1
0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-12-23 00:16:48 +00:00

Compare commits

...

14 Commits

Author SHA1 Message Date
Alba Mendez
40527f51cf
Merge 20691a11e6 into c5098961b0 2024-08-21 22:32:46 -04:00
dirkf
c5098961b0 [Youtube] Rework n function extraction pattern
Now also succeeds with player b12cc44b
2024-08-06 20:59:09 +01:00
dirkf
dbc08fba83 [jsinterp] Improve slice implementation for player b12cc44b
Partly taken from yt-dlp/yt-dlp#10664, thx seproDev
        Fixes #32896
2024-08-06 20:51:38 +01:00
Aiur Adept
71223bff39
[Youtube] Fix nsig extraction for player 20dfca59 (#32891)
* dirkf's patch for nsig extraction
* add generic search per  yt-dlp/yt-dlp/pull/10611 - thx bashonly

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>
2024-08-01 19:18:34 +01:00
dirkf
20691a11e6
Really pass TestAllURLsMatching.test_no_duplicates 2022-10-10 10:54:19 +01:00
dirkf
585e806d9a
Pass TestAllURLsMatching.test_no_duplicates ? 2022-10-10 10:21:59 +01:00
Alba Mendez
e4c57418df generalize to audios too 2022-09-17 20:24:15 +02:00
Alba Mendez
d7939e2c07 improve metadata
grab metadata from the new endpoint (videos/%d.json)
instead of the legacy endpoint
(videos/%d/config/alacarta_videos.json),
which is what is actually used for the UI now.

- gives more up to date titles
- adds description / URL
- makes supporting audios easy (see next commit)
2022-09-17 20:24:15 +02:00
Alba Mendez
4a48a17eea make tests up to date 2022-09-17 20:24:15 +02:00
Alba Mendez
52858d5879 generalize to other URLs 2022-09-17 20:24:15 +02:00
Alba Mendez
050b52baf9 rename rtve.es:alacarta to rtve.es:play 2022-09-17 20:24:15 +02:00
Alba Mendez
11bd5b9612 fix rtve.es:live 2022-09-17 20:24:15 +02:00
Alba Mendez
33650c8eb6 fix URLs
change to ztnr.rtve.es domain doesn't seem to be required,
but switch to it just in case the old route is dropped someday
2022-09-17 20:24:15 +02:00
Alba Mendez
7cc35d1051 fix decoding logic 2022-09-17 20:24:15 +02:00
6 changed files with 215 additions and 71 deletions

View File

@ -425,6 +425,34 @@ class TestJSInterpreter(unittest.TestCase):
self._test(jsi, [''], args=['', '-']) self._test(jsi, [''], args=['', '-'])
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__': if __name__ == '__main__':
unittest.main() unittest.main()

View File

@ -174,6 +174,14 @@ _NSIG_TESTS = [
'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js', 'https://www.youtube.com/s/player/5604538d/player_ias.vflset/en_US/base.js',
'7X-he4jjvMx7BCX', 'sViSydX8IHtdWA', '7X-he4jjvMx7BCX', 'sViSydX8IHtdWA',
), ),
(
'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

@ -1065,7 +1065,7 @@ from .rtl2 import (
) )
from .rtp import RTPIE from .rtp import RTPIE
from .rts import RTSIE from .rts import RTSIE
from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE from .rtve import RTVEPlayIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
from .rtvnh import RTVNHIE from .rtvnh import RTVNHIE
from .rtvs import RTVSIE from .rtvs import RTVSIE
from .ruhd import RUHDIE from .ruhd import RUHDIE

View File

@ -12,30 +12,30 @@ from ..compat import (
compat_struct_unpack, compat_struct_unpack,
) )
from ..utils import ( from ..utils import (
clean_html,
determine_ext, determine_ext,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
qualities, qualities,
remove_end,
remove_start,
std_headers, std_headers,
) )
_bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x)) _bytes_to_chr = (lambda x: x) if sys.version_info[0] == 2 else (lambda x: map(chr, x))
class RTVEALaCartaIE(InfoExtractor): class RTVEPlayIE(InfoExtractor):
IE_NAME = 'rtve.es:alacarta' IE_NAME = 'rtve.es:play'
IE_DESC = 'RTVE a la carta' IE_DESC = 'RTVE Play'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/(m/)?(alacarta/videos|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)' _VALID_URL = r'https?://(?:www\.)?rtve\.es/(?P<kind>(?:playz?|(?:m/)?alacarta)/(?:audios|videos)|filmoteca)/[^/]+/[^/]+/(?P<id>\d+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/', 'url': 'http://www.rtve.es/alacarta/videos/balonmano/o-swiss-cup-masculina-final-espana-suecia/2491869/',
'md5': '1d49b7e1ca7a7502c56a4bf1b60f1b43', 'md5': '2c70aacf8a415d1b4e7fcc0525951162',
'info_dict': { 'info_dict': {
'id': '2491869', 'id': '2491869',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Balonmano - Swiss Cup masculina. Final: España-Suecia', 'title': 'Final de la Swiss Cup masculina: España-Suecia',
'description': 'Swiss Cup masculina, Final: España-Suecia.',
'duration': 5024.566, 'duration': 5024.566,
'series': 'Balonmano', 'series': 'Balonmano',
}, },
@ -47,6 +47,7 @@ class RTVEALaCartaIE(InfoExtractor):
'id': '1694255', 'id': '1694255',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'title': 're:^24H LIVE [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': '24H LIVE',
'is_live': True, 'is_live': True,
}, },
'params': { 'params': {
@ -54,11 +55,12 @@ class RTVEALaCartaIE(InfoExtractor):
}, },
}, { }, {
'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/', 'url': 'http://www.rtve.es/alacarta/videos/servir-y-proteger/servir-proteger-capitulo-104/4236788/',
'md5': 'd850f3c8731ea53952ebab489cf81cbf', 'md5': '30b8827cba25f39d1af5a7c482cc8ac5',
'info_dict': { 'info_dict': {
'id': '4236788', 'id': '4236788',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Servir y proteger - Capítulo 104', 'title': 'Capítulo 104',
'description': 'md5:caae29ae04291875e611dd667fe84641',
'duration': 3222.0, 'duration': 3222.0,
}, },
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'], 'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
@ -68,6 +70,17 @@ class RTVEALaCartaIE(InfoExtractor):
}, { }, {
'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/', 'url': 'http://www.rtve.es/filmoteca/no-do/not-1-introduccion-primer-noticiario-espanol/1465256/',
'only_matching': True, 'only_matching': True,
}, {
'url': 'http://www.rtve.es/alacarta/audios/a-hombros-de-gigantes/palabra-ingeniero-codigos-informaticos-27-04-21/5889192/',
'md5': 'ae06d27bff945c4e87a50f89f6ce48ce',
'info_dict': {
'id': '5889192',
'ext': 'mp3',
'title': 'Códigos informáticos',
'description': 'md5:72b0d7c1ca20fd327bdfff7ac0171afb',
'thumbnail': r're:https?://.+/1598856591583.jpg',
'duration': 349.440,
},
}] }]
def _real_initialize(self): def _real_initialize(self):
@ -86,8 +99,12 @@ class RTVEALaCartaIE(InfoExtractor):
break break
data = encrypted_data.read(length) data = encrypted_data.read(length)
if chunk_type == b'tEXt': if chunk_type == b'tEXt':
alphabet_data, text = data.split(b'\0') alphabet_data, text = data.replace(b'\0', b'').split(b'#')
quality, url_data = text.split(b'%%') components = text.split(b'%%')
if len(components) < 2:
components.insert(0, b'')
quality, url_data = components
alphabet = [] alphabet = []
e = 0 e = 0
d = 0 d = 0
@ -120,7 +137,7 @@ class RTVEALaCartaIE(InfoExtractor):
def _extract_png_formats(self, video_id): def _extract_png_formats(self, video_id):
png = self._download_webpage( png = self._download_webpage(
'http://www.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id), 'http://ztnr.rtve.es/ztnr/movil/thumbnail/%s/videos/%s.png' % (self._manager, video_id),
video_id, 'Downloading url information', query={'q': 'v2'}) video_id, 'Downloading url information', query={'q': 'v2'})
q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL']) q = qualities(['Media', 'Alta', 'HQ', 'HD_READY', 'HD_FULL'])
formats = [] formats = []
@ -143,11 +160,16 @@ class RTVEALaCartaIE(InfoExtractor):
return formats return formats
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) groups = re.match(self._VALID_URL, url).groupdict()
is_audio = groups.get('kind') == 'play/audios'
return self._real_extract_from_id(groups['id'], is_audio)
def _real_extract_from_id(self, video_id, is_audio=False):
kind = 'audios' if is_audio else 'videos'
info = self._download_json( info = self._download_json(
'http://www.rtve.es/api/videos/%s/config/alacarta_videos.json' % video_id, 'http://www.rtve.es/api/%s/%s.json' % (kind, video_id),
video_id)['page']['items'][0] video_id)['page']['items'][0]
if info['state'] == 'DESPU': if (info.get('pubState') or {}).get('code') == 'DESPU':
raise ExtractorError('The video is no longer available', expected=True) raise ExtractorError('The video is no longer available', expected=True)
title = info['title'].strip() title = info['title'].strip()
formats = self._extract_png_formats(video_id) formats = self._extract_png_formats(video_id)
@ -157,17 +179,19 @@ class RTVEALaCartaIE(InfoExtractor):
if sbt_file: if sbt_file:
subtitles = self.extract_subtitles(video_id, sbt_file) subtitles = self.extract_subtitles(video_id, sbt_file)
is_live = info.get('live') is True is_live = info.get('consumption') == 'live'
return { return {
'id': video_id, 'id': video_id,
'title': self._live_title(title) if is_live else title, 'title': self._live_title(title) if is_live else title,
'formats': formats, 'formats': formats,
'thumbnail': info.get('image'), 'url': info.get('htmlUrl'),
'description': clean_html(info.get('description')),
'thumbnail': info.get('thumbnail'),
'subtitles': subtitles, 'subtitles': subtitles,
'duration': float_or_none(info.get('duration'), 1000), 'duration': float_or_none(info.get('duration'), 1000),
'is_live': is_live, 'is_live': is_live,
'series': info.get('programTitle'), 'series': (info.get('programInfo') or {}).get('title'),
} }
def _get_subtitles(self, video_id, sub_file): def _get_subtitles(self, video_id, sub_file):
@ -179,36 +203,60 @@ class RTVEALaCartaIE(InfoExtractor):
for s in subs) for s in subs)
class RTVEInfantilIE(RTVEALaCartaIE): class RTVEInfantilIE(RTVEPlayIE):
IE_NAME = 'rtve.es:infantil' IE_NAME = 'rtve.es:infantil'
IE_DESC = 'RTVE infantil' IE_DESC = 'RTVE infantil'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/' _VALID_URL = r'https?://(?:www\.)?rtve\.es/infantil/serie/[^/]+/video/[^/]+/(?P<id>[0-9]+)/'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtve.es/infantil/serie/cleo/video/maneras-vivir/3040283/', 'url': 'https://www.rtve.es/infantil/serie/dino-ranch/video/pequeno-gran-ayudante/6693248/',
'md5': '5747454717aedf9f9fdf212d1bcfc48d', 'md5': '06d3f57eec593ad93fe9dcf079fbd940',
'info_dict': { 'info_dict': {
'id': '3040283', 'id': '6693248',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Maneras de vivir', 'title': 'Un pequeño gran ayudante',
'thumbnail': r're:https?://.+/1426182947956\.JPG', 'description': 'md5:144ca351e31f9ee99a637ab9fc2787d5',
'duration': 357.958, 'thumbnail': r're:https?://.+/1663318364501\.jpg',
'duration': 691.44,
}, },
'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'], 'expected_warnings': ['Failed to download MPD manifest', 'Failed to download m3u8 information'],
}] }]
class RTVELiveIE(RTVEALaCartaIE): class RTVELiveIE(RTVEPlayIE):
IE_NAME = 'rtve.es:live' IE_NAME = 'rtve.es:live'
IE_DESC = 'RTVE.es live streams' IE_DESC = 'RTVE.es live streams'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/directo/(?P<id>[a-zA-Z0-9-]+)' _VALID_URL = r'https?://(?:www\.)?rtve\.es/play/videos/directo/(?P<id>.+)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.rtve.es/directo/la-1/', 'url': 'https://www.rtve.es/play/videos/directo/la-1/',
'info_dict': { 'info_dict': {
'id': 'la-1', 'id': '1688877',
'ext': 'mp4', 'ext': 'mp4',
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$', 'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'La 1',
},
'params': {
'skip_download': 'live stream',
}
}, {
'url': 'https://www.rtve.es/play/videos/directo/canales-lineales/la-1/',
'info_dict': {
'id': '1688877',
'ext': 'mp4',
'title': 're:^La 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'La 1',
},
'params': {
'skip_download': 'live stream',
}
}, {
'url': 'https://www.rtve.es/play/videos/directo/canales-lineales/capilla-ardiente-isabel-westminster/10886/',
'info_dict': {
'id': '1938028',
'ext': 'mp4',
'title': 're:^Mas24 - 1 [0-9]{4}-[0-9]{2}-[0-9]{2} [0-9]{2}:[0-9]{2}$',
'description': 'Mas24 - 1',
}, },
'params': { 'params': {
'skip_download': 'live stream', 'skip_download': 'live stream',
@ -216,53 +264,77 @@ class RTVELiveIE(RTVEALaCartaIE):
}] }]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) webpage = self._download_webpage(url, self._match_id(url))
video_id = mobj.group('id') asset_id = self._search_regex(
r'class=["\'].*?\bvideoPlayer\b.*?["\'][^>]+data-setup=[^>]+?(?:"|&quot;)idAsset(?:"|&quot;)\s*:\s*(?:"|&quot;)(\d+)(?:"|&quot;)',
webpage = self._download_webpage(url, video_id)
title = remove_end(self._og_search_title(webpage), ' en directo en RTVE.es')
title = remove_start(title, 'Estoy viendo ')
vidplayer_id = self._search_regex(
(r'playerId=player([0-9]+)',
r'class=["\'].*?\blive_mod\b.*?["\'][^>]+data-assetid=["\'](\d+)',
r'data-id=["\'](\d+)'),
webpage, 'internal video ID') webpage, 'internal video ID')
return self._real_extract_from_id(asset_id)
return {
'id': video_id,
'title': self._live_title(title),
'formats': self._extract_png_formats(vidplayer_id),
'is_live': True,
}
class RTVETelevisionIE(InfoExtractor): class RTVETelevisionIE(InfoExtractor):
IE_NAME = 'rtve.es:television' IE_NAME = 'rtve.es:television'
_VALID_URL = r'https?://(?:www\.)?rtve\.es/television/[^/]+/[^/]+/(?P<id>\d+).shtml' # https://www.rtve.es/SECTION/YYYYMMDD/CONTENT_SLUG/CONTENT_ID.shtml
_VALID_URL = r'https?://(?:www\.)?rtve\.es/[^/]+/\d{8}/[^/]+/(?P<id>\d+)\.shtml'
_TEST = { _TESTS = [{
'url': 'http://www.rtve.es/television/20160628/revolucion-del-movil/1364141.shtml', 'url': 'https://www.rtve.es/television/20220916/destacados-festival-san-sebastian-rtve-play/2395620.shtml',
'info_dict': { 'info_dict': {
'id': '3069778', 'id': '6668919',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Documentos TV - La revolución del móvil', 'title': 'Las películas del Festival de San Sebastián en RTVE Play',
'duration': 3496.948, 'description': 'El\xa0Festival de San Sebastián vuelve a llenarse de artistas. Y en su honor,\xa0RTVE Play\xa0destacará cada viernes una\xa0película galardonada\xa0con la\xa0Concha de Oro\xa0en su catálogo.',
'duration': 20.048,
}, },
'params': { 'params': {
'skip_download': True, 'skip_download': True,
}, },
} }, {
'url': 'https://www.rtve.es/noticias/20220917/penelope-cruz-san-sebastian-premio-nacional/2402565.shtml',
'info_dict': {
'id': '6694087',
'ext': 'mp4',
'title': 'Penélope Cruz recoge el Premio Nacional de Cinematografía: "No dejen nunca de proteger nuestro cine"',
'description': 'md5:eda9e6baa78dbbbcc7708c0cc8150a91',
'duration': 388.2,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.rtve.es/deportes/20220917/motogp-bagnaia-pole-marquez-decimotercero-motorland-aragon/2402566.shtml',
'info_dict': {
'id': '6694142',
'ext': 'mp4',
'title': "Bagnaia logra su quinta 'pole' del año y Márquez partirá decimotercero",
'description': 'md5:07e2ccb983a046cb42f896cce225f0a7',
'duration': 153.44,
},
'params': {
'skip_download': True,
},
}, {
'url': 'https://www.rtve.es/playz/20220807/covaleda-fest-final/2394809.shtml',
'info_dict': {
'id': '6665408',
'ext': 'mp4',
'title': 'Covaleda Fest (Soria) - Día 3 con Marc Seguí y Paranoid 1966',
'description': 'Festivales Playz viaja a Covaleda, Soria, para contarte todo lo que sucede en el Covaleda Fest. Entrevistas, challenges a los artistas, juegos... Khan, Adriana Jiménez y María García no dejarán pasar ni una. ¡No te lo pierdas!',
'duration': 12009.92,
},
'params': {
'skip_download': True,
},
}]
def _real_extract(self, url): def _real_extract(self, url):
page_id = self._match_id(url) page_id = self._match_id(url)
webpage = self._download_webpage(url, page_id) webpage = self._download_webpage(url, page_id)
alacarta_url = self._search_regex( alacarta_url = self._search_regex(
r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(http://www\.rtve\.es/alacarta.+?)&', r'data-location="alacarta_videos"[^<]+url&quot;:&quot;(https?://www\.rtve\.es/play.+?)&',
webpage, 'alacarta url', default=None) webpage, 'alacarta url', default=None)
if alacarta_url is None: if alacarta_url is None:
raise ExtractorError( raise ExtractorError(
'The webpage doesn\'t contain any video', expected=True) 'The webpage doesn\'t contain any video', expected=True)
return self.url_result(alacarta_url, ie=RTVEALaCartaIE.ie_key()) return self.url_result(alacarta_url, ie=RTVEPlayIE.ie_key())

View File

@ -1659,17 +1659,46 @@ class YoutubeIE(YoutubeBaseInfoExtractor):
def _extract_n_function_name(self, jscode): def _extract_n_function_name(self, jscode):
func_name, idx = self._search_regex( func_name, idx = self._search_regex(
# new: (b=String.fromCharCode(110),c=a.get(b))&&c=nfunc[idx](c) # new: (b=String.fromCharCode(110),c=a.get(b))&&c=nfunc[idx](c)
# or: (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)s # or: (b="nn"[+a.D],c=a.get(b))&&(c=nfunc[idx](c)
# old: .get("n"))&&(b=nfunc[idx](b) # or: (PL(a),b=a.j.n||null)&&(b=nfunc[idx](b)
# older: .get("n"))&&(b=nfunc(b) # or: (b="nn"[+a.D],vL(a),c=a.j[b]||null)&&(c=narray[idx](c),a.set(b,c),narray.length||nfunc("")
# old: (b=a.get("n"))&&(b=nfunc[idx](b)(?P<c>[a-z])\s*=\s*[a-z]\s*
# older: (b=a.get("n"))&&(b=nfunc(b)
r'''(?x) r'''(?x)
(?:\(\s*(?P<b>[a-z])\s*=\s*(?: \((?:[\w$()\s]+,)*?\s* # (
String\s*\.\s*fromCharCode\s*\(\s*110\s*\)| (?P<b>[a-z])\s*=\s* # b=
"n+"\[\s*\+?s*[\w$.]+\s*] (?:
)\s*,(?P<c>[a-z])\s*=\s*[a-z]\s*)? (?: # expect ,c=a.get(b) (etc)
\.\s*get\s*\(\s*(?(b)(?P=b)|"n{1,2}")(?:\s*\)){2}\s*&&\s*\(\s*(?(c)(?P=c)|b)\s*=\s* String\s*\.\s*fromCharCode\s*\(\s*110\s*\)|
(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\) "n+"\[\s*\+?s*[\w$.]+\s*]
''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx')) )\s*(?:,[\w$()\s]+(?=,))*|
(?P<old>[\w$]+) # a (old[er])
)\s*
(?(old)
# b.get("n")
(?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
(?:\.\s*n|\[\s*"n"\s*]|\.\s*get\s*\(\s*"n"\s*\))
| # ,c=a.get(b)
,\s*(?P<c>[a-z])\s*=\s*[a-z]\s*
(?:\.\s*[\w$]+\s*|\[\s*[\w$]+\s*]\s*)*?
(?:\[\s*(?P=b)\s*]|\.\s*get\s*\(\s*(?P=b)\s*\))
)
# interstitial junk
\s*(?:\|\|\s*null\s*)?(?:\)\s*)?&&\s*(?:\(\s*)?
(?(c)(?P=c)|(?P=b))\s*=\s* # [c|b]=
# nfunc|nfunc[idx]
(?P<nfunc>[a-zA-Z_$][\w$]*)(?:\s*\[(?P<idx>\d+)\])?\s*\(\s*[\w$]+\s*\)
''', jscode, 'Initial JS player n function name', group=('nfunc', 'idx'),
default=(None, None))
# thx bashonly: yt-dlp/yt-dlp/pull/10611
if not func_name:
self.report_warning('Falling back to generic n function search')
return self._search_regex(
r'''(?xs)
(?:(?<=[^\w$])|^) # instead of \b, which ignores $
(?P<name>(?!\d)[a-zA-Z\d_$]+)\s*=\s*function\((?!\d)[a-zA-Z\d_$]+\)
\s*\{(?:(?!};).)+?["']enhanced_except_
''', jscode, 'Initial JS player n function name', group='name')
if not idx: if not idx:
return func_name return func_name

View File

@ -925,9 +925,16 @@ class JSInterpreter(object):
obj.reverse() obj.reverse()
return obj return obj
elif member == 'slice': elif member == 'slice':
assertion(isinstance(obj, list), 'must be applied on a list') assertion(isinstance(obj, (list, compat_str)), 'must be applied on a list or string')
assertion(len(argvals) == 1, 'takes exactly one argument') # From [1]:
return obj[argvals[0]:] # .slice() - like [:]
# .slice(n) - like [n:] (not [slice(n)]
# .slice(m, n) - like [m:n] or [slice(m, n)]
# [1] https://developer.mozilla.org/en-US/docs/Web/JavaScript/Reference/Global_Objects/Array/slice
assertion(len(argvals) <= 2, 'takes between 0 and 2 arguments')
if len(argvals) < 2:
argvals += (None,)
return obj[slice(*argvals)]
elif member == 'splice': elif member == 'splice':
assertion(isinstance(obj, list), 'must be applied on a list') assertion(isinstance(obj, list), 'must be applied on a list')
assertion(argvals, 'takes one or more arguments') assertion(argvals, 'takes one or more arguments')