mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2026-01-13 02:11:18 +00:00
Compare commits
18 Commits
2025.06.25
...
2025.06.30
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
30fa54280b | ||
|
|
b018784498 | ||
|
|
11b9416e10 | ||
|
|
35fc33fbc5 | ||
|
|
b16722ede8 | ||
|
|
500761e41a | ||
|
|
2ba5391cd6 | ||
|
|
e9f157669e | ||
|
|
958153a226 | ||
|
|
1b88384634 | ||
|
|
7b81634fb1 | ||
|
|
7e2504f941 | ||
|
|
4bd9a7ade7 | ||
|
|
b5bd057fe8 | ||
|
|
5e292baad6 | ||
|
|
0a6b104489 | ||
|
|
06c1a8cdff | ||
|
|
99b85ac102 |
41
.github/workflows/signature-tests.yml
vendored
Normal file
41
.github/workflows/signature-tests.yml
vendored
Normal file
@@ -0,0 +1,41 @@
|
||||
name: Signature Tests
|
||||
on:
|
||||
push:
|
||||
paths:
|
||||
- .github/workflows/signature-tests.yml
|
||||
- test/test_youtube_signature.py
|
||||
- yt_dlp/jsinterp.py
|
||||
pull_request:
|
||||
paths:
|
||||
- .github/workflows/signature-tests.yml
|
||||
- test/test_youtube_signature.py
|
||||
- yt_dlp/jsinterp.py
|
||||
permissions:
|
||||
contents: read
|
||||
|
||||
concurrency:
|
||||
group: signature-tests-${{ github.event.pull_request.number || github.ref }}
|
||||
cancel-in-progress: ${{ github.event_name == 'pull_request' }}
|
||||
|
||||
jobs:
|
||||
tests:
|
||||
name: Signature Tests
|
||||
runs-on: ${{ matrix.os }}
|
||||
strategy:
|
||||
fail-fast: false
|
||||
matrix:
|
||||
os: [ubuntu-latest, windows-latest]
|
||||
python-version: ['3.9', '3.10', '3.11', '3.12', '3.13', pypy-3.10, pypy-3.11]
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
- name: Set up Python ${{ matrix.python-version }}
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: ${{ matrix.python-version }}
|
||||
- name: Install test requirements
|
||||
run: python3 ./devscripts/install_deps.py --only-optional --include test
|
||||
- name: Run tests
|
||||
timeout-minutes: 15
|
||||
run: |
|
||||
python3 -m yt_dlp -v || true # Print debug head
|
||||
python3 ./devscripts/run_tests.py test/test_youtube_signature.py
|
||||
@@ -781,3 +781,6 @@ maxbin123
|
||||
nullpos
|
||||
anlar
|
||||
eason1478
|
||||
ceandreasen
|
||||
chauhantirth
|
||||
helpimnotdrowning
|
||||
|
||||
23
Changelog.md
23
Changelog.md
@@ -4,6 +4,29 @@
|
||||
# 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
|
||||
|
||||
@@ -254,5 +254,13 @@
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "d596824c2f8428362c072518856065070616e348"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "7b81634fb1d15999757e7a9883daa6ef09ea785b"
|
||||
},
|
||||
{
|
||||
"action": "remove",
|
||||
"when": "500761e41acb96953a5064e951d41d190c287e46"
|
||||
}
|
||||
]
|
||||
|
||||
@@ -575,9 +575,7 @@ The only reliable way to check if a site is supported is to try it.
|
||||
- **HollywoodReporterPlaylist**
|
||||
- **Holodex**
|
||||
- **HotNewHipHop**: (**Currently broken**)
|
||||
- **hotstar**
|
||||
- **hotstar:playlist**
|
||||
- **hotstar:season**
|
||||
- **hotstar**: JioHotstar
|
||||
- **hotstar:series**
|
||||
- **hrfernsehen**
|
||||
- **HRTi**: [*hrti*](## "netrc machine")
|
||||
@@ -647,8 +645,6 @@ 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**
|
||||
@@ -1299,6 +1295,7 @@ 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**
|
||||
|
||||
@@ -478,6 +478,10 @@ 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)
|
||||
|
||||
@@ -133,6 +133,11 @@ _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 = [
|
||||
|
||||
@@ -5,47 +5,46 @@ import time
|
||||
from .common import FileDownloader
|
||||
from .external import FFmpegFD
|
||||
from ..networking import Request
|
||||
from ..utils import DownloadError, str_or_none, try_get
|
||||
from ..networking.websocket import WebSocketResponse
|
||||
from ..utils import DownloadError, str_or_none, truncate_string
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class NiconicoLiveFD(FileDownloader):
|
||||
""" Downloads niconico live without being stopped """
|
||||
|
||||
def real_download(self, filename, info_dict):
|
||||
video_id = info_dict['video_id']
|
||||
ws_url = info_dict['url']
|
||||
ws_extractor = info_dict['ws']
|
||||
ws_origin_host = info_dict['origin']
|
||||
live_quality = info_dict.get('live_quality', 'high')
|
||||
live_latency = info_dict.get('live_latency', 'high')
|
||||
video_id = info_dict['id']
|
||||
opts = info_dict['downloader_options']
|
||||
quality, ws_extractor, ws_url = opts['max_quality'], opts['ws'], opts['ws_url']
|
||||
dl = FFmpegFD(self.ydl, self.params or {})
|
||||
|
||||
new_info_dict = info_dict.copy()
|
||||
new_info_dict.update({
|
||||
'protocol': 'm3u8',
|
||||
})
|
||||
new_info_dict['protocol'] = 'm3u8'
|
||||
|
||||
def communicate_ws(reconnect):
|
||||
if reconnect:
|
||||
ws = self.ydl.urlopen(Request(ws_url, headers={'Origin': f'https://{ws_origin_host}'}))
|
||||
# Support --load-info-json as if it is a reconnect attempt
|
||||
if reconnect or not isinstance(ws_extractor, WebSocketResponse):
|
||||
ws = self.ydl.urlopen(Request(
|
||||
ws_url, headers={'Origin': 'https://live.nicovideo.jp'}))
|
||||
if self.ydl.params.get('verbose', False):
|
||||
self.to_screen('[debug] Sending startWatching request')
|
||||
self.write_debug('Sending startWatching request')
|
||||
ws.send(json.dumps({
|
||||
'type': 'startWatching',
|
||||
'data': {
|
||||
'reconnect': True,
|
||||
'room': {
|
||||
'commentable': True,
|
||||
'protocol': 'webSocket',
|
||||
},
|
||||
'stream': {
|
||||
'quality': live_quality,
|
||||
'protocol': 'hls+fmp4',
|
||||
'latency': live_latency,
|
||||
'accessRightMethod': 'single_cookie',
|
||||
'chasePlay': False,
|
||||
'latency': 'high',
|
||||
'protocol': 'hls',
|
||||
'quality': quality,
|
||||
},
|
||||
'room': {
|
||||
'protocol': 'webSocket',
|
||||
'commentable': True,
|
||||
},
|
||||
'reconnect': True,
|
||||
},
|
||||
'type': 'startWatching',
|
||||
}))
|
||||
else:
|
||||
ws = ws_extractor
|
||||
@@ -58,7 +57,6 @@ 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':
|
||||
@@ -66,12 +64,10 @@ class NiconicoLiveFD(FileDownloader):
|
||||
return True
|
||||
elif data.get('type') == 'error':
|
||||
self.write_debug(data)
|
||||
message = try_get(data, lambda x: x['body']['code'], str) or recv
|
||||
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
|
||||
return DownloadError(message)
|
||||
elif self.ydl.params.get('verbose', False):
|
||||
if len(recv) > 100:
|
||||
recv = recv[:100] + '...'
|
||||
self.to_screen(f'[debug] Server said: {recv}')
|
||||
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
|
||||
|
||||
def ws_main():
|
||||
reconnect = False
|
||||
@@ -81,7 +77,8 @@ class NiconicoLiveFD(FileDownloader):
|
||||
if ret is True:
|
||||
return
|
||||
except BaseException as e:
|
||||
self.to_screen('[{}] {}: Connection error occured, reconnecting after 10 seconds: {}'.format('niconico:live', video_id, str_or_none(e)))
|
||||
self.to_screen(
|
||||
f'[niconico:live] {video_id}: Connection error occured, reconnecting after 10 seconds: {e}')
|
||||
time.sleep(10)
|
||||
continue
|
||||
finally:
|
||||
|
||||
@@ -805,9 +805,7 @@ from .holodex import HolodexIE
|
||||
from .hotnewhiphop import HotNewHipHopIE
|
||||
from .hotstar import (
|
||||
HotStarIE,
|
||||
HotStarPlaylistIE,
|
||||
HotStarPrefixIE,
|
||||
HotStarSeasonIE,
|
||||
HotStarSeriesIE,
|
||||
)
|
||||
from .hrefli import HrefLiRedirectIE
|
||||
@@ -921,10 +919,6 @@ from .japandiet import (
|
||||
ShugiinItvVodIE,
|
||||
)
|
||||
from .jeuxvideo import JeuxVideoIE
|
||||
from .jiocinema import (
|
||||
JioCinemaIE,
|
||||
JioCinemaSeriesIE,
|
||||
)
|
||||
from .jiosaavn import (
|
||||
JioSaavnAlbumIE,
|
||||
JioSaavnArtistIE,
|
||||
@@ -1830,6 +1824,7 @@ 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,
|
||||
|
||||
@@ -1226,6 +1226,26 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
|
||||
'id': '313580179',
|
||||
},
|
||||
'playlist_mincount': 92,
|
||||
}, {
|
||||
# Hidden-mode collection
|
||||
'url': 'https://space.bilibili.com/3669403/video',
|
||||
'info_dict': {
|
||||
'id': '3669403',
|
||||
},
|
||||
'playlist': [{
|
||||
'info_dict': {
|
||||
'_type': 'playlist',
|
||||
'id': '3669403_3958082',
|
||||
'title': '合集·直播回放',
|
||||
'description': '',
|
||||
'uploader': '月路Yuel',
|
||||
'uploader_id': '3669403',
|
||||
'timestamp': int,
|
||||
'upload_date': str,
|
||||
'thumbnail': str,
|
||||
},
|
||||
}],
|
||||
'params': {'playlist_items': '7'},
|
||||
}]
|
||||
|
||||
def _real_extract(self, url):
|
||||
@@ -1282,8 +1302,14 @@ class BilibiliSpaceVideoIE(BilibiliSpaceBaseIE):
|
||||
}
|
||||
|
||||
def get_entries(page_data):
|
||||
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'])
|
||||
for entry in traverse_obj(page_data, ('list', 'vlist', ..., {dict})):
|
||||
if traverse_obj(entry, ('meta', 'attribute')) == 156:
|
||||
# hidden-mode collection doesn't show its videos in uploads; extract as playlist instead
|
||||
yield self.url_result(
|
||||
f'https://space.bilibili.com/{entry["mid"]}/lists/{entry["meta"]["id"]}?type=season',
|
||||
BilibiliCollectionListIE, f'{entry["mid"]}_{entry["meta"]["id"]}')
|
||||
else:
|
||||
yield self.url_result(f'https://www.bilibili.com/video/{entry["bvid"]}', BiliBiliIE, entry['bvid'])
|
||||
|
||||
metadata, paged_list = self._extract_playlist(fetch_page, get_metadata, get_entries)
|
||||
return self.playlist_result(paged_list, playlist_id)
|
||||
|
||||
@@ -263,6 +263,9 @@ class InfoExtractor:
|
||||
* http_chunk_size Chunk size for HTTP downloads
|
||||
* ffmpeg_args Extra arguments for ffmpeg downloader (input)
|
||||
* ffmpeg_args_out Extra arguments for ffmpeg downloader (output)
|
||||
* ws (NiconicoLiveFD only) WebSocketResponse
|
||||
* ws_url (NiconicoLiveFD only) Websockets URL
|
||||
* max_quality (NiconicoLiveFD only) Max stream quality string
|
||||
* is_dash_periods Whether the format is a result of merging
|
||||
multiple DASH periods.
|
||||
RTMP formats can also have the additional fields: page_url,
|
||||
|
||||
@@ -17,8 +17,140 @@ from ..utils import (
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class FloatplaneIE(InfoExtractor):
|
||||
class FloatplaneBaseIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
post_id = self._match_id(url)
|
||||
|
||||
post_data = self._download_json(
|
||||
f'{self._BASE_URL}/api/v3/content/post', post_id, query={'id': post_id},
|
||||
note='Downloading post data', errnote='Unable to download post data',
|
||||
impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
|
||||
raise ExtractorError('Post does not contain a video or audio track', expected=True)
|
||||
|
||||
uploader_url = format_field(
|
||||
post_data, [('creator', 'urlname')], f'{self._BASE_URL}/channel/%s/home') or None
|
||||
|
||||
common_info = {
|
||||
'uploader_url': uploader_url,
|
||||
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
|
||||
'availability': self._availability(needs_subscription=True),
|
||||
**traverse_obj(post_data, {
|
||||
'uploader': ('creator', 'title', {str}),
|
||||
'uploader_id': ('creator', 'id', {str}),
|
||||
'channel': ('channel', 'title', {str}),
|
||||
'channel_id': ('channel', 'id', {str}),
|
||||
'release_timestamp': ('releaseDate', {parse_iso8601}),
|
||||
}),
|
||||
}
|
||||
|
||||
items = []
|
||||
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
|
||||
media_id = media['id']
|
||||
media_typ = media.get('type') or 'video'
|
||||
|
||||
metadata = self._download_json(
|
||||
f'{self._BASE_URL}/api/v3/content/{media_typ}', media_id, query={'id': media_id},
|
||||
note=f'Downloading {media_typ} metadata', impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
stream = self._download_json(
|
||||
f'{self._BASE_URL}/api/v2/cdn/delivery', media_id, query={
|
||||
'type': 'vod' if media_typ == 'video' else 'aod',
|
||||
'guid': metadata['guid'],
|
||||
}, note=f'Downloading {media_typ} stream data',
|
||||
impersonate=self._IMPERSONATE_TARGET)
|
||||
|
||||
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
|
||||
|
||||
def format_path(params):
|
||||
path = path_template
|
||||
for i, val in (params or {}).items():
|
||||
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
|
||||
return path
|
||||
|
||||
formats = []
|
||||
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
|
||||
url = urljoin(stream['cdn'], format_path(traverse_obj(
|
||||
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
|
||||
format_id = traverse_obj(quality, ('name', {str}))
|
||||
hls_aes = {}
|
||||
m3u8_data = None
|
||||
|
||||
# If we need impersonation for the API, then we need it for HLS keys too: extract in advance
|
||||
if self._IMPERSONATE_TARGET is not None:
|
||||
m3u8_data = self._download_webpage(
|
||||
url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
|
||||
note=join_nonempty('Downloading', format_id, 'm3u8 information', delim=' '),
|
||||
errnote=join_nonempty('Failed to download', format_id, 'm3u8 information', delim=' '))
|
||||
if not m3u8_data:
|
||||
continue
|
||||
|
||||
key_url = self._search_regex(
|
||||
r'#EXT-X-KEY:METHOD=AES-128,URI="(https?://[^"]+)"',
|
||||
m3u8_data, 'HLS AES key URI', default=None)
|
||||
if key_url:
|
||||
urlh = self._request_webpage(
|
||||
key_url, media_id, fatal=False, impersonate=self._IMPERSONATE_TARGET, headers=self._HEADERS,
|
||||
note=join_nonempty('Downloading', format_id, 'HLS AES key', delim=' '),
|
||||
errnote=join_nonempty('Failed to download', format_id, 'HLS AES key', delim=' '))
|
||||
if urlh:
|
||||
hls_aes['key'] = urlh.read().hex()
|
||||
|
||||
formats.append({
|
||||
**traverse_obj(quality, {
|
||||
'format_note': ('label', {str}),
|
||||
'width': ('width', {int}),
|
||||
'height': ('height', {int}),
|
||||
}),
|
||||
**parse_codecs(quality.get('codecs')),
|
||||
'url': url,
|
||||
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
|
||||
'format_id': format_id,
|
||||
'hls_media_playlist_data': m3u8_data,
|
||||
'hls_aes': hls_aes or None,
|
||||
})
|
||||
items.append({
|
||||
**common_info,
|
||||
'id': media_id,
|
||||
**traverse_obj(metadata, {
|
||||
'title': ('title', {str}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
post_info = {
|
||||
**common_info,
|
||||
'id': post_id,
|
||||
'display_id': post_id,
|
||||
**traverse_obj(post_data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('text', {clean_html}),
|
||||
'like_count': ('likes', {int_or_none}),
|
||||
'dislike_count': ('dislikes', {int_or_none}),
|
||||
'comment_count': ('comments', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'http_headers': self._HEADERS,
|
||||
}
|
||||
|
||||
if len(items) > 1:
|
||||
return self.playlist_result(items, **post_info)
|
||||
|
||||
post_info.update(items[0])
|
||||
return post_info
|
||||
|
||||
|
||||
class FloatplaneIE(FloatplaneBaseIE):
|
||||
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/post/(?P<id>\w+)'
|
||||
_BASE_URL = 'https://www.floatplane.com'
|
||||
_IMPERSONATE_TARGET = None
|
||||
_HEADERS = {
|
||||
'Origin': _BASE_URL,
|
||||
'Referer': f'{_BASE_URL}/',
|
||||
}
|
||||
_TESTS = [{
|
||||
'url': 'https://www.floatplane.com/post/2Yf3UedF7C',
|
||||
'info_dict': {
|
||||
@@ -170,105 +302,9 @@ class FloatplaneIE(InfoExtractor):
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._get_cookies('https://www.floatplane.com').get('sails.sid'):
|
||||
if not self._get_cookies(self._BASE_URL).get('sails.sid'):
|
||||
self.raise_login_required()
|
||||
|
||||
def _real_extract(self, url):
|
||||
post_id = self._match_id(url)
|
||||
|
||||
post_data = self._download_json(
|
||||
'https://www.floatplane.com/api/v3/content/post', post_id, query={'id': post_id},
|
||||
note='Downloading post data', errnote='Unable to download post data')
|
||||
|
||||
if not any(traverse_obj(post_data, ('metadata', ('hasVideo', 'hasAudio')))):
|
||||
raise ExtractorError('Post does not contain a video or audio track', expected=True)
|
||||
|
||||
uploader_url = format_field(
|
||||
post_data, [('creator', 'urlname')], 'https://www.floatplane.com/channel/%s/home') or None
|
||||
|
||||
common_info = {
|
||||
'uploader_url': uploader_url,
|
||||
'channel_url': urljoin(f'{uploader_url}/', traverse_obj(post_data, ('channel', 'urlname'))),
|
||||
'availability': self._availability(needs_subscription=True),
|
||||
**traverse_obj(post_data, {
|
||||
'uploader': ('creator', 'title', {str}),
|
||||
'uploader_id': ('creator', 'id', {str}),
|
||||
'channel': ('channel', 'title', {str}),
|
||||
'channel_id': ('channel', 'id', {str}),
|
||||
'release_timestamp': ('releaseDate', {parse_iso8601}),
|
||||
}),
|
||||
}
|
||||
|
||||
items = []
|
||||
for media in traverse_obj(post_data, (('videoAttachments', 'audioAttachments'), ...)):
|
||||
media_id = media['id']
|
||||
media_typ = media.get('type') or 'video'
|
||||
|
||||
metadata = self._download_json(
|
||||
f'https://www.floatplane.com/api/v3/content/{media_typ}', media_id, query={'id': media_id},
|
||||
note=f'Downloading {media_typ} metadata')
|
||||
|
||||
stream = self._download_json(
|
||||
'https://www.floatplane.com/api/v2/cdn/delivery', media_id, query={
|
||||
'type': 'vod' if media_typ == 'video' else 'aod',
|
||||
'guid': metadata['guid'],
|
||||
}, note=f'Downloading {media_typ} stream data')
|
||||
|
||||
path_template = traverse_obj(stream, ('resource', 'uri', {str}))
|
||||
|
||||
def format_path(params):
|
||||
path = path_template
|
||||
for i, val in (params or {}).items():
|
||||
path = path.replace(f'{{qualityLevelParams.{i}}}', val)
|
||||
return path
|
||||
|
||||
formats = []
|
||||
for quality in traverse_obj(stream, ('resource', 'data', 'qualityLevels', ...)):
|
||||
url = urljoin(stream['cdn'], format_path(traverse_obj(
|
||||
stream, ('resource', 'data', 'qualityLevelParams', quality['name'], {dict}))))
|
||||
formats.append({
|
||||
**traverse_obj(quality, {
|
||||
'format_id': ('name', {str}),
|
||||
'format_note': ('label', {str}),
|
||||
'width': ('width', {int}),
|
||||
'height': ('height', {int}),
|
||||
}),
|
||||
**parse_codecs(quality.get('codecs')),
|
||||
'url': url,
|
||||
'ext': determine_ext(url.partition('/chunk.m3u8')[0], 'mp4'),
|
||||
})
|
||||
|
||||
items.append({
|
||||
**common_info,
|
||||
'id': media_id,
|
||||
**traverse_obj(metadata, {
|
||||
'title': ('title', {str}),
|
||||
'duration': ('duration', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
'formats': formats,
|
||||
})
|
||||
|
||||
post_info = {
|
||||
**common_info,
|
||||
'id': post_id,
|
||||
'display_id': post_id,
|
||||
**traverse_obj(post_data, {
|
||||
'title': ('title', {str}),
|
||||
'description': ('text', {clean_html}),
|
||||
'like_count': ('likes', {int_or_none}),
|
||||
'dislike_count': ('dislikes', {int_or_none}),
|
||||
'comment_count': ('comments', {int_or_none}),
|
||||
'thumbnail': ('thumbnail', 'path', {url_or_none}),
|
||||
}),
|
||||
}
|
||||
|
||||
if len(items) > 1:
|
||||
return self.playlist_result(items, **post_info)
|
||||
|
||||
post_info.update(items[0])
|
||||
return post_info
|
||||
|
||||
|
||||
class FloatplaneChannelIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:(?:www|beta)\.)?floatplane\.com/channel/(?P<id>[\w-]+)/home(?:/(?P<channel>[\w-]+))?'
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
import functools
|
||||
import hashlib
|
||||
import hmac
|
||||
import json
|
||||
@@ -9,18 +10,20 @@ 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):
|
||||
@@ -29,57 +32,86 @@ 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()
|
||||
|
||||
if cookies and cookies.get('userUP'):
|
||||
token = cookies.get('userUP').value
|
||||
else:
|
||||
token = self._download_json(
|
||||
f'{self._API_URL}/um/v3/users',
|
||||
video_id, note='Downloading token',
|
||||
data=json.dumps({'device_ids': [{'id': str(uuid.uuid4()), 'type': 'device_id'}]}).encode(),
|
||||
headers={
|
||||
'hotstarauth': auth,
|
||||
'x-hs-platform': 'PCTV', # or 'web'
|
||||
'Content-Type': 'application/json',
|
||||
})['user_identity']
|
||||
|
||||
response = self._download_json(
|
||||
f'{self._API_URL}/{path}', video_id, query=query,
|
||||
f'{self._API_URL_V2}/{path}', video_id, query=query,
|
||||
headers={
|
||||
'user-agent': 'Disney+;in.startv.hotstar.dplus.tv/23.08.14.4.2915 (Android/13)',
|
||||
'hotstarauth': auth,
|
||||
'x-hs-appversion': '6.72.2',
|
||||
'x-hs-platform': 'web',
|
||||
'x-hs-usertoken': token,
|
||||
'x-hs-usertoken': cookies['userUP'].value,
|
||||
'x-hs-device-id': traverse_obj(cookies, ('deviceId', 'value')) or str(uuid.uuid4()),
|
||||
'x-hs-client': 'platform:androidtv;app_id:in.startv.hotstar.dplus.tv;app_version:23.08.14.4;os:Android;os_version:13;schema_version:0.0.970',
|
||||
'x-hs-platform': 'androidtv',
|
||||
'content-type': 'application/json',
|
||||
})
|
||||
|
||||
if response['message'] != "Playback URL's fetched successfully":
|
||||
raise ExtractorError(
|
||||
response['message'], expected=True)
|
||||
return response['data']
|
||||
if not traverse_obj(response, ('success', {dict})):
|
||||
raise ExtractorError('API call was unsuccessful')
|
||||
return response['success']
|
||||
|
||||
def _call_api_v2(self, path, video_id, st=None, cookies=None):
|
||||
return self._call_api_impl(
|
||||
f'{path}/content/{video_id}', video_id, st=st, cookies=cookies, query={
|
||||
'desired-config': 'audio_channel:stereo|container:fmp4|dynamic_range:hdr|encryption:plain|ladder:tv|package:dash|resolution:fhd|subs-tag:HotstarVIP|video_codec:h265',
|
||||
'device-id': cookies.get('device_id').value if cookies.get('device_id') else str(uuid.uuid4()),
|
||||
'os-name': 'Windows',
|
||||
'os-version': '10',
|
||||
})
|
||||
def _call_api_v2(self, path, video_id, content_type, cookies=None, st=None):
|
||||
return self._call_api_impl(f'{path}', video_id, query={
|
||||
'content_id': video_id,
|
||||
'filters': f'content_type={content_type}',
|
||||
'client_capabilities': json.dumps({
|
||||
'package': ['dash', 'hls'],
|
||||
'container': ['fmp4br', 'fmp4'],
|
||||
'ads': ['non_ssai', 'ssai'],
|
||||
'audio_channel': ['atmos', 'dolby51', 'stereo'],
|
||||
'encryption': ['plain', 'widevine'], # wv only so we can raise appropriate error
|
||||
'video_codec': ['h265', 'h264'],
|
||||
'ladder': ['tv', 'full'],
|
||||
'resolution': ['4k', 'hd'],
|
||||
'true_resolution': ['4k', 'hd'],
|
||||
'dynamic_range': ['hdr', 'sdr'],
|
||||
}, separators=(',', ':')),
|
||||
'drm_parameters': json.dumps({
|
||||
'widevine_security_level': ['SW_SECURE_DECODE', 'SW_SECURE_CRYPTO'],
|
||||
'hdcp_version': ['HDCP_V2_2', 'HDCP_V2_1', 'HDCP_V2', 'HDCP_V1'],
|
||||
}, separators=(',', ':')),
|
||||
}, st=st, cookies=cookies)
|
||||
|
||||
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, video['contentId'])
|
||||
@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 _fetch_page(self, path, item_id, name, query, root, page):
|
||||
results = self._call_api_v1(
|
||||
path, item_id, note=f'Downloading {name} page {page + 1} JSON', query={
|
||||
**query,
|
||||
'tao': page * self._PAGE_SIZE,
|
||||
'tas': self._PAGE_SIZE,
|
||||
})['body']['results']
|
||||
|
||||
for video in traverse_obj(results, (('assets', None), 'items', lambda _, v: v['contentId'])):
|
||||
yield self.url_result(
|
||||
HotStarIE._video_url(video['contentId'], root=root), HotStarIE, **self._parse_metadata_v1(video))
|
||||
|
||||
|
||||
class HotStarIE(HotStarBaseIE):
|
||||
IE_NAME = 'hotstar'
|
||||
IE_DESC = 'JioHotstar'
|
||||
_VALID_URL = r'''(?x)
|
||||
https?://(?:www\.)?hotstar\.com(?:/in)?/(?!in/)
|
||||
(?:
|
||||
@@ -114,15 +146,16 @@ class HotStarIE(HotStarBaseIE):
|
||||
'upload_date': '20190501',
|
||||
'duration': 1219,
|
||||
'channel': 'StarPlus',
|
||||
'channel_id': '3',
|
||||
'channel_id': '821',
|
||||
'series': 'Ek Bhram - Sarvagun Sampanna',
|
||||
'season': 'Chapter 1',
|
||||
'season_number': 1,
|
||||
'season_id': '6771',
|
||||
'season_id': '1260004607',
|
||||
'episode': 'Janhvi Targets Suman',
|
||||
'episode_number': 8,
|
||||
},
|
||||
}, {
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, { # Metadata call gets HTTP Error 504 with tas=10000
|
||||
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/anupama-anuj-share-a-moment/1000282843',
|
||||
'info_dict': {
|
||||
'id': '1000282843',
|
||||
@@ -134,14 +167,14 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'StarPlus',
|
||||
'series': 'Anupama',
|
||||
'season_number': 1,
|
||||
'season_id': '7399',
|
||||
'season_id': '1260022018',
|
||||
'upload_date': '20230307',
|
||||
'episode': 'Anupama, Anuj Share a Moment',
|
||||
'episode_number': 853,
|
||||
'duration': 1272,
|
||||
'channel_id': '3',
|
||||
'duration': 1266,
|
||||
'channel_id': '821',
|
||||
},
|
||||
'skip': 'HTTP Error 504: Gateway Time-out', # XXX: Investigate 504 errors on some episodes
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/shows/kana-kaanum-kaalangal/1260097087/back-to-school/1260097320',
|
||||
'info_dict': {
|
||||
@@ -154,14 +187,15 @@ class HotStarIE(HotStarBaseIE):
|
||||
'channel': 'Hotstar Specials',
|
||||
'series': 'Kana Kaanum Kaalangal',
|
||||
'season_number': 1,
|
||||
'season_id': '9441',
|
||||
'season_id': '1260097089',
|
||||
'upload_date': '20220421',
|
||||
'episode': 'Back To School',
|
||||
'episode_number': 1,
|
||||
'duration': 1810,
|
||||
'channel_id': '54',
|
||||
'channel_id': '1260003991',
|
||||
},
|
||||
}, {
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, { # Metadata call gets HTTP Error 504 with tas=10000
|
||||
'url': 'https://www.hotstar.com/in/clips/e3-sairat-kahani-pyaar-ki/1000262286',
|
||||
'info_dict': {
|
||||
'id': '1000262286',
|
||||
@@ -173,6 +207,7 @@ class HotStarIE(HotStarBaseIE):
|
||||
'timestamp': 1622943900,
|
||||
'duration': 5395,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/movies/premam/1000091195',
|
||||
'info_dict': {
|
||||
@@ -180,12 +215,13 @@ class HotStarIE(HotStarBaseIE):
|
||||
'ext': 'mp4',
|
||||
'title': 'Premam',
|
||||
'release_year': 2015,
|
||||
'description': 'md5:d833c654e4187b5e34757eafb5b72d7f',
|
||||
'description': 'md5:096cd8aaae8dab56524823dc19dfa9f7',
|
||||
'timestamp': 1462149000,
|
||||
'upload_date': '20160502',
|
||||
'episode': 'Premam',
|
||||
'duration': 8994,
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/movies/radha-gopalam/1000057157',
|
||||
'only_matching': True,
|
||||
@@ -208,6 +244,13 @@ class HotStarIE(HotStarBaseIE):
|
||||
None: 'content',
|
||||
}
|
||||
|
||||
_CONTENT_TYPE = {
|
||||
'movie': 'MOVIE',
|
||||
'episode': 'EPISODE',
|
||||
'match': 'SPORT',
|
||||
'content': 'CLIPS',
|
||||
}
|
||||
|
||||
_IGNORE_MAP = {
|
||||
'res': 'resolution',
|
||||
'vcodec': 'video_codec',
|
||||
@@ -229,38 +272,48 @@ class HotStarIE(HotStarBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, video_type = self._match_valid_url(url).group('id', 'type')
|
||||
video_type = self._TYPE.get(video_type, video_type)
|
||||
video_type = self._TYPE[video_type]
|
||||
cookies = self._get_cookies(url) # Cookies before any request
|
||||
|
||||
video_data = traverse_obj(
|
||||
self._call_api_v1(
|
||||
f'{video_type}/detail', video_id, fatal=False, query={'tas': 10000, 'contentId': video_id}),
|
||||
('body', 'results', 'item', {dict})) or {}
|
||||
if not self.get_param('allow_unplayable_formats') and video_data.get('drmProtected'):
|
||||
self._call_api_v1(f'{video_type}/detail', video_id, fatal=False, query={
|
||||
'tas': 5, # See https://github.com/yt-dlp/yt-dlp/issues/7946
|
||||
'contentId': video_id,
|
||||
}), ('body', 'results', 'item', {dict})) or {}
|
||||
|
||||
if video_data.get('drmProtected'):
|
||||
self.report_drm(video_id)
|
||||
|
||||
# See https://github.com/yt-dlp/yt-dlp/issues/396
|
||||
st = self._download_webpage_handle(f'{self._BASE_URL}/in', video_id)[1].headers.get('x-origin-date')
|
||||
|
||||
geo_restricted = False
|
||||
formats, subs = [], {}
|
||||
formats, subs, has_drm = [], {}, False
|
||||
headers = {'Referer': f'{self._BASE_URL}/in'}
|
||||
content_type = traverse_obj(video_data, ('contentType', {str})) or self._CONTENT_TYPE[video_type]
|
||||
|
||||
# change to v2 in the future
|
||||
playback_sets = self._call_api_v2('play/v1/playback', video_id, st=st, cookies=cookies)['playBackSets']
|
||||
for playback_set in playback_sets:
|
||||
if not isinstance(playback_set, dict):
|
||||
continue
|
||||
tags = str_or_none(playback_set.get('tagsCombination')) or ''
|
||||
# See https://github.com/yt-dlp/yt-dlp/issues/396
|
||||
st = self._request_webpage(
|
||||
f'{self._BASE_URL}/in', video_id, 'Fetching server time').get_header('x-origin-date')
|
||||
watch = self._call_api_v2('pages/watch', video_id, content_type, cookies=cookies, st=st)
|
||||
player_config = traverse_obj(watch, (
|
||||
'page', 'spaces', 'player', 'widget_wrappers', lambda _, v: v['template'] == 'PlayerWidget',
|
||||
'widget', 'data', 'player_config', {dict}, any, {require('player config')}))
|
||||
|
||||
for playback_set in traverse_obj(player_config, (
|
||||
('media_asset', 'media_asset_v2'),
|
||||
('primary', 'fallback'),
|
||||
all, lambda _, v: url_or_none(v['content_url']),
|
||||
)):
|
||||
tags = str_or_none(playback_set.get('playback_tags')) or ''
|
||||
if any(f'{prefix}:{ignore}' in tags
|
||||
for key, prefix in self._IGNORE_MAP.items()
|
||||
for ignore in self._configuration_arg(key)):
|
||||
continue
|
||||
|
||||
format_url = url_or_none(playback_set.get('playbackUrl'))
|
||||
if not format_url:
|
||||
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
|
||||
if tag_dict.get('encryption') not in ('plain', None):
|
||||
has_drm = True
|
||||
continue
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', format_url)
|
||||
|
||||
format_url = re.sub(r'(?<=//staragvod)(\d)', r'web\1', playback_set['content_url'])
|
||||
ext = determine_ext(format_url)
|
||||
|
||||
current_formats, current_subs = [], {}
|
||||
@@ -280,14 +333,12 @@ class HotStarIE(HotStarBaseIE):
|
||||
'height': int_or_none(playback_set.get('height')),
|
||||
}]
|
||||
except ExtractorError as e:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status == 403:
|
||||
if isinstance(e.cause, HTTPError) and e.cause.status in (403, 474):
|
||||
geo_restricted = True
|
||||
else:
|
||||
self.write_debug(e)
|
||||
continue
|
||||
|
||||
tag_dict = dict((*t.split(':', 1), None)[:2] for t in tags.split(';'))
|
||||
if tag_dict.get('encryption') not in ('plain', None):
|
||||
for f in current_formats:
|
||||
f['has_drm'] = True
|
||||
for f in current_formats:
|
||||
for k, v in self._TAG_FIELDS.items():
|
||||
if not f.get(k):
|
||||
@@ -299,6 +350,11 @@ 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,
|
||||
@@ -310,27 +366,17 @@ 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')),
|
||||
}
|
||||
|
||||
|
||||
@@ -371,64 +417,6 @@ 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+))/?(?:[#?]|$)'
|
||||
@@ -443,25 +431,29 @@ class HotStarSeriesIE(HotStarBaseIE):
|
||||
'info_dict': {
|
||||
'id': '1260050431',
|
||||
},
|
||||
'playlist_mincount': 43,
|
||||
'playlist_mincount': 42,
|
||||
}, {
|
||||
'url': 'https://www.hotstar.com/in/tv/mahabharat/435/',
|
||||
'info_dict': {
|
||||
'id': '435',
|
||||
},
|
||||
'playlist_mincount': 267,
|
||||
}, {
|
||||
}, { # HTTP Error 504 with tas=10000 (possibly because total size is over 1000 items?)
|
||||
'url': 'https://www.hotstar.com/in/shows/anupama/1260022017/',
|
||||
'info_dict': {
|
||||
'id': '1260022017',
|
||||
},
|
||||
'playlist_mincount': 940,
|
||||
'playlist_mincount': 1601,
|
||||
}]
|
||||
_PAGE_SIZE = 100
|
||||
|
||||
def _real_extract(self, url):
|
||||
url, series_id = self._match_valid_url(url).groups()
|
||||
id_ = self._call_api_v1(
|
||||
url, series_id = self._match_valid_url(url).group('url', 'id')
|
||||
eid = self._call_api_v1(
|
||||
'show/detail', series_id, query={'contentId': series_id})['body']['results']['item']['id']
|
||||
|
||||
return self.playlist_result(self._playlist_entries(
|
||||
'tray/g/1/items', series_id, url, query={'tao': 0, 'tas': 10000, 'etid': 0, 'eid': id_}), series_id)
|
||||
entries = OnDemandPagedList(functools.partial(
|
||||
self._fetch_page, 'tray/g/1/items', series_id,
|
||||
'series', {'etid': 0, 'eid': eid}, url), self._PAGE_SIZE)
|
||||
|
||||
return self.playlist_result(entries, series_id)
|
||||
|
||||
@@ -1,408 +0,0 @@
|
||||
import base64
|
||||
import itertools
|
||||
import json
|
||||
import random
|
||||
import re
|
||||
import string
|
||||
import time
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..utils import (
|
||||
ExtractorError,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
jwt_decode_hs256,
|
||||
parse_age_limit,
|
||||
try_call,
|
||||
url_or_none,
|
||||
)
|
||||
from ..utils.traversal import traverse_obj
|
||||
|
||||
|
||||
class JioCinemaBaseIE(InfoExtractor):
|
||||
_NETRC_MACHINE = 'jiocinema'
|
||||
_GEO_BYPASS = False
|
||||
_ACCESS_TOKEN = None
|
||||
_REFRESH_TOKEN = None
|
||||
_GUEST_TOKEN = None
|
||||
_USER_ID = None
|
||||
_DEVICE_ID = None
|
||||
_API_HEADERS = {'Origin': 'https://www.jiocinema.com', 'Referer': 'https://www.jiocinema.com/'}
|
||||
_APP_NAME = {'appName': 'RJIL_JioCinema'}
|
||||
_APP_VERSION = {'appVersion': '5.0.0'}
|
||||
_API_SIGNATURES = 'o668nxgzwff'
|
||||
_METADATA_API_BASE = 'https://content-jiovoot.voot.com/psapi'
|
||||
_ACCESS_HINT = 'the `accessToken` from your browser local storage'
|
||||
_LOGIN_HINT = (
|
||||
'Log in with "-u phone -p <PHONE_NUMBER>" to authenticate with OTP, '
|
||||
f'or use "-u token -p <ACCESS_TOKEN>" to log in with {_ACCESS_HINT}. '
|
||||
'If you have previously logged in with yt-dlp and your session '
|
||||
'has been cached, you can use "-u device -p <DEVICE_ID>"')
|
||||
|
||||
def _cache_token(self, token_type):
|
||||
assert token_type in ('access', 'refresh', 'all')
|
||||
if token_type in ('access', 'all'):
|
||||
self.cache.store(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-access', JioCinemaBaseIE._ACCESS_TOKEN)
|
||||
if token_type in ('refresh', 'all'):
|
||||
self.cache.store(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh', JioCinemaBaseIE._REFRESH_TOKEN)
|
||||
|
||||
def _call_api(self, url, video_id, note='Downloading API JSON', headers={}, data={}):
|
||||
return self._download_json(
|
||||
url, video_id, note, data=json.dumps(data, separators=(',', ':')).encode(), headers={
|
||||
'Content-Type': 'application/json',
|
||||
'Accept': 'application/json',
|
||||
**self._API_HEADERS,
|
||||
**headers,
|
||||
}, expected_status=(400, 403, 474))
|
||||
|
||||
def _call_auth_api(self, service, endpoint, note, headers={}, data={}):
|
||||
return self._call_api(
|
||||
f'https://auth-jiocinema.voot.com/{service}service/apis/v4/{endpoint}',
|
||||
None, note=note, headers=headers, data=data)
|
||||
|
||||
def _refresh_token(self):
|
||||
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._DEVICE_ID:
|
||||
raise ExtractorError('User token has expired', expected=True)
|
||||
response = self._call_auth_api(
|
||||
'token', 'refreshtoken', 'Refreshing token',
|
||||
headers={'accesstoken': self._ACCESS_TOKEN}, data={
|
||||
**self._APP_NAME,
|
||||
'deviceId': self._DEVICE_ID,
|
||||
'refreshToken': self._REFRESH_TOKEN,
|
||||
**self._APP_VERSION,
|
||||
})
|
||||
refresh_token = response.get('refreshTokenId')
|
||||
if refresh_token and refresh_token != JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
|
||||
self._cache_token('refresh')
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
|
||||
self._cache_token('access')
|
||||
|
||||
def _fetch_guest_token(self):
|
||||
JioCinemaBaseIE._DEVICE_ID = ''.join(random.choices(string.digits, k=10))
|
||||
guest_token = self._call_auth_api(
|
||||
'token', 'guest', 'Downloading guest token', data={
|
||||
**self._APP_NAME,
|
||||
'deviceType': 'phone',
|
||||
'os': 'ios',
|
||||
'deviceId': self._DEVICE_ID,
|
||||
'freshLaunch': False,
|
||||
'adId': self._DEVICE_ID,
|
||||
**self._APP_VERSION,
|
||||
})
|
||||
self._GUEST_TOKEN = guest_token['authToken']
|
||||
self._USER_ID = guest_token['userId']
|
||||
|
||||
def _call_login_api(self, endpoint, guest_token, data, note):
|
||||
return self._call_auth_api(
|
||||
'user', f'loginotp/{endpoint}', note, headers={
|
||||
**self.geo_verification_headers(),
|
||||
'accesstoken': self._GUEST_TOKEN,
|
||||
**self._APP_NAME,
|
||||
**traverse_obj(guest_token, 'data', {
|
||||
'deviceType': ('deviceType', {str}),
|
||||
'os': ('os', {str}),
|
||||
})}, data=data)
|
||||
|
||||
def _is_token_expired(self, token):
|
||||
return (try_call(lambda: jwt_decode_hs256(token)['exp']) or 0) <= int(time.time() - 180)
|
||||
|
||||
def _perform_login(self, username, password):
|
||||
if self._ACCESS_TOKEN and not self._is_token_expired(self._ACCESS_TOKEN):
|
||||
return
|
||||
|
||||
UUID_RE = r'[\da-f]{8}-(?:[\da-f]{4}-){3}[\da-f]{12}'
|
||||
|
||||
if username.lower() == 'token':
|
||||
if try_call(lambda: jwt_decode_hs256(password)):
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = password
|
||||
refresh_hint = 'the `refreshToken` UUID from your browser local storage'
|
||||
refresh_token = self._configuration_arg('refresh_token', [''], ie_key=JioCinemaIE)[0]
|
||||
if not refresh_token:
|
||||
self.to_screen(
|
||||
'To extend the life of your login session, in addition to your access token, '
|
||||
'you can pass --extractor-args "jiocinema:refresh_token=REFRESH_TOKEN" '
|
||||
f'where REFRESH_TOKEN is {refresh_hint}')
|
||||
elif re.fullmatch(UUID_RE, refresh_token):
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = refresh_token
|
||||
else:
|
||||
self.report_warning(f'Invalid refresh_token value. Use {refresh_hint}')
|
||||
else:
|
||||
raise ExtractorError(
|
||||
f'The password given could not be decoded as a token; use {self._ACCESS_HINT}', expected=True)
|
||||
|
||||
elif username.lower() == 'device' and re.fullmatch(rf'(?:{UUID_RE}|\d+)', password):
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-refresh')
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = self.cache.load(JioCinemaBaseIE._NETRC_MACHINE, f'{password}-access')
|
||||
if not JioCinemaBaseIE._REFRESH_TOKEN or not JioCinemaBaseIE._ACCESS_TOKEN:
|
||||
raise ExtractorError(f'Failed to load cached tokens for device ID "{password}"', expected=True)
|
||||
|
||||
elif username.lower() == 'phone' and re.fullmatch(r'\+?\d+', password):
|
||||
self._fetch_guest_token()
|
||||
guest_token = jwt_decode_hs256(self._GUEST_TOKEN)
|
||||
initial_data = {
|
||||
'number': base64.b64encode(password.encode()).decode(),
|
||||
**self._APP_VERSION,
|
||||
}
|
||||
response = self._call_login_api('send', guest_token, initial_data, 'Requesting OTP')
|
||||
if not traverse_obj(response, ('OTPInfo', {dict})):
|
||||
raise ExtractorError('There was a problem with the phone number login attempt')
|
||||
|
||||
is_iphone = guest_token.get('os') == 'ios'
|
||||
response = self._call_login_api('verify', guest_token, {
|
||||
'deviceInfo': {
|
||||
'consumptionDeviceName': 'iPhone' if is_iphone else 'Android',
|
||||
'info': {
|
||||
'platform': {'name': 'iPhone OS' if is_iphone else 'Android'},
|
||||
'androidId': self._DEVICE_ID,
|
||||
'type': 'iOS' if is_iphone else 'Android',
|
||||
},
|
||||
},
|
||||
**initial_data,
|
||||
'otp': self._get_tfa_info('the one-time password sent to your phone'),
|
||||
}, 'Submitting OTP')
|
||||
if traverse_obj(response, 'code') == 1043:
|
||||
raise ExtractorError('Wrong OTP', expected=True)
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = response['refreshToken']
|
||||
JioCinemaBaseIE._ACCESS_TOKEN = response['authToken']
|
||||
|
||||
else:
|
||||
raise ExtractorError(self._LOGIN_HINT, expected=True)
|
||||
|
||||
user_token = jwt_decode_hs256(JioCinemaBaseIE._ACCESS_TOKEN)['data']
|
||||
JioCinemaBaseIE._USER_ID = user_token['userId']
|
||||
JioCinemaBaseIE._DEVICE_ID = user_token['deviceId']
|
||||
if JioCinemaBaseIE._REFRESH_TOKEN and username != 'device':
|
||||
self._cache_token('all')
|
||||
if self.get_param('cachedir') is not False:
|
||||
self.to_screen(
|
||||
f'NOTE: For subsequent logins you can use "-u device -p {JioCinemaBaseIE._DEVICE_ID}"')
|
||||
elif not JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
JioCinemaBaseIE._REFRESH_TOKEN = self.cache.load(
|
||||
JioCinemaBaseIE._NETRC_MACHINE, f'{JioCinemaBaseIE._DEVICE_ID}-refresh')
|
||||
if JioCinemaBaseIE._REFRESH_TOKEN:
|
||||
self._cache_token('access')
|
||||
self.to_screen(f'Logging in as device ID "{JioCinemaBaseIE._DEVICE_ID}"')
|
||||
if self._is_token_expired(JioCinemaBaseIE._ACCESS_TOKEN):
|
||||
self._refresh_token()
|
||||
|
||||
|
||||
class JioCinemaIE(JioCinemaBaseIE):
|
||||
IE_NAME = 'jiocinema'
|
||||
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/?(?:movies?/[^/?#]+/|tv-shows/(?:[^/?#]+/){3})(?P<id>\d{3,})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.jiocinema.com/tv-shows/agnisakshi-ek-samjhauta/1/pradeep-to-stop-the-wedding/3759931',
|
||||
'info_dict': {
|
||||
'id': '3759931',
|
||||
'ext': 'mp4',
|
||||
'title': 'Pradeep to stop the wedding?',
|
||||
'description': 'md5:75f72d1d1a66976633345a3de6d672b1',
|
||||
'episode': 'Pradeep to stop the wedding?',
|
||||
'episode_number': 89,
|
||||
'season': 'Agnisakshi…Ek Samjhauta-S1',
|
||||
'season_number': 1,
|
||||
'series': 'Agnisakshi Ek Samjhauta',
|
||||
'duration': 1238.0,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'age_limit': 13,
|
||||
'season_id': '3698031',
|
||||
'upload_date': '20230606',
|
||||
'timestamp': 1686009600,
|
||||
'release_date': '20230607',
|
||||
'genres': ['Drama'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}, {
|
||||
'url': 'https://www.jiocinema.com/movies/bhediya/3754021/watch',
|
||||
'info_dict': {
|
||||
'id': '3754021',
|
||||
'ext': 'mp4',
|
||||
'title': 'Bhediya',
|
||||
'description': 'md5:a6bf2900371ac2fc3f1447401a9f7bb0',
|
||||
'episode': 'Bhediya',
|
||||
'duration': 8500.0,
|
||||
'thumbnail': r're:https?://.+\.jpg',
|
||||
'age_limit': 13,
|
||||
'upload_date': '20230525',
|
||||
'timestamp': 1685026200,
|
||||
'release_date': '20230524',
|
||||
'genres': ['Comedy'],
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _extract_formats_and_subtitles(self, playback, video_id):
|
||||
m3u8_url = traverse_obj(playback, (
|
||||
'data', 'playbackUrls', lambda _, v: v['streamtype'] == 'hls', 'url', {url_or_none}, any))
|
||||
if not m3u8_url: # DRM-only content only serves dash urls
|
||||
self.report_drm(video_id)
|
||||
formats, subtitles = self._extract_m3u8_formats_and_subtitles(m3u8_url, video_id, m3u8_id='hls')
|
||||
self._remove_duplicate_formats(formats)
|
||||
|
||||
return {
|
||||
# '/_definst_/smil:vod/' m3u8 manifests claim to have 720p+ formats but max out at 480p
|
||||
'formats': traverse_obj(formats, (
|
||||
lambda _, v: '/_definst_/smil:vod/' not in v['url'] or v['height'] <= 480)),
|
||||
'subtitles': subtitles,
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
if not self._ACCESS_TOKEN and self._is_token_expired(self._GUEST_TOKEN):
|
||||
self._fetch_guest_token()
|
||||
elif self._ACCESS_TOKEN and self._is_token_expired(self._ACCESS_TOKEN):
|
||||
self._refresh_token()
|
||||
|
||||
playback = self._call_api(
|
||||
f'https://apis-jiovoot.voot.com/playbackjv/v3/{video_id}', video_id,
|
||||
'Downloading playback JSON', headers={
|
||||
**self.geo_verification_headers(),
|
||||
'accesstoken': self._ACCESS_TOKEN or self._GUEST_TOKEN,
|
||||
**self._APP_NAME,
|
||||
'deviceid': self._DEVICE_ID,
|
||||
'uniqueid': self._USER_ID,
|
||||
'x-apisignatures': self._API_SIGNATURES,
|
||||
'x-platform': 'androidweb',
|
||||
'x-platform-token': 'web',
|
||||
}, data={
|
||||
'4k': False,
|
||||
'ageGroup': '18+',
|
||||
'appVersion': '3.4.0',
|
||||
'bitrateProfile': 'xhdpi',
|
||||
'capability': {
|
||||
'drmCapability': {
|
||||
'aesSupport': 'yes',
|
||||
'fairPlayDrmSupport': 'none',
|
||||
'playreadyDrmSupport': 'none',
|
||||
'widevineDRMSupport': 'none',
|
||||
},
|
||||
'frameRateCapability': [{
|
||||
'frameRateSupport': '30fps',
|
||||
'videoQuality': '1440p',
|
||||
}],
|
||||
},
|
||||
'continueWatchingRequired': False,
|
||||
'dolby': False,
|
||||
'downloadRequest': False,
|
||||
'hevc': False,
|
||||
'kidsSafe': False,
|
||||
'manufacturer': 'Windows',
|
||||
'model': 'Windows',
|
||||
'multiAudioRequired': True,
|
||||
'osVersion': '10',
|
||||
'parentalPinValid': True,
|
||||
'x-apisignatures': self._API_SIGNATURES,
|
||||
})
|
||||
|
||||
status_code = traverse_obj(playback, ('code', {int}))
|
||||
if status_code == 474:
|
||||
self.raise_geo_restricted(countries=['IN'])
|
||||
elif status_code == 1008:
|
||||
error_msg = 'This content is only available for premium users'
|
||||
if self._ACCESS_TOKEN:
|
||||
raise ExtractorError(error_msg, expected=True)
|
||||
self.raise_login_required(f'{error_msg}. {self._LOGIN_HINT}', method=None)
|
||||
elif status_code == 400:
|
||||
raise ExtractorError('The requested content is not available', expected=True)
|
||||
elif status_code is not None and status_code != 200:
|
||||
raise ExtractorError(
|
||||
f'JioCinema says: {traverse_obj(playback, ("message", {str})) or status_code}')
|
||||
|
||||
metadata = self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/query/asset-details',
|
||||
video_id, fatal=False, query={
|
||||
'ids': f'include:{video_id}',
|
||||
'responseType': 'common',
|
||||
'devicePlatformType': 'desktop',
|
||||
})
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'http_headers': self._API_HEADERS,
|
||||
**self._extract_formats_and_subtitles(playback, video_id),
|
||||
**traverse_obj(playback, ('data', {
|
||||
# fallback metadata
|
||||
'title': ('name', {str}),
|
||||
'description': ('fullSynopsis', {str}),
|
||||
'series': ('show', 'name', {str}, filter),
|
||||
'season': ('tournamentName', {str}, {lambda x: x if x != 'Season 0' else None}),
|
||||
'season_number': ('episode', 'season', {int_or_none}, filter),
|
||||
'episode': ('fullTitle', {str}),
|
||||
'episode_number': ('episode', 'episodeNo', {int_or_none}, filter),
|
||||
'age_limit': ('ageNemonic', {parse_age_limit}),
|
||||
'duration': ('totalDuration', {float_or_none}),
|
||||
'thumbnail': ('images', {url_or_none}),
|
||||
})),
|
||||
**traverse_obj(metadata, ('result', 0, {
|
||||
'title': ('fullTitle', {str}),
|
||||
'description': ('fullSynopsis', {str}),
|
||||
'series': ('showName', {str}, filter),
|
||||
'season': ('seasonName', {str}, filter),
|
||||
'season_number': ('season', {int_or_none}),
|
||||
'season_id': ('seasonId', {str}, filter),
|
||||
'episode': ('fullTitle', {str}),
|
||||
'episode_number': ('episode', {int_or_none}),
|
||||
'timestamp': ('uploadTime', {int_or_none}),
|
||||
'release_date': ('telecastDate', {str}),
|
||||
'age_limit': ('ageNemonic', {parse_age_limit}),
|
||||
'duration': ('duration', {float_or_none}),
|
||||
'genres': ('genres', ..., {str}),
|
||||
'thumbnail': ('seo', 'ogImage', {url_or_none}),
|
||||
})),
|
||||
}
|
||||
|
||||
|
||||
class JioCinemaSeriesIE(JioCinemaBaseIE):
|
||||
IE_NAME = 'jiocinema:series'
|
||||
_VALID_URL = r'https?://(?:www\.)?jiocinema\.com/tv-shows/(?P<slug>[\w-]+)/(?P<id>\d{3,})'
|
||||
_TESTS = [{
|
||||
'url': 'https://www.jiocinema.com/tv-shows/naagin/3499917',
|
||||
'info_dict': {
|
||||
'id': '3499917',
|
||||
'title': 'naagin',
|
||||
},
|
||||
'playlist_mincount': 120,
|
||||
}, {
|
||||
'url': 'https://www.jiocinema.com/tv-shows/mtv-splitsvilla-x5/3499820',
|
||||
'info_dict': {
|
||||
'id': '3499820',
|
||||
'title': 'mtv-splitsvilla-x5',
|
||||
},
|
||||
'playlist_mincount': 310,
|
||||
}]
|
||||
|
||||
def _entries(self, series_id):
|
||||
seasons = traverse_obj(self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/view/show/{series_id}', series_id,
|
||||
'Downloading series metadata JSON', query={'responseType': 'common'}), (
|
||||
'trays', lambda _, v: v['trayId'] == 'season-by-show-multifilter',
|
||||
'trayTabs', lambda _, v: v['id']))
|
||||
|
||||
for season_num, season in enumerate(seasons, start=1):
|
||||
season_id = season['id']
|
||||
label = season.get('label') or season_num
|
||||
for page_num in itertools.count(1):
|
||||
episodes = traverse_obj(self._download_json(
|
||||
f'{self._METADATA_API_BASE}/voot/v1/voot-web/content/generic/series-wise-episode',
|
||||
season_id, f'Downloading season {label} page {page_num} JSON', query={
|
||||
'sort': 'episode:asc',
|
||||
'id': season_id,
|
||||
'responseType': 'common',
|
||||
'page': page_num,
|
||||
}), ('result', lambda _, v: v['id'] and url_or_none(v['slug'])))
|
||||
if not episodes:
|
||||
break
|
||||
for episode in episodes:
|
||||
yield self.url_result(
|
||||
episode['slug'], JioCinemaIE, **traverse_obj(episode, {
|
||||
'video_id': 'id',
|
||||
'video_title': ('fullTitle', {str}),
|
||||
'season_number': ('season', {int_or_none}),
|
||||
'episode_number': ('episode', {int_or_none}),
|
||||
}))
|
||||
|
||||
def _real_extract(self, url):
|
||||
slug, series_id = self._match_valid_url(url).group('slug', 'id')
|
||||
return self.playlist_result(self._entries(series_id), series_id, slug)
|
||||
@@ -1,12 +1,12 @@
|
||||
import functools
|
||||
import urllib.parse
|
||||
|
||||
from .common import InfoExtractor
|
||||
from ..networking import HEADRequest
|
||||
from ..utils import (
|
||||
UserNotLive,
|
||||
determine_ext,
|
||||
float_or_none,
|
||||
int_or_none,
|
||||
merge_dicts,
|
||||
parse_iso8601,
|
||||
str_or_none,
|
||||
traverse_obj,
|
||||
@@ -16,21 +16,17 @@ from ..utils import (
|
||||
|
||||
|
||||
class KickBaseIE(InfoExtractor):
|
||||
def _real_initialize(self):
|
||||
self._request_webpage(
|
||||
HEADRequest('https://kick.com/'), None, 'Setting up session', fatal=False, impersonate=True)
|
||||
xsrf_token = self._get_cookies('https://kick.com/').get('XSRF-TOKEN')
|
||||
if not xsrf_token:
|
||||
self.write_debug('kick.com did not set XSRF-TOKEN cookie')
|
||||
KickBaseIE._API_HEADERS = {
|
||||
'Authorization': f'Bearer {xsrf_token.value}',
|
||||
'X-XSRF-TOKEN': xsrf_token.value,
|
||||
} if xsrf_token else {}
|
||||
@functools.cached_property
|
||||
def _api_headers(self):
|
||||
token = traverse_obj(
|
||||
self._get_cookies('https://kick.com/'),
|
||||
('session_token', 'value', {urllib.parse.unquote}))
|
||||
return {'Authorization': f'Bearer {token}'} if token else {}
|
||||
|
||||
def _call_api(self, path, display_id, note='Downloading API JSON', headers={}, **kwargs):
|
||||
return self._download_json(
|
||||
f'https://kick.com/api/{path}', display_id, note=note,
|
||||
headers=merge_dicts(headers, self._API_HEADERS), impersonate=True, **kwargs)
|
||||
headers={**self._api_headers, **headers}, impersonate=True, **kwargs)
|
||||
|
||||
|
||||
class KickIE(KickBaseIE):
|
||||
|
||||
@@ -4,16 +4,15 @@ 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,
|
||||
@@ -22,9 +21,8 @@ from ..utils import (
|
||||
parse_qs,
|
||||
parse_resolution,
|
||||
qualities,
|
||||
remove_start,
|
||||
str_or_none,
|
||||
unescapeHTML,
|
||||
truncate_string,
|
||||
unified_timestamp,
|
||||
update_url_query,
|
||||
url_basename,
|
||||
@@ -32,7 +30,11 @@ 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):
|
||||
@@ -806,41 +808,39 @@ class NiconicoLiveIE(NiconicoBaseIE):
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id = self._match_id(url)
|
||||
webpage, urlh = self._download_webpage_handle(f'https://live.nicovideo.jp/watch/{video_id}', video_id)
|
||||
webpage = self._download_webpage(url, video_id, expected_status=404)
|
||||
if err_msg := traverse_obj(webpage, ({find_element(cls='message')}, {clean_html})):
|
||||
raise ExtractorError(err_msg, expected=True)
|
||||
|
||||
embedded_data = self._parse_json(unescapeHTML(self._search_regex(
|
||||
r'<script\s+id="embedded-data"\s*data-props="(.+?)"', webpage, 'embedded data')), video_id)
|
||||
|
||||
ws_url = traverse_obj(embedded_data, ('site', 'relive', 'webSocketUrl'))
|
||||
if not ws_url:
|
||||
raise ExtractorError('The live hasn\'t started yet or already ended.', expected=True)
|
||||
ws_url = update_url_query(ws_url, {
|
||||
'frontend_id': traverse_obj(embedded_data, ('site', 'frontendId')) or '9',
|
||||
})
|
||||
|
||||
hostname = remove_start(urllib.parse.urlparse(urlh.url).hostname, 'sp.')
|
||||
embedded_data = traverse_obj(webpage, (
|
||||
{find_element(tag='script', id='embedded-data', html=True)},
|
||||
{extract_attributes}, 'data-props', {json.loads}))
|
||||
frontend_id = traverse_obj(embedded_data, ('site', 'frontendId', {str_or_none}), default='9')
|
||||
|
||||
ws_url = traverse_obj(embedded_data, (
|
||||
'site', 'relive', 'webSocketUrl', {url_or_none}, {require('websocket URL')}))
|
||||
ws_url = update_url_query(ws_url, {'frontend_id': frontend_id})
|
||||
ws = self._request_webpage(
|
||||
Request(ws_url, headers={'Origin': f'https://{hostname}'}),
|
||||
video_id=video_id, note='Connecting to WebSocket server')
|
||||
ws_url, video_id, 'Connecting to WebSocket server',
|
||||
headers={'Origin': 'https://live.nicovideo.jp'})
|
||||
|
||||
self.write_debug('Sending HLS server request')
|
||||
ws.send(json.dumps({
|
||||
'type': 'startWatching',
|
||||
'data': {
|
||||
'reconnect': False,
|
||||
'room': {
|
||||
'commentable': True,
|
||||
'protocol': 'webSocket',
|
||||
},
|
||||
'stream': {
|
||||
'quality': 'abr',
|
||||
'protocol': 'hls',
|
||||
'latency': 'high',
|
||||
'accessRightMethod': 'single_cookie',
|
||||
'chasePlay': False,
|
||||
'latency': 'high',
|
||||
'protocol': 'hls',
|
||||
'quality': 'abr',
|
||||
},
|
||||
'room': {
|
||||
'protocol': 'webSocket',
|
||||
'commentable': True,
|
||||
},
|
||||
'reconnect': False,
|
||||
},
|
||||
'type': 'startWatching',
|
||||
}))
|
||||
|
||||
while True:
|
||||
@@ -860,17 +860,15 @@ 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')) or recv
|
||||
message = traverse_obj(data, ('body', 'code', {str_or_none}), default=recv)
|
||||
raise ExtractorError(message)
|
||||
elif self.get_param('verbose', False):
|
||||
if len(recv) > 100:
|
||||
recv = recv[:100] + '...'
|
||||
self.write_debug(f'Server said: {recv}')
|
||||
self.write_debug(f'Server response: {truncate_string(recv, 100)}')
|
||||
|
||||
title = traverse_obj(embedded_data, ('program', 'title')) or self._html_search_meta(
|
||||
('og:title', 'twitter:title'), webpage, 'live title', fatal=False)
|
||||
|
||||
raw_thumbs = traverse_obj(embedded_data, ('program', 'thumbnail')) or {}
|
||||
raw_thumbs = traverse_obj(embedded_data, ('program', 'thumbnail', {dict})) or {}
|
||||
thumbnails = []
|
||||
for name, value in raw_thumbs.items():
|
||||
if not isinstance(value, dict):
|
||||
@@ -897,31 +895,30 @@ 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'),
|
||||
|
||||
41
yt_dlp/extractor/sauceplus.py
Normal file
41
yt_dlp/extractor/sauceplus.py
Normal file
@@ -0,0 +1,41 @@
|
||||
from .floatplane import FloatplaneBaseIE
|
||||
|
||||
|
||||
class SaucePlusIE(FloatplaneBaseIE):
|
||||
IE_DESC = 'Sauce+'
|
||||
_VALID_URL = r'https?://(?:(?:www|beta)\.)?sauceplus\.com/post/(?P<id>\w+)'
|
||||
_BASE_URL = 'https://www.sauceplus.com'
|
||||
_HEADERS = {
|
||||
'Origin': _BASE_URL,
|
||||
'Referer': f'{_BASE_URL}/',
|
||||
}
|
||||
_IMPERSONATE_TARGET = True
|
||||
_TESTS = [{
|
||||
'url': 'https://www.sauceplus.com/post/YbBwIa2A5g',
|
||||
'info_dict': {
|
||||
'id': 'eit4Ugu5TL',
|
||||
'ext': 'mp4',
|
||||
'display_id': 'YbBwIa2A5g',
|
||||
'title': 'Scare the Coyote - Episode 3',
|
||||
'description': '',
|
||||
'thumbnail': r're:^https?://.*\.jpe?g$',
|
||||
'duration': 2975,
|
||||
'comment_count': int,
|
||||
'like_count': int,
|
||||
'dislike_count': int,
|
||||
'release_date': '20250627',
|
||||
'release_timestamp': 1750993500,
|
||||
'uploader': 'Scare The Coyote',
|
||||
'uploader_id': '683e0a3269688656a5a49a44',
|
||||
'uploader_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home',
|
||||
'channel': 'Scare The Coyote',
|
||||
'channel_id': '683e0a326968866ceba49a45',
|
||||
'channel_url': 'https://www.sauceplus.com/channel/ScareTheCoyote/home/main',
|
||||
'availability': 'subscriber_only',
|
||||
},
|
||||
'params': {'skip_download': 'm3u8'},
|
||||
}]
|
||||
|
||||
def _real_initialize(self):
|
||||
if not self._get_cookies(self._BASE_URL).get('__Host-sp-sess'):
|
||||
self.raise_login_required()
|
||||
@@ -98,11 +98,8 @@ class SproutVideoIE(InfoExtractor):
|
||||
def _real_extract(self, url):
|
||||
url, smuggled_data = unsmuggle_url(url, {})
|
||||
video_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, video_id, headers={
|
||||
**traverse_obj(smuggled_data, {'Referer': 'referer'}),
|
||||
# yt-dlp's default Chrome user-agents are too old
|
||||
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; rv:140.0) Gecko/20100101 Firefox/140.0',
|
||||
})
|
||||
webpage = self._download_webpage(
|
||||
url, video_id, headers=traverse_obj(smuggled_data, {'Referer': 'referer'}), impersonate=True)
|
||||
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'["\'];',
|
||||
|
||||
@@ -63,6 +63,7 @@ INNERTUBE_CLIENTS = {
|
||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 1,
|
||||
'PO_TOKEN_REQUIRED_CONTEXTS': [_PoTokenContext.GVS],
|
||||
'SUPPORTS_COOKIES': True,
|
||||
'PLAYER_PARAMS': '8AEB',
|
||||
},
|
||||
'web_embedded': {
|
||||
'INNERTUBE_CONTEXT': {
|
||||
@@ -174,6 +175,7 @@ INNERTUBE_CLIENTS = {
|
||||
},
|
||||
'INNERTUBE_CONTEXT_CLIENT_NAME': 7,
|
||||
'SUPPORTS_COOKIES': True,
|
||||
'PLAYER_PARAMS': '8AEB',
|
||||
},
|
||||
'tv_simply': {
|
||||
'INNERTUBE_CONTEXT': {
|
||||
|
||||
@@ -2820,10 +2820,6 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
|
||||
context['signatureTimestamp'] = sts
|
||||
return {
|
||||
'playbackContext': {
|
||||
'adPlaybackContext': {
|
||||
'pyv': True,
|
||||
'adType': 'AD_TYPE_INSTREAM',
|
||||
},
|
||||
'contentPlaybackContext': context,
|
||||
},
|
||||
**cls._get_checkok_params(),
|
||||
|
||||
@@ -857,7 +857,7 @@ class JSInterpreter:
|
||||
obj = {}
|
||||
obj_m = re.search(
|
||||
r'''(?x)
|
||||
(?<!\.)%s\s*=\s*{\s*
|
||||
(?<![a-zA-Z$0-9.])%s\s*=\s*{\s*
|
||||
(?P<fields>(%s\s*:\s*function\s*\(.*?\)\s*{.*?}(?:,\s*)?)*)
|
||||
}\s*;
|
||||
''' % (re.escape(objname), _FUNC_NAME_RE),
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
# Autogenerated by devscripts/update-version.py
|
||||
|
||||
__version__ = '2025.06.25'
|
||||
__version__ = '2025.06.30'
|
||||
|
||||
RELEASE_GIT_HEAD = '1838a1ce5d4ade80770ba9162eaffc9a1607dc70'
|
||||
RELEASE_GIT_HEAD = 'b0187844988e557c7e1e6bb1aabd4c1176768d86'
|
||||
|
||||
VARIANT = None
|
||||
|
||||
@@ -12,4 +12,4 @@ CHANNEL = 'stable'
|
||||
|
||||
ORIGIN = 'yt-dlp/yt-dlp'
|
||||
|
||||
_pkg_version = '2025.06.25'
|
||||
_pkg_version = '2025.06.30'
|
||||
|
||||
Reference in New Issue
Block a user