if not title:
title = video_id
info_dict['title'] = title
info_dict['title'] = traverse_obj(info_dict, 'episode', 'series')
return info_dict
def _real_extract(self, url):
mobj = self._match_valid_url(url)
video_id = mobj.group('id')
svt_id = mobj.group('svt_id') or mobj.group('modal_id')
if svt_id:
return self._extract_by_video_id(svt_id)
webpage = self._download_webpage(url, video_id)
data = self._parse_json(
self._search_regex(
self._SVTPLAY_RE, webpage, 'embedded data', default='{}',
group='json'),
video_id, fatal=False)
thumbnail = self._og_search_thumbnail(webpage)
if data:
video_info = try_get(
data, lambda x: x['context']['dispatcher']['stores']['VideoTitlePageStore']['data']['video'],
dict)
if video_info:
info_dict = self._extract_video(video_info, video_id)
info_dict.update({
'title': data['context']['dispatcher']['stores']['MetaStore']['title'],
'thumbnail': thumbnail,
})
return info_dict
svt_id = try_get(
data, lambda x: x['statistics']['dataLake']['content']['id'],
str)
data = traverse_obj(self._search_nextjs_data(webpage, video_id), (
'props', 'urqlState', ..., 'data', {json.loads},
'detailsPageByPath', {dict}, any, {require('video data')}))
details = traverse_obj(data, (
'modules', lambda _, v: v['details']['smartStart']['item']['videos'], 'details', any))
svt_id = traverse_obj(details, (
'smartStart', 'item', 'videos',
# There can be 'AudioDescribed' and 'SignInterpreted' variants; try 'Default' or else get first
(lambda _, v: v['accessibility'] == 'Default', 0),
'svtId', {str}, any))
if not svt_id:
nextjs_data = self._search_nextjs_data(webpage, video_id, fatal=False)
svt_id = traverse_obj(nextjs_data, (
'props', 'urqlState', ..., 'data', {json.loads}, 'detailsPageByPath',
'video', 'svtId', {str}), get_all=False)
svt_id = traverse_obj(data, ('video', 'svtId', {str}, {require('SVT ID')}))
if not svt_id:
svt_id = self._search_regex(
(r'<video[^>]+data-video-id=["\']([\da-zA-Z-]+)',
r'<[^>]+\bdata-rt=["\']top-area-play-button["\'][^>]+\bhref=["\'][^"\']*video/[\w-]+/[^"\']*\b(?:modalId|id)=([\w-]+)'),
webpage, 'video id')
info_dict = self._extract_by_video_id(svt_id)
info_dict = self._extract_by_video_id(svt_id, webpage)
info_dict['thumbnail'] = thumbnail
if not info_dict.get('title'):
info_dict['title'] = re.sub(r'\s*\|\s*.+?$', '', self._og_search_title(webpage))
if not info_dict.get('thumbnail'):
info_dict['thumbnail'] = self._og_search_thumbnail(webpage)
if not info_dict.get('description'):
info_dict['description'] = traverse_obj(details, ('description', {str}))
return info_dict
class SVTSeriesIE(SVTPlayBaseIE):
class SVTSeriesIE(SVTBaseIE):
IE_NAME = 'svt:play:series'
_VALID_URL = r'https?://(?:www\.)?svtplay\.se/(?P<id>[^/?&#]+)(?:.+?\btab=(?P<season_slug>[^&#]+))?'
_TESTS = [{
'url': 'https://www.svtplay.se/rederiet',
'info_dict': {
'id': '14445680',
'id': 'jpmQYgn',
'title': 'Rederiet',
'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
'description': 'md5:f71122f7cf2e52b643e75915e04cb83d',
},
'playlist_mincount': 318,
}, {
'url': 'https://www.svtplay.se/rederiet?tab=season-2-14445680',
'url': 'https://www.svtplay.se/rederiet?tab=season-2-jpmQYgn',
'info_dict': {
'id': 'season-2-14445680',
'id': 'season-2-jpmQYgn',
'title': 'Rederiet - Säsong 2',
'description': 'md5:d9fdfff17f5d8f73468176ecd2836039',
'description': 'md5:f71122f7cf2e52b643e75915e04cb83d',
},
'playlist_mincount': 12,
}]
@classmethod
def suitable(cls, url):
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super().suitable(url)
return False if SVTPlayIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
series_slug, season_id = self._match_valid_url(url).groups()
@ -386,6 +339,7 @@ def _real_extract(self, url):
class SVTPageIE(SVTBaseIE):
IE_NAME = 'svt:page'
_VALID_URL = r'https?://(?:www\.)?svt\.se/(?:[^/?#]+/)*(?P<id>[^/?&#]+)'
_TESTS = [{
'url': 'https://www.svt.se/nyheter/lokalt/skane/viktor-18-forlorade-armar-och-ben-i-sepsis-vill-ateruppta-karaten-och-bli-svetsare',
@ -463,7 +417,7 @@ class SVTPageIE(SVTBaseIE):
@classmethod
def suitable(cls, url):
return False if SVTIE.suitable(url) or SVTPlayIE.suitable(url) else super().suitable(url)
return False if SVTPlayIE.suitable(url) else super().suitable(url)
def _real_extract(self, url):
display_id = self._match_id(url)

View File

@ -1,58 +0,0 @@
from .adobepass import AdobePassIE
from ..utils import (
smuggle_url,
update_url_query,
)
class SyfyIE(AdobePassIE):
_WORKING = False
_VALID_URL = r'https?://(?:www\.)?syfy\.com/(?:[^/]+/)?videos/(?P<id>[^/?#]+)'
_TESTS = [{
'url': 'http://www.syfy.com/theinternetruinedmylife/videos/the-internet-ruined-my-life-season-1-trailer',
'info_dict': {
'id': '2968097',
'ext': 'mp4',
'title': 'The Internet Ruined My Life: Season 1 Trailer',
'description': 'One tweet, one post, one click, can destroy everything.',
'uploader': 'NBCU-MPAT',
'upload_date': '20170113',
'timestamp': 1484345640,
},
'params': {
# m3u8 download
'skip_download': True,
},
'add_ie': ['ThePlatform'],
'skip': 'Redirects to main page',
}]
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
syfy_mpx = next(iter(self._parse_json(self._search_regex(
r'jQuery\.extend\(Drupal\.settings\s*,\s*({.+?})\);', webpage, 'drupal settings'),
display_id)['syfy']['syfy_mpx'].values()))
video_id = syfy_mpx['mpxGUID']
title = syfy_mpx['episodeTitle']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
if syfy_mpx.get('entitlement') == 'auth':
resource = self._get_mvpd_resource(
'syfy', title, video_id,
syfy_mpx.get('mpxRating', 'TV-14'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'syfy', resource)
return {
'_type': 'url_transparent',
'ie_key': 'ThePlatform',
'url': smuggle_url(update_url_query(
self._proto_relative_url(syfy_mpx['releaseURL']), query),
{'force_smil_url': True}),
'title': title,
'id': video_id,
'display_id': display_id,
}

View File

@ -32,6 +32,10 @@ class TBSIE(TurnerBaseIE):
'url': 'http://www.tntdrama.com/movies/star-wars-a-new-hope',
'only_matching': True,
}]
_SOFTWARE_STATEMENT_MAP = {
'tbs': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJkZTA0NTYxZS1iMTFhLTRlYTgtYTg5NC01NjI3MGM1NmM2MWIiLCJuYmYiOjE1MzcxODkzOTAsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTg5MzkwfQ.Z7ny66kaqNDdCHf9Y9KsV12LrBxrLkGGxlYe2XGm6qsw2T-k1OCKC1TMzeqiZP735292MMRAQkcJDKrMIzNbAuf9nCdIcv4kE1E2nqUnjPMBduC1bHffZp8zlllyrN2ElDwM8Vhwv_5nElLRwWGEt0Kaq6KJAMZA__WDxKWC18T-wVtsOZWXQpDqO7nByhfj2t-Z8c3TUNVsA_wHgNXlkzJCZ16F2b7yGLT5ZhLPupOScd3MXC5iPh19HSVIok22h8_F_noTmGzmMnIRQi6bWYWK2zC7TQ_MsYHfv7V6EaG5m1RKZTV6JAwwoJQF_9ByzarLV1DGwZxD9-eQdqswvg',
'tntdrama': 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwOTMxYTU4OS1jZjEzLTRmNjMtYTJmYy03MzhjMjE1NWU5NjEiLCJuYmYiOjE1MzcxOTA4MjcsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODI3fQ.AucKvtws7oekTXi80_zX4-BlgJD9GLvlOI9FlBCjdlx7Pa3eJ0AqbogynKMiatMbnLOTMHGjd7tTiq422unmZjBz70dhePAe9BbW0dIo7oQ57vZ-VBYw_tWYRPmON61MwAbLVlqROD3n_zURs85S8TlkQx9aNx9x_riGGELjd8l05CVa_pOluNhYvuIFn6wmrASOKI1hNEblBDWh468UWP571-fe4zzi0rlYeeHd-cjvtWvOB3bQsWrUVbK4pRmqvzEH59j0vNF-ihJF9HncmUicYONe47Mib3elfMok23v4dB1_UAlQY_oawfNcynmEnJQCcqFmbHdEwTW6gMiYsA',
}
def _real_extract(self, url):
site, path, display_id = self._match_valid_url(url).groups()
@ -48,7 +52,7 @@ def _real_extract(self, url):
drupal_settings['ngtv_token_url']).query)
info = self._extract_ngtv_info(
media_id, tokenizer_query, {
media_id, tokenizer_query, self._SOFTWARE_STATEMENT_MAP[site], {
'url': url,
'site_name': site[:3].upper(),
'auth_required': video_data.get('authRequired') == '1' or is_live,

View File

@ -156,6 +156,7 @@ def _real_extract(self, url):
class ConanClassicIE(TeamcocoBaseIE):
_WORKING = False
_VALID_URL = r'https?://(?:(?:www\.)?conanclassic|conan25\.teamcoco)\.com/(?P<id>([^/]+/)*[^/?#]+)'
_TESTS = [{
'url': 'https://conanclassic.com/video/ice-cube-kevin-hart-conan-share-lyft',
@ -263,7 +264,7 @@ def _real_extract(self, url):
info.update(self._extract_ngtv_info(media_id, {
'accessToken': token,
'accessTokenType': 'jws',
}))
}, None)) # TODO: the None arg needs to be the AdobePass software_statement
else:
formats, subtitles = self._get_formats_and_subtitles(
traverse_obj(response, ('data', 'findRecordVideoMetadata')), video_id)

View File

@ -63,6 +63,17 @@ def _parse_content(self, content, url):
'http_headers': headers,
}
def _download_akamai_webpage(self, url, display_id):
try: # yt-dlp's default user-agents are too old and blocked by akamai
return self._download_webpage(url, display_id, headers={
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:136.0) Gecko/20100101 Firefox/136.0',
})
except ExtractorError as e:
if not isinstance(e.cause, HTTPError) or e.cause.status != 403:
raise
# Retry with impersonation if hardcoded UA is insufficient to bypass akamai
return self._download_webpage(url, display_id, impersonate=True)
class TelecincoIE(TelecincoBaseIE):
IE_DESC = 'telecinco.es, cuatro.com and mediaset.es'
@ -140,7 +151,7 @@ class TelecincoIE(TelecincoBaseIE):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
webpage = self._download_akamai_webpage(url, display_id)
article = self._search_json(
r'window\.\$REACTBASE_STATE\.article(?:_multisite)?\s*=',
webpage, 'article', display_id)['article']

View File

@ -6,32 +6,32 @@
class TenPlayIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/]+/)+(?P<id>tpv\d{6}[a-z]{5})'
IE_NAME = '10play'
_VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?:[^/?#]+/)+(?P<id>tpv\d{6}[a-z]{5})'
_NETRC_MACHINE = '10play'
_TESTS = [{
'url': 'https://10play.com.au/neighbours/web-extras/season-41/heres-a-first-look-at-mischa-bartons-neighbours-debut/tpv230911hyxnz',
# Geo-restricted to Australia
'url': 'https://10play.com.au/australian-survivor/web-extras/season-10-brains-v-brawn-ii/myless-journey/tpv250414jdmtf',
'info_dict': {
'id': '6336940246112',
'id': '7440980000013868',
'ext': 'mp4',
'title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
'alt_title': 'Here\'s A First Look At Mischa Barton\'s Neighbours Debut',
'description': 'Neighbours Premieres Monday, September 18 At 4:30pm On 10 And 10 Play And 6:30pm On 10 Peach',
'duration': 74,
'season': 'Season 41',
'season_number': 41,
'series': 'Neighbours',
'thumbnail': r're:https://.*\.jpg',
'title': 'Myles\'s Journey',
'alt_title': 'Myles\'s Journey',
'description': 'Relive Myles\'s epic Brains V Brawn II journey to reach the game\'s final two',
'uploader': 'Channel 10',
'age_limit': 15,
'timestamp': 1694386800,
'upload_date': '20230910',
'uploader_id': '2199827728001',
'age_limit': 15,
'duration': 249,
'thumbnail': r're:https://.+/.+\.jpg',
'series': 'Australian Survivor',
'season': 'Season 10',
'season_number': 10,
'timestamp': 1744629420,
'upload_date': '20250414',
},
'params': {
'skip_download': True,
},
'skip': 'Only available in Australia',
'params': {'skip_download': 'm3u8'},
}, {
# Geo-restricted to Australia
'url': 'https://10play.com.au/neighbours/episodes/season-42/episode-9107/tpv240902nzqyp',
'info_dict': {
'id': '9000000000091177',
@ -45,17 +45,38 @@ class TenPlayIE(InfoExtractor):
'season': 'Season 42',
'season_number': 42,
'series': 'Neighbours',
'thumbnail': r're:https://.*\.jpg',
'thumbnail': r're:https://.+/.+\.jpg',
'age_limit': 15,
'timestamp': 1725517860,
'upload_date': '20240905',
'uploader': 'Channel 10',
'uploader_id': '2199827728001',
},
'params': {
'skip_download': True,
'params': {'skip_download': 'm3u8'},
}, {
# Geo-restricted to Australia; upgrading the m3u8 quality fails and we need the fallback
'url': 'https://10play.com.au/tiny-chef-show/episodes/season-1/episode-2/tpv240228pofvt',
'info_dict': {
'id': '9000000000084116',
'ext': 'mp4',
'uploader': 'Channel 10',
'uploader_id': '2199827728001',
'duration': 1297,
'title': 'The Tiny Chef Show - S1 Ep. 2',
'alt_title': 'S1 Ep. 2 - Popcorn/banana',
'description': 'md5:d4758b52b5375dfaa67a78261dcb5763',
'age_limit': 0,
'series': 'The Tiny Chef Show',
'season_number': 1,
'episode_number': 2,
'timestamp': 1747957740,
'thumbnail': r're:https://.+/.+\.jpg',
'upload_date': '20250522',
'season': 'Season 1',
'episode': 'Episode 2',
},
'skip': 'Only available in Australia',
'params': {'skip_download': 'm3u8'},
'expected_warnings': ['Failed to download m3u8 information: HTTP Error 502'],
}, {
'url': 'https://10play.com.au/how-to-stay-married/web-extras/season-1/terrys-talks-ep-1-embracing-change/tpv190915ylupc',
'only_matching': True,
@ -86,7 +107,10 @@ def _real_extract(self, url):
if '10play-not-in-oz' in m3u8_url:
self.raise_geo_restricted(countries=['AU'])
# Attempt to get a higher quality stream
m3u8_url = m3u8_url.replace(',150,75,55,0000', ',300,150,75,55,0000')
formats = self._extract_m3u8_formats(
m3u8_url.replace(',150,75,55,0000', ',300,150,75,55,0000'),
content_id, 'mp4', fatal=False)
if not formats:
formats = self._extract_m3u8_formats(m3u8_url, content_id, 'mp4')
return {
@ -112,21 +136,22 @@ def _real_extract(self, url):
class TenPlaySeasonIE(InfoExtractor):
IE_NAME = '10play:season'
_VALID_URL = r'https?://(?:www\.)?10play\.com\.au/(?P<show>[^/?#]+)/episodes/(?P<season>[^/?#]+)/?(?:$|[?#])'
_TESTS = [{
'url': 'https://10play.com.au/masterchef/episodes/season-14',
'url': 'https://10play.com.au/masterchef/episodes/season-15',
'info_dict': {
'title': 'Season 14',
'id': 'MjMyOTIy',
'title': 'Season 15',
'id': 'MTQ2NjMxOQ==',
},
'playlist_mincount': 64,
'playlist_mincount': 50,
}, {
'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2022',
'url': 'https://10play.com.au/the-bold-and-the-beautiful-fast-tracked/episodes/season-2024',
'info_dict': {
'title': 'Season 2022',
'title': 'Season 2024',
'id': 'Mjc0OTIw',
},
'playlist_mincount': 256,
'playlist_mincount': 159,
}]
def _entries(self, load_more_url, display_id=None):

View File

@ -12,11 +12,13 @@
float_or_none,
int_or_none,
mimetype2ext,
parse_age_limit,
parse_qs,
traverse_obj,
unsmuggle_url,
update_url,
update_url_query,
url_or_none,
urlhandle_detect_ext,
xpath_with_ns,
)
@ -63,62 +65,53 @@ def _extract_theplatform_smil(self, smil_url, video_id, note='Downloading SMIL d
return formats, subtitles
def _download_theplatform_metadata(self, path, video_id):
info_url = f'http://link.theplatform.{self._TP_TLD}/s/{path}?format=preview'
return self._download_json(info_url, video_id)
def _download_theplatform_metadata(self, path, video_id, fatal=True):
return self._download_json(
f'https://link.theplatform.{self._TP_TLD}/s/{path}', video_id,
fatal=fatal, query={'format': 'preview'}) or {}
def _parse_theplatform_metadata(self, info):
subtitles = {}
captions = info.get('captions')
if isinstance(captions, list):
for caption in captions:
lang, src, mime = caption.get('lang', 'en'), caption.get('src'), caption.get('type')
subtitles.setdefault(lang, []).append({
'ext': mimetype2ext(mime),
'url': src,
@staticmethod
def _parse_theplatform_metadata(tp_metadata):
def site_specific_filter(*fields):
return lambda k, v: v and k.endswith(tuple(f'${f}' for f in fields))
info = traverse_obj(tp_metadata, {
'title': ('title', {str}),
'episode': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('defaultThumbnailUrl', {url_or_none}),
'duration': ('duration', {float_or_none(scale=1000)}),
'timestamp': ('pubDate', {float_or_none(scale=1000)}),
'uploader': ('billingCode', {str}),
'creators': ('author', {str}, filter, all, filter),
'categories': (
'categories', lambda _, v: v.get('label') in ['category', None],
'name', {str}, filter, all, filter),
'tags': ('keywords', {str}, filter, {lambda x: re.split(r'[;,]\s?', x)}, filter),
'age_limit': ('ratings', ..., 'rating', {parse_age_limit}, any),
'season_number': (site_specific_filter('seasonNumber'), {int_or_none}, any),
'episode_number': (site_specific_filter('episodeNumber', 'airOrder'), {int_or_none}, any),
'series': (site_specific_filter('show', 'seriesTitle', 'seriesShortTitle'), (None, ...), {str}, any),
'location': (site_specific_filter('region'), {str}, any),
'media_type': (site_specific_filter('programmingType', 'type'), {str}, any),
})
duration = info.get('duration')
tp_chapters = info.get('chapters', [])
chapters = []
if tp_chapters:
def _add_chapter(start_time, end_time):
start_time = float_or_none(start_time, 1000)
end_time = float_or_none(end_time, 1000)
if start_time is None or end_time is None:
return
chapters.append({
'start_time': start_time,
'end_time': end_time,
chapters = traverse_obj(tp_metadata, ('chapters', ..., {
'start_time': ('startTime', {float_or_none(scale=1000)}),
'end_time': ('endTime', {float_or_none(scale=1000)}),
}))
# Ignore pointless single chapters from short videos that span the entire video's duration
if len(chapters) > 1 or traverse_obj(chapters, (0, 'end_time')):
info['chapters'] = chapters
info['subtitles'] = {}
for caption in traverse_obj(tp_metadata, ('captions', lambda _, v: url_or_none(v['src']))):
info['subtitles'].setdefault(caption.get('lang') or 'en', []).append({
'url': caption['src'],
'ext': mimetype2ext(caption.get('type')),
})
for chapter in tp_chapters[:-1]:
_add_chapter(chapter.get('startTime'), chapter.get('endTime'))
_add_chapter(tp_chapters[-1].get('startTime'), tp_chapters[-1].get('endTime') or duration)
def extract_site_specific_field(field):
# A number of sites have custom-prefixed keys, e.g. 'cbc$seasonNumber'
return traverse_obj(info, lambda k, v: v and k.endswith(f'${field}'), get_all=False)
return {
'title': info['title'],
'subtitles': subtitles,
'description': info['description'],
'thumbnail': info['defaultThumbnailUrl'],
'duration': float_or_none(duration, 1000),
'timestamp': int_or_none(info.get('pubDate'), 1000) or None,
'uploader': info.get('billingCode'),
'chapters': chapters,
'creator': traverse_obj(info, ('author', {str})) or None,
'categories': traverse_obj(info, (
'categories', lambda _, v: v.get('label') in ('category', None), 'name', {str})) or None,
'tags': traverse_obj(info, ('keywords', {lambda x: re.split(r'[;,]\s?', x) if x else None})),
'location': extract_site_specific_field('region'),
'series': extract_site_specific_field('show') or extract_site_specific_field('seriesTitle'),
'season_number': int_or_none(extract_site_specific_field('seasonNumber')),
'episode_number': int_or_none(extract_site_specific_field('episodeNumber')),
'media_type': extract_site_specific_field('programmingType') or extract_site_specific_field('type'),
}
return info
def _extract_theplatform_metadata(self, path, video_id):
info = self._download_theplatform_metadata(path, video_id)

View File

@ -20,6 +20,7 @@ class TruTVIE(TurnerBaseIE):
'skip_download': True,
},
}
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiJhYzQyOTkwMi0xMDYzLTQyNTQtYWJlYS1iZTY2ODM4MTVmZGIiLCJuYmYiOjE1MzcxOTA4NjgsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNTM3MTkwODY4fQ.ewXl5LDMDvvx3nDXV4jCdSwUq_sOluKoOVsIjznAo6Zo4zrGe9rjlZ9DOmQKW66g6VRMexJsJ5vM1EkY8TC5-YcQw_BclK1FPGO1rH3Wf7tX_l0b1BVbSJQKIj9UgqDp_QbGcBXz24kN4So3U22mhs6di9PYyyfG68ccKL2iRprcVKWCslIHwUF-T7FaEqb0K57auilxeW1PONG2m-lIAcZ62DUwqXDWvw0CRoWI08aVVqkkhnXaSsQfLs5Ph1Pfh9Oq3g_epUm9Ss45mq6XM7gbOb5omTcKLADRKK-PJVB_JXnZnlsXbG0ttKE1cTKJ738qu7j4aipYTf-W0nKF5Q'
def _real_extract(self, url):
series_slug, clip_slug, video_id = self._match_valid_url(url).groups()
@ -39,7 +40,7 @@ def _real_extract(self, url):
title = video_data['title'].strip()
info = self._extract_ngtv_info(
media_id, {}, {
media_id, {}, self._SOFTWARE_STATEMENT, {
'url': url,
'site_name': 'truTV',
'auth_required': video_data.get('isAuthRequired'),

View File

@ -22,7 +22,7 @@ class TurnerBaseIE(AdobePassIE):
def _extract_timestamp(self, video_data):
return int_or_none(xpath_attr(video_data, 'dateCreated', 'uts'))
def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data, custom_tokenizer_query=None):
def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data, software_statement, custom_tokenizer_query=None):
secure_path = self._search_regex(r'https?://[^/]+(.+/)', video_url, 'secure path') + '*'
token = self._AKAMAI_SPE_TOKEN_CACHE.get(secure_path)
if not token:
@ -34,7 +34,8 @@ def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data, c
else:
query['videoId'] = content_id
if ap_data.get('auth_required'):
query['accessToken'] = self._extract_mvpd_auth(ap_data['url'], content_id, ap_data['site_name'], ap_data['site_name'])
query['accessToken'] = self._extract_mvpd_auth(
ap_data['url'], content_id, ap_data['site_name'], ap_data['site_name'], software_statement)
auth = self._download_xml(
tokenizer_src, content_id, query=query)
error_msg = xpath_text(auth, 'error/msg')
@ -46,7 +47,7 @@ def _add_akamai_spe_token(self, tokenizer_src, video_url, content_id, ap_data, c
self._AKAMAI_SPE_TOKEN_CACHE[secure_path] = token
return video_url + '?hdnea=' + token
def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}, fatal=False):
def _extract_cvp_info(self, data_src, video_id, software_statement, path_data={}, ap_data={}, fatal=False):
video_data = self._download_xml(
data_src, video_id,
transform_source=lambda s: fix_xml_ampersands(s).strip(),
@ -101,7 +102,7 @@ def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}, fatal=
video_url = self._add_akamai_spe_token(
secure_path_data['tokenizer_src'],
secure_path_data['media_src'] + video_url,
content_id, ap_data)
content_id, ap_data, software_statement)
elif not re.match('https?://', video_url):
base_path_data = path_data.get(ext, path_data.get('default', {}))
media_src = base_path_data.get('media_src')
@ -215,10 +216,12 @@ def _extract_cvp_info(self, data_src, video_id, path_data={}, ap_data={}, fatal=
'is_live': is_live,
}
def _extract_ngtv_info(self, media_id, tokenizer_query, ap_data=None):
def _extract_ngtv_info(self, media_id, tokenizer_query, software_statement, ap_data=None):
if not isinstance(ap_data, dict):
ap_data = {}
is_live = ap_data.get('is_live')
streams_data = self._download_json(
f'http://medium.ngtv.io/media/{media_id}/tv',
f'https://medium.ngtv.io/media/{media_id}/tv',
media_id)['media']['tv']
duration = None
chapters = []
@ -230,8 +233,8 @@ def _extract_ngtv_info(self, media_id, tokenizer_query, ap_data=None):
continue
if stream_data.get('playlistProtection') == 'spe':
m3u8_url = self._add_akamai_spe_token(
'http://token.ngtv.io/token/token_spe',
m3u8_url, media_id, ap_data or {}, tokenizer_query)
'https://token.ngtv.io/token/token_spe',
m3u8_url, media_id, ap_data, software_statement, tokenizer_query)
formats.extend(self._extract_m3u8_formats(
m3u8_url, media_id, 'mp4', m3u8_id='hls', live=is_live, fatal=False))

View File

@ -1,98 +1,53 @@
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_filesize,
parse_iso8601,
)
from ..utils import clean_html
from ..utils.traversal import find_element, traverse_obj
class UMGDeIE(InfoExtractor):
_WORKING = False
IE_NAME = 'umg:de'
IE_DESC = 'Universal Music Deutschland'
_VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/]+/videos/[^/?#]+-(?P<id>\d+)'
_TEST = {
_VALID_URL = r'https?://(?:www\.)?universal-music\.de/[^/?#]+/videos/(?P<slug>[^/?#]+-(?P<id>\d+))'
_TESTS = [{
'url': 'https://www.universal-music.de/sido/videos/jedes-wort-ist-gold-wert-457803',
'md5': 'ebd90f48c80dcc82f77251eb1902634f',
'info_dict': {
'id': '457803',
'ext': 'mp4',
'title': 'Jedes Wort ist Gold wert',
'artists': ['Sido'],
'description': 'md5:df2dbffcff1a74e0a7c9bef4b497aeec',
'display_id': 'jedes-wort-ist-gold-wert-457803',
'duration': 210.0,
'thumbnail': r're:https?://images\.universal-music\.de/img/assets/.+\.jpg',
'timestamp': 1513591800,
'upload_date': '20171218',
'view_count': int,
},
}
}, {
'url': 'https://www.universal-music.de/alexander-eder/videos/der-doktor-hat-gesagt-609533',
'info_dict': {
'id': '609533',
'ext': 'mp4',
'title': 'Der Doktor hat gesagt',
'artists': ['Alexander Eder'],
'display_id': 'der-doktor-hat-gesagt-609533',
'duration': 146.0,
'thumbnail': r're:https?://images\.universal-music\.de/img/assets/.+\.jpg',
'timestamp': 1742982100,
'upload_date': '20250326',
},
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
'https://graphql.universal-music.de/',
video_id, query={
'query': '''{
universalMusic(channel:16) {
video(id:%s) {
headline
formats {
formatId
url
type
width
height
mimeType
fileSize
}
duration
createdDate
}
}
}''' % video_id})['data']['universalMusic']['video'] # noqa: UP031
title = video_data['headline']
hls_url_template = 'http://mediadelivery.universal-music-services.de/vod/mp4:autofill/storage/' + '/'.join(list(video_id)) + '/content/%s/file/playlist.m3u8'
thumbnails = []
formats = []
def add_m3u8_format(format_id):
formats.extend(self._extract_m3u8_formats(
hls_url_template % format_id, video_id, 'mp4',
'm3u8_native', m3u8_id='hls', fatal=False))
for f in video_data.get('formats', []):
f_url = f.get('url')
mime_type = f.get('mimeType')
if not f_url or mime_type == 'application/mxf':
continue
fmt = {
'url': f_url,
'width': int_or_none(f.get('width')),
'height': int_or_none(f.get('height')),
'filesize': parse_filesize(f.get('fileSize')),
}
f_type = f.get('type')
if f_type == 'Image':
thumbnails.append(fmt)
elif f_type == 'Video':
format_id = f.get('formatId')
if format_id:
fmt['format_id'] = format_id
if mime_type == 'video/mp4':
add_m3u8_format(format_id)
urlh = self._request_webpage(f_url, video_id, fatal=False)
if urlh:
first_byte = urlh.read(1)
if first_byte not in (b'F', b'\x00'):
continue
formats.append(fmt)
if not formats:
for format_id in (867, 836, 940):
add_m3u8_format(format_id)
display_id, video_id = self._match_valid_url(url).group('slug', 'id')
webpage = self._download_webpage(url, display_id)
return {
**self._search_json_ld(webpage, display_id),
'id': video_id,
'title': title,
'duration': int_or_none(video_data.get('duration')),
'timestamp': parse_iso8601(video_data.get('createdDate'), ' '),
'thumbnails': thumbnails,
'formats': formats,
'artists': traverse_obj(self._html_search_meta('umg-artist-screenname', webpage), (filter, all)),
# The JSON LD description duplicates the title
'description': traverse_obj(webpage, ({find_element(cls='_3Y0Lj')}, {clean_html})),
'display_id': display_id,
'formats': self._extract_m3u8_formats(
'https://hls.universal-music.de/get', display_id, 'mp4', query={'id': video_id}),
}

View File

@ -32,6 +32,7 @@ def _call_api(self, resource, resource_key, resource_id, locale, fields, args=''
class ViceIE(ViceBaseIE, AdobePassIE):
_WORKING = False
IE_NAME = 'vice'
_VALID_URL = r'https?://(?:(?:video|vms)\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P<locale>[^/]+)/(?:video/[^/]+|embed)/(?P<id>[\da-f]{24})'
_EMBED_REGEX = [r'<iframe\b[^>]+\bsrc=["\'](?P<url>(?:https?:)?//video\.vice\.com/[^/]+/embed/[\da-f]{24})']
@ -99,6 +100,7 @@ class ViceIE(ViceBaseIE, AdobePassIE):
'url': 'https://www.viceland.com/en_us/video/thursday-march-1-2018/5a8f2d7ff1cdb332dd446ec1',
'only_matching': True,
}]
_SOFTWARE_STATEMENT = 'eyJhbGciOiJSUzI1NiJ9.eyJzdWIiOiIwMTVjODBlZC04ZDcxLTQ4ZGEtOTZkZi00NzU5NjIwNzJlYTQiLCJuYmYiOjE2NjgwMTM0ODQsImlzcyI6ImF1dGguYWRvYmUuY29tIiwiaWF0IjoxNjY4MDEzNDg0fQ.CjhUnTrlh-bmYnEFHyC2Y4it5Y_Zfza1x66O4-ki5gBR7JT6aUunYI_YflXomQPACriMpObkITFz4grVaDwdd8Xp9hrQ2R0SwRBdaklkdy1_j68RqSP5PnexJIa0q_ThtOwfRBd5uGcb33nMJ9Qs92W4kVXuca0Ta-i7SJyWgXUaPDlRDdgyCL3hKj5wuM7qUIwrd9A5CMm-j3dMIBCDgw7X6TwRK65eUQe6gTWqcvL2yONHHTpmIfeOTUxGwwKFr29COOTBowm0VJ6HE08xjXCShP08Neusu-JsgkjzhkEbiDE2531EKgfAki_7WCd2JUZVsAsCusv4a1maokk6NA'
def _real_extract(self, url):
locale, video_id = self._match_valid_url(url).groups()
@ -116,7 +118,7 @@ def _real_extract(self, url):
resource = self._get_mvpd_resource(
'VICELAND', title, video_id, rating)
query['tvetoken'] = self._extract_mvpd_auth(
url, video_id, 'VICELAND', resource)
url, video_id, 'VICELAND', resource, self._SOFTWARE_STATEMENT)
# signature generation algorithm is reverse engineered from signatureGenerator in
# webpack:///../shared/~/vice-player/dist/js/vice-player.js in
@ -181,6 +183,7 @@ def _real_extract(self, url):
class ViceShowIE(ViceBaseIE):
_WORKING = False
IE_NAME = 'vice:show'
_VALID_URL = r'https?://(?:video\.vice|(?:www\.)?vice(?:land|tv))\.com/(?P<locale>[^/]+)/show/(?P<id>[^/?#&]+)'
_PAGE_SIZE = 25
@ -221,6 +224,7 @@ def _real_extract(self, url):
class ViceArticleIE(ViceBaseIE):
_WORKING = False
IE_NAME = 'vice:article'
_VALID_URL = r'https?://(?:www\.)?vice\.com/(?P<locale>[^/]+)/article/(?:[0-9a-z]{6}/)?(?P<id>[^?#]+)'

View File

@ -236,7 +236,7 @@ def _parse_config(self, config, video_id):
for tt in (request.get('text_tracks') or []):
subtitles.setdefault(tt['lang'], []).append({
'ext': 'vtt',
'url': urljoin('https://vimeo.com', tt['url']),
'url': urljoin('https://player.vimeo.com/', tt['url']),
})
thumbnails = []

View File

@ -548,21 +548,21 @@ def _real_extract(self, url):
'formats': formats,
'subtitles': subtitles,
**traverse_obj(mv_data, {
'title': ('title', {unescapeHTML}),
'title': ('title', {str}, {unescapeHTML}),
'description': ('desc', {clean_html}, filter),
'duration': ('duration', {int_or_none}),
'like_count': ('likes', {int_or_none}),
'comment_count': ('commcount', {int_or_none}),
}),
**traverse_obj(data, {
'title': ('md_title', {unescapeHTML}),
'title': ('md_title', {str}, {unescapeHTML}),
'description': ('description', {clean_html}, filter),
'thumbnail': ('jpg', {url_or_none}),
'uploader': ('md_author', {unescapeHTML}),
'uploader': ('md_author', {str}, {unescapeHTML}),
'uploader_id': (('author_id', 'authorId'), {str_or_none}, any),
'duration': ('duration', {int_or_none}),
'chapters': ('time_codes', lambda _, v: isinstance(v['time'], int), {
'title': ('text', {unescapeHTML}),
'title': ('text', {str}, {unescapeHTML}),
'start_time': 'time',
}),
}),

View File

@ -1,4 +1,5 @@
import base64
import functools
import hashlib
import hmac
import itertools
@ -17,99 +18,227 @@
UserNotLive,
float_or_none,
int_or_none,
join_nonempty,
jwt_decode_hs256,
str_or_none,
traverse_obj,
try_call,
update_url_query,
url_or_none,
)
from ..utils.traversal import require, traverse_obj
class WeverseBaseIE(InfoExtractor):
_NETRC_MACHINE = 'weverse'
_ACCOUNT_API_BASE = 'https://accountapi.weverse.io/web/api'
_ACCOUNT_API_BASE = 'https://accountapi.weverse.io'
_CLIENT_PLATFORM = 'WEB'
_SIGNING_KEY = b'1b9cb6378d959b45714bec49971ade22e6e24e42'
_ACCESS_TOKEN_KEY = 'we2_access_token'
_REFRESH_TOKEN_KEY = 'we2_refresh_token'
_DEVICE_ID_KEY = 'we2_device_id'
_API_HEADERS = {
'Accept': 'application/json',
'Origin': 'https://weverse.io',
'Referer': 'https://weverse.io/',
'WEV-device-Id': str(uuid.uuid4()),
}
_LOGIN_HINT_TMPL = (
'You can log in using your refresh token with --username "{}" --password "REFRESH_TOKEN" '
'(replace REFRESH_TOKEN with the actual value of the "{}" cookie found in your web browser). '
'You can add an optional username suffix, e.g. --username "{}" , '
'if you need to manage multiple accounts. ')
_LOGIN_ERRORS_MAP = {
'login_required': 'This content is only available for logged-in users. ',
'invalid_username': '"{}" is not valid login username for this extractor. ',
'invalid_password': (
'Your password is not a valid refresh token. Make sure that '
'you are passing the refresh token, and NOT the access token. '),
'no_refresh_token': (
'Your access token has expired and there is no refresh token available. '
'Refresh your session/cookies in the web browser and try again. '),
'expired_refresh_token': (
'Your refresh token has expired. Log in to the site again using '
'your web browser to get a new refresh token or export fresh cookies. '),
}
_OAUTH_PREFIX = 'oauth'
_oauth_tokens = {}
_device_id = None
@property
def _oauth_headers(self):
return {
**self._API_HEADERS,
'X-ACC-APP-SECRET': '5419526f1c624b38b10787e5c10b2a7a',
'X-ACC-SERVICE-ID': 'weverse',
'X-ACC-TRACE-ID': str(uuid.uuid4()),
}
def _perform_login(self, username, password):
if self._API_HEADERS.get('Authorization'):
return
@functools.cached_property
def _oauth_cache_key(self):
username = self._get_login_info()[0]
if not username:
return 'cookies'
return join_nonempty(self._OAUTH_PREFIX, username.partition('+')[2])
headers = {
'x-acc-app-secret': '5419526f1c624b38b10787e5c10b2a7a',
'x-acc-app-version': '3.3.6',
'x-acc-language': 'en',
'x-acc-service-id': 'weverse',
'x-acc-trace-id': str(uuid.uuid4()),
'x-clog-user-device-id': str(uuid.uuid4()),
}
valid_username = traverse_obj(self._download_json(
f'{self._ACCOUNT_API_BASE}/v2/signup/email/status', None, note='Checking username',
query={'email': username}, headers=headers, expected_status=(400, 404)), 'hasPassword')
if not valid_username:
raise ExtractorError('Invalid username provided', expected=True)
@property
def _is_logged_in(self):
return bool(self._oauth_tokens.get(self._ACCESS_TOKEN_KEY))
def _access_token_is_valid(self):
response = self._download_json(
f'{self._ACCOUNT_API_BASE}/api/v1/token/validate', None,
'Validating access token', 'Unable to valid access token',
expected_status=401, headers={
**self._oauth_headers,
'Authorization': f'Bearer {self._oauth_tokens[self._ACCESS_TOKEN_KEY]}',
})
return traverse_obj(response, ('expiresIn', {int}), default=0) > 60
def _token_is_expired(self, key):
is_expired = jwt_decode_hs256(self._oauth_tokens[key])['exp'] - time.time() < 3600
if key == self._REFRESH_TOKEN_KEY or not is_expired:
return is_expired
return not self._access_token_is_valid()
def _refresh_access_token(self):
if not self._oauth_tokens.get(self._REFRESH_TOKEN_KEY):
self._report_login_error('no_refresh_token')
if self._token_is_expired(self._REFRESH_TOKEN_KEY):
self._report_login_error('expired_refresh_token')
headers = {'Content-Type': 'application/json'}
if self._is_logged_in:
headers['Authorization'] = f'Bearer {self._oauth_tokens[self._ACCESS_TOKEN_KEY]}'
headers['content-type'] = 'application/json'
try:
auth = self._download_json(
f'{self._ACCOUNT_API_BASE}/v3/auth/token/by-credentials', None, data=json.dumps({
'email': username,
'otpSessionId': 'BY_PASS',
'password': password,
}, separators=(',', ':')).encode(), headers=headers, note='Logging in')
response = self._download_json(
f'{self._ACCOUNT_API_BASE}/api/v1/token/refresh', None,
'Refreshing access token', 'Unable to refresh access token',
headers={**self._oauth_headers, **headers},
data=json.dumps({
'refreshToken': self._oauth_tokens[self._REFRESH_TOKEN_KEY],
}, separators=(',', ':')).encode())
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
raise ExtractorError('Invalid password provided', expected=True)
self._oauth_tokens.clear()
if self._oauth_cache_key == 'cookies':
self.cookiejar.clear(domain='.weverse.io', path='/', name=self._ACCESS_TOKEN_KEY)
self.cookiejar.clear(domain='.weverse.io', path='/', name=self._REFRESH_TOKEN_KEY)
else:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, self._oauth_tokens)
self._report_login_error('expired_refresh_token')
raise
WeverseBaseIE._API_HEADERS['Authorization'] = f'Bearer {auth["accessToken"]}'
self._oauth_tokens.update(traverse_obj(response, {
self._ACCESS_TOKEN_KEY: ('accessToken', {str}, {require('access token')}),
self._REFRESH_TOKEN_KEY: ('refreshToken', {str}, {require('refresh token')}),
}))
def _real_initialize(self):
if self._API_HEADERS.get('Authorization'):
if self._oauth_cache_key == 'cookies':
self._set_cookie('.weverse.io', self._ACCESS_TOKEN_KEY, self._oauth_tokens[self._ACCESS_TOKEN_KEY])
self._set_cookie('.weverse.io', self._REFRESH_TOKEN_KEY, self._oauth_tokens[self._REFRESH_TOKEN_KEY])
else:
self.cache.store(self._NETRC_MACHINE, self._oauth_cache_key, self._oauth_tokens)
def _get_authorization_header(self):
if not self._is_logged_in:
return {}
if self._token_is_expired(self._ACCESS_TOKEN_KEY):
self._refresh_access_token()
return {'Authorization': f'Bearer {self._oauth_tokens[self._ACCESS_TOKEN_KEY]}'}
def _report_login_error(self, error_id):
error_msg = self._LOGIN_ERRORS_MAP[error_id]
username = self._get_login_info()[0]
if error_id == 'invalid_username':
error_msg = error_msg.format(username)
username = f'{self._OAUTH_PREFIX}+{username}'
elif not username:
username = f'{self._OAUTH_PREFIX}+USERNAME'
raise ExtractorError(join_nonempty(
error_msg, self._LOGIN_HINT_TMPL.format(self._OAUTH_PREFIX, self._REFRESH_TOKEN_KEY, username),
'Or else you can u', self._login_hint(method='session_cookies')[1:], delim=''), expected=True)
def _perform_login(self, username, password):
if self._is_logged_in:
return
token = try_call(lambda: self._get_cookies('https://weverse.io/')['we2_access_token'].value)
if token:
WeverseBaseIE._API_HEADERS['Authorization'] = f'Bearer {token}'
if username.partition('+')[0] != self._OAUTH_PREFIX:
self._report_login_error('invalid_username')
self._oauth_tokens.update(self.cache.load(self._NETRC_MACHINE, self._oauth_cache_key, default={}))
if self._is_logged_in and self._access_token_is_valid():
return
rt_key = self._REFRESH_TOKEN_KEY
if not self._oauth_tokens.get(rt_key) or self._token_is_expired(rt_key):
if try_call(lambda: jwt_decode_hs256(password)['scope']) != 'refresh':
self._report_login_error('invalid_password')
self._oauth_tokens[rt_key] = password
self._refresh_access_token()
def _real_initialize(self):
cookies = self._get_cookies('https://weverse.io/')
if not self._device_id:
self._device_id = traverse_obj(cookies, (self._DEVICE_ID_KEY, 'value')) or str(uuid.uuid4())
if self._is_logged_in:
return
self._oauth_tokens.update(traverse_obj(cookies, {
self._ACCESS_TOKEN_KEY: (self._ACCESS_TOKEN_KEY, 'value'),
self._REFRESH_TOKEN_KEY: (self._REFRESH_TOKEN_KEY, 'value'),
}))
if self._is_logged_in and not self._access_token_is_valid():
self._refresh_access_token()
def _call_api(self, ep, video_id, data=None, note='Downloading API JSON'):
# Ref: https://ssl.pstatic.net/static/wevweb/2_3_2_11101725/public/static/js/2488.a09b41ff.chunk.js
# From https://ssl.pstatic.net/static/wevweb/2_3_2_11101725/public/static/js/main.e206f7c1.js:
key = b'1b9cb6378d959b45714bec49971ade22e6e24e42'
api_path = update_url_query(ep, {
# 'gcc': 'US',
'appId': 'be4d79eb8fc7bd008ee82c8ec4ff6fd4',
'language': 'en',
'os': 'WEB',
'platform': 'WEB',
'os': self._CLIENT_PLATFORM,
'platform': self._CLIENT_PLATFORM,
'wpf': 'pc',
})
for is_retry in (False, True):
wmsgpad = int(time.time() * 1000)
wmd = base64.b64encode(hmac.HMAC(
key, f'{api_path[:255]}{wmsgpad}'.encode(), digestmod=hashlib.sha1).digest()).decode()
headers = {'Content-Type': 'application/json'} if data else {}
self._SIGNING_KEY, f'{api_path[:255]}{wmsgpad}'.encode(),
digestmod=hashlib.sha1).digest()).decode()
try:
return self._download_json(
f'https://global.apis.naver.com/weverse/wevweb{api_path}', video_id, note=note,
data=data, headers={**self._API_HEADERS, **headers}, query={
data=data, headers={
**self._API_HEADERS,
**self._get_authorization_header(),
**({'Content-Type': 'application/json'} if data else {}),
'WEV-device-Id': self._device_id,
}, query={
'wmsgpad': wmsgpad,
'wmd': wmd,
})
except ExtractorError as e:
if isinstance(e.cause, HTTPError) and e.cause.status == 401:
self.raise_login_required(
'Session token has expired. Log in again or refresh cookies in browser')
elif isinstance(e.cause, HTTPError) and e.cause.status == 403:
if 'Authorization' in self._API_HEADERS:
raise ExtractorError('Your account does not have access to this content', expected=True)
self.raise_login_required()
if is_retry or not isinstance(e.cause, HTTPError):
raise
elif self._is_logged_in and e.cause.status == 401:
self._refresh_access_token()
continue
elif e.cause.status == 403:
if self._is_logged_in:
raise ExtractorError(
'Your account does not have access to this content', expected=True)
self._report_login_error('login_required')
raise
def _call_post_api(self, video_id):
path = '' if 'Authorization' in self._API_HEADERS else '/preview'
path = '' if self._is_logged_in else '/preview'
return self._call_api(f'/post/v1.0/post-{video_id}{path}?fieldSet=postV1', video_id)
def _get_community_id(self, channel):

View File

@ -63,6 +63,7 @@ class _PoTokenContext(enum.Enum):
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
'SUPPORTS_COOKIES': True,
'PLAYER_PARAMS': '8AEB',
},
'web_embedded': {
'INNERTUBE_CONTEXT': {
@ -174,6 +175,16 @@ class _PoTokenContext(enum.Enum):
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
'SUPPORTS_COOKIES': True,
'PLAYER_PARAMS': '8AEB',
},
'tv_simply': {
'INNERTUBE_CONTEXT': {
'client': {
'clientName': 'TVHTML5_SIMPLY',
'clientVersion': '1.0',
},
},
'INNERTUBE_CONTEXT_CLIENT_NAME': 75,
},
# This client now requires sign-in for every video
# It was previously an age-gate workaround for videos that were `playable_in_embed`

View File

@ -250,7 +250,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
'400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
'401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
}
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
_SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'srt', 'vtt')
_DEFAULT_CLIENTS = ('tv', 'ios', 'web')
_DEFAULT_AUTHED_CLIENTS = ('tv', 'web')
@ -2228,21 +2228,21 @@ def _decrypt_nsig(self, s, video_id, player_url):
def _extract_n_function_name(self, jscode, player_url=None):
varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
if debug_str := traverse_obj(global_list, (lambda _, v: v.endswith('_w8_'), any)):
funcname = self._search_regex(
r'''(?xs)
[;\n](?:
(?P<f>function\s+)|
(?:var\s+)?
)(?P<funcname>[a-zA-Z0-9_$]+)\s*(?(f)|=\s*function\s*)
\((?P<argname>[a-zA-Z0-9_$]+)\)\s*\{
(?:(?!\}[;\n]).)+
\}\s*catch\(\s*[a-zA-Z0-9_$]+\s*\)\s*
\{\s*return\s+%s\[%d\]\s*\+\s*(?P=argname)\s*\}\s*return\s+[^}]+\}[;\n]
''' % (re.escape(varname), global_list.index(debug_str)),
jscode, 'nsig function name', group='funcname', default=None)
if funcname:
return funcname
if debug_str := traverse_obj(global_list, (lambda _, v: v.endswith('-_w8_'), any)):
pattern = r'''(?x)
\{\s*return\s+%s\[%d\]\s*\+\s*(?P<argname>[a-zA-Z0-9_$]+)\s*\}
''' % (re.escape(varname), global_list.index(debug_str))
if match := re.search(pattern, jscode):
pattern = r'''(?x)
\{\s*\)%s\(\s*
(?:
(?P<funcname_a>[a-zA-Z0-9_$]+)\s*noitcnuf\s*
|noitcnuf\s*=\s*(?P<funcname_b>[a-zA-Z0-9_$]+)(?:\s+rav)?
)[;\n]
''' % re.escape(match.group('argname')[::-1])
if match := re.search(pattern, jscode[match.start()::-1]):
a, b = match.group('funcname_a', 'funcname_b')
return (a or b)[::-1]
self.write_debug(join_nonempty(
'Initial search was unable to find nsig function name',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
@ -2289,8 +2289,8 @@ def _extract_n_function_name(self, jscode, player_url=None):
rf'var {re.escape(funcname)}\s*=\s*(\[.+?\])\s*[,;]', jscode,
f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
def _extract_player_js_global_var(self, jscode, player_url):
"""Returns tuple of strings: variable assignment code, variable name, variable value code"""
def _interpret_player_js_global_var(self, jscode, player_url):
"""Returns tuple of: variable name string, variable value list"""
extract_global_var = self._cached(self._search_regex, 'js global array', player_url)
varcode, varname, varvalue = extract_global_var(
r'''(?x)
@ -2308,27 +2308,23 @@ def _extract_player_js_global_var(self, jscode, player_url):
self.write_debug(join_nonempty(
'No global array variable found in player JS',
player_url and f' player = {player_url}', delim='\n'), only_once=True)
return varcode, varname, varvalue
return None, None
def _interpret_player_js_global_var(self, jscode, player_url):
"""Returns tuple of: variable name string, variable value list"""
_, varname, array_code = self._extract_player_js_global_var(jscode, player_url)
jsi = JSInterpreter(array_code)
jsi = JSInterpreter(varcode)
interpret_global_var = self._cached(jsi.interpret_expression, 'js global list', player_url)
return varname, interpret_global_var(array_code, {}, allow_recursion=10)
return varname, interpret_global_var(varvalue, {}, allow_recursion=10)
def _fixup_n_function_code(self, argnames, nsig_code, jscode, player_url):
varcode, varname, _ = self._extract_player_js_global_var(jscode, player_url)
if varcode and varname:
nsig_code = varcode + '; ' + nsig_code
_, global_list = self._interpret_player_js_global_var(jscode, player_url)
varname, global_list = self._interpret_player_js_global_var(jscode, player_url)
if varname and global_list:
nsig_code = f'var {varname}={json.dumps(global_list)}; {nsig_code}'
else:
varname = 'dlp_wins'
global_list = []
undefined_idx = global_list.index('undefined') if 'undefined' in global_list else r'\d+'
fixed_code = re.sub(
rf'''(?x)
fr'''(?x)
;\s*if\s*\(\s*typeof\s+[a-zA-Z0-9_$]+\s*===?\s*(?:
(["\'])undefined\1|
{re.escape(varname)}\[{undefined_idx}\]
@ -2402,6 +2398,11 @@ def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=F
return sts
def _mark_watched(self, video_id, player_responses):
# cpn generation algorithm is reverse engineered from base.js.
# In fact it works even with dummy cpn.
CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(16))
for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
label = 'fully ' if is_full else ''
url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
@ -2412,11 +2413,6 @@ def _mark_watched(self, video_id, player_responses):
parsed_url = urllib.parse.urlparse(url)
qs = urllib.parse.parse_qs(parsed_url.query)
# cpn generation algorithm is reverse engineered from base.js.
# In fact it works even with dummy cpn.
CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(16))
# # more consistent results setting it to right before the end
video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
@ -3402,8 +3398,15 @@ def build_fragments(f):
self._decrypt_signature(encrypted_sig, video_id, player_url),
)
except ExtractorError as e:
self.report_warning('Signature extraction failed: Some formats may be missing',
self.report_warning(
f'Signature extraction failed: Some formats may be missing\n'
f' player = {player_url}\n'
f' {bug_reports_message(before="")}',
video_id=video_id, only_once=True)
self.write_debug(
f'{video_id}: Signature extraction failure info:\n'
f' encrypted sig = {encrypted_sig}\n'
f' player = {player_url}')
self.write_debug(e, only_once=True)
continue
@ -3549,6 +3552,11 @@ def process_manifest_format(f, proto, client_name, itag, po_token):
f['format_note'] = join_nonempty(f.get('format_note'), 'MISSING POT', delim=' ')
f['source_preference'] -= 20
# XXX: Check if IOS HLS formats are affected by player PO token enforcement; temporary
# See https://github.com/yt-dlp/yt-dlp/issues/13511
if proto == 'hls' and client_name == 'ios':
f['__needs_testing'] = True
itags[itag].add(key)
if itag and all_formats:
@ -4277,6 +4285,7 @@ def process_language(container, base_url, lang_code, sub_name, client_name, quer
if upload_date and live_status not in ('is_live', 'post_live', 'is_upcoming'):
# Newly uploaded videos' HLS formats are potentially problematic and need to be checked
# XXX: This is redundant for as long as we are already checking all IOS HLS formats
upload_datetime = datetime_from_str(upload_date).replace(tzinfo=dt.timezone.utc)
if upload_datetime >= datetime_from_str('today-2days'):
for fmt in info['formats']:

View File

@ -20,6 +20,7 @@
'WEB_EMBEDDED_PLAYER',
'WEB_CREATOR',
'WEB_REMIX',
'TVHTML5_SIMPLY',
'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
)

View File

@ -6,6 +6,7 @@
from .common import InfoExtractor
from ..utils import (
ExtractorError,
ISO639Utils,
determine_ext,
filter_dict,
float_or_none,
@ -118,10 +119,7 @@ def _extract_ptmd(self, ptmd_urls, video_id, api_token=None, aspect_ratio=None):
if ext == 'm3u8':
fmts = self._extract_m3u8_formats(
format_url, video_id, 'mp4', m3u8_id='hls', fatal=False)
elif ext == 'mpd':
fmts = self._extract_mpd_formats(
format_url, video_id, mpd_id='dash', fatal=False)
else:
elif ext in ('mp4', 'webm'):
height = int_or_none(quality.get('highestVerticalResolution'))
width = round(aspect_ratio * height) if aspect_ratio and height else None
fmts = [{
@ -132,16 +130,31 @@ def _extract_ptmd(self, ptmd_urls, video_id, api_token=None, aspect_ratio=None):
'format_id': join_nonempty('http', stream.get('type')),
'tbr': int_or_none(self._search_regex(r'_(\d+)k_', format_url, 'tbr', default=None)),
}]
else:
self.report_warning(f'Skipping unsupported extension "{ext}"', video_id=video_id)
fmts = []
f_class = variant.get('class')
for f in fmts:
f_lang = ISO639Utils.short2long(
(f.get('language') or variant.get('language') or '').lower())
is_audio_only = f.get('vcodec') == 'none'
formats.append({
**f,
'format_id': join_nonempty(f.get('format_id'), is_dgs and 'dgs'),
'format_id': join_nonempty(f['format_id'], is_dgs and 'dgs'),
'format_note': join_nonempty(
f_class, is_dgs and 'German Sign Language', f.get('format_note'), delim=', '),
'language': variant.get('language') or f.get('language'),
not is_audio_only and f_class,
is_dgs and 'German Sign Language',
f.get('format_note'), delim=', '),
'preference': -2 if is_dgs else -1,
'language_preference': 10 if f_class == 'main' else -10 if f_class == 'ad' else -1,
'language': f_lang,
'language_preference': (
-10 if ((is_audio_only and f.get('format_note') == 'Audiodeskription')
or (not is_audio_only and f_class == 'ad'))
else 10 if f_lang == 'deu' and f_class == 'main'
else 5 if f_lang == 'deu'
else 1 if f_class == 'main'
else -1),
})
return {
@ -333,12 +346,13 @@ class ZDFIE(ZDFBaseIE):
'title': 'Dobrindt schließt Steuererhöhungen aus',
'description': 'md5:9a117646d7b8df6bc902eb543a9c9023',
'duration': 325,
'thumbnail': 'https://www.zdf.de/assets/dobrindt-csu-berlin-direkt-100~1920x1080?cb=1743357653736',
'thumbnail': 'https://www.zdfheute.de/assets/dobrindt-csu-berlin-direkt-100~1920x1080?cb=1743357653736',
'timestamp': 1743374520,
'upload_date': '20250330',
'_old_archive_ids': ['zdf 250330_clip_2_bdi'],
},
}, {
# FUNK video (hosted on a different CDN, has atypical PTMD and HLS files)
'url': 'https://www.zdf.de/funk/druck-11790/funk-alles-ist-verzaubert-102.html',
'md5': '57af4423db0455a3975d2dc4578536bc',
'info_dict': {
@ -651,6 +665,7 @@ class ZDFChannelIE(ZDFBaseIE):
'description': 'md5:6edad39189abf8431795d3d6d7f986b3',
},
'playlist_count': 242,
'skip': 'Video count changes daily, needs support for playlist_maxcount',
}]
_PAGE_SIZE = 24

View File

@ -857,7 +857,7 @@ def extract_object(self, objname, *global_stack):
obj = {}
obj_m = re.search(
r'''(?x)
(?<!\.)%s\s*=\s*{\s*
(?<![a-zA-Z$0-9.])%s\s*=\s*{\s*
(?P<fields>(%s\s*:\s*function\s*\(.*?\)\s*{.*?}(?:,\s*)?)*)
}\s*;
''' % (re.escape(objname), _FUNC_NAME_RE),

View File

@ -140,6 +140,12 @@ def __init__(self, res: requests.models.Response):
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:
# 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)

View File

@ -529,14 +529,14 @@ def _preset_alias_callback(option, opt_str, value, parser):
'no-attach-info-json', 'embed-thumbnail-atomicparsley', 'no-external-downloader-progress',
'embed-metadata', 'seperate-video-versions', 'no-clean-infojson', 'no-keep-subs', 'no-certifi',
'no-youtube-channel-redirect', 'no-youtube-unavailable-videos', 'no-youtube-prefer-utc-upload-date',
'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext', 'prefer-vp9-sort',
'prefer-legacy-http-handler', 'manifest-filesize-approx', 'allow-unsafe-ext', 'prefer-vp9-sort', 'mtime-by-default',
}, 'aliases': {
'youtube-dl': ['all', '-multistreams', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
'youtube-dlc': ['all', '-no-youtube-channel-redirect', '-no-live-chat', '-playlist-match-filter', '-manifest-filesize-approx', '-allow-unsafe-ext', '-prefer-vp9-sort'],
'2021': ['2022', 'no-certifi', 'filename-sanitization'],
'2022': ['2023', 'no-external-downloader-progress', 'playlist-match-filter', 'prefer-legacy-http-handler', 'manifest-filesize-approx'],
'2023': ['2024', 'prefer-vp9-sort'],
'2024': [],
'2024': ['mtime-by-default'],
},
}, help=(
'Options that can help keep compatibility with youtube-dl or youtube-dlc '
@ -1466,12 +1466,12 @@ def _preset_alias_callback(option, opt_str, value, parser):
help='Do not use .part files - write directly into output file')
filesystem.add_option(
'--mtime',
action='store_true', dest='updatetime', default=True,
help='Use the Last-modified header to set the file modification time (default)')
action='store_true', dest='updatetime', default=None,
help='Use the Last-modified header to set the file modification time')
filesystem.add_option(
'--no-mtime',
action='store_false', dest='updatetime',
help='Do not use the Last-modified header to set the file modification time')
help='Do not use the Last-modified header to set the file modification time (default)')
filesystem.add_option(
'--write-description',
action='store_true', dest='writedescription', default=False,

View File

@ -0,0 +1 @@
# Utility functions for handling web input based on commonly used JavaScript libraries

View File

@ -0,0 +1,167 @@
from __future__ import annotations
import array
import base64
import datetime as dt
import math
import re
from .._utils import parse_iso8601
TYPE_CHECKING = False
if TYPE_CHECKING:
import collections.abc
import typing
T = typing.TypeVar('T')
_ARRAY_TYPE_LOOKUP = {
'Int8Array': 'b',
'Uint8Array': 'B',
'Uint8ClampedArray': 'B',
'Int16Array': 'h',
'Uint16Array': 'H',
'Int32Array': 'i',
'Uint32Array': 'I',
'Float32Array': 'f',
'Float64Array': 'd',
'BigInt64Array': 'l',
'BigUint64Array': 'L',
'ArrayBuffer': 'B',
}
def parse_iter(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Callable[[list], typing.Any]] | None = None):
# based on https://github.com/Rich-Harris/devalue/blob/f3fd2aa93d79f21746555671f955a897335edb1b/src/parse.js
resolved = {
-1: None,
-2: None,
-3: math.nan,
-4: math.inf,
-5: -math.inf,
-6: -0.0,
}
if isinstance(parsed, int) and not isinstance(parsed, bool):
if parsed not in resolved or parsed == -2:
raise ValueError('invalid integer input')
return resolved[parsed]
elif not isinstance(parsed, list):
raise ValueError('expected int or list as input')
elif not parsed:
raise ValueError('expected a non-empty list as input')
if revivers is None:
revivers = {}
return_value = [None]
stack: list[tuple] = [(return_value, 0, 0)]
while stack:
target, index, source = stack.pop()
if isinstance(source, tuple):
name, source, reviver = source
try:
resolved[source] = target[index] = reviver(target[index])
except Exception as error:
yield TypeError(f'failed to parse {source} as {name!r}: {error}')
resolved[source] = target[index] = None
continue
if source in resolved:
target[index] = resolved[source]
continue
# guard against Python negative indexing
if source < 0:
yield IndexError(f'invalid index: {source!r}')
continue
try:
value = parsed[source]
except IndexError as error:
yield error
continue
if isinstance(value, list):
if value and isinstance(value[0], str):
# TODO: implement zips `strict=True`
if reviver := revivers.get(value[0]):
if value[1] == source:
# XXX: avoid infinite loop
yield IndexError(f'{value[0]!r} cannot point to itself (index: {source})')
continue
# inverse order: resolve index, revive value
stack.append((target, index, (value[0], value[1], reviver)))
stack.append((target, index, value[1]))
continue
elif value[0] == 'Date':
try:
result = dt.datetime.fromtimestamp(parse_iso8601(value[1]), tz=dt.timezone.utc)
except Exception:
yield ValueError(f'invalid date: {value[1]!r}')
result = None
elif value[0] == 'Set':
result = [None] * (len(value) - 1)
for offset, new_source in enumerate(value[1:]):
stack.append((result, offset, new_source))
elif value[0] == 'Map':
result = []
for key, new_source in zip(*(iter(value[1:]),) * 2):
pair = [None, None]
stack.append((pair, 0, key))
stack.append((pair, 1, new_source))
result.append(pair)
elif value[0] == 'RegExp':
# XXX: use jsinterp to translate regex flags
# currently ignores `value[2]`
result = re.compile(value[1])
elif value[0] == 'Object':
result = value[1]
elif value[0] == 'BigInt':
result = int(value[1])
elif value[0] == 'null':
result = {}
for key, new_source in zip(*(iter(value[1:]),) * 2):
stack.append((result, key, new_source))
elif value[0] in _ARRAY_TYPE_LOOKUP:
typecode = _ARRAY_TYPE_LOOKUP[value[0]]
data = base64.b64decode(value[1])
result = array.array(typecode, data).tolist()
else:
yield TypeError(f'invalid type at {source}: {value[0]!r}')
result = None
else:
result = len(value) * [None]
for offset, new_source in enumerate(value):
stack.append((result, offset, new_source))
elif isinstance(value, dict):
result = {}
for key, new_source in value.items():
stack.append((result, key, new_source))
else:
result = value
target[index] = resolved[source] = result
return return_value[0]
def parse(parsed: typing.Any, /, *, revivers: dict[str, collections.abc.Callable[[typing.Any], typing.Any]] | None = None):
generator = parse_iter(parsed, revivers=revivers)
while True:
try:
raise generator.send(None)
except StopIteration as error:
return error.value

View File

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2025.05.22'
__version__ = '2025.06.30'
RELEASE_GIT_HEAD = '7977b329ed97b216e37bd402f4935f28c00eac9e'
RELEASE_GIT_HEAD = 'b0187844988e557c7e1e6bb1aabd4c1176768d86'
VARIANT = None
@ -12,4 +12,4 @@
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2025.05.22'
_pkg_version = '2025.06.30'