Merge branch 'yt-dlp:master' into master

This commit is contained in:
DEVENU 2024-08-15 20:51:28 +05:30 committed by GitHub
commit b981449466
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
11 changed files with 170 additions and 54 deletions

View file

@ -655,3 +655,5 @@ iancmy
mokrueger
luvyana
szantnerb
hugepower
scribblemaniac

View file

@ -4,6 +4,21 @@
# To create a release, dispatch the https://github.com/yt-dlp/yt-dlp/actions/workflows/release.yml workflow on master
-->
### 2024.08.06
#### Core changes
- **jsinterp**: [Improve `slice` implementation](https://github.com/yt-dlp/yt-dlp/commit/bb8bf1db993f59752d20b73b861bd55e40cf0e31) ([#10664](https://github.com/yt-dlp/yt-dlp/issues/10664)) by [seproDev](https://github.com/seproDev)
#### Extractor changes
- **discoveryplusitaly**: [Support sport and olympics URLs](https://github.com/yt-dlp/yt-dlp/commit/e7d73bc4531ee3f91a46b15e218dcc1fbeb6226c) ([#10655](https://github.com/yt-dlp/yt-dlp/issues/10655)) by [bashonly](https://github.com/bashonly)
- **gem.cbc.ca**: live: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/fc5eecfa31c9571b6031cc3968aaa0394be55d7a) ([#10565](https://github.com/yt-dlp/yt-dlp/issues/10565)) by [bashonly](https://github.com/bashonly), [scribblemaniac](https://github.com/scribblemaniac)
- **niconico**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/4d9231208332d4c32364b8cd814bff8b20232cae) ([#10677](https://github.com/yt-dlp/yt-dlp/issues/10677)) by [bashonly](https://github.com/bashonly)
- **olympics**: [Fix extraction](https://github.com/yt-dlp/yt-dlp/commit/919540a9644e55deb78cdd6751757ec8fdaf76f4) ([#10625](https://github.com/yt-dlp/yt-dlp/issues/10625)) by [bashonly](https://github.com/bashonly)
- **youku**: [Fix extractor](https://github.com/yt-dlp/yt-dlp/commit/0088c6de23d832b117061a33e984dc452d992e9c) ([#10626](https://github.com/yt-dlp/yt-dlp/issues/10626)) by [hugepower](https://github.com/hugepower)
- **youtube**
- [Change default player clients to `ios,web_creator`](https://github.com/yt-dlp/yt-dlp/commit/406f4c2e47502fffc1b0c210b4ee6487c89a44cb) ([#10674](https://github.com/yt-dlp/yt-dlp/issues/10674)) by [bashonly](https://github.com/bashonly)
- [Fix `n` function name extraction for player `b12cc44b`](https://github.com/yt-dlp/yt-dlp/commit/c86891eb9434b4d7eec426d38c0c625b5e13cb2f) ([#10668](https://github.com/yt-dlp/yt-dlp/issues/10668)) by [seproDev](https://github.com/seproDev)
### 2024.08.01
#### Core changes

View file

@ -1767,7 +1767,7 @@ The following extractors use this feature:
#### youtube
* `lang`: Prefer translated metadata (`title`, `description` etc) of this language code (case-sensitive). By default, the video primary language metadata is preferred, with a fallback to `en` translated. See [youtube.py](https://github.com/yt-dlp/yt-dlp/blob/c26f9b991a0681fd3ea548d535919cec1fbbd430/yt_dlp/extractor/youtube.py#L381-L390) for list of supported content language codes
* `skip`: One or more of `hls`, `dash` or `translated_subs` to skip extraction of the m3u8 manifests, dash manifests and [auto-translated subtitles](https://github.com/yt-dlp/yt-dlp/issues/4090#issuecomment-1158102032) respectively
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,tv` is used, but `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_client`: Clients to extract video data from. The main clients are `web`, `ios` and `android`, with variants `_music` and `_creator` (e.g. `ios_creator`); and `mediaconnect`, `mweb`, `android_producer`, `android_testsuite`, `android_vr`, `web_safari`, `web_embedded`, `tv` and `tv_embedded` with no variants. By default, `ios,web_creator` is used, and `tv_embedded`, `web_creator` and `mediaconnect` are added as required for age-gated videos. Similarly, the music variants are added for `music.youtube.com` urls. Most `android` clients will be given lowest priority since their formats are broken. You can use `all` to use all the clients, and `default` for the default clients.
* `player_skip`: Skip some network requests that are generally needed for robust extraction. One or more of `configs` (skip client configs), `webpage` (skip initial webpage), `js` (skip js player). While these options can help reduce the number of requests needed or avoid some rate-limiting, they could cause some issues. See [#860](https://github.com/yt-dlp/yt-dlp/pull/860) for more details
* `player_params`: YouTube player parameters to use for player requests. Will overwrite any default ones set by yt-dlp.
* `comment_sort`: `top` or `new` (default) - choose comment sorting mode (on YouTube's side)

View file

@ -403,6 +403,34 @@ class TestJSInterpreter(unittest.TestCase):
self._test(jsi, [''], args=['', '-'])
self._test(jsi, [], args=['', ''])
def test_slice(self):
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice()}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(5)}', [5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(99)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-2)}', [7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-99)}', [0, 1, 2, 3, 4, 5, 6, 7, 8])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, 0)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(0, 1)}', [0])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(3, 6)}', [3, 4, 5])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(1, -1)}', [1, 2, 3, 4, 5, 6, 7])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-1, 1)}', [])
self._test('function f(){return [0, 1, 2, 3, 4, 5, 6, 7, 8].slice(-3, -1)}', [6, 7])
self._test('function f(){return "012345678".slice()}', '012345678')
self._test('function f(){return "012345678".slice(0)}', '012345678')
self._test('function f(){return "012345678".slice(5)}', '5678')
self._test('function f(){return "012345678".slice(99)}', '')
self._test('function f(){return "012345678".slice(-2)}', '78')
self._test('function f(){return "012345678".slice(-99)}', '012345678')
self._test('function f(){return "012345678".slice(0, 0)}', '')
self._test('function f(){return "012345678".slice(1, 0)}', '')
self._test('function f(){return "012345678".slice(0, 1)}', '0')
self._test('function f(){return "012345678".slice(3, 6)}', '345')
self._test('function f(){return "012345678".slice(1, -1)}', '1234567')
self._test('function f(){return "012345678".slice(-1, 1)}', '')
self._test('function f(){return "012345678".slice(-3, -1)}', '67')
if __name__ == '__main__':
unittest.main()

View file

@ -179,6 +179,10 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/20dfca59/player_ias.vflset/en_US/base.js',
'-fLCxedkAk4LUTK2', 'O8kfRq1y1eyHGw',
),
(
'https://www.youtube.com/s/player/b12cc44b/player_ias.vflset/en_US/base.js',
'keLa5R2U00sR9SQK', 'N1OGyujjEwMnLw',
),
]

View file

@ -806,11 +806,11 @@ class CBCGemLiveIE(InfoExtractor):
'title': 'Ottawa',
'description': 'The live TV channel and local programming from Ottawa',
'thumbnail': 'https://thumbnails.cbc.ca/maven_legacy/thumbnails/CBC_OTT_VMS/Live_Channel_Static_Images/Ottawa_2880x1620.jpg',
'is_live': True,
'live_status': 'is_live',
'id': 'AyqZwxRqh8EH',
'ext': 'mp4',
'timestamp': 1492106160,
'upload_date': '20170413',
'release_timestamp': 1492106160,
'release_date': '20170413',
'uploader': 'CBCC-NEW',
},
'skip': 'Live might have ended',
@ -839,49 +839,84 @@ class CBCGemLiveIE(InfoExtractor):
'description': 'March 24, 2023 | President Bidens Ottawa visit ends with big pledges from both countries. Plus, Gwyneth Paltrow testifies in her ski collision trial.',
'live_status': 'is_live',
'thumbnail': r're:https://images.gem.cbc.ca/v1/cbc-gem/live/.*',
'timestamp': 1679706000,
'upload_date': '20230325',
'release_timestamp': 1679706000,
'release_date': '20230325',
},
'params': {'skip_download': True},
'skip': 'Live might have ended',
},
{ # event replay (medianetlive)
'url': 'https://gem.cbc.ca/live-event/42314',
'md5': '297a9600f554f2258aed01514226a697',
'info_dict': {
'id': '42314',
'ext': 'mp4',
'live_status': 'was_live',
'title': 'Women\'s Soccer - Canada vs New Zealand',
'description': 'md5:36200e5f1a70982277b5a6ecea86155d',
'thumbnail': r're:https://.+default\.jpg',
'release_timestamp': 1721917200,
'release_date': '20240725',
},
'params': {'skip_download': True},
'skip': 'Replay might no longer be available',
},
{ # event replay (medianetlive)
'url': 'https://gem.cbc.ca/live-event/43273',
'only_matching': True,
},
]
_GEO_COUNTRIES = ['CA']
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
video_info = self._search_nextjs_data(webpage, video_id)['props']['pageProps']['data']
# Two types of metadata JSON
# Three types of video_info JSON: info in root, freeTv stream/item, event replay
if not video_info.get('formattedIdMedia'):
video_info = traverse_obj(
video_info, (('freeTv', ('streams', ...)), 'items', lambda _, v: v['key'] == video_id, {dict}),
get_all=False, default={})
if traverse_obj(video_info, ('event', 'key')) == video_id:
video_info = video_info['event']
else:
video_info = traverse_obj(video_info, (
('freeTv', ('streams', ...)), 'items',
lambda _, v: v['key'].partition('-')[0] == video_id, any)) or {}
video_stream_id = video_info.get('formattedIdMedia')
if not video_stream_id:
raise ExtractorError('Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
raise ExtractorError(
'Couldn\'t find video metadata, maybe this livestream is now offline', expected=True)
stream_data = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
'appCode': 'mpx',
'connectionType': 'hd',
'deviceType': 'ipad',
'idMedia': video_stream_id,
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestType': 'desktop',
})
live_status = 'was_live' if video_info.get('isVodEnabled') else 'is_live'
release_timestamp = traverse_obj(video_info, ('airDate', {parse_iso8601}))
if live_status == 'is_live' and release_timestamp and release_timestamp > time.time():
formats = []
live_status = 'is_upcoming'
self.raise_no_formats('This livestream has not yet started', expected=True)
else:
stream_data = self._download_json(
'https://services.radio-canada.ca/media/validation/v2/', video_id, query={
'appCode': 'medianetlive',
'connectionType': 'hd',
'deviceType': 'ipad',
'idMedia': video_stream_id,
'multibitrate': 'true',
'output': 'json',
'tech': 'hls',
'manifestType': 'desktop',
})
formats = self._extract_m3u8_formats(
stream_data['url'], video_id, 'mp4', live=live_status == 'is_live')
return {
'id': video_id,
'formats': self._extract_m3u8_formats(stream_data['url'], video_id, 'mp4', live=True),
'is_live': True,
'formats': formats,
'live_status': live_status,
'release_timestamp': release_timestamp,
**traverse_obj(video_info, {
'title': 'title',
'description': 'description',
'title': ('title', {str}),
'description': ('description', {str}),
'thumbnail': ('images', 'card', 'url'),
'timestamp': ('airDate', {parse_iso8601}),
}),
}

View file

@ -40,7 +40,6 @@ class NiconicoIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.nicovideo.jp/watch/sm22312215',
'md5': 'd1a75c0823e2f629128c43e1212760f9',
'info_dict': {
'id': 'sm22312215',
'ext': 'mp4',
@ -56,8 +55,8 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['未設定'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# File downloaded with and without credentials are different, so omit
# the md5 field
@ -77,8 +76,8 @@ class NiconicoIE(InfoExtractor):
'view_count': int,
'genres': ['音楽・サウンド'],
'tags': ['Translation_Request', 'Kagamine_Rin', 'Rin_Original'],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# 'video exists but is marked as "deleted"
# md5 is unstable
@ -112,7 +111,6 @@ class NiconicoIE(InfoExtractor):
}, {
# video not available via `getflv`; "old" HTML5 video
'url': 'http://www.nicovideo.jp/watch/sm1151009',
'md5': 'f95a3d259172667b293530cc2e41ebda',
'info_dict': {
'id': 'sm1151009',
'ext': 'mp4',
@ -128,11 +126,10 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['ゲーム'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# "New" HTML5 video
# md5 is unstable
'url': 'http://www.nicovideo.jp/watch/sm31464864',
'info_dict': {
'id': 'sm31464864',
@ -149,12 +146,11 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['アニメ'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
# Video without owner
'url': 'http://www.nicovideo.jp/watch/sm18238488',
'md5': 'd265680a1f92bdcbbd2a507fc9e78a9e',
'info_dict': {
'id': 'sm18238488',
'ext': 'mp4',
@ -168,8 +164,8 @@ class NiconicoIE(InfoExtractor):
'comment_count': int,
'genres': ['エンターテイメント'],
'tags': [],
'expected_protocol': str,
},
'params': {'skip_download': 'm3u8'},
}, {
'url': 'http://sp.nicovideo.jp/watch/sm28964488?ss_pos=1&cp_in=wt_tg',
'only_matching': True,
@ -458,9 +454,11 @@ class NiconicoIE(InfoExtractor):
if video_id.startswith('so'):
video_id = self._match_id(handle.url)
api_data = self._parse_json(self._html_search_regex(
'data-api-data="([^"]+)"', webpage,
'API data', default='{}'), video_id)
api_data = traverse_obj(
self._parse_json(self._html_search_meta('server-response', webpage) or '', video_id),
('data', 'response', {dict}))
if not api_data:
raise ExtractorError('Server response data not found')
except ExtractorError as e:
try:
api_data = self._download_json(

View file

@ -420,7 +420,7 @@ class PatreonIE(PatreonBaseIE):
class PatreonCampaignIE(PatreonBaseIE):
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m/(?P<campaign_id>\d+))|(?P<vanity>[-\w]+))'
_VALID_URL = r'https?://(?:www\.)?patreon\.com/(?!rss)(?:(?:m|api/campaigns)/(?P<campaign_id>\d+)|(?P<vanity>[-\w]+))'
_TESTS = [{
'url': 'https://www.patreon.com/dissonancepod/',
'info_dict': {
@ -442,25 +442,44 @@ class PatreonCampaignIE(PatreonBaseIE):
'url': 'https://www.patreon.com/m/4767637/posts',
'info_dict': {
'title': 'Not Just Bikes',
'channel_follower_count': int,
'id': '4767637',
'channel_id': '4767637',
'channel_url': 'https://www.patreon.com/notjustbikes',
'description': 'md5:595c6e7dca76ae615b1d38c298a287a1',
'description': 'md5:9f4b70051216c4d5c58afe580ffc8d0f',
'age_limit': 0,
'channel': 'Not Just Bikes',
'uploader_url': 'https://www.patreon.com/notjustbikes',
'uploader': 'Not Just Bikes',
'uploader': 'Jason',
'uploader_id': '37306634',
'thumbnail': r're:^https?://.*$',
},
'playlist_mincount': 71,
}, {
'url': 'https://www.patreon.com/api/campaigns/4243769/posts',
'info_dict': {
'title': 'Second Thought',
'channel_follower_count': int,
'id': '4243769',
'channel_id': '4243769',
'channel_url': 'https://www.patreon.com/secondthought',
'description': 'md5:69c89a3aba43efdb76e85eb023e8de8b',
'age_limit': 0,
'channel': 'Second Thought',
'uploader_url': 'https://www.patreon.com/secondthought',
'uploader': 'JT Chapman',
'uploader_id': '32718287',
'thumbnail': r're:^https?://.*$',
},
'playlist_mincount': 201,
}, {
'url': 'https://www.patreon.com/dissonancepod/posts',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/m/5932659',
'only_matching': True,
}, {
'url': 'https://www.patreon.com/api/campaigns/4243769',
'only_matching': True,
}]
@classmethod

View file

@ -1339,6 +1339,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
short_client_name(client): client
for client in ('android', 'android_creator', 'android_music')
}
_DEFAULT_CLIENTS = ('ios', 'web_creator')
_GEO_BYPASS = False
@ -3180,6 +3181,7 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# * b=String.fromCharCode(110),c=a.get(b))&&c=narray[idx](c)
# * a.D&&(b="nn"[+a.D],c=a.get(b))&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# * a.D&&(PL(a),b=a.j.n||null)&&(b=narray[0](b),a.set("n",b),narray.length||nfunc("")
# * a.D&&(b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
funcname, idx = self._search_regex(
r'''(?x)
(?:
@ -3187,7 +3189,13 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
(?:
b=String\.fromCharCode\(110\)|
(?P<str_idx>[a-zA-Z0-9_$.]+)&&\(b="nn"\[\+(?P=str_idx)\]
),c=a\.get\(b\)\)&&\(c=|
)
(?:
,[a-zA-Z0-9_$]+\(a\))?,c=a\.
(?:
get\(b\)|
[a-zA-Z0-9_$]+\[b\]\|\|null
)\)&&\(c=|
\b(?P<var>[a-zA-Z0-9_$]+)=
)(?P<nfunc>[a-zA-Z0-9_$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z]\)
(?(var),[a-zA-Z0-9_$]+\.set\("n"\,(?P=var)\),(?P=nfunc)\.length)''',
@ -3737,17 +3745,19 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _get_requested_clients(self, url, smuggled_data):
requested_clients = []
broken_clients = []
default = ['ios', 'tv']
excluded_clients = []
allowed_clients = sorted(
(client for client in INNERTUBE_CLIENTS if client[:1] != '_'),
key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
for client in self._configuration_arg('player_client'):
if client == 'default':
requested_clients.extend(default)
requested_clients.extend(self._DEFAULT_CLIENTS)
elif client == 'all':
requested_clients.extend(allowed_clients)
elif client.startswith('-'):
excluded_clients.append(client[1:])
elif client not in allowed_clients:
self.report_warning(f'Skipping unsupported client {client}')
self.report_warning(f'Skipping unsupported client "{client}"')
elif client in self._BROKEN_CLIENTS.values():
broken_clients.append(client)
else:
@ -3755,7 +3765,12 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
# Force deprioritization of _BROKEN_CLIENTS for format de-duplication
requested_clients.extend(broken_clients)
if not requested_clients:
requested_clients = default
requested_clients.extend(self._DEFAULT_CLIENTS)
for excluded_client in excluded_clients:
if excluded_client in requested_clients:
requested_clients.remove(excluded_client)
if not requested_clients:
raise ExtractorError('No player clients have been requested', expected=True)
if smuggled_data.get('is_music_url') or self.is_music_url(url):
for requested_client in requested_clients:

View file

@ -709,9 +709,9 @@ class JSInterpreter:
obj.reverse()
return obj
elif member == 'slice':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(len(argvals) == 1, 'takes exactly one argument')
return obj[argvals[0]:]
assertion(isinstance(obj, (list, str)), 'must be applied on a list or string')
assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments')
return obj[slice(*argvals, None)]
elif member == 'splice':
assertion(isinstance(obj, list), 'must be applied on a list')
assertion(argvals, 'takes one or more arguments')

View file

@ -1,8 +1,8 @@
# Autogenerated by devscripts/update-version.py
__version__ = '2024.08.01'
__version__ = '2024.08.06'
RELEASE_GIT_HEAD = 'ffd7781d6588926f820b44a34b9e6e3068fb9f97'
RELEASE_GIT_HEAD = '4d9231208332d4c32364b8cd814bff8b20232cae'
VARIANT = None
@ -12,4 +12,4 @@ CHANNEL = 'stable'
ORIGIN = 'yt-dlp/yt-dlp'
_pkg_version = '2024.08.01'
_pkg_version = '2024.08.06'