mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2025-07-01 05:51:00 +02:00
Compare commits
No commits in common. "master" and "2025.06.09" have entirely different histories.
master
...
2025.06.09
41
.github/workflows/signature-tests.yml
vendored
41
.github/workflows/signature-tests.yml
vendored
@ -1,41 +0,0 @@
|
||||
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
|
||||
@ -779,8 +779,3 @@ brian6932
|
||||
iednod55
|
||||
maxbin123
|
||||
nullpos
|
||||
anlar
|
||||
eason1478
|
||||
ceandreasen
|
||||
chauhantirth
|
||||
helpimnotdrowning
|
||||
|
||||
42
Changelog.md
42
Changelog.md
@ -4,48 +4,6 @@
|
||||
# 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
|
||||
|
||||
@ -254,13 +254,5 @@
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "d596824c2f8428362c072518856065070616e348"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "7b81634fb1d15999757e7a9883daa6ef09ea785b"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "500761e41acb96953a5064e951d41d190c287e46"
|
||||
}
|
||||
]
|
||||
|
||||
@ -575,7 +575,9 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **HollywoodReporterPlaylist**
|
||||
- **Holodex**
|
||||
- **HotNewHipHop**: (**Currently broken**)
|
||||
- **hotstar**: JioHotstar
|
||||
- **hotstar**
|
||||
- **hotstar:playlist**
|
||||
- **hotstar:season**
|
||||
- **hotstar:series**
|
||||
- **hrfernsehen**
|
||||
- **HRTi**: [*hrti*](## "netrc machine")
|
||||
@ -588,7 +590,7 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **Hungama**
|
||||
- **HungamaAlbumPlaylist**
|
||||
- **HungamaSong**
|
||||
- **huya:live**: 虎牙直播
|
||||
- **huya:live**: huya.com
|
||||
- **huya:video**: 虎牙视频
|
||||
- **Hypem**
|
||||
- **Hytale**
|
||||
@ -645,6 +647,8 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **Jamendo**
|
||||
- **JamendoAlbum**
|
||||
- **JeuxVideo**: (**Currently broken**)
|
||||
- **jiocinema**: [*jiocinema*](## "netrc machine")
|
||||
- **jiocinema:series**: [*jiocinema*](## "netrc machine")
|
||||
- **jiosaavn:album**
|
||||
- **jiosaavn:artist**
|
||||
- **jiosaavn:playlist**
|
||||
@ -772,7 +776,6 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **massengeschmack.tv**
|
||||
- **Masters**
|
||||
- **MatchTV**
|
||||
- **Mave**
|
||||
- **MBN**: mbn.co.kr (매일방송)
|
||||
- **MDR**: MDR.DE
|
||||
- **MedalTV**
|
||||
@ -829,7 +832,7 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **Mojevideo**: mojevideo.sk
|
||||
- **Mojvideo**
|
||||
- **Monstercat**
|
||||
- **monstersiren**: 塞壬唱片
|
||||
- **MonsterSirenHypergryphMusic**
|
||||
- **Motherless**
|
||||
- **MotherlessGallery**
|
||||
- **MotherlessGroup**
|
||||
@ -1295,7 +1298,6 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **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**
|
||||
|
||||
@ -1947,137 +1947,6 @@ jwplayer("mediaplayer").setup({"abouttext":"Visit Indie DB","aboutlink":"http:\/
|
||||
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)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
unittest.main()
|
||||
|
||||
@ -1,235 +0,0 @@
|
||||
#!/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()
|
||||
@ -478,10 +478,6 @@ class TestJSInterpreter(unittest.TestCase):
|
||||
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)
|
||||
|
||||
@ -416,8 +416,18 @@ class TestTraversal:
|
||||
'`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'
|
||||
|
||||
@ -133,11 +133,6 @@ _SIG_TESTS = [
|
||||
'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 = [
|
||||
|
||||
@ -2219,7 +2219,6 @@ class YoutubeDL:
|
||||
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']))
|
||||
@ -3964,7 +3963,6 @@ class YoutubeDL:
|
||||
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=' '),
|
||||
|
||||
@ -5,46 +5,47 @@ import time
|
||||
from .common import FileDownloader
|
||||
from .external import FFmpegFD
|
||||
from ..networking import Request
|
||||
from ..networking.websocket import WebSocketResponse
|
||||
from ..utils import DownloadError, str_or_none, truncate_string
|
||||
from ..utils.traversal import traverse_obj
|
||||
from ..utils import DownloadError, str_or_none, try_get
|
||||
|
||||
|
||||
class NiconicoLiveFD(FileDownloader):
|
||||
""" Downloads niconico live without being stopped """
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
video_id = info_dict['id']
|
||||
opts = info_dict['downloader_options']
|
||||
quality, ws_extractor, ws_url = opts['max_quality'], opts['ws'], opts['ws_url']
|
||||
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')
|
||||
dl = FFmpegFD(self.ydl, self.params or {})
|
||||
|
||||
new_info_dict = info_dict.copy()
|
||||
new_info_dict['protocol'] = 'm3u8'
|
||||
new_info_dict.update({
|
||||
'protocol': 'm3u8',
|
||||
})
|
||||
|
||||
def communicate_ws(reconnect):
|
||||
# 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 reconnect:
|
||||
ws = self.ydl.urlopen(Request(ws_url, headers={'Origin': f'https://{ws_origin_host}'}))
|
||||
if self.ydl.params.get('verbose', False):
|
||||
self.write_debug('Sending startWatching request')
|
||||
self.to_screen('[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
|
||||
@ -57,6 +58,7 @@ class NiconicoLiveFD(FileDownloader):
|
||||
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':
|
||||
@ -64,10 +66,12 @@ class NiconicoLiveFD(FileDownloader):
|
||||
return True
|
||||
elif data.get('type') == 'error':
|
||||
self.write_debug(data)
|
||||
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
|
||||
message = try_get(data, lambda x: x['body']['code'], str) or recv
|
||||
return DownloadError(message)
|
||||
elif self.ydl.params.get('verbose', False):
|
||||
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
|
||||
if len(recv) > 100:
|
||||
recv = recv[:100] + '...'
|
||||
self.to_screen(f'[debug] Server said: {recv}')
|
||||
|
||||
def ws_main():
|
||||
reconnect = False
|
||||
@ -77,8 +81,7 @@ class NiconicoLiveFD(FileDownloader):
|
||||
if ret is True:
|
||||
return
|
||||
except BaseException as e:
|
||||
self.to_screen(
|
||||
f'[niconico:live] {video_id}: Connection error occured, reconnecting after 10 seconds: {e}')
|
||||
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
|
||||
time.sleep(10)
|
||||
continue
|
||||
finally:
|
||||
|
||||
@ -805,7 +805,9 @@ from .holodex import HolodexIE
|
||||
from .hotnewhiphop import HotNewHipHopIE
|
||||
from .hotstar import (
|
||||
HotStarIE,
|
||||
HotStarPlaylistIE,
|
||||
HotStarPrefixIE,
|
||||
HotStarSeasonIE,
|
||||
HotStarSeriesIE,
|
||||
)
|
||||
from .hrefli import HrefLiRedirectIE
|
||||
@ -919,6 +921,10 @@ from .japandiet import (
|
||||
ShugiinItvVodIE,
|
||||
)
|
||||
from .jeuxvideo import JeuxVideoIE
|
||||
from .jiocinema import (
|
||||
JioCinemaIE,
|
||||
JioCinemaSeriesIE,
|
||||
)
|
||||
from .jiosaavn import (
|
||||
JioSaavnAlbumIE,
|
||||
JioSaavnArtistIE,
|
||||
@ -1101,7 +1107,6 @@ from .markiza import (
|
||||
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
|
||||
@ -1824,7 +1829,6 @@ from .safari import (
|
||||
from .saitosan import SaitosanIE
|
||||
from .samplefocus import SampleFocusIE
|
||||
from .sapo import SapoIE
|
||||
from .sauceplus import SaucePlusIE
|
||||
from .sbs import SBSIE
|
||||
from .sbscokr import (
|
||||
SBSCoKrAllvodProgramIE,
|
||||
|
||||
@ -1226,26 +1226,6 @@ 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):
|
||||
@ -1302,13 +1282,7 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
|
||||
}
|
||||
|
||||
def get_entries(page_data):
|
||||
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:
|
||||
for entry in traverse_obj(page_data, ('list', 'vlist')) or []:
|
||||
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)
|
||||
|
||||
@ -495,6 +495,8 @@ class BrightcoveLegacyIE(InfoExtractor):
|
||||
|
||||
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:
|
||||
@ -598,18 +600,16 @@ class BrightcoveNewBaseIE(AdobePassIE):
|
||||
|
||||
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}),
|
||||
}),
|
||||
}
|
||||
|
||||
|
||||
@ -645,7 +645,10 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
|
||||
'uploader_id': '4036320279001',
|
||||
'formats': 'mincount:39',
|
||||
},
|
||||
'skip': '404 Not Found',
|
||||
'params': {
|
||||
# m3u8 download
|
||||
'skip_download': True,
|
||||
},
|
||||
}, {
|
||||
# playlist stream
|
||||
'url': 'https://players.brightcove.net/1752604059001/S13cJdUBz_default/index.html?playlistId=5718313430001',
|
||||
@ -706,6 +709,7 @@ class BrightcoveNewIE(BrightcoveNewBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'TGD_01-032_5',
|
||||
'thumbnail': r're:^https?://.*\.jpg$',
|
||||
'tags': [],
|
||||
'timestamp': 1646078943,
|
||||
'uploader_id': '1569565978001',
|
||||
'upload_date': '20220228',
|
||||
@ -717,6 +721,7 @@ 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',
|
||||
|
||||
@ -11,7 +11,7 @@ from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class CloudyCDNIE(InfoExtractor):
|
||||
_VALID_URL = r'(?:https?:)?//embed\.(?P<domain>cloudycdn\.services|backscreen\.com)/(?P<site_id>[^/?#]+)/media/(?P<id>[\w-]+)'
|
||||
_VALID_URL = r'(?:https?:)?//embed\.cloudycdn\.services/(?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.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
|
||||
'thumbnail': 'https://store.cloudycdn.services/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.bstrm.net/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
|
||||
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/488306/placeholder1679423604.jpg',
|
||||
'duration': 1205,
|
||||
'upload_date': '20221130',
|
||||
},
|
||||
@ -48,21 +48,9 @@ class CloudyCDNIE(InfoExtractor):
|
||||
'duration': 1673,
|
||||
'title': 'D24-6000-074-cetstud',
|
||||
'timestamp': 1718902233,
|
||||
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/788392/placeholder1718903938.jpg',
|
||||
'thumbnail': 'https://store.cloudycdn.services/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/',
|
||||
@ -72,17 +60,17 @@ class CloudyCDNIE(InfoExtractor):
|
||||
'ext': 'mp4',
|
||||
'upload_date': '20230223',
|
||||
'duration': 629,
|
||||
'thumbnail': 'https://store.bstrm.net/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
|
||||
'thumbnail': 'https://store.cloudycdn.services/tmsp00120/assets/media/518407/placeholder1678748124.jpg',
|
||||
'timestamp': 1677181513,
|
||||
'title': 'LIB-2',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
domain, site_id, video_id = self._match_valid_url(url).group('domain', 'site_id', 'id')
|
||||
site_id, video_id = self._match_valid_url(url).group('site_id', 'id')
|
||||
|
||||
data = self._download_json(
|
||||
f'https://player.{domain}/player/{site_id}/media/{video_id}/',
|
||||
f'https://player.cloudycdn.services/player/{site_id}/media/{video_id}/',
|
||||
video_id, data=urlencode_postdata({
|
||||
'version': '6.4.0',
|
||||
'referer': url,
|
||||
|
||||
@ -101,7 +101,6 @@ from ..utils import (
|
||||
xpath_with_ns,
|
||||
)
|
||||
from ..utils._utils import _request_dump_filename
|
||||
from ..utils.jslib import devalue
|
||||
|
||||
|
||||
class InfoExtractor:
|
||||
@ -263,9 +262,6 @@ 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,
|
||||
@ -1799,63 +1795,6 @@ class InfoExtractor:
|
||||
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)
|
||||
|
||||
@ -17,140 +17,8 @@ from ..utils import (
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
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):
|
||||
class FloatplaneIE(InfoExtractor):
|
||||
_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': {
|
||||
@ -302,9 +170,105 @@ class FloatplaneIE(FloatplaneBaseIE):
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
|
||||
if not self._get_cookies('https://www.floatplane.com').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-]+))?'
|
||||
|
||||
@ -1,4 +1,3 @@
|
||||
import functools
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
@ -10,20 +9,18 @@ from .common import InfoExtractor
|
||||
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):
|
||||
@ -32,86 +29,57 @@ class HotStarBaseIE(InfoExtractor):
|
||||
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()
|
||||
response = self._download_json(
|
||||
f'{self._API_URL_V2}/{path}', video_id, query=query,
|
||||
|
||||
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={
|
||||
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
|
||||
'hotstarauth': auth,
|
||||
'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',
|
||||
'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,
|
||||
headers={
|
||||
'hotstarauth': auth,
|
||||
'x-hs-appversion': '6.72.2',
|
||||
'x-hs-platform': 'web',
|
||||
'x-hs-usertoken': token,
|
||||
})
|
||||
|
||||
if not traverse_obj(response, ('success', {dict})):
|
||||
raise ExtractorError('API call was unsuccessful')
|
||||
return response['success']
|
||||
if response['message'] != "Playback URL's fetched successfully":
|
||||
raise ExtractorError(
|
||||
response['message'], expected=True)
|
||||
return response['data']
|
||||
|
||||
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 _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 _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'])):
|
||||
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'):
|
||||
yield self.url_result(
|
||||
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
|
||||
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, video['contentId'])
|
||||
|
||||
|
||||
class HotStarIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar'
|
||||
IE_DESC = 'JioHotstar'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
|
||||
(?:
|
||||
@ -146,16 +114,15 @@ class HotStarIE(HotStarBaseIE):
|
||||
'upload_date': '20190501',
|
||||
'duration': 1219,
|
||||
'channel': 'StarPlus',
|
||||
'channel_id': '821',
|
||||
'channel_id': '3',
|
||||
'series': 'Ek Bhram - Sarvagun Sampanna',
|
||||
'season': 'Chapter 1',
|
||||
'season_number': 1,
|
||||
'season_id': '1260004607',
|
||||
'season_id': '6771',
|
||||
'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',
|
||||
@ -167,14 +134,14 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'StarPlus',
|
||||
'series': 'Anupama',
|
||||
'season_number': 1,
|
||||
'season_id': '1260022018',
|
||||
'season_id': '7399',
|
||||
'upload_date': '20230307',
|
||||
'episode': 'Anupama, Anuj Share a Moment',
|
||||
'episode_number': 853,
|
||||
'duration': 1266,
|
||||
'channel_id': '821',
|
||||
'duration': 1272,
|
||||
'channel_id': '3',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
|
||||
'info_dict': {
|
||||
@ -187,15 +154,14 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'Hotstar Specials',
|
||||
'series': 'Kana Kaanum Kaalangal',
|
||||
'season_number': 1,
|
||||
'season_id': '1260097089',
|
||||
'season_id': '9441',
|
||||
'upload_date': '20220421',
|
||||
'episode': 'Back To School',
|
||||
'episode_number': 1,
|
||||
'duration': 1810,
|
||||
'channel_id': '1260003991',
|
||||
'channel_id': '54',
|
||||
},
|
||||
'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',
|
||||
@ -207,7 +173,6 @@ class HotStarIE(HotStarBaseIE):
|
||||
'timestamp': 1622943900,
|
||||
'duration': 5395,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
|
||||
'info_dict': {
|
||||
@ -215,13 +180,12 @@ class HotStarIE(HotStarBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Premam',
|
||||
'release_year': 2015,
|
||||
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
|
||||
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
|
||||
'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,
|
||||
@ -244,13 +208,6 @@ class HotStarIE(HotStarBaseIE):
|
||||
None: 'content',
|
||||
}
|
||||
|
||||
_CONTENT_TYPE = {
|
||||
'movie': 'MOVIE',
|
||||
'episode': 'EPISODE',
|
||||
'match': 'SPORT',
|
||||
'content': 'CLIPS',
|
||||
}
|
||||
|
||||
_IGNORE_MAP = {
|
||||
'res': 'resolution',
|
||||
'vcodec': 'video_codec',
|
||||
@ -272,48 +229,38 @@ class HotStarIE(HotStarBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, video_type = self._match_valid_url(url).group('id', 'type')
|
||||
video_type = self._TYPE[video_type]
|
||||
video_type = self._TYPE.get(video_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': 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._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.report_drm(video_id)
|
||||
|
||||
geo_restricted = False
|
||||
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]
|
||||
|
||||
# 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')}))
|
||||
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
|
||||
|
||||
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 ''
|
||||
geo_restricted = False
|
||||
formats, subs = [], {}
|
||||
headers = {'Referer': f'{self._BASE_URL}/in'}
|
||||
|
||||
# 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 ''
|
||||
if any(f'{prefix}:{ignore}' in tags
|
||||
for key, prefix in self._IGNORE_MAP.items()
|
||||
for ignore in self._configuration_arg(key)):
|
||||
continue
|
||||
|
||||
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
|
||||
format_url = url_or_none(playback_set.get('playbackUrl'))
|
||||
if not format_url:
|
||||
continue
|
||||
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
|
||||
ext = determine_ext(format_url)
|
||||
|
||||
current_formats, current_subs = [], {}
|
||||
@ -333,12 +280,14 @@ class HotStarIE(HotStarBaseIE):
|
||||
'height': int_or_none(playback_set.get('height')),
|
||||
}]
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
|
||||
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):
|
||||
@ -350,11 +299,6 @@ class HotStarIE(HotStarBaseIE):
|
||||
'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,
|
||||
@ -366,17 +310,27 @@ class HotStarIE(HotStarBaseIE):
|
||||
|
||||
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')),
|
||||
}
|
||||
|
||||
|
||||
@ -417,6 +371,64 @@ class HotStarPrefixIE(InfoExtractor):
|
||||
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+))/?(?:[#?]|$)'
|
||||
@ -431,29 +443,25 @@ class HotStarSeriesIE(HotStarBaseIE):
|
||||
'info_dict': {
|
||||
'id': '1260050431',
|
||||
},
|
||||
'playlist_mincount': 42,
|
||||
'playlist_mincount': 43,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
|
||||
'info_dict': {
|
||||
'id': '435',
|
||||
},
|
||||
'playlist_mincount': 267,
|
||||
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
|
||||
'info_dict': {
|
||||
'id': '1260022017',
|
||||
},
|
||||
'playlist_mincount': 1601,
|
||||
'playlist_mincount': 940,
|
||||
}]
|
||||
_PAGE_SIZE = 100
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, series_id = self._match_valid_url(url).group('url', 'id')
|
||||
eid = self._call_api_v1(
|
||||
url, series_id = self._match_valid_url(url).groups()
|
||||
id_ = self._call_api_v1(
|
||||
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
|
||||
|
||||
entries = OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, 'tray/g/1/items', series_id,
|
||||
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
|
||||
|
||||
return self.playlist_result(entries, series_id)
|
||||
return self.playlist_result(self._playlist_entries(
|
||||
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
|
||||
|
||||
@ -7,13 +7,12 @@ import urllib.parse
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
int_or_none,
|
||||
parse_duration,
|
||||
str_or_none,
|
||||
try_get,
|
||||
unescapeHTML,
|
||||
update_url,
|
||||
unified_strdate,
|
||||
update_url_query,
|
||||
url_or_none,
|
||||
)
|
||||
@ -23,8 +22,8 @@ from ..utils.traversal import traverse_obj
|
||||
class HuyaLiveIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.|m\.)?huya\.com/(?!(?:video/play/))(?P<id>[^/#?&]+)(?:\D|$)'
|
||||
IE_NAME = 'huya:live'
|
||||
IE_DESC = '虎牙直播'
|
||||
_TESTS = [{
|
||||
IE_DESC = 'huya.com'
|
||||
TESTS = [{
|
||||
'url': 'https://www.huya.com/572329',
|
||||
'info_dict': {
|
||||
'id': '572329',
|
||||
@ -150,94 +149,63 @@ class HuyaVideoIE(InfoExtractor):
|
||||
'id': '1002412640',
|
||||
'ext': 'mp4',
|
||||
'title': '8月3日',
|
||||
'categories': ['主机游戏'],
|
||||
'duration': 14.0,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'duration': 14,
|
||||
'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',
|
||||
'categories': ['英雄联盟'],
|
||||
'description': 'md5:58184869687d18ce62dc7b4b2ad21201',
|
||||
'duration': 1864.0,
|
||||
'thumbnail': r're:https?://.*\.jpg',
|
||||
'duration': 1864,
|
||||
'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)
|
||||
moment = self._download_json(
|
||||
'https://liveapi.huya.com/moment/getMomentContent',
|
||||
video_id, query={'videoId': video_id})['data']['moment']
|
||||
video_data = self._download_json(
|
||||
'https://liveapi.huya.com/moment/getMomentContent', video_id,
|
||||
query={'videoId': video_id})['data']['moment']['videoInfo']
|
||||
|
||||
formats = []
|
||||
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}),
|
||||
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}),
|
||||
'height': ('height', {int_or_none}),
|
||||
'quality': ('definition', {int_or_none}),
|
||||
'width': ('width', {int_or_none}),
|
||||
}))
|
||||
formats.extend(fmts)
|
||||
'height': ('height', {int_or_none}),
|
||||
'filesize': ('size', {int_or_none}),
|
||||
}),
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'formats': formats,
|
||||
**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', {
|
||||
**traverse_obj(video_data, {
|
||||
'title': ('videoTitle', {str}),
|
||||
'categories': ('category', {str}, filter, all, filter),
|
||||
'thumbnail': ('videoCover', {url_or_none}),
|
||||
'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}),
|
||||
}),
|
||||
}
|
||||
|
||||
@ -1,66 +1,32 @@
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
clean_html,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import subs_list_to_dict, traverse_obj
|
||||
from ..utils import js_to_json, 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',
|
||||
'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',
|
||||
'album': 'Flame Shadow',
|
||||
'title': 'Flame Shadow',
|
||||
},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
audio_id = self._match_id(url)
|
||||
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)
|
||||
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)
|
||||
|
||||
return {
|
||||
'id': audio_id,
|
||||
'title': traverse_obj(json_data, ('player', 'songDetail', 'name')),
|
||||
'url': traverse_obj(json_data, ('player', 'songDetail', 'sourceUrl')),
|
||||
'ext': 'wav',
|
||||
'vcodec': 'none',
|
||||
**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}),
|
||||
})),
|
||||
'artists': traverse_obj(json_data, ('player', 'songDetail', 'artists', ...)),
|
||||
'album': traverse_obj(json_data, ('musicPlay', 'albumDetail', 'name')),
|
||||
}
|
||||
|
||||
408
yt_dlp/extractor/jiocinema.py
Normal file
408
yt_dlp/extractor/jiocinema.py
Normal file
@ -0,0 +1,408 @@
|
||||
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)
|
||||
@ -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,
|
||||
@ -16,17 +16,21 @@ from ..utils import (
|
||||
|
||||
|
||||
class KickBaseIE(InfoExtractor):
|
||||
@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 _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 {}
|
||||
|
||||
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={**self._api_headers, **headers}, impersonate=True, **kwargs)
|
||||
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
|
||||
|
||||
|
||||
class KickIE(KickBaseIE):
|
||||
|
||||
@ -167,11 +167,11 @@ class LSMLTVEmbedIE(InfoExtractor):
|
||||
'duration': 1442,
|
||||
'upload_date': '20231121',
|
||||
'title': 'D23-6000-105_cetstud',
|
||||
'thumbnail': 'https://store.bstrm.net/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
|
||||
'thumbnail': 'https://store.cloudycdn.services/tmsp00060/assets/media/660858/placeholder1700589200.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://ltv.lsm.lv/embed?enablesdkjs=1&c=eyJpdiI6IncwVzZmUFk2MU12enVWK1I3SUcwQ1E9PSIsInZhbHVlIjoid3FhV29vamc3T2sxL1RaRmJ5Rm1GTXozU0o2dVczdUtLK0cwZEZJMDQ2a3ZIRG5DK2pneGlnbktBQy9uazVleHN6VXhxdWIweWNvcHRDSnlISlNYOHlVZ1lpcTUrcWZSTUZPQW14TVdkMW9aOUtRWVNDcFF4eWpHNGcrT0VZbUNFQStKQk91cGpndW9FVjJIa0lpbkh3PT0iLCJtYWMiOiIyZGI1NDJlMWRlM2QyMGNhOGEwYTM2MmNlN2JlOGRhY2QyYjdkMmEzN2RlOTEzYTVkNzI1ODlhZDlhZjU4MjQ2IiwidGFnIjoiIn0=',
|
||||
'md5': 'f236cef2fd5953612754e4e66be51e7a',
|
||||
'md5': 'a1711e190fe680fdb68fd8413b378e87',
|
||||
'info_dict': {
|
||||
'id': 'wUnFArIPDSY',
|
||||
'ext': 'mp4',
|
||||
@ -198,8 +198,6 @@ class LSMLTVEmbedIE(InfoExtractor):
|
||||
'uploader_url': 'https://www.youtube.com/@LTV16plus',
|
||||
'like_count': int,
|
||||
'description': 'md5:7ff0c42ba971e3c13e4b8a2ff03b70b5',
|
||||
'media_type': 'livestream',
|
||||
'timestamp': 1652550741,
|
||||
},
|
||||
}]
|
||||
|
||||
@ -210,7 +208,7 @@ class LSMLTVEmbedIE(InfoExtractor):
|
||||
r'window\.ltvEmbedPayload\s*=', webpage, 'embed json', video_id)
|
||||
embed_type = traverse_obj(data, ('source', 'name', {str}))
|
||||
|
||||
if embed_type in ('backscreen', 'telia'): # 'telia' only for backwards compat
|
||||
if embed_type == 'telia':
|
||||
ie_key = 'CloudyCDN'
|
||||
embed_url = traverse_obj(data, ('source', 'embed_url', {url_or_none}))
|
||||
elif embed_type == 'youtube':
|
||||
@ -228,9 +226,9 @@ class LSMLTVEmbedIE(InfoExtractor):
|
||||
|
||||
|
||||
class LSMReplayIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:skaties/|klausies/)?(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
|
||||
_VALID_URL = r'https?://replay\.lsm\.lv/[^/?#]+/(?:ieraksts|statja)/[^/?#]+/(?P<id>\d+)'
|
||||
_TESTS = [{
|
||||
'url': 'https://replay.lsm.lv/lv/skaties/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
|
||||
'url': 'https://replay.lsm.lv/lv/ieraksts/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
|
||||
'md5': '64f72a360ca530d5ed89c77646c9eee5',
|
||||
'info_dict': {
|
||||
'id': '46k_d23-6000-105',
|
||||
@ -243,23 +241,20 @@ class LSMReplayIE(InfoExtractor):
|
||||
'thumbnail': 'https://ltv.lsm.lv/storage/media/8/7/large/5/1f9604e1.jpg',
|
||||
},
|
||||
}, {
|
||||
'url': 'https://replay.lsm.lv/lv/klausies/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
|
||||
'md5': '84feb80fd7e6ec07744726a9f01cda4d',
|
||||
'url': 'https://replay.lsm.lv/lv/ieraksts/lr/183522/138-nepilniga-kompensejamo-zalu-sistema-pat-menesiem-dzena-pacientus-pa-aptiekam',
|
||||
'md5': '719b33875cd1429846eeeaeec6df2830',
|
||||
'info_dict': {
|
||||
'id': '183522',
|
||||
'ext': 'm4a',
|
||||
'id': 'a342781',
|
||||
'ext': 'mp3',
|
||||
'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': 1698913860,
|
||||
'timestamp': 1698921060,
|
||||
'description': 'md5:7bac3b2dd41e44325032943251c357b1',
|
||||
},
|
||||
}, {
|
||||
'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',
|
||||
'url': 'https://replay.lsm.lv/ru/statja/ltv/311130/4-studija-zolitudes-tragedija-un-incupes-stacija',
|
||||
'only_matching': True,
|
||||
}]
|
||||
|
||||
@ -272,24 +267,12 @@ class LSMReplayIE(InfoExtractor):
|
||||
|
||||
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}),
|
||||
|
||||
@ -1,107 +0,0 @@
|
||||
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}),
|
||||
})),
|
||||
}
|
||||
@ -4,15 +4,16 @@ import itertools
|
||||
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,
|
||||
@ -21,8 +22,9 @@ from ..utils import (
|
||||
parse_qs,
|
||||
parse_resolution,
|
||||
qualities,
|
||||
remove_start,
|
||||
str_or_none,
|
||||
truncate_string,
|
||||
unescapeHTML,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
url_basename,
|
||||
@ -30,11 +32,7 @@ from ..utils import (
|
||||
urlencode_postdata,
|
||||
urljoin,
|
||||
)
|
||||
from ..utils.traversal import (
|
||||
find_element,
|
||||
require,
|
||||
traverse_obj,
|
||||
)
|
||||
from ..utils.traversal import find_element, require, traverse_obj
|
||||
|
||||
|
||||
class NiconicoBaseIE(InfoExtractor):
|
||||
@ -808,39 +806,41 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
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)
|
||||
webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
|
||||
|
||||
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')
|
||||
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.')
|
||||
|
||||
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(
|
||||
ws_url, video_id, 'Connecting to WebSocket server',
|
||||
headers={'Origin': 'https://live.nicovideo.jp'})
|
||||
Request(ws_url, headers={'Origin': f'https://{hostname}'}),
|
||||
video_id=video_id, note='Connecting to WebSocket server')
|
||||
|
||||
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:
|
||||
@ -860,15 +860,17 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
raise ExtractorError('Disconnected at middle of extraction')
|
||||
elif data.get('type') == 'error':
|
||||
self.write_debug(recv)
|
||||
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
|
||||
message = traverse_obj(data, ('body', 'code')) or recv
|
||||
raise ExtractorError(message)
|
||||
elif self.get_param('verbose', False):
|
||||
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
|
||||
if len(recv) > 100:
|
||||
recv = recv[:100] + '...'
|
||||
self.write_debug(f'Server said: {recv}')
|
||||
|
||||
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', {dict})) or {}
|
||||
raw_thumbs = traverse_obj(embedded_data, ('program', 'thumbnail')) or {}
|
||||
thumbnails = []
|
||||
for name, value in raw_thumbs.items():
|
||||
if not isinstance(value, dict):
|
||||
@ -895,30 +897,31 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
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'),
|
||||
|
||||
@ -1,41 +0,0 @@
|
||||
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()
|
||||
@ -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',
|
||||
@ -227,19 +227,6 @@ 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'
|
||||
|
||||
|
||||
@ -25,7 +25,6 @@ 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': {
|
||||
@ -42,7 +41,6 @@ class SportDeutschlandIE(InfoExtractor):
|
||||
'upload_date': '20220309',
|
||||
'timestamp': 1646860727.0,
|
||||
},
|
||||
'skip': 'not found',
|
||||
}, {
|
||||
'url': 'https://sportdeutschland.tv/ggcbremen/formationswochenende-latein-2023',
|
||||
'info_dict': {
|
||||
@ -70,7 +68,6 @@ class SportDeutschlandIE(InfoExtractor):
|
||||
'live_status': 'was_live',
|
||||
},
|
||||
}],
|
||||
'skip': 'not found',
|
||||
}, {
|
||||
'url': 'https://sportdeutschland.tv/dtb/gymnastik-international-tag-1',
|
||||
'info_dict': {
|
||||
@ -85,30 +82,13 @@ 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/web/personal/asset-token/{asset_id}',
|
||||
video['id'], query={'type': video['type'], 'playback_id': video['src']},
|
||||
headers={'Referer': 'https://sportdeutschland.tv/'})['token']
|
||||
f'https://api.sportdeutschland.tv/api/frontend/asset-token/{asset_id}',
|
||||
video['id'], query={'type': video['type'], 'playback_id': video['src']})['token']
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(
|
||||
f'https://stream.mux.com/{video["src"]}.m3u8?token={token}', video['id'], live=is_live)
|
||||
|
||||
|
||||
@ -41,7 +41,6 @@ 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',
|
||||
@ -99,17 +98,10 @@ class SproutVideoIE(InfoExtractor):
|
||||
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'}), impersonate=True)
|
||||
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}))
|
||||
data = self._search_json(
|
||||
r'var\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})')
|
||||
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())
|
||||
|
||||
formats, subtitles = [], {}
|
||||
headers = {
|
||||
|
||||
@ -63,7 +63,6 @@ INNERTUBE_CLIENTS = {
|
||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
|
||||
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
|
||||
'SUPPORTS_COOKIES': True,
|
||||
'PLAYER_PARAMS': '8AEB',
|
||||
},
|
||||
'web_embedded': {
|
||||
'INNERTUBE_CONTEXT': {
|
||||
@ -175,7 +174,6 @@ INNERTUBE_CLIENTS = {
|
||||
},
|
||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
|
||||
'SUPPORTS_COOKIES': True,
|
||||
'PLAYER_PARAMS': '8AEB',
|
||||
},
|
||||
'tv_simply': {
|
||||
'INNERTUBE_CONTEXT': {
|
||||
|
||||
@ -3552,11 +3552,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
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:
|
||||
@ -4285,7 +4280,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
|
||||
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']:
|
||||
|
||||
@ -857,7 +857,7 @@ class JSInterpreter:
|
||||
obj = {}
|
||||
obj_m = re.search(
|
||||
r'''(?x)
|
||||
(?<![a-zA-Z$0-9.])%s\s*=\s*{\s*
|
||||
(?<!\.)%s\s*=\s*{\s*
|
||||
(?P<fields>(%s\s*:\s*function\s*\(.*?\)\s*{.*?}(?:,\s*)?)*)
|
||||
}\s*;
|
||||
''' % (re.escape(objname), _FUNC_NAME_RE),
|
||||
|
||||
@ -1 +0,0 @@
|
||||
# Utility functions for handling web input based on commonly used JavaScript libraries
|
||||
@ -1,167 +0,0 @@
|
||||
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
|
||||
@ -1,8 +1,8 @@
|
||||
# Autogenerated by devscripts/update-version.py
|
||||
|
||||
__version__ = '2025.06.30'
|
||||
__version__ = '2025.06.09'
|
||||
|
||||
RELEASE_GIT_HEAD = 'b0187844988e557c7e1e6bb1aabd4c1176768d86'
|
||||
RELEASE_GIT_HEAD = '339614a173c74b42d63e858c446a9cae262a13af'
|
||||
|
||||
VARIANT = None
|
||||
|
||||
@ -12,4 +12,4 @@ CHANNEL = 'stable'
|
||||
|
||||
ORIGIN = 'yt-dlp/yt-dlp'
|
||||
|
||||
_pkg_version = '2025.06.30'
|
||||
_pkg_version = '2025.06.09'
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user