21 from .common
import InfoExtractor
, SearchInfoExtractor
22 from .openload
import PhantomJSwrapper
23 from ..compat
import functools
24 from ..jsinterp
import JSInterpreter
69 # any clients starting with _ cannot be explicitly requested by the user
72 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
73 'INNERTUBE_CONTEXT': {
76 'clientVersion': '2.20220801.00.00',
79 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
85 'clientName': 'WEB_EMBEDDED_PLAYER',
86 'clientVersion': '1.20220731.00.00',
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
92 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
93 'INNERTUBE_HOST': 'music.youtube.com',
94 'INNERTUBE_CONTEXT': {
96 'clientName': 'WEB_REMIX',
97 'clientVersion': '1.20220727.01.00',
100 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
103 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
104 'INNERTUBE_CONTEXT': {
106 'clientName': 'WEB_CREATOR',
107 'clientVersion': '1.20220726.00.00',
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
113 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
114 'INNERTUBE_CONTEXT': {
116 'clientName': 'ANDROID',
117 'clientVersion': '17.31.35',
118 'androidSdkVersion': 30,
119 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
122 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
123 'REQUIRE_JS_PLAYER': False
125 'android_embedded': {
126 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
127 'INNERTUBE_CONTEXT': {
129 'clientName': 'ANDROID_EMBEDDED_PLAYER',
130 'clientVersion': '17.31.35',
131 'androidSdkVersion': 30,
132 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
140 'INNERTUBE_CONTEXT': {
142 'clientName': 'ANDROID_MUSIC',
143 'clientVersion': '5.16.51',
144 'androidSdkVersion': 30,
145 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
149 'REQUIRE_JS_PLAYER': False
152 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
153 'INNERTUBE_CONTEXT': {
155 'clientName': 'ANDROID_CREATOR',
156 'clientVersion': '22.30.100',
157 'androidSdkVersion': 30,
158 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
161 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
162 'REQUIRE_JS_PLAYER': False
164 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
165 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
167 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
168 'INNERTUBE_CONTEXT': {
171 'clientVersion': '17.33.2',
172 'deviceModel': 'iPhone14,3',
173 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
180 'INNERTUBE_CONTEXT': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
183 'clientVersion': '17.33.2',
184 'deviceModel': 'iPhone14,3',
185 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
193 'INNERTUBE_CONTEXT': {
195 'clientName': 'IOS_MUSIC',
196 'clientVersion': '5.21',
197 'deviceModel': 'iPhone14,3',
198 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
201 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
202 'REQUIRE_JS_PLAYER': False
205 'INNERTUBE_CONTEXT': {
207 'clientName': 'IOS_CREATOR',
208 'clientVersion': '22.33.101',
209 'deviceModel': 'iPhone14,3',
210 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
213 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
214 'REQUIRE_JS_PLAYER': False
216 # mweb has 'ultralow' formats
217 # See: https://github.com/yt-dlp/yt-dlp/pull/557
219 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
220 'INNERTUBE_CONTEXT': {
222 'clientName': 'MWEB',
223 'clientVersion': '2.20220801.00.00',
226 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
228 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
229 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
231 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
232 'INNERTUBE_CONTEXT': {
234 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
235 'clientVersion': '2.0',
238 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
243 def _split_innertube_client(client_name
):
244 variant
, *base
= client_name
.rsplit('.', 1)
246 return variant
, base
[0], variant
247 base
, *variant
= client_name
.split('_', 1)
248 return client_name
, base
, variant
[0] if variant
else None
251 def build_innertube_clients():
253 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
255 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
256 priority
= qualities(BASE_CLIENTS
[::-1])
258 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
259 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
260 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
261 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
262 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
264 _
, base_client
, variant
= _split_innertube_client(client
)
265 ytcfg
['priority'] = 10 * priority(base_client
)
268 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
269 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
270 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
271 embedscreen
['priority'] -= 3
272 elif variant
== 'embedded':
273 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
274 ytcfg
['priority'] -= 2
276 ytcfg
['priority'] -= 3
279 build_innertube_clients()
282 class BadgeType(enum
.Enum
):
283 AVAILABILITY_UNLISTED
= enum
.auto()
284 AVAILABILITY_PRIVATE
= enum
.auto()
285 AVAILABILITY_PUBLIC
= enum
.auto()
286 AVAILABILITY_PREMIUM
= enum
.auto()
287 AVAILABILITY_SUBSCRIPTION
= enum
.auto()
288 LIVE_NOW
= enum
.auto()
291 class YoutubeBaseInfoExtractor(InfoExtractor
):
292 """Provide base functions for Youtube extractors"""
295 r
'channel|c|user|playlist|watch|w|v|embed|e|live|watch_popup|clip|'
296 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
297 r
'browse|oembed|get_video_info|iframe_api|s/player|source|'
298 r
'storefront|oops|index|account|t/terms|about|upload|signin|logout')
300 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
302 # _NETRC_MACHINE = 'youtube'
304 # If True it will raise an error if no login info is provided
305 _LOGIN_REQUIRED
= False
308 # invidious-redirect websites
309 r
'(?:www\.)?redirect\.invidious\.io',
310 r
'(?:(?:www|dev)\.)?invidio\.us',
311 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
312 r
'(?:www\.)?invidious\.pussthecat\.org',
313 r
'(?:www\.)?invidious\.zee\.li',
314 r
'(?:www\.)?invidious\.ethibox\.fr',
315 r
'(?:www\.)?iv\.ggtyler\.dev',
316 r
'(?:www\.)?inv\.vern\.i2p',
317 r
'(?:www\.)?am74vkcrjp2d5v36lcdqgsj2m6x36tbrkhsruoegwfcizzabnfgf5zyd\.onion',
318 r
'(?:www\.)?inv\.riverside\.rocks',
319 r
'(?:www\.)?invidious\.silur\.me',
320 r
'(?:www\.)?inv\.bp\.projectsegfau\.lt',
321 r
'(?:www\.)?invidious\.g4c3eya4clenolymqbpgwz3q3tawoxw56yhzk4vugqrl6dtu3ejvhjid\.onion',
322 r
'(?:www\.)?invidious\.slipfox\.xyz',
323 r
'(?:www\.)?invidious\.esmail5pdn24shtvieloeedh7ehz3nrwcdivnfhfcedl7gf4kwddhkqd\.onion',
324 r
'(?:www\.)?inv\.vernccvbvyi5qhfzyqengccj7lkove6bjot2xhh5kajhwvidqafczrad\.onion',
325 r
'(?:www\.)?invidious\.tiekoetter\.com',
326 r
'(?:www\.)?iv\.odysfvr23q5wgt7i456o5t3trw2cw5dgn56vbjfbq2m7xsc5vqbqpcyd\.onion',
327 r
'(?:www\.)?invidious\.nerdvpn\.de',
328 r
'(?:www\.)?invidious\.weblibre\.org',
329 r
'(?:www\.)?inv\.odyssey346\.dev',
330 r
'(?:www\.)?invidious\.dhusch\.de',
331 r
'(?:www\.)?iv\.melmac\.space',
332 r
'(?:www\.)?watch\.thekitty\.zone',
333 r
'(?:www\.)?invidious\.privacydev\.net',
334 r
'(?:www\.)?ng27owmagn5amdm7l5s3rsqxwscl5ynppnis5dqcasogkyxcfqn7psid\.onion',
335 r
'(?:www\.)?invidious\.drivet\.xyz',
336 r
'(?:www\.)?vid\.priv\.au',
337 r
'(?:www\.)?euxxcnhsynwmfidvhjf6uzptsmh4dipkmgdmcmxxuo7tunp3ad2jrwyd\.onion',
338 r
'(?:www\.)?inv\.vern\.cc',
339 r
'(?:www\.)?invidious\.esmailelbob\.xyz',
340 r
'(?:www\.)?invidious\.sethforprivacy\.com',
341 r
'(?:www\.)?yt\.oelrichsgarcia\.de',
342 r
'(?:www\.)?yt\.artemislena\.eu',
343 r
'(?:www\.)?invidious\.flokinet\.to',
344 r
'(?:www\.)?invidious\.baczek\.me',
345 r
'(?:www\.)?y\.com\.sb',
346 r
'(?:www\.)?invidious\.epicsite\.xyz',
347 r
'(?:www\.)?invidious\.lidarshield\.cloud',
348 r
'(?:www\.)?yt\.funami\.tech',
349 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
350 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
351 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
352 # youtube-dl invidious instances list
353 r
'(?:(?:www|no)\.)?invidiou\.sh',
354 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
355 r
'(?:www\.)?invidious\.kabi\.tk',
356 r
'(?:www\.)?invidious\.mastodon\.host',
357 r
'(?:www\.)?invidious\.zapashcanon\.fr',
358 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
359 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
360 r
'(?:www\.)?invidious\.himiko\.cloud',
361 r
'(?:www\.)?invidious\.reallyancient\.tech',
362 r
'(?:www\.)?invidious\.tube',
363 r
'(?:www\.)?invidiou\.site',
364 r
'(?:www\.)?invidious\.site',
365 r
'(?:www\.)?invidious\.xyz',
366 r
'(?:www\.)?invidious\.nixnet\.xyz',
367 r
'(?:www\.)?invidious\.048596\.xyz',
368 r
'(?:www\.)?invidious\.drycat\.fr',
369 r
'(?:www\.)?inv\.skyn3t\.in',
370 r
'(?:www\.)?tube\.poal\.co',
371 r
'(?:www\.)?tube\.connect\.cafe',
372 r
'(?:www\.)?vid\.wxzm\.sx',
373 r
'(?:www\.)?vid\.mint\.lgbt',
374 r
'(?:www\.)?vid\.puffyan\.us',
375 r
'(?:www\.)?yewtu\.be',
376 r
'(?:www\.)?yt\.elukerio\.org',
377 r
'(?:www\.)?yt\.lelux\.fi',
378 r
'(?:www\.)?invidious\.ggc-project\.de',
379 r
'(?:www\.)?yt\.maisputain\.ovh',
380 r
'(?:www\.)?ytprivate\.com',
381 r
'(?:www\.)?invidious\.13ad\.de',
382 r
'(?:www\.)?invidious\.toot\.koeln',
383 r
'(?:www\.)?invidious\.fdn\.fr',
384 r
'(?:www\.)?watch\.nettohikari\.com',
385 r
'(?:www\.)?invidious\.namazso\.eu',
386 r
'(?:www\.)?invidious\.silkky\.cloud',
387 r
'(?:www\.)?invidious\.exonip\.de',
388 r
'(?:www\.)?invidious\.riverside\.rocks',
389 r
'(?:www\.)?invidious\.blamefran\.net',
390 r
'(?:www\.)?invidious\.moomoo\.de',
391 r
'(?:www\.)?ytb\.trom\.tf',
392 r
'(?:www\.)?yt\.cyberhost\.uk',
393 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
394 r
'(?:www\.)?qklhadlycap4cnod\.onion',
395 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
396 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
397 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
398 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
399 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
400 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
401 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
402 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
403 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
404 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
405 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
406 r
'(?:www\.)?piped\.kavin\.rocks',
407 r
'(?:www\.)?piped\.tokhmi\.xyz',
408 r
'(?:www\.)?piped\.syncpundit\.io',
409 r
'(?:www\.)?piped\.mha\.fi',
410 r
'(?:www\.)?watch\.whatever\.social',
411 r
'(?:www\.)?piped\.garudalinux\.org',
412 r
'(?:www\.)?piped\.rivo\.lol',
413 r
'(?:www\.)?piped-libre\.kavin\.rocks',
414 r
'(?:www\.)?yt\.jae\.fi',
415 r
'(?:www\.)?piped\.mint\.lgbt',
417 r
'(?:www\.)?piped\.esmailelbob\.xyz',
418 r
'(?:www\.)?piped\.projectsegfau\.lt',
419 r
'(?:www\.)?piped\.privacydev\.net',
420 r
'(?:www\.)?piped\.palveluntarjoaja\.eu',
421 r
'(?:www\.)?piped\.smnz\.de',
422 r
'(?:www\.)?piped\.adminforge\.de',
423 r
'(?:www\.)?watch\.whatevertinfoil\.de',
424 r
'(?:www\.)?piped\.qdi\.fi',
425 r
'(?:www\.)?piped\.video',
426 r
'(?:www\.)?piped\.aeong\.one',
427 r
'(?:www\.)?piped\.moomoo\.me',
428 r
'(?:www\.)?piped\.chauvet\.pro',
429 r
'(?:www\.)?watch\.leptons\.xyz',
430 r
'(?:www\.)?pd\.vern\.cc',
431 r
'(?:www\.)?piped\.hostux\.net',
432 r
'(?:www\.)?piped\.lunar\.icu',
433 # Hyperpipe instances from https://hyperpipe.codeberg.page/
434 r
'(?:www\.)?hyperpipe\.surge\.sh',
435 r
'(?:www\.)?hyperpipe\.esmailelbob\.xyz',
436 r
'(?:www\.)?listen\.whatever\.social',
437 r
'(?:www\.)?music\.adminforge\.de',
440 # extracted from account/account_menu ep
441 # XXX: These are the supported YouTube UI and API languages,
442 # which is slightly different from languages supported for translation in YouTube studio
443 _SUPPORTED_LANG_CODES
= [
444 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
445 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
446 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
447 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
448 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
449 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
452 _IGNORED_WARNINGS
= {'Unavailable videos will be hidden during playback'}
454 @functools.cached_property
455 def _preferred_lang(self
):
457 Returns a language code supported by YouTube for the user preferred language.
458 Returns None if no preferred language set.
460 preferred_lang
= self
._configuration
_arg
('lang', ie_key
='Youtube', casesense
=True, default
=[''])[0]
461 if not preferred_lang
:
463 if preferred_lang
not in self
._SUPPORTED
_LANG
_CODES
:
464 raise ExtractorError(
465 f
'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
467 elif preferred_lang
!= 'en':
469 f
'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
470 return preferred_lang
472 def _initialize_consent(self
):
473 cookies
= self
._get
_cookies
('https://www.youtube.com/')
474 if cookies
.get('__Secure-3PSID'):
477 consent
= cookies
.get('CONSENT')
479 if 'YES' in consent
.value
:
481 consent_id
= self
._search
_regex
(
482 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
484 consent_id
= random
.randint(100, 999)
485 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
487 def _initialize_pref(self
):
488 cookies
= self
._get
_cookies
('https://www.youtube.com/')
489 pref_cookie
= cookies
.get('PREF')
493 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
495 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
496 pref
.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}
)
497 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
499 def _real_initialize(self
):
500 self
._initialize
_pref
()
501 self
._initialize
_consent
()
502 self
._check
_login
_required
()
504 def _check_login_required(self
):
505 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
506 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
508 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
509 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
511 def _get_default_ytcfg(self, client='web'):
512 return copy.deepcopy(INNERTUBE_CLIENTS[client])
514 def _get_innertube_host(self, client='web'):
515 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
517 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
518 # try_get but with fallback to default ytcfg client values when present
519 _func = lambda y: try_get(y, getter, expected_type)
520 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
522 def _extract_client_name(self, ytcfg, default_client='web'):
523 return self._ytcfg_get_safe(
524 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
525 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
527 def _extract_client_version(self, ytcfg, default_client='web'):
528 return self._ytcfg_get_safe(
529 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
530 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
532 def _select_api_hostname(self, req_api_hostname, default_client=None):
533 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
534 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
536 def _extract_api_key(self, ytcfg=None, default_client='web'):
537 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
539 def _extract_context(self, ytcfg=None, default_client='web'):
541 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
542 # Enforce language and tz for extraction
543 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
544 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
549 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
550 time_now = round(time.time())
551 if self._SAPISID is None:
552 yt_cookies = self._get_cookies('https://www.youtube.com')
553 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
554 # See: https://github.com/yt-dlp/yt-dlp/issues/393
555 sapisid_cookie = dict_get(
556 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
557 if sapisid_cookie and sapisid_cookie.value:
558 self._SAPISID = sapisid_cookie.value
559 self.write_debug('Extracted SAPISID cookie')
560 # SAPISID cookie is required if not already present
561 if not yt_cookies.get('SAPISID'):
562 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
564 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
566 self._SAPISID = False
567 if not self._SAPISID:
569 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
570 sapisidhash = hashlib.sha1(
571 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
572 return f'SAPISIDHASH {time_now}_{sapisidhash}'
574 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
575 note='Downloading API JSON', errnote='Unable to download API page',
576 context=None, api_key=None, api_hostname=None, default_client='web'):
578 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
580 real_headers = self.generate_api_headers(default_client=default_client)
581 real_headers.update({'content-type': 'application/json'})
583 real_headers.update(headers)
584 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
585 or api_key or self._extract_api_key(default_client=default_client))
586 return self._download_json(
587 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
588 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
589 data=json.dumps(data).encode('utf8'), headers=real_headers,
590 query={'key': api_key, 'prettyPrint': 'false'})
592 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
593 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
596 def _extract_session_index(*data):
598 Index of current account in account list.
599 See: https://github.com/yt-dlp/yt-dlp/pull/519
602 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
603 if session_index is not None:
607 def _extract_identity_token(self, ytcfg=None, webpage=None):
609 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
613 return self._search_regex(
614 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
615 'identity token
', default=None, fatal=False)
618 def _extract_account_syncid(*args):
620 Extract syncId required to download private playlists of secondary channels
621 @params response and/or ytcfg
624 # ytcfg includes channel_syncid if on secondary channel
625 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
629 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
630 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
631 if len(sync_ids) >= 2 and sync_ids[1]:
632 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
633 # and just "user_syncid||" for primary channel. We only want the channel_syncid
637 def _extract_visitor_data(*args):
639 Extracts visitorData from an API response or ytcfg
640 Appears to be used to track session state
643 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
646 @functools.cached_property
647 def is_authenticated(self):
648 return bool(self._generate_sapisidhash_header())
650 def extract_ytcfg(self, video_id, webpage):
653 return self._parse_json(
655 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
656 default='{}'), video_id, fatal=False) or {}
658 def generate_api_headers(
659 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
660 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
662 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
664 'X-YouTube-Client-Name': str(
665 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
666 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
668 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
669 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
670 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
),
671 'User-Agent': self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT']['client']['userAgent'], default_client
=default_client
)
673 if session_index
is None:
674 session_index
= self
._extract
_session
_index
(ytcfg
)
675 if account_syncid
or session_index
is not None:
676 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
678 auth
= self
._generate
_sapisidhash
_header
(origin
)
680 headers
['Authorization'] = auth
681 headers
['X-Origin'] = origin
682 return filter_dict(headers
)
684 def _download_ytcfg(self
, client
, video_id
):
686 'web': 'https://www.youtube.com',
687 'web_music': 'https://music.youtube.com',
688 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
692 webpage
= self
._download
_webpage
(
693 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
694 return self
.extract_ytcfg(video_id
, webpage
) or {}
697 def _build_api_continuation_query(continuation
, ctp
=None):
699 'continuation': continuation
701 # TODO: Inconsistency with clickTrackingParams.
702 # Currently we have a fixed ctp contained within context (from ytcfg)
703 # and a ctp in root query for continuation.
705 query
['clickTracking'] = {'clickTrackingParams': ctp}
709 def _extract_next_continuation_data(cls
, renderer
):
710 next_continuation
= try_get(
711 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
712 lambda x
: x
['continuation']['reloadContinuationData']), dict)
713 if not next_continuation
:
715 continuation
= next_continuation
.get('continuation')
718 ctp
= next_continuation
.get('clickTrackingParams')
719 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
722 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
723 if isinstance(continuation_ep
, dict):
724 continuation
= try_get(
725 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
728 ctp
= continuation_ep
.get('clickTrackingParams')
729 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
732 def _extract_continuation(cls
, renderer
):
733 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
734 if next_continuation
:
735 return next_continuation
737 return traverse_obj(renderer
, (
738 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
739 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
740 ), get_all
=False, expected_type
=cls
._extract
_continuation
_ep
_data
)
743 def _extract_alerts(cls
, data
):
744 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
745 if not isinstance(alert_dict
, dict):
747 for alert
in alert_dict
.values():
748 alert_type
= alert
.get('type')
751 message
= cls
._get
_text
(alert
, 'text')
753 yield alert_type
, message
755 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
756 errors
, warnings
= [], []
757 for alert_type
, alert_message
in alerts
:
758 if alert_type
.lower() == 'error' and fatal
:
759 errors
.append([alert_type
, alert_message
])
760 elif alert_message
not in self
._IGNORED
_WARNINGS
:
761 warnings
.append([alert_type
, alert_message
])
763 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
764 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
766 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
768 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
769 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
771 def _extract_badges(self
, renderer
: dict):
773 'PRIVACY_UNLISTED': BadgeType
.AVAILABILITY_UNLISTED
,
774 'PRIVACY_PRIVATE': BadgeType
.AVAILABILITY_PRIVATE
,
775 'PRIVACY_PUBLIC': BadgeType
.AVAILABILITY_PUBLIC
779 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType
.AVAILABILITY_SUBSCRIPTION
,
780 'BADGE_STYLE_TYPE_PREMIUM': BadgeType
.AVAILABILITY_PREMIUM
,
781 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType
.LIVE_NOW
785 'unlisted': BadgeType
.AVAILABILITY_UNLISTED
,
786 'private': BadgeType
.AVAILABILITY_PRIVATE
,
787 'members only': BadgeType
.AVAILABILITY_SUBSCRIPTION
,
788 'live': BadgeType
.LIVE_NOW
,
789 'premium': BadgeType
.AVAILABILITY_PREMIUM
793 for badge
in traverse_obj(renderer
, ('badges', ..., 'metadataBadgeRenderer')):
795 privacy_icon_map
.get(traverse_obj(badge
, ('icon', 'iconType'), expected_type
=str))
796 or badge_style_map
.get(traverse_obj(badge
, 'style'))
799 badges
.append({'type': badge_type}
)
802 # fallback, won't work in some languages
803 label
= traverse_obj(badge
, 'label', expected_type
=str, default
='')
804 for match
, label_badge_type
in label_map
.items():
805 if match
in label
.lower():
806 badges
.append({'type': badge_type}
)
812 def _has_badge(badges
, badge_type
):
813 return bool(traverse_obj(badges
, lambda _
, v
: v
['type'] == badge_type
))
816 def _get_text(data
, *path_list
, max_runs
=None):
817 for path
in path_list
or [None]:
821 obj
= traverse_obj(data
, path
, default
=[])
822 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
825 text
= try_get(item
, lambda x
: x
['simpleText'], str)
828 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
829 if not runs
and isinstance(item
, list):
832 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
833 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str))
837 def _get_count(self
, data
, *path_list
):
838 count_text
= self
._get
_text
(data
, *path_list
) or ''
839 count
= parse_count(count_text
)
842 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
846 def _extract_thumbnails(data
, *path_list
):
848 Extract thumbnails from thumbnails dict
849 @param path_list: path list to level that contains 'thumbnails' key
852 for path
in path_list
or [()]:
853 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...)):
854 thumbnail_url
= url_or_none(thumbnail
.get('url'))
855 if not thumbnail_url
:
857 # Sometimes youtube gives a wrong thumbnail URL. See:
858 # https://github.com/yt-dlp/yt-dlp/issues/233
859 # https://github.com/ytdl-org/youtube-dl/issues/28023
860 if 'maxresdefault' in thumbnail_url
:
861 thumbnail_url
= thumbnail_url
.split('?')[0]
863 'url': thumbnail_url
,
864 'height': int_or_none(thumbnail
.get('height')),
865 'width': int_or_none(thumbnail
.get('width')),
870 def extract_relative_time(relative_time_text
):
872 Extracts a relative time from string and converts to dt object
873 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
875 mobj
= re
.search(r
'(?P<start>today|yesterday|now)|(?P<time>\d+)\s*(?P<unit>microsecond|second|minute|hour|day|week|month|year)s?\s*ago', relative_time_text
)
877 start
= mobj
.group('start')
879 return datetime_from_str(start
)
881 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
885 def _parse_time_text(self
, text
):
888 dt
= self
.extract_relative_time(text
)
890 if isinstance(dt
, datetime
.datetime
):
891 timestamp
= calendar
.timegm(dt
.timetuple())
893 if timestamp
is None:
895 unified_timestamp(text
) or unified_timestamp(
897 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
898 text
.lower(), 'time text', default
=None)))
900 if text
and timestamp
is None and self
._preferred
_lang
in (None, 'en'):
902 f
'Cannot parse localized time text "{text}"', only_once
=True)
905 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
906 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
907 default_client
='web'):
908 for retry
in self
.RetryManager():
910 response
= self
._call
_api
(
911 ep
=ep
, fatal
=True, headers
=headers
,
912 video_id
=item_id
, query
=query
, note
=note
,
913 context
=self
._extract
_context
(ytcfg
, default_client
),
914 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
915 api_hostname
=api_hostname
, default_client
=default_client
)
916 except ExtractorError
as e
:
917 if not isinstance(e
.cause
, network_exceptions
):
918 return self
._error
_or
_warning
(e
, fatal
=fatal
)
919 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
923 first_bytes
= e
.cause
.read(512)
924 if not is_html(first_bytes
):
927 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
928 lambda x
: x
['error']['message'], str)
930 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
931 # Downloading page may result in intermittent 5xx HTTP error
932 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
933 # We also want to catch all other network exceptions since errors in later pages can be troublesome
934 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
935 if e
.cause
.code
not in (403, 429):
938 return self
._error
_or
_warning
(e
, fatal
=fatal
)
941 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
942 except ExtractorError
as e
:
943 # YouTube servers may return errors we want to retry on in a 200 OK response
944 # See: https://github.com/yt-dlp/yt-dlp/issues/839
945 if 'unknown error' in e
.msg
.lower():
948 return self
._error
_or
_warning
(e
, fatal
=fatal
)
949 # Youtube sometimes sends incomplete data
950 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
951 if not traverse_obj(response
, *variadic(check_get_keys
)):
952 retry
.error
= ExtractorError('Incomplete data received', expected
=True)
958 def is_music_url(url
):
959 return re
.match(r
'(https?://)?music\.youtube\.com/', url
) is not None
961 def _extract_video(self
, renderer
):
962 video_id
= renderer
.get('videoId')
964 reel_header_renderer
= traverse_obj(renderer
, (
965 'navigationEndpoint', 'reelWatchEndpoint', 'overlay', 'reelPlayerOverlayRenderer',
966 'reelPlayerHeaderSupportedRenderers', 'reelPlayerHeaderRenderer'))
968 title
= self
._get
_text
(renderer
, 'title', 'headline') or self
._get
_text
(reel_header_renderer
, 'reelTitleText')
969 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
971 duration
= int_or_none(renderer
.get('lengthSeconds'))
973 duration
= parse_duration(self
._get
_text
(
974 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
976 # XXX: should write a parser to be more general to support more cases (e.g. shorts in shorts tab)
977 duration
= parse_duration(self
._search
_regex
(
978 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
979 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
980 video_id
, default
=None, group
='duration'))
982 channel_id
= traverse_obj(
983 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
984 expected_type
=str, get_all
=False)
986 channel_id
= traverse_obj(reel_header_renderer
, ('channelNavigationEndpoint', 'browseEndpoint', 'browseId'))
988 overlay_style
= traverse_obj(
989 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
990 get_all
=False, expected_type
=str)
991 badges
= self
._extract
_badges
(renderer
)
993 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
994 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
995 expected_type
=str)) or ''
996 url
= f
'https://www.youtube.com/watch?v={video_id}'
997 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
998 url
= f
'https://www.youtube.com/shorts/{video_id}'
1000 time_text
= (self
._get
_text
(renderer
, 'publishedTimeText', 'videoInfo')
1001 or self
._get
_text
(reel_header_renderer
, 'timestampText') or '')
1002 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
1005 'is_upcoming' if scheduled_timestamp
is not None
1006 else 'was_live' if 'streamed' in time_text
.lower()
1007 else 'is_live' if overlay_style
== 'LIVE' or self
._has
_badge
(badges
, BadgeType
.LIVE_NOW
)
1010 # videoInfo is a string like '50K views • 10 years ago'.
1011 view_count_text
= self
._get
_text
(renderer
, 'viewCountText', 'shortViewCountText', 'videoInfo') or ''
1012 view_count
= (0 if 'no views' in view_count_text
.lower()
1013 else self
._get
_count
({'simpleText': view_count_text}
))
1014 view_count_field
= 'concurrent_view_count' if live_status
in ('is_live', 'is_upcoming') else 'view_count'
1018 'ie_key': YoutubeIE
.ie_key(),
1022 'description': description
,
1023 'duration': duration
,
1024 'channel_id': channel_id
,
1025 'channel': (self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
1026 or self
._get
_text
(reel_header_renderer
, 'channelTitleText')),
1027 'channel_url': f
'https://www.youtube.com/channel/{channel_id}' if channel_id
else None,
1028 'thumbnails': self
._extract
_thumbnails
(renderer
, 'thumbnail'),
1029 'timestamp': (self
._parse
_time
_text
(time_text
)
1030 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
)
1032 'release_timestamp': scheduled_timestamp
,
1034 'public' if self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
1035 else self
._availability
(
1036 is_private
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
) or None,
1037 needs_premium
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
) or None,
1038 needs_subscription
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
) or None,
1039 is_unlisted
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
) or None),
1040 view_count_field
: view_count
,
1041 'live_status': live_status
1045 class YoutubeIE(YoutubeBaseInfoExtractor
):
1047 _VALID_URL
= r
"""(?x)^
1049 (?:https?://|//) # http(s):// or protocol-independent URL
1050 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
1051 (?:www\.)?deturl\.com/www\.youtube\.com|
1052 (?:www\.)?pwnyoutube\.com|
1053 (?:www\.)?hooktube\.com|
1054 (?:www\.)?yourepeat\.com|
1055 tube\.majestyc\.net|
1057 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
1058 (?:.*?\#/)? # handle anchor (#/) redirect urls
1059 (?: # the various things that can precede the ID:
1060 (?:(?:v|embed|e|shorts|live)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
1061 |(?: # or the v= param in all its forms
1062 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
1063 (?:\?|\#!?) # the params delimiter ? or # or #!
1064 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
1069 youtu\.be| # just youtu.be/xxxx
1070 vid\.plus| # or vid.plus/xxxx
1071 zwearz\.com/watch| # or zwearz.com/watch/xxxx
1074 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
1076 )? # all until now is optional -> you can pass the naked ID
1077 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
1078 (?(1).+)? # if we found the ID, everything can follow
1080 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
1085 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1093 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1094 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1096 # https://wordpress.org/plugins/lazy-load-for-videos/
1098 <a\s
[^
>]*\bhref
="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1099 \s
[^
>]*\bclass
="[^"]*\blazy
-load
-youtube
''',
1101 _RETURN_TYPE = 'video' # XXX: How to handle multifeed?
1104 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1105 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
1106 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1109 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1110 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1111 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1112 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1113 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1114 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1115 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1116 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1117 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1118 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1119 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1120 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1121 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1122 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1123 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1124 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1125 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1126 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1130 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1131 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1132 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1133 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1134 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1135 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1136 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1138 # Apple HTTP Live Streaming
1139 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1140 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1141 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1142 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1143 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1144 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1145 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1146 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1149 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1150 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1151 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1152 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1153 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1154 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1155 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1156 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1157 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1158 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1159 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1160 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1163 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1164 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1165 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1166 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1167 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1168 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1169 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1172 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1173 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1174 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1175 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1176 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1177 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1178 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1179 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1180 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1181 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1182 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1183 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1184 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1185 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1186 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1187 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1188 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1189 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1190 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1191 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1192 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1193 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1196 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1197 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1199 # Dash webm audio with opus inside
1200 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1201 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1202 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1205 '_rtmp': {'protocol': 'rtmp'},
1207 # av01 video only formats sometimes served with "unknown" codecs
1208 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1209 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1210 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1211 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1212 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1213 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1214 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1215 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1217 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1224 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1226 'id': 'BaW_jenozKc',
1228 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1229 'uploader': 'Philipp Hagemeister',
1230 'uploader_id': 'phihag',
1231 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1232 'channel': 'Philipp Hagemeister',
1233 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1234 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1235 'upload_date': '20121002',
1236 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1237 'categories': ['Science & Technology'],
1238 'tags': ['youtube-dl'],
1242 'availability': 'public',
1243 'playable_in_embed': True,
1244 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1245 'live_status': 'not_live',
1249 'comment_count': int,
1250 'channel_follower_count': int
1254 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1255 'note': 'Embed-only video (#1746)',
1257 'id': 'yZIXLfi8CZQ',
1259 'upload_date': '20120608',
1260 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1261 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1262 'uploader': 'SET India',
1263 'uploader_id': 'setindia',
1264 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1267 'skip': 'Private video',
1270 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1271 'note': 'Use the first video ID in the URL',
1273 'id': 'BaW_jenozKc',
1275 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1276 'uploader': 'Philipp Hagemeister',
1277 'uploader_id': 'phihag',
1278 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1279 'channel': 'Philipp Hagemeister',
1280 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1281 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1282 'upload_date': '20121002',
1283 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1284 'categories': ['Science & Technology'],
1285 'tags': ['youtube-dl'],
1289 'availability': 'public',
1290 'playable_in_embed': True,
1291 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1292 'live_status': 'not_live',
1294 'comment_count': int,
1295 'channel_follower_count': int
1298 'skip_download': True,
1302 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1303 'note': '256k DASH audio (format 141) via DASH manifest',
1305 'id': 'a9LDPn-MO4I',
1307 'upload_date': '20121002',
1308 'uploader_id': '8KVIDEO',
1309 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1311 'uploader': '8KVIDEO',
1312 'title': 'UHDTV TEST 8K VIDEO.mp4'
1315 'youtube_include_dash_manifest': True,
1318 'skip': 'format 141 not served anymore',
1320 # DASH manifest with encrypted signature
1322 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1324 'id': 'IB3lcPjvWLA',
1326 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1327 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1329 'uploader': 'AfrojackVEVO',
1330 'uploader_id': 'AfrojackVEVO',
1331 'upload_date': '20131011',
1334 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1335 'playable_in_embed': True,
1336 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1338 'track': 'The Spark',
1339 'live_status': 'not_live',
1340 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1341 'channel': 'Afrojack',
1342 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1344 'availability': 'public',
1345 'categories': ['Music'],
1347 'alt_title': 'The Spark',
1348 'channel_follower_count': int
1351 'youtube_include_dash_manifest': True,
1352 'format': '141/bestaudio[ext=m4a]',
1355 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1357 'note': 'Embed allowed age-gate video',
1358 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1360 'id': 'HtVdAasjOgU',
1362 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1363 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1365 'uploader': 'The Witcher',
1366 'uploader_id': 'WitcherGame',
1367 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1368 'upload_date': '20140605',
1370 'categories': ['Gaming'],
1371 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1372 'availability': 'needs_auth',
1373 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1375 'channel': 'The Witcher',
1376 'live_status': 'not_live',
1378 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1379 'playable_in_embed': True,
1381 'channel_follower_count': int
1385 'note': 'Age-gate video with embed allowed in public site',
1386 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1388 'id': 'HsUATh_Nc2U',
1390 'title': 'Godzilla 2 (Official Video)',
1391 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1392 'upload_date': '20200408',
1393 'uploader_id': 'FlyingKitty900',
1394 'uploader': 'FlyingKitty',
1396 'availability': 'needs_auth',
1397 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1398 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1399 'channel': 'FlyingKitty',
1400 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1402 'categories': ['Entertainment'],
1403 'live_status': 'not_live',
1404 'tags': ['Flyingkitty', 'godzilla 2'],
1405 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1408 'playable_in_embed': True,
1409 'channel_follower_count': int
1413 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1414 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1416 'id': 'Tq92D6wQ1mg',
1417 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1419 'upload_date': '20191228',
1420 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1421 'uploader': 'Projekt Melody',
1422 'description': 'md5:17eccca93a786d51bc67646756894066',
1425 'availability': 'needs_auth',
1426 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1427 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1429 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1430 'channel': 'Projekt Melody',
1431 'live_status': 'not_live',
1432 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1433 'playable_in_embed': True,
1434 'categories': ['Entertainment'],
1436 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1437 'comment_count': int,
1438 'channel_follower_count': int
1442 'note': 'Non-Agegated non-embeddable video',
1443 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1445 'id': 'MeJVWBSsPAY',
1447 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1448 'uploader': 'Herr Lurik',
1449 'uploader_id': 'st3in234',
1450 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1451 'upload_date': '20130730',
1452 'track': 'Such mich find mich',
1454 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1456 'playable_in_embed': False,
1457 'creator': 'OOMPH!',
1458 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1460 'alt_title': 'Such mich find mich',
1462 'channel': 'Herr Lurik',
1463 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1464 'categories': ['Music'],
1465 'availability': 'public',
1466 'uploader_url': 'http://www.youtube.com/user/st3in234',
1467 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1468 'live_status': 'not_live',
1470 'channel_follower_count': int
1474 'note': 'Non-bypassable age-gated video',
1475 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1476 'only_matching': True,
1478 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1479 # YouTube Red ad is not captured for creator
1481 'url': '__2ABJjxzNo',
1483 'id': '__2ABJjxzNo',
1486 'upload_date': '20100430',
1487 'uploader_id': 'deadmau5',
1488 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1489 'creator': 'deadmau5',
1490 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1491 'uploader': 'deadmau5',
1492 'title': 'Deadmau5 - Some Chords (HD)',
1493 'alt_title': 'Some Chords',
1494 'availability': 'public',
1496 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1498 'live_status': 'not_live',
1499 'channel': 'deadmau5',
1500 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1502 'track': 'Some Chords',
1503 'artist': 'deadmau5',
1504 'playable_in_embed': True,
1506 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1507 'categories': ['Music'],
1508 'album': 'Some Chords',
1509 'channel_follower_count': int
1511 'expected_warnings': [
1512 'DASH manifest missing',
1515 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1517 'url': 'lqQg6PlCWgI',
1519 'id': 'lqQg6PlCWgI',
1522 'upload_date': '20150827',
1523 'uploader_id': 'olympic',
1524 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1525 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1526 'uploader': 'Olympics',
1527 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1529 'release_timestamp': 1343767800,
1530 'playable_in_embed': True,
1531 'categories': ['Sports'],
1532 'release_date': '20120731',
1533 'channel': 'Olympics',
1534 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1535 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1536 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1538 'availability': 'public',
1539 'live_status': 'was_live',
1541 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1542 'channel_follower_count': int
1545 'skip_download': 'requires avconv',
1550 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1552 'id': '_b-2C3KPAM0',
1554 'stretched_ratio': 16 / 9.,
1556 'upload_date': '20110310',
1557 'uploader_id': 'AllenMeow',
1558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1559 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
1561 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1562 'playable_in_embed': True,
1566 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1567 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1568 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1570 'categories': ['People & Blogs'],
1572 'live_status': 'not_live',
1573 'availability': 'unlisted',
1574 'comment_count': int,
1575 'channel_follower_count': int
1578 # url_encoded_fmt_stream_map is empty string
1580 'url': 'qEJwOuvDf7I',
1582 'id': 'qEJwOuvDf7I',
1584 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1586 'upload_date': '20150404',
1587 'uploader_id': 'spbelect',
1588 'uploader': 'Наблюдатели Петербурга',
1591 'skip_download': 'requires avconv',
1593 'skip': 'This live event has ended.',
1595 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1597 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1599 'id': 'FIl7x6_3R5Y',
1601 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1602 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1604 'upload_date': '20150625',
1605 'uploader_id': 'dorappi2000',
1606 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1607 'uploader': 'dorappi2000',
1608 'formats': 'mincount:31',
1610 'skip': 'not actual anymore',
1612 # DASH manifest with segment_list
1614 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1615 'md5': '8ce563a1d667b599d21064e982ab9e31',
1617 'id': 'CsmdDsKjzN8',
1619 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1620 'uploader': 'Airtek',
1621 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1622 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1623 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1626 'youtube_include_dash_manifest': True,
1627 'format': '135', # bestvideo
1629 'skip': 'This live event has ended.',
1632 # Multifeed videos (multiple cameras), URL can be of any Camera
1633 'url': 'https://www.youtube.com/watch?v=zaPI8MvL8pg',
1635 'id': 'zaPI8MvL8pg',
1636 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04',
1637 'description': 'md5:563ccbc698b39298481ca3c571169519',
1641 'id': 'j5yGuxZ8lLU',
1643 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Chris)',
1644 'uploader': 'WiiLikeToPlay',
1645 'description': 'md5:563ccbc698b39298481ca3c571169519',
1646 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1648 'channel_follower_count': int,
1649 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1650 'availability': 'public',
1651 'playable_in_embed': True,
1652 'upload_date': '20131105',
1653 'uploader_id': 'WiiRikeToPray',
1654 'categories': ['Gaming'],
1655 'live_status': 'was_live',
1657 'release_timestamp': 1383701910,
1658 'thumbnail': 'https://i.ytimg.com/vi/j5yGuxZ8lLU/maxresdefault.jpg',
1659 'comment_count': int,
1662 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1663 'channel': 'WiiLikeToPlay',
1665 'release_date': '20131106',
1669 'id': 'zaPI8MvL8pg',
1671 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Tyson)',
1672 'uploader_id': 'WiiRikeToPray',
1673 'availability': 'public',
1674 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1675 'channel': 'WiiLikeToPlay',
1676 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1677 'channel_follower_count': int,
1678 'description': 'md5:563ccbc698b39298481ca3c571169519',
1683 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1684 'uploader': 'WiiLikeToPlay',
1685 'release_timestamp': 1383701915,
1686 'comment_count': int,
1687 'upload_date': '20131105',
1688 'thumbnail': 'https://i.ytimg.com/vi/zaPI8MvL8pg/maxresdefault.jpg',
1689 'release_date': '20131106',
1690 'playable_in_embed': True,
1691 'live_status': 'was_live',
1692 'categories': ['Gaming'],
1697 'id': 'R7r3vfO7Hao',
1699 'title': 'Terraria 1.2 Live Stream | Let\'s Play - Part 04 (Spencer)',
1700 'thumbnail': 'https://i.ytimg.com/vi/R7r3vfO7Hao/maxresdefault.jpg',
1701 'channel_id': 'UCN2XePorRokPB9TEgRZpddg',
1703 'availability': 'public',
1704 'playable_in_embed': True,
1705 'upload_date': '20131105',
1706 'description': 'md5:563ccbc698b39298481ca3c571169519',
1707 'uploader_id': 'WiiRikeToPray',
1708 'uploader_url': 'http://www.youtube.com/user/WiiRikeToPray',
1709 'channel_follower_count': int,
1711 'release_date': '20131106',
1712 'uploader': 'WiiLikeToPlay',
1713 'comment_count': int,
1714 'channel_url': 'https://www.youtube.com/channel/UCN2XePorRokPB9TEgRZpddg',
1715 'channel': 'WiiLikeToPlay',
1716 'categories': ['Gaming'],
1717 'release_timestamp': 1383701914,
1718 'live_status': 'was_live',
1724 'params': {'skip_download': True},
1727 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1728 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1730 'id': 'gVfLd0zydlo',
1731 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1733 'playlist_count': 2,
1734 'skip': 'Not multifeed anymore',
1737 'url': 'https://vid.plus/FlRa-iH7PGw',
1738 'only_matching': True,
1741 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1742 'only_matching': True,
1745 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1746 # Also tests cut-off URL expansion in video description (see
1747 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1748 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1749 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1751 'id': 'lsguqyKfVQg',
1753 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1754 'alt_title': 'Dark Walk',
1755 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1757 'upload_date': '20151119',
1758 'uploader_id': 'IronSoulElf',
1759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1760 'uploader': 'IronSoulElf',
1761 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1762 'track': 'Dark Walk',
1763 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1764 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1765 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1766 'categories': ['Film & Animation'],
1768 'live_status': 'not_live',
1769 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1770 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1772 'availability': 'public',
1773 'channel': 'IronSoulElf',
1774 'playable_in_embed': True,
1777 'channel_follower_count': int
1780 'skip_download': True,
1784 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1785 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1786 'only_matching': True,
1789 # Video with yt:stretch=17:0
1790 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1792 'id': 'Q39EVAstoRM',
1794 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1795 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1796 'upload_date': '20151107',
1797 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1798 'uploader': 'CH GAMER DROID',
1801 'skip_download': True,
1803 'skip': 'This video does not exist.',
1806 # Video with incomplete 'yt:stretch=16:'
1807 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1808 'only_matching': True,
1811 # Video licensed under Creative Commons
1812 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1814 'id': 'M4gD1WSo5mA',
1816 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1817 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1819 'upload_date': '20150128',
1820 'uploader_id': 'BerkmanCenter',
1821 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1822 'uploader': 'The Berkman Klein Center for Internet & Society',
1823 'license': 'Creative Commons Attribution license (reuse allowed)',
1824 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1825 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1828 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1829 'channel': 'The Berkman Klein Center for Internet & Society',
1830 'availability': 'public',
1832 'categories': ['Education'],
1833 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1834 'live_status': 'not_live',
1835 'playable_in_embed': True,
1836 'comment_count': int,
1837 'channel_follower_count': int,
1841 'skip_download': True,
1845 # Channel-like uploader_url
1846 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1848 'id': 'eQcmzGIKrzg',
1850 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1851 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1853 'upload_date': '20151120',
1854 'uploader': 'Bernie Sanders',
1855 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1856 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1857 'license': 'Creative Commons Attribution license (reuse allowed)',
1858 'playable_in_embed': True,
1861 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1863 'availability': 'public',
1864 'categories': ['News & Politics'],
1865 'channel': 'Bernie Sanders',
1866 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1868 'live_status': 'not_live',
1869 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1870 'comment_count': int,
1871 'channel_follower_count': int,
1875 'skip_download': True,
1879 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1880 'only_matching': True,
1883 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1884 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1885 'only_matching': True,
1888 # Rental video preview
1889 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1891 'id': 'uGpuVWrhIzE',
1893 'title': 'Piku - Trailer',
1894 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1895 'upload_date': '20150811',
1896 'uploader': 'FlixMatrix',
1897 'uploader_id': 'FlixMatrixKaravan',
1898 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1899 'license': 'Standard YouTube License',
1902 'skip_download': True,
1904 'skip': 'This video is not available.',
1907 # YouTube Red video with episode data
1908 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1910 'id': 'iqKdEhx-dD4',
1912 'title': 'Isolation - Mind Field (Ep 1)',
1913 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1915 'upload_date': '20170118',
1916 'uploader': 'Vsauce',
1917 'uploader_id': 'Vsauce',
1918 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1919 'series': 'Mind Field',
1921 'episode_number': 1,
1922 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1925 'availability': 'public',
1927 'channel': 'Vsauce',
1928 'episode': 'Episode 1',
1929 'categories': ['Entertainment'],
1930 'season': 'Season 1',
1931 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1932 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1934 'playable_in_embed': True,
1935 'live_status': 'not_live',
1936 'channel_follower_count': int
1939 'skip_download': True,
1941 'expected_warnings': [
1942 'Skipping DASH manifest',
1946 # The following content has been identified by the YouTube community
1947 # as inappropriate or offensive to some audiences.
1948 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1950 'id': '6SJNVb0GnPI',
1952 'title': 'Race Differences in Intelligence',
1953 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1955 'upload_date': '20140124',
1956 'uploader': 'New Century Foundation',
1957 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1958 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1961 'skip_download': True,
1963 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1967 'url': '1t24XAntNCY',
1968 'only_matching': True,
1971 # geo restricted to JP
1972 'url': 'sJL6WA-aGkQ',
1973 'only_matching': True,
1976 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1977 'only_matching': True,
1980 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1981 'only_matching': True,
1984 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1985 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1986 'only_matching': True,
1990 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1991 'only_matching': True,
1994 # Video with unsupported adaptive stream type formats
1995 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1997 'id': 'Z4Vy8R84T1U',
1999 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
2000 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
2002 'upload_date': '20130923',
2003 'uploader': 'Amelia Putri Harwita',
2004 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
2005 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
2006 'formats': 'maxcount:10',
2009 'skip_download': True,
2010 'youtube_include_dash_manifest': False,
2012 'skip': 'not actual anymore',
2015 # Youtube Music Auto-generated description
2016 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2018 'id': 'MgNrAu2pzNs',
2020 'title': 'Voyeur Girl',
2021 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
2022 'upload_date': '20190312',
2023 'uploader': 'Stephen - Topic',
2024 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2025 'artist': 'Stephen',
2026 'track': 'Voyeur Girl',
2027 'album': 'it\'s too much love to know my dear',
2028 'release_date': '20190313',
2029 'release_year': 2019,
2030 'alt_title': 'Voyeur Girl',
2032 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2033 'playable_in_embed': True,
2035 'categories': ['Music'],
2036 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
2037 'channel': 'Stephen',
2038 'availability': 'public',
2039 'creator': 'Stephen',
2041 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
2043 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
2045 'live_status': 'not_live',
2046 'channel_follower_count': int
2049 'skip_download': True,
2053 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
2054 'only_matching': True,
2057 # invalid -> valid video id redirection
2058 'url': 'DJztXj2GPfl',
2060 'id': 'DJztXj2GPfk',
2062 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
2063 'description': 'md5:bf577a41da97918e94fa9798d9228825',
2064 'upload_date': '20090125',
2065 'uploader': 'Prochorowka',
2066 'uploader_id': 'Prochorowka',
2067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
2068 'artist': 'Panjabi MC',
2069 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
2070 'album': 'Beware of the Boys (Mundian To Bach Ke)',
2073 'skip_download': True,
2075 'skip': 'Video unavailable',
2078 # empty description results in an empty string
2079 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
2081 'id': 'x41yOUIvK2k',
2083 'title': 'IMG 3456',
2085 'upload_date': '20170613',
2086 'uploader_id': 'ElevageOrVert',
2087 'uploader': 'ElevageOrVert',
2089 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
2090 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
2092 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
2094 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
2095 'availability': 'public',
2097 'categories': ['Pets & Animals'],
2099 'playable_in_embed': True,
2100 'live_status': 'not_live',
2101 'channel': 'ElevageOrVert',
2102 'channel_follower_count': int
2105 'skip_download': True,
2109 # with '};' inside yt initial data (see [1])
2110 # see [2] for an example with '};' inside ytInitialPlayerResponse
2111 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2112 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
2113 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2115 'id': 'CHqg6qOn4no',
2117 'title': 'Part 77 Sort a list of simple types in c#',
2118 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2119 'upload_date': '20130831',
2120 'uploader_id': 'kudvenkat',
2121 'uploader': 'kudvenkat',
2122 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2124 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2125 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2126 'live_status': 'not_live',
2127 'categories': ['Education'],
2128 'availability': 'public',
2129 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2131 'playable_in_embed': True,
2135 'channel': 'kudvenkat',
2136 'comment_count': int,
2137 'channel_follower_count': int,
2141 'skip_download': True,
2145 # another example of '};' in ytInitialData
2146 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2147 'only_matching': True,
2150 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2151 'only_matching': True,
2154 # https://github.com/ytdl-org/youtube-dl/pull/28094
2155 'url': 'OtqTfy26tG0',
2157 'id': 'OtqTfy26tG0',
2159 'title': 'Burn Out',
2160 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2161 'upload_date': '20141120',
2162 'uploader': 'The Cinematic Orchestra - Topic',
2163 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2164 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2165 'artist': 'The Cinematic Orchestra',
2166 'track': 'Burn Out',
2167 'album': 'Every Day',
2169 'live_status': 'not_live',
2170 'alt_title': 'Burn Out',
2174 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2175 'creator': 'The Cinematic Orchestra',
2176 'channel': 'The Cinematic Orchestra',
2177 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2178 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2179 'availability': 'public',
2180 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2181 'categories': ['Music'],
2182 'playable_in_embed': True,
2183 'channel_follower_count': int
2186 'skip_download': True,
2190 # controversial video, only works with bpctr when authenticated with cookies
2191 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2192 'only_matching': True,
2195 # controversial video, requires bpctr/contentCheckOk
2196 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2198 'id': 'SZJvDhaSDnc',
2200 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2201 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2202 'uploader': 'CBS Mornings',
2203 'uploader_id': 'CBSThisMorning',
2204 'upload_date': '20140716',
2205 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2207 'categories': ['News & Politics'],
2208 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2210 'channel': 'CBS Mornings',
2211 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2212 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2214 'availability': 'needs_auth',
2215 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2217 'live_status': 'not_live',
2218 'playable_in_embed': True,
2219 'channel_follower_count': int
2223 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2224 'url': 'cBvYw8_A0vQ',
2226 'id': 'cBvYw8_A0vQ',
2228 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2229 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2230 'upload_date': '20201120',
2231 'uploader': 'Walk around Japan',
2232 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2233 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2235 'categories': ['Travel & Events'],
2236 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2238 'channel': 'Walk around Japan',
2239 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2240 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2242 'availability': 'public',
2243 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2244 'live_status': 'not_live',
2245 'playable_in_embed': True,
2246 'channel_follower_count': int
2249 'skip_download': True,
2252 # Has multiple audio streams
2253 'url': 'WaOKSUlf4TM',
2254 'only_matching': True
2256 # Requires Premium: has format 141 when requested using YTM url
2257 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2258 'only_matching': True
2260 # multiple subtitles with same lang_code
2261 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2262 'only_matching': True,
2264 # Force use android client fallback
2265 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2267 'id': 'YOelRv7fMxY',
2268 'title': 'DIGGING A SECRET TUNNEL Part 1',
2270 'upload_date': '20210624',
2271 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2272 'uploader': 'colinfurze',
2273 'uploader_id': 'colinfurze',
2274 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2275 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2277 'categories': ['Entertainment'],
2278 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2280 'channel': 'colinfurze',
2281 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2282 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2284 'availability': 'public',
2286 'live_status': 'not_live',
2287 'playable_in_embed': True,
2288 'channel_follower_count': int,
2292 'format': '17', # 3gp format available on android
2293 'extractor_args': {'youtube': {'player_client': ['android']}},
2297 # Skip download of additional client configs (remix client config in this case)
2298 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2299 'only_matching': True,
2301 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2305 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2306 'only_matching': True,
2308 'note': 'Storyboards',
2309 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2311 'id': '5KLPxDtMqe8',
2314 'title': 'Your Brain is Plastic',
2315 'uploader_id': 'scishow',
2316 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2317 'upload_date': '20140324',
2318 'uploader': 'SciShow',
2320 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2321 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2323 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2324 'playable_in_embed': True,
2326 'uploader_url': 'http://www.youtube.com/user/scishow',
2327 'availability': 'public',
2328 'channel': 'SciShow',
2329 'live_status': 'not_live',
2331 'categories': ['Education'],
2333 'channel_follower_count': int,
2335 }, 'params': {'format': 'mhtml', 'skip_download': True}
2337 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2338 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2340 'id': '2NUZ8W2llS4',
2342 'title': 'The NP that test your phone performance 🙂',
2343 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2344 'uploader': 'Leon Nguyen',
2345 'uploader_id': 'VNSXIII',
2346 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2347 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2348 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2352 'categories': ['Gaming'],
2354 'playable_in_embed': True,
2355 'live_status': 'not_live',
2356 'upload_date': '20220103',
2358 'availability': 'public',
2359 'channel': 'Leon Nguyen',
2360 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2361 'comment_count': int,
2362 'channel_follower_count': int
2365 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2366 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2368 'id': '2NUZ8W2llS4',
2370 'title': 'The NP that test your phone performance 🙂',
2371 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2372 'uploader': 'Leon Nguyen',
2373 'uploader_id': 'VNSXIII',
2374 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2375 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2376 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2380 'categories': ['Gaming'],
2382 'playable_in_embed': True,
2383 'live_status': 'not_live',
2384 'upload_date': '20220102',
2386 'availability': 'public',
2387 'channel': 'Leon Nguyen',
2388 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2389 'comment_count': int,
2390 'channel_follower_count': int
2392 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2394 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2395 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2397 'id': 'mzZzzBU6lrM',
2399 'title': 'I Met GeorgeNotFound In Real Life...',
2400 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2401 'uploader': 'Quackity',
2402 'uploader_id': 'QuackityHQ',
2403 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2404 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2405 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2409 'categories': ['Entertainment'],
2411 'playable_in_embed': True,
2412 'live_status': 'not_live',
2413 'release_timestamp': 1641172509,
2414 'release_date': '20220103',
2415 'upload_date': '20220103',
2417 'availability': 'public',
2418 'channel': 'Quackity',
2419 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2420 'channel_follower_count': int
2423 { # continuous livestream. Microformat upload date should be preferred.
2424 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2425 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2427 'id': 'kgx4WGK0oNU',
2428 'title': r're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2430 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2431 'availability': 'public',
2433 'release_timestamp': 1637975704,
2434 'upload_date': '20210619',
2435 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2436 'live_status': 'is_live',
2437 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2438 'uploader': '阿鲍Abao',
2439 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2440 'channel': 'Abao in Tokyo',
2441 'channel_follower_count': int,
2442 'release_date': '20211127',
2444 'categories': ['People & Blogs'],
2446 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2448 'playable_in_embed': True,
2449 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2450 'concurrent_view_count': int,
2452 'params': {'skip_download': True}
2454 # Story. Requires specific player params to work.
2455 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2457 'id': 'vv8qTUWmulI',
2459 'availability': 'unlisted',
2461 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2462 'upload_date': '20220526',
2463 'categories': ['Education'],
2465 'channel': 'IT\'S HISTORY',
2467 'uploader_id': 'BlastfromthePast',
2469 'uploader': 'IT\'S HISTORY',
2470 'playable_in_embed': True,
2472 'live_status': 'not_live',
2474 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2475 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2476 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2478 'skip': 'stories get removed after some period of time',
2480 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2482 'id': 'tjjjtzRLHvA',
2484 'title': 'ハッシュタグ無し };if window.ytcsi',
2485 'upload_date': '20220323',
2487 'availability': 'unlisted',
2488 'channel': 'nao20010128nao',
2489 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2491 'uploader': 'nao20010128nao',
2492 'uploader_id': 'nao20010128nao',
2493 'categories': ['Music'],
2496 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2497 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2498 'live_status': 'not_live',
2499 'playable_in_embed': True,
2500 'channel_follower_count': int,
2503 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2506 # Prefer primary title+description language metadata by default
2507 # Do not prefer translated description if primary is empty
2508 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2510 'id': 'el3E4MbxRqQ',
2512 'title': 'dlp test video 2 - primary sv no desc',
2514 'channel': 'cole-dlp-test-acc',
2517 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2519 'playable_in_embed': True,
2520 'availability': 'unlisted',
2521 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2524 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2525 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2526 'live_status': 'not_live',
2527 'upload_date': '20220908',
2528 'categories': ['People & Blogs'],
2529 'uploader': 'cole-dlp-test-acc',
2530 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2532 'params': {'skip_download': True}
2534 # Extractor argument: prefer translated title+description
2535 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2537 'id': 'gHKT4uU8Zng',
2539 'channel': 'cole-dlp-test-acc',
2542 'live_status': 'not_live',
2543 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2544 'upload_date': '20220728',
2545 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2547 'categories': ['People & Blogs'],
2548 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2549 'title': 'dlp test video title translated (fr)',
2550 'availability': 'public',
2551 'uploader': 'cole-dlp-test-acc',
2553 'description': 'dlp test video description translated (fr)',
2554 'playable_in_embed': True,
2555 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2556 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2558 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2559 'expected_warnings': [r'Preferring "fr" translated fields'],
2561 'note': '6 channel audio',
2562 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2563 'only_matching': True,
2565 'note': 'Multiple HLS formats with same itag',
2566 'url': 'https://www.youtube.com/watch?v=kX3nB4PpJko',
2568 'id': 'kX3nB4PpJko',
2570 'categories': ['Entertainment'],
2571 'description': 'md5:e8031ff6e426cdb6a77670c9b81f6fa6',
2572 'uploader_url': 'http://www.youtube.com/user/MrBeast6000',
2573 'live_status': 'not_live',
2575 'channel_follower_count': int,
2576 'thumbnail': 'https://i.ytimg.com/vi_webp/kX3nB4PpJko/maxresdefault.webp',
2577 'title': 'Last To Take Hand Off Jet, Keeps It!',
2578 'channel': 'MrBeast',
2579 'playable_in_embed': True,
2581 'upload_date': '20221112',
2582 'uploader': 'MrBeast',
2583 'uploader_id': 'MrBeast6000',
2584 'channel_url': 'https://www.youtube.com/channel/UCX6OQ3DkcsbYNE6H8uQQuVA',
2586 'availability': 'public',
2587 'channel_id': 'UCX6OQ3DkcsbYNE6H8uQQuVA',
2591 'params': {'extractor_args': {'youtube': {'player_client': ['ios']}}, 'format': '233-1'},
2593 'note': 'Audio formats with Dynamic Range Compression',
2594 'url': 'https://www.youtube.com/watch?v=Tq92D6wQ1mg',
2596 'id': 'Tq92D6wQ1mg',
2598 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
2599 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2600 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2601 'channel_follower_count': int,
2602 'description': 'md5:17eccca93a786d51bc67646756894066',
2603 'upload_date': '20191228',
2604 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
2605 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
2606 'playable_in_embed': True,
2608 'categories': ['Entertainment'],
2609 'thumbnail': 'https://i.ytimg.com/vi/Tq92D6wQ1mg/sddefault.jpg',
2611 'channel': 'Projekt Melody',
2612 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
2614 'availability': 'needs_auth',
2615 'comment_count': int,
2616 'live_status': 'not_live',
2617 'uploader': 'Projekt Melody',
2620 'params': {'extractor_args': {'youtube': {'player_client': ['tv_embedded']}}, 'format': '251-drc'},
2623 'url': 'https://www.youtube.com/live/qVv6vCqciTM',
2625 'id': 'qVv6vCqciTM',
2628 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2629 'comment_count': int,
2630 'chapters': 'count:13',
2631 'upload_date': '20221223',
2632 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
2633 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2634 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
2636 'release_date': '20221223',
2637 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
2638 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
2640 'playable_in_embed': True,
2642 'availability': 'public',
2643 'channel_follower_count': int,
2644 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
2645 'categories': ['Entertainment'],
2646 'live_status': 'was_live',
2647 'release_timestamp': 1671793345,
2648 'channel': 'さなちゃんねる',
2649 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
2650 'uploader': 'さなちゃんねる',
2656 # YouTube <object> embed
2658 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2659 'md5': '873c81d308b979f0e23ee7e620b312a3',
2661 'id': 'msN87y-iEx0',
2663 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2664 'upload_date': '20080526',
2665 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2666 'uploader': 'Christopher Sykes',
2667 'uploader_id': 'ChristopherJSykes',
2669 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2670 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2671 'playable_in_embed': True,
2672 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2674 'comment_count': int,
2675 'channel': 'Christopher Sykes',
2676 'live_status': 'not_live',
2677 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2678 'availability': 'public',
2681 'categories': ['Science & Technology'],
2682 'channel_follower_count': int,
2683 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2686 'skip_download': True,
2692 def suitable(cls, url):
2693 from ..utils import parse_qs
2696 if qs.get('list', [None])[0]:
2698 return super().suitable(url)
2700 def __init__(self, *args, **kwargs):
2701 super().__init__(*args, **kwargs)
2702 self._code_cache = {}
2703 self._player_cache = {}
2705 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2706 lock = threading.Lock()
2707 start_time = time.time()
2708 formats = [f for f in formats if f.get('is_from_start')]
2710 def refetch_manifest(format_id, delay):
2711 nonlocal formats, start_time, is_live
2712 if time.time() <= start_time + delay:
2715 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2716 video_details = traverse_obj(prs, (..., 'videoDetails'), expected_type=dict)
2717 microformats = traverse_obj(
2718 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2720 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2721 is_live = live_status == 'is_live'
2722 start_time = time.time()
2724 def mpd_feed(format_id, delay):
2726 @returns (manifest_url, manifest_stream_number, is_live) or None
2728 for retry in self.RetryManager(fatal=False):
2730 refetch_manifest(format_id, delay)
2732 f = next((f for f in formats if f['format_id'] == format_id), None)
2735 retry.error = f'{video_id}: Video is no longer live'
2737 retry.error = f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}'
2739 return f['manifest_url'], f['manifest_stream_number'], is_live
2743 f['is_live'] = is_live
2744 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2745 live_start_time, mpd_feed, not is_live and f.copy())
2747 f['fragments'] = gen
2748 f['protocol'] = 'http_dash_segments_generator'
2750 f['fragments'] = LazyList(gen({}))
2751 del f['is_from_start']
2753 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2754 FETCH_SPAN, MAX_DURATION = 5, 432000
2756 mpd_url, stream_number, is_live = None, None, True
2759 download_start_time = ctx.get('start') or time.time()
2761 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2762 if lack_early_segments:
2763 self.report_warning(bug_reports_message(
2764 'Starting download from the last 120 hours of the live stream since '
2765 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2766 lack_early_segments = True
2768 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2769 fragments, fragment_base_url = None, None
2771 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2772 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2773 # Obtain from MPD's maximum seq value
2774 old_mpd_url = mpd_url
2775 last_error = ctx.pop('last_error', None)
2776 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2777 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2778 or (mpd_url, stream_number, False))
2779 if not refresh_sequence:
2780 if expire_fast and not is_live:
2781 return False, last_seq
2782 elif old_mpd_url == mpd_url:
2783 return True, last_seq
2784 if manifestless_orig_fmt:
2785 fmt_info = manifestless_orig_fmt
2788 fmts, _ = self._extract_mpd_formats_and_subtitles(
2789 mpd_url, None, note=False, errnote=False, fatal=False)
2790 except ExtractorError:
2793 no_fragment_score += 2
2794 return False, last_seq
2795 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2796 fragments = fmt_info['fragments']
2797 fragment_base_url = fmt_info['fragment_base_url']
2798 assert fragment_base_url
2800 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2801 return True, _last_seq
2803 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2805 fetch_time = time.time()
2806 if no_fragment_score > 30:
2808 if last_segment_url:
2809 # Obtain from "X-Head-Seqnum" header value from each segment
2811 urlh = self._request_webpage(
2812 last_segment_url, None, note=False, errnote=False, fatal=False)
2813 except ExtractorError:
2815 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2816 if last_seq is None:
2817 no_fragment_score += 2
2818 last_segment_url = None
2821 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2822 no_fragment_score += 2
2823 if not should_continue:
2826 if known_idx > last_seq:
2827 last_segment_url = None
2832 if begin_index < 0 and known_idx < 0:
2833 # skip from the start when it's negative value
2834 known_idx = last_seq + begin_index
2835 if lack_early_segments:
2836 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2838 for idx in range(known_idx, last_seq):
2839 # do not update sequence here or you'll get skipped some part of it
2840 should_continue, _ = _extract_sequence_from_mpd(False, False)
2841 if not should_continue:
2843 raise ExtractorError('breaking out of outer loop')
2844 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2846 'url': last_segment_url,
2847 'fragment_count': last_seq,
2849 if known_idx == last_seq:
2850 no_fragment_score += 5
2852 no_fragment_score = 0
2853 known_idx = last_seq
2854 except ExtractorError:
2857 if manifestless_orig_fmt:
2858 # Stop at the first iteration if running for post-live manifestless;
2859 # fragment count no longer increase since it starts
2862 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2864 def _extract_player_url(self, *ytcfgs, webpage=None):
2865 player_url = traverse_obj(
2866 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2867 get_all=False, expected_type=str)
2870 return urljoin('https://www.youtube.com', player_url)
2872 def _download_player_url(self, video_id, fatal=False):
2873 res = self._download_webpage(
2874 'https://www.youtube.com/iframe_api',
2875 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2877 player_version = self._search_regex(
2878 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2880 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2882 def _signature_cache_id(self, example_sig):
2883 """ Return a string representation of a signature """
2884 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2887 def _extract_player_info(cls, player_url):
2888 for player_re in cls._PLAYER_INFO_RE:
2889 id_m = re.search(player_re, player_url)
2893 raise ExtractorError('Cannot identify player %r' % player_url)
2894 return id_m.group('id')
2896 def _load_player(self, video_id, player_url, fatal=True):
2897 player_id = self._extract_player_info(player_url)
2898 if player_id not in self._code_cache:
2899 code = self._download_webpage(
2900 player_url, video_id, fatal=fatal,
2901 note='Downloading player ' + player_id,
2902 errnote='Download of %s failed' % player_url)
2904 self._code_cache[player_id] = code
2905 return self._code_cache.get(player_id)
2907 def _extract_signature_function(self, video_id, player_url, example_sig):
2908 player_id = self._extract_player_info(player_url)
2910 # Read from filesystem cache
2911 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2912 assert os.path.basename(func_id) == func_id
2914 self.write_debug(f'Extracting signature function {func_id}')
2915 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2918 code = self._load_player(video_id, player_url)
2920 res = self._parse_sig_js(code)
2921 test_string = ''.join(map(chr, range(len(example_sig))))
2922 cache_spec = [ord(c) for c in res(test_string)]
2923 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2925 return lambda s: ''.join(s[i] for i in cache_spec)
2927 def _print_sig_code(self, func, example_sig):
2928 if not self.get_param('youtube_print_sig_code'):
2931 def gen_sig_code(idxs):
2932 def _genslice(start, end, step):
2933 starts = '' if start == 0 else str(start)
2934 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2935 steps = '' if step == 1 else (':%d' % step)
2936 return f's[{starts}{ends}{steps}]'
2939 # Quelch pyflakes warnings - start will be set when step is set
2940 start = '(Never used)'
2941 for i, prev in zip(idxs[1:], idxs[:-1]):
2942 if step is not None:
2943 if i - prev == step:
2945 yield _genslice(start, prev, step)
2948 if i - prev in [-1, 1]:
2953 yield 's[%d]' % prev
2957 yield _genslice(start, i, step)
2959 test_string = ''.join(map(chr, range(len(example_sig))))
2960 cache_res = func(test_string)
2961 cache_spec = [ord(c) for c in cache_res]
2962 expr_code = ' + '.join(gen_sig_code(cache_spec))
2963 signature_id_tuple = '(%s)' % (
2964 ', '.join(str(len(p)) for p in example_sig.split('.')))
2965 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2966 ' return %s\n') % (signature_id_tuple, expr_code)
2967 self.to_screen('Extracted signature function:\n' + code)
2969 def _parse_sig_js(self, jscode):
2970 funcname = self._search_regex(
2971 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2972 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2973 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2974 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2975 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2976 r'(?:\b|[^a-zA-Z0-9$])(?P<sig>[a-zA-Z0-9$]{2,})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2977 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2979 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2980 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2981 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2982 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2983 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2984 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2985 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2986 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2987 jscode, 'Initial JS player signature function name', group='sig')
2989 jsi = JSInterpreter(jscode)
2990 initial_function = jsi.extract_function(funcname)
2991 return lambda s: initial_function([s])
2993 def _cached(self, func, *cache_id):
2994 def inner(*args, **kwargs):
2995 if cache_id not in self._player_cache:
2997 self._player_cache[cache_id] = func(*args, **kwargs)
2998 except ExtractorError as e:
2999 self._player_cache[cache_id] = e
3000 except Exception as e:
3001 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
3003 ret = self._player_cache[cache_id]
3004 if isinstance(ret, Exception):
3009 def _decrypt_signature(self, s, video_id, player_url):
3010 """Turn the encrypted s field into a working signature"""
3011 extract_sig = self._cached(
3012 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
3013 func = extract_sig(video_id, player_url, s)
3014 self._print_sig_code(func, s)
3017 def _decrypt_nsig(self, s, video_id, player_url):
3018 """Turn the encrypted n field into a working signature"""
3019 if player_url is None:
3020 raise ExtractorError('Cannot decrypt nsig without player_url')
3021 player_url = urljoin('https://www.youtube.com', player_url)
3024 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
3025 except ExtractorError as e:
3026 raise ExtractorError('Unable to extract nsig function code', cause=e)
3027 if self.get_param('youtube_print_sig_code'):
3028 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
3031 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
3032 ret = extract_nsig(jsi, func_code)(s)
3033 except JSInterpreter.Exception as e:
3035 jsi = PhantomJSwrapper(self, timeout=5000)
3036 except ExtractorError:
3038 self.report_warning(
3039 f'Native nsig extraction failed: Trying with PhantomJS\n'
3040 f' n = {s} ; player = {player_url}', video_id)
3041 self.write_debug(e, only_once=True)
3043 args, func_body = func_code
3045 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
3046 video_id=video_id, note='Executing signature code').strip()
3048 self.write_debug(f'Decrypted nsig {s} => {ret}')
3051 def _extract_n_function_name(self, jscode):
3052 funcname, idx = self._search_regex(
3053 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
3054 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
3058 return json.loads(js_to_json(self._search_regex(
3059 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
3060 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
3062 def _extract_n_function_code(self, video_id, player_url):
3063 player_id = self._extract_player_info(player_url)
3064 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
3065 jscode = func_code or self._load_player(video_id, player_url)
3066 jsi = JSInterpreter(jscode)
3069 return jsi, player_id, func_code
3071 func_name = self._extract_n_function_name(jscode)
3074 func_code = self._search_regex(
3075 r'''(?xs
)%s\s
*=\s
*function\s
*\
((?P
<var
>[\w$
]+)\
)\s
*
3076 # NB: The end of the regex is intentionally kept strict
3077 {(?P<code>.+?}\s
*return\
[\w$
]+.join\
(""\
))};''' % func_name,
3078 jscode, 'nsig function', group=('var', 'code'), default=None)
3080 func_code = ([func_code[0]], func_code[1])
3082 self.write_debug('Extracting nsig function with jsinterp')
3083 func_code = jsi.extract_function_code(func_name)
3085 self.cache.store('youtube-nsig', player_id, func_code)
3086 return jsi, player_id, func_code
3088 def _extract_n_function_from_code(self, jsi, func_code):
3089 func = jsi.extract_function_from_code(*func_code)
3091 def extract_nsig(s):
3094 except JSInterpreter.Exception:
3096 except Exception as e:
3097 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
3099 if ret.startswith('enhanced_except_'):
3100 raise JSInterpreter.Exception('Signature function returned an exception')
3105 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
3107 Extract signatureTimestamp (sts)
3108 Required to tell API what sig/player version is in use.
3111 if isinstance(ytcfg, dict):
3112 sts = int_or_none(ytcfg.get('STS'))
3115 # Attempt to extract from player
3116 if player_url is None:
3117 error_msg = 'Cannot extract signature timestamp without player_url.'
3119 raise ExtractorError(error_msg)
3120 self.report_warning(error_msg)
3122 code = self._load_player(video_id, player_url, fatal=fatal)
3124 sts = int_or_none(self._search_regex(
3125 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
3126 'JS player signature timestamp', group='sts', fatal=fatal))
3129 def _mark_watched(self, video_id, player_responses):
3130 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
3131 label = 'fully ' if is_full else ''
3132 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
3133 expected_type=url_or_none)
3135 self.report_warning(f'Unable to mark {label}watched')
3137 parsed_url = urllib.parse.urlparse(url)
3138 qs = urllib.parse.parse_qs(parsed_url.query)
3140 # cpn generation algorithm is reverse engineered from base.js.
3141 # In fact it works even with dummy cpn.
3142 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
3143 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
3145 # # more consistent results setting it to right before the end
3146 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
3151 'cmt': video_length,
3152 'el': 'detailpage', # otherwise defaults to "shorts"
3156 # these seem to mark watchtime "history" in the real world
3157 # they're required, so send in a single value
3163 url = urllib.parse.urlunparse(
3164 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
3166 self._download_webpage(
3167 url, video_id, f'Marking {label}watched',
3168 'Unable to mark watched', fatal=False)
3171 def _extract_from_webpage(cls, url, webpage):
3172 # Invidious Instances
3173 # https://github.com/yt-dlp/yt-dlp/issues/195
3174 # https://github.com/iv-org/invidious/pull/1730
3176 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
3179 yield cls.url_result(mobj.group('url'), cls)
3180 raise cls.StopExtraction()
3182 yield from super()._extract_from_webpage(url, webpage)
3184 # lazyYT YouTube embed
3185 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3186 yield cls.url_result(unescapeHTML(id_), cls, id_)
3188 # Wordpress "YouTube Video Importer" plugin
3189 for m in re.findall(r'''(?x
)<div
[^
>]+
3190 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
3191 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
3192 yield cls.url_result(m[-1], cls, m[-1])
3195 def extract_id(cls, url):
3196 video_id = cls.get_temp_id(url)
3198 raise ExtractorError(f'Invalid URL: {url}')
3201 def _extract_chapters_from_json(self, data, duration):
3202 chapter_list = traverse_obj(
3204 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3205 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3206 ), expected_type=list)
3208 return self._extract_chapters_helper(
3210 start_function=lambda chapter: float_or_none(
3211 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3212 title_function=lambda chapter: traverse_obj(
3213 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3216 def _extract_chapters_from_engagement_panel(self, data, duration):
3217 content_list = traverse_obj(
3219 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3221 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3222 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3224 return next(filter(None, (
3225 self._extract_chapters_helper(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3226 chapter_time, chapter_title, duration)
3227 for contents in content_list)), [])
3229 def _extract_comment(self, comment_renderer, parent=None):
3230 comment_id = comment_renderer.get('commentId')
3234 text = self._get_text(comment_renderer, 'contentText')
3236 # Timestamp is an estimate calculated from the current time and time_text
3237 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3238 timestamp = self._parse_time_text(time_text)
3240 author = self._get_text(comment_renderer, 'authorText')
3241 author_id = try_get(comment_renderer,
3242 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3244 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3245 lambda x: x['likeCount']), str)) or 0
3246 author_thumbnail = try_get(comment_renderer,
3247 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3249 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3250 is_favorited = 'creatorHeart' in (try_get(
3251 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3255 'timestamp': timestamp,
3256 'time_text': time_text,
3257 'like_count': votes,
3258 'is_favorited': is_favorited,
3260 'author_id': author_id,
3261 'author_thumbnail': author_thumbnail,
3262 'author_is_uploader': author_is_uploader,
3263 'parent': parent or 'root'
3266 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3268 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3270 def extract_header(contents):
3271 _continuation = None
3272 for content in contents:
3273 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3274 expected_comment_count = self._get_count(
3275 comments_header_renderer, 'countText', 'commentsCount')
3277 if expected_comment_count:
3278 tracker['est_total'] = expected_comment_count
3279 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3280 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3282 sort_menu_item = try_get(
3283 comments_header_renderer,
3284 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3285 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3287 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3288 if not _continuation:
3291 sort_text = str_or_none(sort_menu_item.get('title'))
3293 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3294 self.to_screen('Sorting comments by %s' % sort_text.lower())
3296 return _continuation
3298 def extract_thread(contents):
3300 tracker['current_page_thread'] = 0
3301 for content in contents:
3302 if not parent and tracker['total_parent_comments'] >= max_parents:
3304 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3305 comment_renderer = get_first(
3306 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3307 expected_type=dict, default={})
3309 comment = self._extract_comment(comment_renderer, parent)
3312 # Sometimes YouTube may break and give us infinite looping comments.
3313 # See: https://github.com/yt-dlp/yt-dlp/issues/6290
3314 if comment['id'] in tracker['seen_comment_ids']:
3315 self.report_warning('Detected YouTube comments looping. Stopping comment extraction as we probably cannot get any more.')
3318 tracker['seen_comment_ids'].add(comment['id'])
3320 tracker['running_total'] += 1
3321 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3324 # Attempt to get the replies
3325 comment_replies_renderer = try_get(
3326 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3328 if comment_replies_renderer:
3329 tracker['current_page_thread'] += 1
3330 comment_entries_iter = self._comment_entries(
3331 comment_replies_renderer, ytcfg, video_id,
3332 parent=comment.get('id'), tracker=tracker)
3333 yield from itertools.islice(comment_entries_iter, min(
3334 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3336 # Keeps track of counts across recursive calls
3341 current_page_thread=0,
3342 total_parent_comments=0,
3343 total_reply_comments=0,
3344 seen_comment_ids=set())
3347 # YouTube comments have a max depth of 2
3348 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3350 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3351 'Set max replies in the max-comments extractor argument instead')
3352 if max_depth == 1 and parent:
3355 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3356 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3358 continuation = self._extract_continuation(root_continuation_data)
3361 is_forced_continuation = False
3362 is_first_continuation = parent is None
3363 if is_first_continuation and not continuation:
3364 # Sometimes you can get comments by generating the continuation yourself,
3365 # even if YouTube initially reports them being disabled - e.g. stories comments.
3366 # Note: if the comment section is actually disabled, YouTube may return a response with
3367 # required check_get_keys missing. So we will disable that check initially in this case.
3368 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3369 is_forced_continuation = True
3371 for page_num in itertools.count(0):
3372 if not continuation:
3374 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3375 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
3377 if is_first_continuation:
3378 note_prefix = 'Downloading comment section API JSON'
3380 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3381 tracker['current_page_thread'], comment_prog_str)
3383 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3384 ' ' if parent else '', ' replies' if parent else '',
3385 page_num, comment_prog_str)
3387 response = self._extract_response(
3388 item_id=None, query=continuation,
3389 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3390 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3391 except ExtractorError as e:
3392 # Ignore incomplete data error for replies if retries didn't work.
3393 # This is to allow any other parent comments and comment threads to be downloaded.
3394 # See: https://github.com/yt-dlp/yt-dlp/issues/4669
3395 if 'incomplete data' in str(e).lower() and parent and self.get_param('ignoreerrors') is True:
3396 self.report_warning(
3397 'Received incomplete data for a comment reply thread and retrying did not help. '
3398 'Ignoring to let other comments be downloaded.')
3401 is_forced_continuation = False
3402 continuation_contents = traverse_obj(
3403 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3406 for continuation_section in continuation_contents:
3407 continuation_items = traverse_obj(
3408 continuation_section,
3409 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3410 get_all=False, expected_type=list) or []
3411 if is_first_continuation:
3412 continuation = extract_header(continuation_items)
3413 is_first_continuation = False
3418 for entry in extract_thread(continuation_items):
3422 continuation = self._extract_continuation({'contents': continuation_items})
3426 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3427 if message and not parent and tracker['running_total'] == 0:
3428 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3429 raise self.CommentsDisabled
3432 def _generate_comment_continuation(video_id):
3434 Generates initial comment section continuation token from given video id
3436 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3437 return base64.b64encode(token.encode()).decode()
3439 def _get_comments(self, ytcfg, video_id, contents, webpage):
3440 """Entry for comment extraction"""
3441 def _real_comment_extract(contents):
3443 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3444 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3445 yield from self._comment_entries(renderer, ytcfg, video_id)
3447 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3448 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3451 def _get_checkok_params():
3452 return {'contentCheckOk': True, 'racyCheckOk': True}
3455 def _generate_player_context(cls, sts=None):
3457 'html5Preference': 'HTML5_PREF_WANTS',
3460 context['signatureTimestamp'] = sts
3462 'playbackContext': {
3463 'contentPlaybackContext': context
3465 **cls._get_checkok_params()
3469 def _is_agegated(player_response):
3470 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3473 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')))
3474 AGE_GATE_REASONS = (
3475 'confirm your age', 'age-restricted', 'inappropriate', # reason
3476 'age_verification_required', 'age_check_required', # status
3478 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3481 def _is_unplayable(player_response):
3482 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3484 _STORY_PLAYER_PARAMS = '8AEB'
3486 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3488 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3489 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3490 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3491 headers = self.generate_api_headers(
3492 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3495 'videoId': video_id,
3497 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3498 yt_query['params'] = self._STORY_PLAYER_PARAMS
3500 yt_query.update(self._generate_player_context(sts))
3501 return self._extract_response(
3502 item_id=video_id, ep='player', query=yt_query,
3503 ytcfg=player_ytcfg, headers=headers, fatal=True,
3504 default_client=client,
3505 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3508 def _get_requested_clients(self, url, smuggled_data):
3509 requested_clients = []
3510 default = ['android', 'web']
3511 allowed_clients = sorted(
3512 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3513 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3514 for client in self._configuration_arg('player_client'):
3515 if client in allowed_clients:
3516 requested_clients.append(client)
3517 elif client == 'default':
3518 requested_clients.extend(default)
3519 elif client == 'all':
3520 requested_clients.extend(allowed_clients)
3522 self.report_warning(f'Skipping unsupported client {client}')
3523 if not requested_clients:
3524 requested_clients = default
3526 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3527 requested_clients.extend(
3528 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3530 return orderedSet(requested_clients)
3532 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3535 initial_pr = self._search_json(
3536 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3538 all_clients = set(clients)
3539 clients = clients[::-1]
3542 def append_client(*client_names):
3543 """ Append the first client name that exists but not already used """
3544 for client_name in client_names:
3545 actual_client = _split_innertube_client(client_name)[0]
3546 if actual_client in INNERTUBE_CLIENTS:
3547 if actual_client not in all_clients:
3548 clients.append(client_name)
3549 all_clients.add(actual_client)
3552 # Android player_response does not have microFormats which are needed for
3553 # extraction of some data. So we return the initial_pr with formats
3554 # stripped out even if not requested by the user
3555 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3557 pr = dict(initial_pr)
3558 pr['streamingData'] = None
3562 tried_iframe_fallback = False
3565 client, base_client, variant = _split_innertube_client(clients.pop())
3566 player_ytcfg = master_ytcfg if client == 'web' else {}
3567 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3568 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3570 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3571 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3572 if 'js' in self._configuration_arg('player_skip'):
3573 require_js_player = False
3576 if not player_url and not tried_iframe_fallback and require_js_player:
3577 player_url = self._download_player_url(video_id)
3578 tried_iframe_fallback = True
3581 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3582 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3583 except ExtractorError as e:
3585 self.report_warning(last_error)
3590 # YouTube may return a different video player response than expected.
3591 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3592 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3593 if pr_video_id and pr_video_id != video_id:
3594 self.report_warning(
3595 f'Skipping player response from {client} client (got player response for video "{pr_video_id}
" instead of "{video_id}
")' + bug_reports_message())
3599 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3600 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3601 append_client(f'{base_client}_creator')
3602 elif self._is_agegated(pr):
3603 if variant == 'tv_embedded':
3604 append_client(f'{base_client}_embedded')
3606 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3611 self.report_warning(last_error)
3612 return prs, player_url
3614 def _needs_live_processing(self, live_status, duration):
3615 if (live_status == 'is_live' and self.get_param('live_from_start')
3616 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3619 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3620 itags, stream_ids = collections.defaultdict(set), []
3621 itag_qualities, res_qualities = {}, {0: None}
3623 # Normally tiny is the smallest video-only formats. But
3624 # audio-only formats with unknown quality may get tagged as tiny
3626 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3627 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3629 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...))
3631 for fmt in streaming_formats:
3632 if fmt.get('targetDurationSec'):
3635 itag = str_or_none(fmt.get('itag'))
3636 audio_track = fmt.get('audioTrack') or {}
3637 stream_id = (itag, audio_track.get('id'), fmt.get('isDrc'))
3638 if stream_id in stream_ids:
3641 quality = fmt.get('quality')
3642 height = int_or_none(fmt.get('height'))
3643 if quality == 'tiny' or not quality:
3644 quality = fmt.get('audioQuality', '').lower() or quality
3645 # The 3gp format (17) in android client has a quality of "small
",
3646 # but is actually worse than other formats
3651 itag_qualities[itag] = quality
3653 res_qualities[height] = quality
3654 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3655 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3656 # number of fragment that would subsequently requested with (`&sq=N`)
3657 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3660 fmt_url = fmt.get('url')
3662 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3663 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3664 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3665 if not all((sc, fmt_url, player_url, encrypted_sig)):
3668 fmt_url += '&%s=%s' % (
3669 traverse_obj(sc, ('sp', -1)) or 'signature',
3670 self._decrypt_signature(encrypted_sig, video_id, player_url)
3672 except ExtractorError as e:
3673 self.report_warning('Signature extraction failed: Some formats may be missing',
3674 video_id=video_id, only_once=True)
3675 self.write_debug(e, only_once=True)
3678 query = parse_qs(fmt_url)
3682 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3683 fmt_url = update_url_query(fmt_url, {
3684 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3686 except ExtractorError as e:
3688 if isinstance(e, JSInterpreter.Exception):
3689 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3690 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3692 self.report_warning(
3693 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3694 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3695 self.write_debug(e, only_once=True)
3697 self.report_warning(
3698 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3699 video_id=video_id, only_once=True)
3702 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3703 language_preference = (
3704 10 if audio_track.get('audioIsDefault') and 10
3705 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3707 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3708 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3709 # Make sure to avoid false positives with small duration differences.
3710 # E.g. __2ABJjxzNo, ySuUZEjARPY
3711 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3713 self.report_warning(
3714 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3716 'asr': int_or_none(fmt.get('audioSampleRate')),
3717 'filesize': int_or_none(fmt.get('contentLength')),
3718 'format_id': f'{itag}{"-drc" if fmt.get("isDrc") else ""}',
3719 'format_note': join_nonempty(
3720 join_nonempty(audio_track.get('displayName'),
3721 language_preference > 0 and ' (default)', delim=''),
3722 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3723 fmt.get('isDrc') and 'DRC',
3724 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3725 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3726 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3727 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3728 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3729 'fps': int_or_none(fmt.get('fps')) or None,
3730 'audio_channels': fmt.get('audioChannels'),
3732 'quality': q(quality) - bool(fmt.get('isDrc')) / 2,
3733 'has_drm': bool(fmt.get('drmFamilies')),
3736 'width': int_or_none(fmt.get('width')),
3737 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3738 'desc' if language_preference < -1 else '') or None,
3739 'language_preference': language_preference,
3740 # Strictly de-prioritize damaged and 3gp formats
3741 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3743 mime_mobj = re.match(
3744 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3746 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3747 dct.update(parse_codecs(mime_mobj.group(2)))
3749 single_stream = 'none
' in (dct.get('acodec
'), dct.get('vcodec
'))
3750 if single_stream and dct.get('ext
'):
3751 dct['container
'] = dct['ext
'] + '_dash
'
3752 if single_stream or itag == '17':
3753 CHUNK_SIZE = 10 << 20
3755 'protocol
': 'http_dash_segments
',
3757 'url
': update_url_query(dct['url
'], {
3758 'range': f'{range_start}
-{min(range_start + CHUNK_SIZE - 1, dct["filesize"])}
'
3760 } for range_start in range(0, dct['filesize
'], CHUNK_SIZE)]
3761 } if itag != '17' and dct['filesize
'] else {
3762 'downloader_options
': {'http_chunk_size': CHUNK_SIZE}
3766 itags[itag].add(('https
', dct.get('language
')))
3767 stream_ids.append(stream_id)
3770 needs_live_processing = self._needs_live_processing(live_status, duration)
3771 skip_bad_formats = not self._configuration_arg('include_incomplete_formats
')
3773 skip_manifests = set(self._configuration_arg('skip
'))
3774 if (not self.get_param('youtube_include_hls_manifest
', True)
3775 or needs_live_processing == 'is_live
' # These will be filtered out by YoutubeDL anyway
3776 or needs_live_processing and skip_bad_formats):
3777 skip_manifests.add('hls
')
3779 if not self.get_param('youtube_include_dash_manifest
', True):
3780 skip_manifests.add('dash
')
3781 if self._configuration_arg('include_live_dash
'):
3782 self._downloader.deprecated_feature('[youtube
] include_live_dash extractor argument
is deprecated
. '
3783 'Use include_incomplete_formats extractor argument instead
')
3784 elif skip_bad_formats and live_status == 'is_live
' and needs_live_processing != 'is_live
':
3785 skip_manifests.add('dash
')
3787 def process_manifest_format(f, proto, itag):
3788 key = (proto, f.get('language
'))
3789 if key in itags[itag]:
3791 itags[itag].add(key)
3793 if any(p != proto for p, _ in itags[itag]):
3794 f['format_id
'] = f'{itag}
-{proto}
'
3796 f['format_id
'] = itag
3798 f['quality
'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id
'].split('-')[0]), -1))
3799 if f['quality
'] == -1 and f.get('height
'):
3800 f['quality
'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height
']))])
3804 for sd in streaming_data:
3805 hls_manifest_url = 'hls
' not in skip_manifests and sd.get('hlsManifestUrl
')
3806 if hls_manifest_url:
3807 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3808 hls_manifest_url, video_id, 'mp4
', fatal=False, live=live_status == 'is_live
')
3809 subtitles = self._merge_subtitles(subs, subtitles)
3811 if process_manifest_format(f, 'hls
', self._search_regex(
3812 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3815 dash_manifest_url = 'dash
' not in skip_manifests and sd.get('dashManifestUrl
')
3816 if dash_manifest_url:
3817 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3818 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3820 if process_manifest_format(f, 'dash
', f['format_id
']):
3821 f['filesize
'] = int_or_none(self._search_regex(
3822 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3823 if needs_live_processing:
3824 f['is_from_start
'] = True
3829 def _extract_storyboard(self, player_responses, duration):
3831 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3832 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3836 for i, args in enumerate(spec):
3837 args = args.split('#')
3838 counts
= list(map(int_or_none
, args
[:5]))
3839 if len(args
) != 8 or not all(counts
):
3840 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3842 width
, height
, frame_count
, cols
, rows
= counts
3845 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3846 fragment_count
= frame_count
/ (cols
* rows
)
3847 fragment_duration
= duration
/ fragment_count
3849 'format_id': f
'sb{i}',
3850 'format_note': 'storyboard',
3852 'protocol': 'mhtml',
3858 'fps': frame_count
/ duration
,
3862 'url': url
.replace('$M', str(j
)),
3863 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3864 } for j
in range(math
.ceil(fragment_count
))],
3867 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3869 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3870 query
= {'bpctr': '9999999999', 'has_verified': '1'}
3871 if smuggled_data
.get('is_story'):
3872 query
['pp'] = self
._STORY
_PLAYER
_PARAMS
3873 webpage
= self
._download
_webpage
(
3874 webpage_url
, video_id
, fatal
=False, query
=query
)
3876 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3878 player_responses
, player_url
= self
._extract
_player
_responses
(
3879 self
._get
_requested
_clients
(url
, smuggled_data
),
3880 video_id
, webpage
, master_ytcfg
, smuggled_data
)
3882 return webpage
, master_ytcfg
, player_responses
, player_url
3884 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3885 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3886 is_live
= get_first(video_details
, 'isLive')
3888 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3889 live_content
= get_first(video_details
, 'isLiveContent')
3890 is_upcoming
= get_first(video_details
, 'isUpcoming')
3891 post_live
= get_first(video_details
, 'isPostLiveDvr')
3892 live_status
= ('post_live' if post_live
3893 else 'is_live' if is_live
3894 else 'is_upcoming' if is_upcoming
3895 else 'was_live' if live_content
3896 else 'not_live' if False in (is_live
, live_content
)
3898 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'))
3899 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, live_status
, duration
)
3901 return live_broadcast_details
, live_status
, streaming_data
, formats
, subtitles
3903 def _real_extract(self
, url
):
3904 url
, smuggled_data
= unsmuggle_url(url
, {})
3905 video_id
= self
._match
_id
(url
)
3907 base_url
= self
.http_scheme() + '//www.youtube.com/'
3908 webpage_url
= base_url
+ 'watch?v=' + video_id
3910 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3912 playability_statuses
= traverse_obj(
3913 player_responses
, (..., 'playabilityStatus'), expected_type
=dict)
3915 trailer_video_id
= get_first(
3916 playability_statuses
,
3917 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3919 if trailer_video_id
:
3920 return self
.url_result(
3921 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3923 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3924 if webpage
else (lambda x
: None))
3926 video_details
= traverse_obj(player_responses
, (..., 'videoDetails'), expected_type
=dict)
3927 microformats
= traverse_obj(
3928 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3931 translated_title
= self
._get
_text
(microformats
, (..., 'title'))
3932 video_title
= (self
._preferred
_lang
and translated_title
3933 or get_first(video_details
, 'title') # primary
3935 or search_meta(['og:title', 'twitter:title', 'title']))
3936 translated_description
= self
._get
_text
(microformats
, (..., 'description'))
3937 original_description
= get_first(video_details
, 'shortDescription')
3938 video_description
= (
3939 self
._preferred
_lang
and translated_description
3940 # If original description is blank, it will be an empty string.
3941 # Do not prefer translated description in this case.
3942 or original_description
if original_description
is not None else translated_description
)
3944 multifeed_metadata_list
= get_first(
3946 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3948 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3949 if self
.get_param('noplaylist'):
3950 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3954 for feed
in multifeed_metadata_list
.split(','):
3955 # Unquote should take place before split on comma (,) since textual
3956 # fields may contain comma as well (see
3957 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3958 feed_data
= urllib
.parse
.parse_qs(
3959 urllib
.parse
.unquote_plus(feed
))
3961 def feed_entry(name
):
3963 feed_data
, lambda x
: x
[name
][0], str)
3965 feed_id
= feed_entry('id')
3968 feed_title
= feed_entry('title')
3971 title
+= ' (%s)' % feed_title
3973 '_type': 'url_transparent',
3974 'ie_key': 'Youtube',
3976 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3977 {'force_singlefeed': True}
),
3980 feed_ids
.append(feed_id
)
3982 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3983 % (', '.join(feed_ids
), video_id
))
3984 return self
.playlist_result(
3985 entries
, video_id
, video_title
, video_description
)
3987 duration
= (int_or_none(get_first(video_details
, 'lengthSeconds'))
3988 or int_or_none(get_first(microformats
, 'lengthSeconds'))
3989 or parse_duration(search_meta('duration')) or None)
3991 live_broadcast_details
, live_status
, streaming_data
, formats
, automatic_captions
= \
3992 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
, duration
)
3993 if live_status
== 'post_live':
3994 self
.write_debug(f
'{video_id}: Video is in Post-Live Manifestless mode')
3997 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3998 self
.report_drm(video_id
)
4000 playability_statuses
,
4001 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
4002 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
4003 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
4005 if subreason
== 'The uploader has not made this video available in your country.':
4006 countries
= get_first(microformats
, 'availableCountries')
4008 regions_allowed
= search_meta('regionsAllowed')
4009 countries
= regions_allowed
.split(',') if regions_allowed
else None
4010 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
4011 reason
+= f
'. {subreason}'
4013 self
.raise_no_formats(reason
, expected
=True)
4015 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
4016 if not keywords
and webpage
:
4018 unescapeHTML(m
.group('content'))
4019 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
4020 for keyword
in keywords
:
4021 if keyword
.startswith('yt:stretch='):
4022 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
4024 # NB: float is intentional for forcing float division
4025 w
, h
= (float(v
) for v
in mobj
.groups())
4029 if f
.get('vcodec') != 'none':
4030 f
['stretched_ratio'] = ratio
4032 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
4033 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
4036 'url': thumbnail_url
,
4038 original_thumbnails
= thumbnails
.copy()
4040 # The best resolution thumbnails sometimes does not appear in the webpage
4041 # See: https://github.com/yt-dlp/yt-dlp/issues/340
4042 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
4044 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
4045 # in resolution, these are not the custom thumbnail. So de-prioritize them
4046 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
4047 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
4049 n_thumbnail_names
= len(thumbnail_names
)
4051 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
4052 video_id
=video_id
, name
=name
, ext
=ext
,
4053 webp
='_webp' if ext
== 'webp' else '', live
='_live' if live_status
== 'is_live' else ''),
4054 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
4055 for thumb
in thumbnails
:
4056 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
4057 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
4058 self
._remove
_duplicate
_formats
(thumbnails
)
4059 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
4061 category
= get_first(microformats
, 'category') or search_meta('genre')
4062 channel_id
= str_or_none(
4063 get_first(video_details
, 'channelId')
4064 or get_first(microformats
, 'externalChannelId')
4065 or search_meta('channelId'))
4066 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
4068 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
4069 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
4070 if not duration
and live_end_time
and live_start_time
:
4071 duration
= live_end_time
- live_start_time
4073 needs_live_processing
= self
._needs
_live
_processing
(live_status
, duration
)
4075 def is_bad_format(fmt
):
4076 if needs_live_processing
and not fmt
.get('is_from_start'):
4078 elif (live_status
== 'is_live' and needs_live_processing
!= 'is_live'
4079 and fmt
.get('protocol') == 'http_dash_segments'):
4082 for fmt
in filter(is_bad_format
, formats
):
4083 fmt
['preference'] = (fmt
.get('preference') or -1) - 10
4084 fmt
['format_note'] = join_nonempty(fmt
.get('format_note'), '(Last 4 hours)', delim
=' ')
4086 if needs_live_processing
:
4087 self
._prepare
_live
_from
_start
_formats
(
4088 formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
, live_status
== 'is_live')
4090 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
4094 'title': video_title
,
4096 'thumbnails': thumbnails
,
4097 # The best thumbnail that we are sure exists. Prevents unnecessary
4098 # URL checking if user don't care about getting the best possible thumbnail
4099 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
4100 'description': video_description
,
4101 'uploader': get_first(video_details
, 'author'),
4102 'uploader_id': self
._search
_regex
(r
'/(?:channel/|user/|(?=@))([^/?&#]+)', owner_profile_url
, 'uploader id', default
=None),
4103 'uploader_url': owner_profile_url
,
4104 'channel_id': channel_id
,
4105 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
4106 'duration': duration
,
4107 'view_count': int_or_none(
4108 get_first((video_details
, microformats
), (..., 'viewCount'))
4109 or search_meta('interactionCount')),
4110 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
4111 'age_limit': 18 if (
4112 get_first(microformats
, 'isFamilySafe') is False
4113 or search_meta('isFamilyFriendly') == 'false'
4114 or search_meta('og:restrictions:age') == '18+') else 0,
4115 'webpage_url': webpage_url
,
4116 'categories': [category
] if category
else None,
4118 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
4119 'live_status': live_status
,
4120 'release_timestamp': live_start_time
,
4121 '_format_sort_fields': ( # source_preference is lower for throttled/potentially damaged formats
4122 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto')
4126 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
4128 def get_lang_code(track
):
4129 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
4130 or track
.get('languageCode'))
4132 # Converted into dicts to remove duplicates
4134 get_lang_code(sub
): sub
4135 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...))}
4136 translation_languages
= {
4137 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
4138 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...))}
4140 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
4141 lang_subs
= container
.setdefault(lang_code
, [])
4142 for fmt
in self
._SUBTITLE
_FORMATS
:
4148 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
4152 # NB: Constructing the full subtitle dictionary is slow
4153 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
4154 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
4155 for lang_code
, caption_track
in captions
.items():
4156 base_url
= caption_track
.get('baseUrl')
4157 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
4160 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
4161 if caption_track
.get('kind') != 'asr':
4165 subtitles
, base_url
, lang_code
, lang_name
, {})
4166 if not caption_track
.get('isTranslatable'):
4168 for trans_code
, trans_name
in translation_languages
.items():
4171 orig_trans_code
= trans_code
4172 if caption_track
.get('kind') != 'asr' and trans_code
!= 'und':
4173 if not get_translated_subs
:
4175 trans_code
+= f
'-{lang_code}'
4176 trans_name
+= format_field(lang_name
, None, ' from %s')
4177 # Add an "-orig" label to the original language so that it can be distinguished.
4178 # The subs are returned without "-orig" as well for compatibility
4179 if lang_code
== f
'a-{orig_trans_code}':
4181 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
4182 # Setting tlang=lang returns damaged subtitles.
4183 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
4184 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
4186 info
['automatic_captions'] = automatic_captions
4187 info
['subtitles'] = subtitles
4189 parsed_url
= urllib
.parse
.urlparse(url
)
4190 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
4191 query
= urllib
.parse
.parse_qs(component
)
4192 for k
, v
in query
.items():
4193 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
4195 if d_k
not in info
and k
in s_ks
:
4196 info
[d_k
] = parse_duration(query
[k
][0])
4198 # Youtube Music Auto-generated description
4199 if video_description
:
4202 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4204 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4205 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4206 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4207 .+\nAuto-generated\ by\ YouTube\.\s*$
4208 ''', video_description
)
4210 release_year
= mobj
.group('release_year')
4211 release_date
= mobj
.group('release_date')
4213 release_date
= release_date
.replace('-', '')
4214 if not release_year
:
4215 release_year
= release_date
[:4]
4217 'album': mobj
.group('album'.strip()),
4218 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
4219 'track': mobj
.group('track').strip(),
4220 'release_date': release_date
,
4221 'release_year': int_or_none(release_year
),
4226 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
4227 if not initial_data
:
4228 query
= {'videoId': video_id}
4229 query
.update(self
._get
_checkok
_params
())
4230 initial_data
= self
._extract
_response
(
4231 item_id
=video_id
, ep
='next', fatal
=False,
4232 ytcfg
=master_ytcfg
, query
=query
,
4233 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
4234 note
='Downloading initial data API JSON')
4236 info
['comment_count'] = traverse_obj(initial_data
, (
4237 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4238 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4240 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4241 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4242 ), expected_type
=int_or_none
, get_all
=False)
4244 try: # This will error if there is no livechat
4245 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4246 except (KeyError, IndexError, TypeError):
4249 info
.setdefault('subtitles', {})['live_chat'] = [{
4250 # url is needed to set cookies
4251 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4252 'video_id': video_id
,
4254 'protocol': ('youtube_live_chat' if live_status
in ('is_live', 'is_upcoming')
4255 else 'youtube_live_chat_replay'),
4259 info
['chapters'] = (
4260 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
4261 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
4262 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
4265 contents
= traverse_obj(
4266 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4267 expected_type
=list, default
=[])
4269 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
4271 stl
= vpir
.get('superTitleLink')
4273 stl
= self
._get
_text
(stl
)
4276 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4277 info
['location'] = stl
4279 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
4282 'series': mobj
.group(1),
4283 'season_number': int(mobj
.group(2)),
4284 'episode_number': int(mobj
.group(3)),
4286 for tlb
in (try_get(
4288 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
4292 tlb
, ('toggleButtonRenderer', ...),
4293 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer')))
4295 for getter
, regex
in [(
4296 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
4297 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4298 lambda x
: x
['accessibility'],
4299 lambda x
: x
['accessibilityData']['accessibilityData'],
4300 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4301 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
4303 mobj
= re
.match(regex
, label
)
4305 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
4307 sbr_tooltip
= try_get(
4308 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
4310 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
4312 'like_count': str_to_int(like_count
),
4313 'dislike_count': str_to_int(dislike_count
),
4315 vcr
= traverse_obj(vpir
, ('viewCount', 'videoViewCountRenderer'))
4317 vc
= self
._get
_count
(vcr
, 'viewCount')
4318 # Upcoming premieres with waiting count are treated as live here
4319 if vcr
.get('isLive'):
4320 info
['concurrent_view_count'] = vc
4321 elif info
.get('view_count') is None:
4322 info
['view_count'] = vc
4324 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
4326 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
4328 'channel': self
._get
_text
(vor
, 'title'),
4329 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
4333 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4335 multiple_songs
= False
4337 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
4338 multiple_songs
= True
4341 mrr
= row
.get('metadataRowRenderer') or {}
4342 mrr_title
= mrr
.get('title')
4345 mrr_title
= self
._get
_text
(mrr
, 'title')
4346 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
4347 if mrr_title
== 'License':
4348 info
['license'] = mrr_contents_text
4349 elif not multiple_songs
:
4350 if mrr_title
== 'Album':
4351 info
['album'] = mrr_contents_text
4352 elif mrr_title
== 'Artist':
4353 info
['artist'] = mrr_contents_text
4354 elif mrr_title
== 'Song':
4355 info
['track'] = mrr_contents_text
4358 'channel': 'uploader',
4359 'channel_id': 'uploader_id',
4360 'channel_url': 'uploader_url',
4363 # The upload date for scheduled, live and past live streams / premieres in microformats
4364 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4365 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4367 unified_strdate(get_first(microformats
, 'uploadDate'))
4368 or unified_strdate(search_meta('uploadDate')))
4369 if not upload_date
or (
4370 live_status
in ('not_live', None)
4371 and 'no-youtube-prefer-utc-upload-date' not in self
.get_param('compat_opts', [])
4373 upload_date
= strftime_or_none(
4374 self
._parse
_time
_text
(self
._get
_text
(vpir
, 'dateText')), '%Y%m%d') or upload_date
4375 info
['upload_date'] = upload_date
4377 for to
, frm
in fallbacks
.items():
4378 if not info
.get(to
):
4379 info
[to
] = info
.get(frm
)
4381 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
4386 badges
= self
._extract
_badges
(traverse_obj(contents
, (..., 'videoPrimaryInfoRenderer'), get_all
=False))
4388 is_private
= (self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
)
4389 or get_first(video_details
, 'isPrivate', expected_type
=bool))
4391 info
['availability'] = (
4392 'public' if self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
4393 else self
._availability
(
4394 is_private
=is_private
,
4396 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
)
4397 or False if initial_data
and is_private
is not None else None),
4398 needs_subscription
=(
4399 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
)
4400 or False if initial_data
and is_private
is not None else None),
4401 needs_auth
=info
['age_limit'] >= 18,
4402 is_unlisted
=None if is_private
is None else (
4403 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
)
4404 or get_first(microformats
, 'isUnlisted', expected_type
=bool))))
4406 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
4408 self
.mark_watched(video_id
, player_responses
)
4413 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
4415 def passthrough_smuggled_data(func
):
4416 def _smuggle(info
, smuggled_data
):
4417 if info
.get('_type') not in ('url', 'url_transparent'):
4419 if smuggled_data
.get('is_music_url'):
4420 parsed_url
= urllib
.parse
.urlparse(info
['url'])
4421 if parsed_url
.netloc
in ('www.youtube.com', 'music.youtube.com'):
4422 smuggled_data
.pop('is_music_url')
4423 info
['url'] = urllib
.parse
.urlunparse(parsed_url
._replace
(netloc
='music.youtube.com'))
4425 info
['url'] = smuggle_url(info
['url'], smuggled_data
)
4428 @functools.wraps(func
)
4429 def wrapper(self
, url
):
4430 url
, smuggled_data
= unsmuggle_url(url
, {})
4431 if self
.is_music_url(url
):
4432 smuggled_data
['is_music_url'] = True
4433 info_dict
= func(self
, url
, smuggled_data
)
4435 _smuggle(info_dict
, smuggled_data
)
4436 if info_dict
.get('entries'):
4437 info_dict
['entries'] = (_smuggle(i
, smuggled_data
.copy()) for i
in info_dict
['entries'])
4442 def _extract_basic_item_renderer(item
):
4443 # Modified from _extract_grid_item_renderer
4444 known_basic_renderers
= (
4445 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4447 for key
, renderer
in item
.items():
4448 if not isinstance(renderer
, dict):
4450 elif key
in known_basic_renderers
:
4452 elif key
.startswith('grid') and key
.endswith('Renderer'):
4455 def _extract_channel_renderer(self
, renderer
):
4456 channel_id
= renderer
['channelId']
4457 title
= self
._get
_text
(renderer
, 'title')
4458 channel_url
= f
'https://www.youtube.com/channel/{channel_id}'
4463 'ie_key': YoutubeTabIE
.ie_key(),
4465 'channel_id': channel_id
,
4466 'channel_url': channel_url
,
4468 'channel_follower_count': self
._get
_count
(renderer
, 'subscriberCountText'),
4469 'thumbnails': self
._extract
_thumbnails
(renderer
, 'thumbnail'),
4470 'playlist_count': self
._get
_count
(renderer
, 'videoCountText'),
4471 'description': self
._get
_text
(renderer
, 'descriptionSnippet'),
4474 def _grid_entries(self
, grid_renderer
):
4475 for item
in grid_renderer
['items']:
4476 if not isinstance(item
, dict):
4478 renderer
= self
._extract
_basic
_item
_renderer
(item
)
4479 if not isinstance(renderer
, dict):
4481 title
= self
._get
_text
(renderer
, 'title')
4484 playlist_id
= renderer
.get('playlistId')
4486 yield self
.url_result(
4487 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4488 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4492 video_id
= renderer
.get('videoId')
4494 yield self
._extract
_video
(renderer
)
4497 channel_id
= renderer
.get('channelId')
4499 yield self
._extract
_channel
_renderer
(renderer
)
4501 # generic endpoint URL support
4502 ep_url
= urljoin('https://www.youtube.com/', try_get(
4503 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4506 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4507 if ie
.suitable(ep_url
):
4508 yield self
.url_result(
4509 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4512 def _music_reponsive_list_entry(self
, renderer
):
4513 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4515 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4516 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4517 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4519 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4521 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4522 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4523 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4524 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4525 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4527 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4528 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4530 def _shelf_entries_from_content(self
, shelf_renderer
):
4531 content
= shelf_renderer
.get('content')
4532 if not isinstance(content
, dict):
4534 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4536 # TODO: add support for nested playlists so each shelf is processed
4537 # as separate playlist
4538 # TODO: this includes only first N items
4539 yield from self
._grid
_entries
(renderer
)
4540 renderer
= content
.get('horizontalListRenderer')
4545 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4547 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4549 shelf_url
= urljoin('https://www.youtube.com', ep
)
4551 # Skipping links to another channels, note that checking for
4552 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4554 if skip_channels
and '/channels?' in shelf_url
:
4556 title
= self
._get
_text
(shelf_renderer
, 'title')
4557 yield self
.url_result(shelf_url
, video_title
=title
)
4558 # Shelf may not contain shelf URL, fallback to extraction from content
4559 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4561 def _playlist_entries(self
, video_list_renderer
):
4562 for content
in video_list_renderer
['contents']:
4563 if not isinstance(content
, dict):
4565 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4566 if not isinstance(renderer
, dict):
4568 video_id
= renderer
.get('videoId')
4571 yield self
._extract
_video
(renderer
)
4573 def _rich_entries(self
, rich_grid_renderer
):
4574 renderer
= traverse_obj(
4575 rich_grid_renderer
, ('content', ('videoRenderer', 'reelItemRenderer')), get_all
=False) or {}
4576 video_id
= renderer
.get('videoId')
4579 yield self
._extract
_video
(renderer
)
4581 def _video_entry(self
, video_renderer
):
4582 video_id
= video_renderer
.get('videoId')
4584 return self
._extract
_video
(video_renderer
)
4586 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4587 url
= urljoin('https://youtube.com', traverse_obj(
4588 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4590 return self
.url_result(
4591 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4593 def _post_thread_entries(self
, post_thread_renderer
):
4594 post_renderer
= try_get(
4595 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4596 if not post_renderer
:
4599 video_renderer
= try_get(
4600 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4601 video_id
= video_renderer
.get('videoId')
4603 entry
= self
._extract
_video
(video_renderer
)
4606 # playlist attachment
4607 playlist_id
= try_get(
4608 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4610 yield self
.url_result(
4611 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4612 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4613 # inline video links
4614 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4616 if not isinstance(run
, dict):
4619 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4622 if not YoutubeIE
.suitable(ep_url
):
4624 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4625 if video_id
== ep_video_id
:
4627 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4629 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4630 contents
= post_thread_continuation
.get('contents')
4631 if not isinstance(contents
, list):
4633 for content
in contents
:
4634 renderer
= content
.get('backstagePostThreadRenderer')
4635 if isinstance(renderer
, dict):
4636 yield from self
._post
_thread
_entries
(renderer
)
4638 renderer
= content
.get('videoRenderer')
4639 if isinstance(renderer
, dict):
4640 yield self
._video
_entry
(renderer
)
4643 def _rich_grid_entries(self, contents):
4644 for content in contents:
4645 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4647 entry = self._video_entry(video_renderer)
4652 def _report_history_entries(self
, renderer
):
4653 for url
in traverse_obj(renderer
, (
4654 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4655 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4656 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4657 yield self
.url_result(urljoin('https://www.youtube.com', url
), YoutubeIE
)
4659 def _extract_entries(self
, parent_renderer
, continuation_list
):
4660 # continuation_list is modified in-place with continuation_list = [continuation_token]
4661 continuation_list
[:] = [None]
4662 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4663 for content
in contents
:
4664 if not isinstance(content
, dict):
4666 is_renderer
= traverse_obj(
4667 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4670 if content
.get('richItemRenderer'):
4671 for entry
in self
._rich
_entries
(content
['richItemRenderer']):
4673 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4674 elif content
.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4675 table
= traverse_obj(content
, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4676 yield from self
._report
_history
_entries
(table
)
4677 continuation_list
[0] = self
._extract
_continuation
(table
)
4680 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4681 for isr_content
in isr_contents
:
4682 if not isinstance(isr_content
, dict):
4686 'playlistVideoListRenderer': self
._playlist
_entries
,
4687 'gridRenderer': self
._grid
_entries
,
4688 'reelShelfRenderer': self
._grid
_entries
,
4689 'shelfRenderer': self
._shelf
_entries
,
4690 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4691 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4692 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4693 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4694 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4695 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4697 for key
, renderer
in isr_content
.items():
4698 if key
not in known_renderers
:
4700 for entry
in known_renderers
[key
](renderer
):
4703 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4706 if not continuation_list
[0]:
4707 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4709 if not continuation_list
[0]:
4710 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4712 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4713 continuation_list
= [None]
4714 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4715 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4719 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4720 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4721 yield from extract_entries(parent_renderer
)
4722 continuation
= continuation_list
[0]
4724 for page_num
in itertools
.count(1):
4725 if not continuation
:
4727 headers
= self
.generate_api_headers(
4728 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4729 response
= self
._extract
_response
(
4730 item_id
=f
'{item_id} page {page_num}',
4731 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4732 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4736 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4737 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4738 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4741 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4742 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4743 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4744 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4745 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4746 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4747 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4748 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents'),
4749 'reportHistoryTableRowRenderer': (self
._report
_history
_entries
, 'rows'),
4750 'playlistVideoListContinuation': (self
._playlist
_entries
, None),
4751 'gridContinuation': (self
._grid
_entries
, None),
4752 'itemSectionContinuation': (self
._post
_thread
_continuation
_entries
, None),
4753 'sectionListContinuation': (extract_entries
, None), # for feeds
4756 continuation_items
= traverse_obj(response
, (
4757 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4758 'appendContinuationItemsAction', 'continuationItems'
4759 ), 'continuationContents', get_all
=False)
4760 continuation_item
= traverse_obj(continuation_items
, 0, None, expected_type
=dict, default
={})
4762 video_items_renderer
= None
4763 for key
in continuation_item
.keys():
4764 if key
not in known_renderers
:
4766 func
, parent_key
= known_renderers
[key
]
4767 video_items_renderer
= {parent_key: continuation_items}
if parent_key
else continuation_items
4768 continuation_list
= [None]
4769 yield from func(video_items_renderer
)
4770 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4772 if not video_items_renderer
:
4776 def _extract_selected_tab(tabs
, fatal
=True):
4777 for tab_renderer
in tabs
:
4778 if tab_renderer
.get('selected'):
4781 raise ExtractorError('Unable to find selected tab')
4784 def _extract_tab_renderers(response
):
4785 return traverse_obj(
4786 response
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type
=dict)
4788 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4789 metadata
= self
._extract
_metadata
_from
_tabs
(item_id
, data
)
4791 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4792 metadata
['title'] += format_field(selected_tab
, 'title', ' - %s')
4793 metadata
['title'] += format_field(selected_tab
, 'expandedText', ' - %s')
4795 return self
.playlist_result(
4797 selected_tab
, metadata
['id'], ytcfg
,
4798 self
._extract
_account
_syncid
(ytcfg
, data
),
4799 self
._extract
_visitor
_data
(data
, ytcfg
)),
4802 def _extract_metadata_from_tabs(self
, item_id
, data
):
4803 info
= {'id': item_id}
4805 metadata_renderer
= traverse_obj(data
, ('metadata', 'channelMetadataRenderer'), expected_type
=dict)
4806 if metadata_renderer
:
4808 'uploader': metadata_renderer
.get('title'),
4809 'uploader_id': metadata_renderer
.get('externalId'),
4810 'uploader_url': metadata_renderer
.get('channelUrl'),
4812 if info
['uploader_id']:
4813 info
['id'] = info
['uploader_id']
4815 metadata_renderer
= traverse_obj(data
, ('metadata', 'playlistMetadataRenderer'), expected_type
=dict)
4817 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4818 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4819 def _get_uncropped(url
):
4820 return url_or_none((url
or '').split('=')[0] + '=s0')
4822 avatar_thumbnails
= self
._extract
_thumbnails
(metadata_renderer
, 'avatar')
4823 if avatar_thumbnails
:
4824 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4825 if uncropped_avatar
:
4826 avatar_thumbnails
.append({
4827 'url': uncropped_avatar
,
4828 'id': 'avatar_uncropped',
4832 channel_banners
= self
._extract
_thumbnails
(
4833 data
, ('header', ..., ('banner', 'mobileBanner', 'tvBanner')))
4834 for banner
in channel_banners
:
4835 banner
['preference'] = -10
4838 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4839 if uncropped_banner
:
4840 channel_banners
.append({
4841 'url': uncropped_banner
,
4842 'id': 'banner_uncropped',
4846 # Deprecated - remove primary_sidebar_renderer when layout discontinued
4847 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4848 playlist_header_renderer
= traverse_obj(data
, ('header', 'playlistHeaderRenderer'), expected_type
=dict)
4850 primary_thumbnails
= self
._extract
_thumbnails
(
4851 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4852 playlist_thumbnails
= self
._extract
_thumbnails
(
4853 playlist_header_renderer
, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4856 'title': (traverse_obj(metadata_renderer
, 'title')
4857 or self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag'))
4859 'availability': self
._extract
_availability
(data
),
4860 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4861 'description': try_get(metadata_renderer
, lambda x
: x
.get('description', '')),
4862 'tags': try_get(metadata_renderer
or {}, lambda x
: x
.get('keywords', '').split()),
4863 'thumbnails': (primary_thumbnails
or playlist_thumbnails
) + avatar_thumbnails
+ channel_banners
,
4866 # Playlist stats is a text runs array containing [video count, view count, last updated].
4867 # last updated or (view count and last updated) may be missing.
4868 playlist_stats
= get_first(
4869 (primary_sidebar_renderer
, playlist_header_renderer
), (('stats', 'briefStats', 'numVideosText'), ))
4871 last_updated_unix
= self
._parse
_time
_text
(
4872 self
._get
_text
(playlist_stats
, 2) # deprecated, remove when old layout discontinued
4873 or self
._get
_text
(playlist_header_renderer
, ('byline', 1, 'playlistBylineRenderer', 'text')))
4874 info
['modified_date'] = strftime_or_none(last_updated_unix
, '%Y%m%d')
4876 info
['view_count'] = self
._get
_count
(playlist_stats
, 1)
4877 if info
['view_count'] is None: # 0 is allowed
4878 info
['view_count'] = self
._get
_count
(playlist_header_renderer
, 'viewCountText')
4879 if info
['view_count'] is None:
4880 info
['view_count'] = self
._get
_count
(data
, (
4881 'contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., 'tabRenderer', 'content', 'sectionListRenderer',
4882 'contents', ..., 'itemSectionRenderer', 'contents', ..., 'channelAboutFullMetadataRenderer', 'viewCountText'))
4884 info
['playlist_count'] = self
._get
_count
(playlist_stats
, 0)
4885 if info
['playlist_count'] is None: # 0 is allowed
4886 info
['playlist_count'] = self
._get
_count
(playlist_header_renderer
, ('byline', 0, 'playlistBylineRenderer', 'text'))
4888 if not info
.get('uploader_id'):
4889 owner
= traverse_obj(playlist_header_renderer
, 'ownerText')
4890 if not owner
: # Deprecated
4891 owner
= traverse_obj(
4892 self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer'),
4893 ('videoOwner', 'videoOwnerRenderer', 'title'))
4894 owner_text
= self
._get
_text
(owner
)
4895 browse_ep
= traverse_obj(owner
, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4897 'uploader': self
._search
_regex
(r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
),
4898 'uploader_id': browse_ep
.get('browseId'),
4899 'uploader_url': urljoin('https://www.youtube.com', browse_ep
.get('canonicalBaseUrl'))
4903 'channel': info
['uploader'],
4904 'channel_id': info
['uploader_id'],
4905 'channel_url': info
['uploader_url']
4909 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4910 first_id
= last_id
= response
= None
4911 for page_num
in itertools
.count(1):
4912 videos
= list(self
._playlist
_entries
(playlist
))
4915 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4916 if start
>= len(videos
):
4918 yield from videos
[start
:]
4919 first_id
= first_id
or videos
[0]['id']
4920 last_id
= videos
[-1]['id']
4921 watch_endpoint
= try_get(
4922 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4923 headers
= self
.generate_api_headers(
4924 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4925 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4927 'playlistId': playlist_id
,
4928 'videoId': watch_endpoint
.get('videoId') or last_id
,
4929 'index': watch_endpoint
.get('index') or len(videos
),
4930 'params': watch_endpoint
.get('params') or 'OAE%3D'
4932 response
= self
._extract
_response
(
4933 item_id
='%s page %d' % (playlist_id
, page_num
),
4934 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4935 check_get_keys
='contents'
4938 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4940 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4941 title
= playlist
.get('title') or try_get(
4942 data
, lambda x
: x
['titleText']['simpleText'], str)
4943 playlist_id
= playlist
.get('playlistId') or item_id
4945 # Delegating everything except mix playlists to regular tab-based playlist URL
4946 playlist_url
= urljoin(url
, try_get(
4947 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4950 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4951 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4952 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4954 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4955 return self
.url_result(
4956 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4959 return self
.playlist_result(
4960 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4961 playlist_id
=playlist_id
, playlist_title
=title
)
4963 def _extract_availability(self
, data
):
4965 Gets the availability of a given playlist/tab.
4966 Note: Unless YouTube tells us explicitly, we do not assume it is public
4967 @param data: response
4969 sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4970 playlist_header_renderer
= traverse_obj(data
, ('header', 'playlistHeaderRenderer')) or {}
4971 player_header_privacy
= playlist_header_renderer
.get('privacy')
4973 badges
= self
._extract
_badges
(sidebar_renderer
)
4975 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4976 privacy_setting_icon
= get_first(
4977 (playlist_header_renderer
, sidebar_renderer
),
4978 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4979 lambda _
, v
: v
['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4982 microformats_is_unlisted
= traverse_obj(
4983 data
, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type
=bool)
4987 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
4988 or player_header_privacy
== 'PUBLIC'
4989 or privacy_setting_icon
== 'PRIVACY_PUBLIC')
4990 else self
._availability
(
4992 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
)
4993 or player_header_privacy
== 'PRIVATE' if player_header_privacy
is not None
4994 else privacy_setting_icon
== 'PRIVACY_PRIVATE' if privacy_setting_icon
is not None else None),
4996 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
)
4997 or player_header_privacy
== 'UNLISTED' if player_header_privacy
is not None
4998 else privacy_setting_icon
== 'PRIVACY_UNLISTED' if privacy_setting_icon
is not None
4999 else microformats_is_unlisted
if microformats_is_unlisted
is not None else None),
5000 needs_subscription
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
) or None,
5001 needs_premium
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
) or None,
5005 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
5006 sidebar_renderer
= try_get(
5007 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
5008 for item
in sidebar_renderer
:
5009 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
5013 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
5015 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
5017 is_playlist
= bool(traverse_obj(
5018 data
, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
5021 headers
= self
.generate_api_headers(
5022 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
5023 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
5025 'params': 'wgYCCAA=',
5026 'browseId': f
'VL{item_id}'
5028 return self
._extract
_response
(
5029 item_id
=item_id
, headers
=headers
, query
=query
,
5030 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
5031 note
='Redownloading playlist API JSON with unavailable videos')
5033 @functools.cached_property
5034 def skip_webpage(self
):
5035 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
5037 def _extract_webpage(self
, url
, item_id
, fatal
=True):
5038 webpage
, data
= None, None
5039 for retry
in self
.RetryManager(fatal
=fatal
):
5041 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
5042 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
5043 except ExtractorError
as e
:
5044 if isinstance(e
.cause
, network_exceptions
):
5045 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
5048 self
._error
_or
_warning
(e
, fatal
=fatal
)
5052 self
._extract
_and
_report
_alerts
(data
)
5053 except ExtractorError
as e
:
5054 self
._error
_or
_warning
(e
, fatal
=fatal
)
5057 # Sometimes youtube returns a webpage with incomplete ytInitialData
5058 # See: https://github.com/yt-dlp/yt-dlp/issues/116
5059 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
5060 retry
.error
= ExtractorError('Incomplete yt initial data received')
5063 return webpage
, data
5065 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
5066 """Use if failed to extract ytcfg (and data) from initial webpage"""
5067 if not ytcfg
and self
.is_authenticated
:
5068 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
5069 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
5070 raise ExtractorError(
5071 f
'{msg}. If you are not downloading private content, or '
5072 'your cookies are only for the first account and channel,'
5073 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
5075 self
.report_warning(msg
, only_once
=True)
5077 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
5079 if not self
.skip_webpage
:
5080 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
5081 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
5082 # Reject webpage data if redirected to home page without explicitly requesting
5083 selected_tab
= self
._extract
_selected
_tab
(self
._extract
_tab
_renderers
(data
), fatal
=False) or {}
5084 if (url
!= 'https://www.youtube.com/feed/recommended'
5085 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
5086 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
5087 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
5089 raise ExtractorError(msg
, expected
=True)
5090 self
.report_warning(msg
, only_once
=True)
5092 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
5093 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
5096 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
5097 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
5098 resolve_response
= self
._extract
_response
(
5099 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
5100 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
5101 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
5102 for ep_key
, ep
in endpoints
.items():
5103 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
5105 return self
._extract
_response
(
5106 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
5107 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
5108 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
5109 err_note
= 'Failed to resolve url (does the playlist exist?)'
5111 raise ExtractorError(err_note
, expected
=True)
5112 self
.report_warning(err_note
, item_id
)
5114 _SEARCH_PARAMS
= None
5116 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
5117 data
= {'query': query}
5118 if params
is NO_DEFAULT
:
5119 params
= self
._SEARCH
_PARAMS
5121 data
['params'] = params
5124 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
5125 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
5127 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
5128 ('continuationContents', ),
5130 display_id
= f
'query "{query}"'
5131 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
5132 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
5133 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
5135 continuation_list
= [None]
5137 for page_num
in itertools
.count(1):
5138 data
.update(continuation_list
[0] or {})
5139 headers
= self
.generate_api_headers(
5140 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
5141 search
= self
._extract
_response
(
5142 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
5143 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
5144 slr_contents
= traverse_obj(search
, *content_keys
)
5145 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
5146 if not continuation_list
[0]:
5150 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
5151 IE_DESC
= 'YouTube Tabs'
5152 _VALID_URL
= r
'''(?x:
5154 (?!consent\.)(?:\w+\.)?
5156 youtube(?:kids)?\.com|
5160 (?P<channel_type>channel|c|user|browse)/|
5163 (?:playlist|watch)\?.*?\blist=
5165 (?!(?:%(reserved_names)s)\b) # Direct URLs
5169 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
5170 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5172 IE_NAME
= 'youtube:tab'
5175 'note': 'playlists, multipage',
5176 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
5177 'playlist_mincount': 94,
5179 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5180 'title': 'Igor Kleiner - Playlists',
5181 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5182 'uploader': 'Igor Kleiner',
5183 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5184 'channel': 'Igor Kleiner',
5185 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5186 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5187 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5188 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5189 'channel_follower_count': int
5192 'note': 'playlists, multipage, different order',
5193 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5194 'playlist_mincount': 94,
5196 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5197 'title': 'Igor Kleiner - Playlists',
5198 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5199 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5200 'uploader': 'Igor Kleiner',
5201 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5202 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5203 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5204 'channel': 'Igor Kleiner',
5205 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5206 'channel_follower_count': int
5209 'note': 'playlists, series',
5210 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5211 'playlist_mincount': 5,
5213 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5214 'title': '3Blue1Brown - Playlists',
5215 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5216 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5217 'uploader': '3Blue1Brown',
5218 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5219 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5220 'channel': '3Blue1Brown',
5221 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5222 'tags': ['Mathematics'],
5223 'channel_follower_count': int
5226 'note': 'playlists, singlepage',
5227 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5228 'playlist_mincount': 4,
5230 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5231 'title': 'ThirstForScience - Playlists',
5232 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5233 'uploader': 'ThirstForScience',
5234 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5235 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5236 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5237 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5239 'channel': 'ThirstForScience',
5240 'channel_follower_count': int
5243 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5244 'only_matching': True,
5246 'note': 'basic, single video playlist',
5247 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5249 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5250 'uploader': 'Sergey M.',
5251 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5252 'title': 'youtube-dl public playlist',
5256 'modified_date': '20201130',
5257 'channel': 'Sergey M.',
5258 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5259 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5260 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5261 'availability': 'public',
5263 'playlist_count': 1,
5265 'note': 'empty playlist',
5266 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5268 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5269 'uploader': 'Sergey M.',
5270 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5271 'title': 'youtube-dl empty playlist',
5273 'channel': 'Sergey M.',
5275 'modified_date': '20160902',
5276 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5277 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5278 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5279 'availability': 'public',
5281 'playlist_count': 0,
5284 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5286 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5287 'title': 'lex will - Home',
5288 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5289 'uploader': 'lex will',
5290 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5291 'channel': 'lex will',
5292 'tags': ['bible', 'history', 'prophesy'],
5293 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5294 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5295 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5296 'channel_follower_count': int
5298 'playlist_mincount': 2,
5300 'note': 'Videos tab',
5301 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5303 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5304 'title': 'lex will - Videos',
5305 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5306 'uploader': 'lex will',
5307 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5308 'tags': ['bible', 'history', 'prophesy'],
5309 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5310 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5311 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5312 'channel': 'lex will',
5313 'channel_follower_count': int
5315 'playlist_mincount': 975,
5317 'note': 'Videos tab, sorted by popular',
5318 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5320 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5321 'title': 'lex will - Videos',
5322 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5323 'uploader': 'lex will',
5324 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5325 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5326 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5327 'channel': 'lex will',
5328 'tags': ['bible', 'history', 'prophesy'],
5329 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5330 'channel_follower_count': int
5332 'playlist_mincount': 199,
5334 'note': 'Playlists tab',
5335 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5337 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5338 'title': 'lex will - Playlists',
5339 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5340 'uploader': 'lex will',
5341 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5342 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5343 'channel': 'lex will',
5344 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5345 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5346 'tags': ['bible', 'history', 'prophesy'],
5347 'channel_follower_count': int
5349 'playlist_mincount': 17,
5351 'note': 'Community tab',
5352 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5354 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5355 'title': 'lex will - Community',
5356 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5357 'uploader': 'lex will',
5358 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5359 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5360 'channel': 'lex will',
5361 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5362 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5363 'tags': ['bible', 'history', 'prophesy'],
5364 'channel_follower_count': int
5366 'playlist_mincount': 18,
5368 'note': 'Channels tab',
5369 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5371 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5372 'title': 'lex will - Channels',
5373 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5374 'uploader': 'lex will',
5375 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5376 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5377 'channel': 'lex will',
5378 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5379 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5380 'tags': ['bible', 'history', 'prophesy'],
5381 'channel_follower_count': int
5383 'playlist_mincount': 12,
5385 'note': 'Search tab',
5386 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5387 'playlist_mincount': 40,
5389 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5390 'title': '3Blue1Brown - Search - linear algebra',
5391 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5392 'uploader': '3Blue1Brown',
5393 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5394 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5395 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5396 'tags': ['Mathematics'],
5397 'channel': '3Blue1Brown',
5398 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5399 'channel_follower_count': int
5402 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5403 'only_matching': True,
5405 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5406 'only_matching': True,
5408 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5409 'only_matching': True,
5411 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5412 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5414 'title': '29C3: Not my department',
5415 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5416 'uploader': 'Christiaan008',
5417 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5418 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5420 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5422 'modified_date': '20150605',
5423 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5424 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5425 'channel': 'Christiaan008',
5426 'availability': 'public',
5428 'playlist_count': 96,
5430 'note': 'Large playlist',
5431 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5433 'title': 'Uploads from Cauchemar',
5434 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5435 'uploader': 'Cauchemar',
5436 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5437 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5439 'modified_date': r
're:\d{8}',
5440 'channel': 'Cauchemar',
5441 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5444 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5445 'availability': 'public',
5447 'playlist_mincount': 1123,
5448 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5450 'note': 'even larger playlist, 8832 videos',
5451 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5452 'only_matching': True,
5454 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5455 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5457 'title': 'Uploads from Interstellar Movie',
5458 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5459 'uploader': 'Interstellar Movie',
5460 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5461 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5464 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5465 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5466 'channel': 'Interstellar Movie',
5468 'modified_date': r
're:\d{8}',
5469 'availability': 'public',
5471 'playlist_mincount': 21,
5473 'note': 'Playlist with "show unavailable videos" button',
5474 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5476 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5477 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5478 'uploader': 'Phim Siêu Nhân Nhật Bản',
5479 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5481 'channel': 'Phim Siêu Nhân Nhật Bản',
5483 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5485 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5486 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5487 'modified_date': r
're:\d{8}',
5488 'availability': 'public',
5490 'playlist_mincount': 200,
5491 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5493 'note': 'Playlist with unavailable videos in page 7',
5494 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5496 'title': 'Uploads from BlankTV',
5497 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5498 'uploader': 'BlankTV',
5499 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5500 'channel': 'BlankTV',
5501 'channel_url': 'https://www.youtube.com/c/blanktv',
5502 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5505 'uploader_url': 'https://www.youtube.com/c/blanktv',
5506 'modified_date': r
're:\d{8}',
5508 'availability': 'public',
5510 'playlist_mincount': 1000,
5511 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5513 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5514 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5516 'title': 'Data Analysis with Dr Mike Pound',
5517 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5518 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5519 'uploader': 'Computerphile',
5520 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5521 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5524 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5525 'channel_url': 'https://www.youtube.com/user/Computerphile',
5526 'channel': 'Computerphile',
5527 'availability': 'public',
5528 'modified_date': '20190712',
5530 'playlist_mincount': 11,
5532 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5533 'only_matching': True,
5535 'note': 'Playlist URL that does not actually serve a playlist',
5536 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5538 'id': 'FqZTN594JQw',
5540 'title': "Smiley's People 01 detective, Adventure Series, Action",
5541 'uploader': 'STREEM',
5542 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5543 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5544 'upload_date': '20150526',
5545 'license': 'Standard YouTube License',
5546 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5547 'categories': ['People & Blogs'],
5553 'skip_download': True,
5555 'skip': 'This video is not available.',
5556 'add_ie': [YoutubeIE
.ie_key()],
5558 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5559 'only_matching': True,
5561 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5562 'only_matching': True,
5564 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5566 'id': 'Wq15eF5vCbI', # This will keep changing
5569 'uploader': 'Sky News',
5570 'uploader_id': 'skynews',
5571 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5572 'upload_date': r
're:\d{8}',
5574 'categories': ['News & Politics'],
5577 'release_timestamp': int,
5578 'channel': 'Sky News',
5579 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5582 'thumbnail': r
're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5583 'playable_in_embed': True,
5584 'release_date': r
're:\d+',
5585 'availability': 'public',
5586 'live_status': 'is_live',
5587 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5588 'channel_follower_count': int,
5589 'concurrent_view_count': int,
5592 'skip_download': True,
5594 'expected_warnings': ['Ignoring subtitle tracks found in '],
5596 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5598 'id': 'a48o2S1cPoo',
5600 'title': 'The Young Turks - Live Main Show',
5601 'uploader': 'The Young Turks',
5602 'uploader_id': 'TheYoungTurks',
5603 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5604 'upload_date': '20150715',
5605 'license': 'Standard YouTube License',
5606 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5607 'categories': ['News & Politics'],
5608 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5612 'skip_download': True,
5614 'only_matching': True,
5616 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5617 'only_matching': True,
5619 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5620 'only_matching': True,
5622 'note': 'A channel that is not live. Should raise error',
5623 'url': 'https://www.youtube.com/user/numberphile/live',
5624 'only_matching': True,
5626 'url': 'https://www.youtube.com/feed/trending',
5627 'only_matching': True,
5629 'url': 'https://www.youtube.com/feed/library',
5630 'only_matching': True,
5632 'url': 'https://www.youtube.com/feed/history',
5633 'only_matching': True,
5635 'url': 'https://www.youtube.com/feed/subscriptions',
5636 'only_matching': True,
5638 'url': 'https://www.youtube.com/feed/watch_later',
5639 'only_matching': True,
5641 'note': 'Recommended - redirects to home page.',
5642 'url': 'https://www.youtube.com/feed/recommended',
5643 'only_matching': True,
5645 'note': 'inline playlist with not always working continuations',
5646 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5647 'only_matching': True,
5649 'url': 'https://www.youtube.com/course',
5650 'only_matching': True,
5652 'url': 'https://www.youtube.com/zsecurity',
5653 'only_matching': True,
5655 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5656 'only_matching': True,
5658 'url': 'https://www.youtube.com/TheYoungTurks/live',
5659 'only_matching': True,
5661 'url': 'https://www.youtube.com/hashtag/cctv9',
5667 'playlist_mincount': 300, # not consistent but should be over 300
5669 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5670 'only_matching': True,
5672 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5673 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5674 'only_matching': True
5676 'note': '/browse/ should redirect to /channel/',
5677 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5678 'only_matching': True
5680 'note': 'VLPL, should redirect to playlist?list=PL...',
5681 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5683 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5684 'uploader': 'NoCopyrightSounds',
5685 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5686 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5687 'title': 'NCS : All Releases 💿',
5688 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5689 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5690 'modified_date': r
're:\d{8}',
5692 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5694 'channel': 'NoCopyrightSounds',
5695 'availability': 'public',
5697 'playlist_mincount': 166,
5698 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5700 'note': 'Topic, should redirect to playlist?list=UU...',
5701 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5703 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5704 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5705 'title': 'Uploads from Royalty Free Music - Topic',
5706 'uploader': 'Royalty Free Music - Topic',
5708 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5709 'channel': 'Royalty Free Music - Topic',
5711 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5712 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5713 'modified_date': r
're:\d{8}',
5714 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5716 'availability': 'public',
5718 'playlist_mincount': 101,
5720 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5721 # Treat as a general feed
5722 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5724 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5725 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5728 'playlist_mincount': 9,
5730 'note': 'Youtube music Album',
5731 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5733 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5734 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5738 'availability': 'unlisted',
5739 'modified_date': r
're:\d{8}',
5741 'playlist_count': 50,
5743 'note': 'unlisted single video playlist',
5744 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5746 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5747 'uploader': 'colethedj',
5748 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5749 'title': 'yt-dlp unlisted playlist test',
5750 'availability': 'unlisted',
5752 'modified_date': '20220418',
5753 'channel': 'colethedj',
5756 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5757 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5758 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5760 'playlist_count': 1,
5762 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5763 'url': 'https://www.youtube.com/feed/recommended',
5765 'id': 'recommended',
5766 'title': 'recommended',
5769 'playlist_mincount': 50,
5771 'skip_download': True,
5772 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5775 'note': 'API Fallback: /videos tab, sorted by oldest first',
5776 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5778 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5779 'title': 'Cody\'sLab - Videos',
5780 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5781 'uploader': 'Cody\'sLab',
5782 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5783 'channel': 'Cody\'sLab',
5784 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5786 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5787 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5788 'channel_follower_count': int
5790 'playlist_mincount': 650,
5792 'skip_download': True,
5793 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5795 'skip': 'Query for sorting no longer works',
5797 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5798 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5800 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5801 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5802 'title': 'Uploads from Royalty Free Music - Topic',
5803 'uploader': 'Royalty Free Music - Topic',
5804 'modified_date': r
're:\d{8}',
5805 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5807 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5809 'channel': 'Royalty Free Music - Topic',
5811 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5812 'availability': 'public',
5814 'playlist_mincount': 101,
5816 'skip_download': True,
5817 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5820 'note': 'non-standard redirect to regional channel',
5821 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5822 'only_matching': True
5824 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5825 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5827 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5828 'modified_date': '20220407',
5829 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5831 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5832 'uploader': 'pukkandan',
5833 'availability': 'unlisted',
5834 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5835 'channel': 'pukkandan',
5836 'description': 'Test for collaborative playlist',
5837 'title': 'yt-dlp test - collaborative playlist',
5839 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5841 'playlist_mincount': 2
5843 'note': 'translated tab name',
5844 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5846 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5848 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5849 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5850 'description': 'test description',
5851 'title': 'cole-dlp-test-acc - 再生リスト',
5852 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5853 'uploader': 'cole-dlp-test-acc',
5854 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5855 'channel': 'cole-dlp-test-acc',
5857 'playlist_mincount': 1,
5858 'params': {'extractor_args': {'youtube': {'lang': ['ja']}
}},
5859 'expected_warnings': ['Preferring "ja"'],
5861 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5862 'note': 'preferred lang set with playlist with translated video titles',
5863 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5865 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5868 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5869 'uploader': 'cole-dlp-test-acc',
5870 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5871 'channel': 'cole-dlp-test-acc',
5872 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5873 'description': 'test',
5874 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5875 'title': 'dlp test playlist',
5876 'availability': 'public',
5878 'playlist_mincount': 1,
5879 'params': {'extractor_args': {'youtube': {'lang': ['ja']}
}},
5880 'expected_warnings': ['Preferring "ja"'],
5882 # shorts audio pivot for 2GtVksBMYFM.
5883 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5885 'id': 'sfv_audio_pivot',
5886 'title': 'sfv_audio_pivot',
5889 'playlist_mincount': 50,
5892 # Channel with a real live tab (not to be mistaken with streams tab)
5893 # Do not treat like it should redirect to live stream
5894 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5896 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5897 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5900 'playlist_mincount': 20,
5902 # Tab name is not the same as tab id
5903 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5905 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5906 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5909 'playlist_mincount': 8,
5911 # Home tab id is literally home. Not to get mistaken with featured
5912 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5914 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5915 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5918 'playlist_mincount': 8,
5920 # Should get three playlists for videos, shorts and streams tabs
5921 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5923 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5924 'title': 'Polka Ch. 尾丸ポルカ',
5925 'channel_follower_count': int,
5926 'channel_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5927 'channel_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5928 'uploader': 'Polka Ch. 尾丸ポルカ',
5929 'description': 'md5:3b8df1ac5af337aa206e37ee3d181ec9',
5930 'channel': 'Polka Ch. 尾丸ポルカ',
5932 'uploader_url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5933 'uploader_id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5935 'playlist_count': 3,
5937 # Shorts tab with channel with handle
5938 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5940 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5941 'title': 'Not Just Bikes - Shorts',
5943 'uploader': 'Not Just Bikes',
5944 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5945 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5946 'channel_follower_count': int,
5947 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5948 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5949 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5950 'channel': 'Not Just Bikes',
5952 'playlist_mincount': 10,
5955 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5957 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5958 'title': '中村悠一 - Live',
5960 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5961 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5962 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5964 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5965 'channel_follower_count': int,
5967 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5969 'playlist_mincount': 60,
5971 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5972 # See test_youtube_lists
5973 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5974 'only_matching': True,
5976 # No uploads and no UCID given. Should fail with no uploads error
5977 # See test_youtube_lists
5978 'url': 'https://www.youtube.com/news',
5979 'only_matching': True
5981 # No videos tab but has a shorts tab
5982 'url': 'https://www.youtube.com/c/TKFShorts',
5984 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5985 'title': 'Shorts Break - Shorts',
5987 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5988 'channel': 'Shorts Break',
5989 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5990 'uploader': 'Shorts Break',
5991 'channel_follower_count': int,
5992 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5993 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5994 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5996 'playlist_mincount': 30,
5998 # Trending Now Tab. tab id is empty
5999 'url': 'https://www.youtube.com/feed/trending',
6002 'title': 'trending - Now',
6005 'playlist_mincount': 30,
6007 # Trending Gaming Tab. tab id is empty
6008 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
6011 'title': 'trending - Gaming',
6014 'playlist_mincount': 30,
6016 # Shorts url result in shorts tab
6017 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/shorts',
6019 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6020 'title': 'cole-dlp-test-acc - Shorts',
6021 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6022 'channel': 'cole-dlp-test-acc',
6023 'description': 'test description',
6024 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6025 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6027 'uploader': 'cole-dlp-test-acc',
6028 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6034 'ie_key': 'Youtube',
6035 'url': 'https://www.youtube.com/shorts/sSM9J5YH_60',
6036 'id': 'sSM9J5YH_60',
6037 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6038 'title': 'SHORT short',
6039 'channel': 'cole-dlp-test-acc',
6040 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6045 'params': {'extract_flat': True}
,
6047 # Live video status should be extracted
6048 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/live',
6050 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
6051 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Live', # TODO, should be Minecraft - Live or Minecraft - Topic - Live
6057 'ie_key': 'Youtube',
6058 'url': 'startswith:https://www.youtube.com/watch?v=',
6061 'live_status': 'is_live',
6064 'concurrent_view_count': int,
6068 'params': {'extract_flat': True, 'playlist_items': '1'}
,
6069 'playlist_mincount': 1
6071 # Channel renderer metadata. Contains number of videos on the channel
6072 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/channels',
6074 'id': 'UCiu-3thuViMebBjw_5nWYrA',
6075 'title': 'cole-dlp-test-acc - Channels',
6076 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
6077 'channel': 'cole-dlp-test-acc',
6078 'description': 'test description',
6079 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
6080 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6082 'uploader': 'cole-dlp-test-acc',
6083 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
6089 'ie_key': 'YoutubeTab',
6090 'url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6091 'id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6092 'channel_id': 'UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6093 'title': 'PewDiePie',
6094 'channel': 'PewDiePie',
6095 'channel_url': 'https://www.youtube.com/channel/UC-lHJZR3Gqxm24_Vd_AJ5Yw',
6097 'channel_follower_count': int,
6098 'playlist_count': int
6101 'params': {'extract_flat': True}
,
6103 'url': 'https://www.youtube.com/@3blue1brown/about',
6105 'id': 'UCYO_jab_esuFRV4b17AJtAw',
6106 'tags': ['Mathematics'],
6107 'title': '3Blue1Brown - About',
6108 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6109 'channel_follower_count': int,
6110 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
6111 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
6112 'channel': '3Blue1Brown',
6113 'uploader': '3Blue1Brown',
6115 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
6116 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
6118 'playlist_count': 0,
6122 def suitable(cls
, url
):
6123 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
6125 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
6127 def _get_url_mobj(self
, url
):
6128 mobj
= self
._URL
_RE
.match(url
).groupdict()
6129 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
6132 def _extract_tab_id_and_name(self
, tab
, base_url
='https://www.youtube.com'):
6133 tab_name
= (tab
.get('title') or '').lower()
6134 tab_url
= urljoin(base_url
, traverse_obj(
6135 tab
, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
6137 tab_id
= (tab_url
and self
._get
_url
_mobj
(tab_url
)['tab'][1:]
6138 or traverse_obj(tab
, 'tabIdentifier', expected_type
=str))
6141 'TAB_ID_SPONSORSHIPS': 'membership',
6142 }.get(tab_id
, tab_id
), tab_name
6144 # Fallback to tab name if we cannot get the tab id.
6145 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
6146 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
6148 self
.write_debug(f
'Falling back to selected tab name: {tab_name}')
6152 }.get(tab_name
, tab_name
), tab_name
6154 def _has_tab(self
, tabs
, tab_id
):
6155 return any(self
._extract
_tab
_id
_and
_name
(tab
)[0] == tab_id
for tab
in tabs
)
6157 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
6158 def _real_extract(self
, url
, smuggled_data
):
6159 item_id
= self
._match
_id
(url
)
6160 url
= urllib
.parse
.urlunparse(
6161 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
6162 compat_opts
= self
.get_param('compat_opts', [])
6164 mobj
= self
._get
_url
_mobj
(url
)
6165 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'], mobj
['post'], not mobj
['not_channel']
6166 if is_channel
and smuggled_data
.get('is_music_url'):
6167 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
6168 return self
.url_result(
6169 f
'https://music.youtube.com/playlist?list={item_id[2:]}', YoutubeTabIE
, item_id
[2:])
6170 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
6171 mdata
= self
._extract
_tab
_endpoint
(
6172 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
6173 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
6174 get_all
=False, expected_type
=str)
6176 raise ExtractorError('Failed to resolve album to playlist')
6177 return self
.url_result(murl
, YoutubeTabIE
)
6178 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
6179 return self
.url_result(
6180 f
'https://music.youtube.com/channel/{item_id}{tab}{post}', YoutubeTabIE
, item_id
)
6182 original_tab_id
, display_id
= tab
[1:], f
'{item_id}{tab}'
6183 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
6184 url
= f
'{pre}/videos{post}'
6185 if smuggled_data
.get('is_music_url'):
6186 self
.report_warning(f
'YouTube Music is not directly supported. Redirecting to {url}')
6188 # Handle both video/playlist URLs
6190 video_id
, playlist_id
= [traverse_obj(qs
, (key
, 0)) for key
in ('v', 'list')]
6191 if not video_id
and mobj
['not_channel'].startswith('watch'):
6193 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
6194 raise ExtractorError('A video URL was given without video ID', expected
=True)
6195 # Common mistake: https://www.youtube.com/watch?list=playlist_id
6196 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
6197 return self
.url_result(
6198 f
'https://www.youtube.com/playlist?list={playlist_id}', YoutubeTabIE
, playlist_id
)
6200 if not self
._yes
_playlist
(playlist_id
, video_id
):
6201 return self
.url_result(
6202 f
'https://www.youtube.com/watch?v={video_id}', YoutubeIE
, video_id
)
6204 data
, ytcfg
= self
._extract
_data
(url
, display_id
)
6206 # YouTube may provide a non-standard redirect to the regional channel
6207 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
6208 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
6209 redirect_url
= traverse_obj(
6210 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
6211 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
6212 redirect_url
= ''.join((urljoin('https://www.youtube.com', redirect_url
), tab
, post
))
6213 self
.to_screen(f
'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
6214 return self
.url_result(redirect_url
, YoutubeTabIE
)
6216 tabs
, extra_tabs
= self
._extract
_tab
_renderers
(data
), []
6217 if is_channel
and tabs
and 'no-youtube-channel-redirect' not in compat_opts
:
6218 selected_tab
= self
._extract
_selected
_tab
(tabs
)
6219 selected_tab_id
, selected_tab_name
= self
._extract
_tab
_id
_and
_name
(selected_tab
, url
) # NB: Name may be translated
6220 self
.write_debug(f
'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
6222 if not original_tab_id
and selected_tab_name
:
6223 self
.to_screen('Downloading all uploads of the channel. '
6224 'To download only the videos in a specific tab, pass the tab\'s URL')
6225 if self
._has
_tab
(tabs
, 'streams'):
6226 extra_tabs
.append(''.join((pre
, '/streams', post
)))
6227 if self
._has
_tab
(tabs
, 'shorts'):
6228 extra_tabs
.append(''.join((pre
, '/shorts', post
)))
6229 # XXX: Members-only tab should also be extracted
6231 if not extra_tabs
and selected_tab_id
!= 'videos':
6232 # Channel does not have streams, shorts or videos tabs
6233 if item_id
[:2] != 'UC':
6234 raise ExtractorError('This channel has no uploads', expected
=True)
6236 # Topic channels don't have /videos. Use the equivalent playlist instead
6237 pl_id
= f
'UU{item_id[2:]}'
6238 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
6240 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
6241 except ExtractorError
:
6242 raise ExtractorError('This channel has no uploads', expected
=True)
6244 item_id
, url
= pl_id
, pl_url
6246 f
'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
6248 elif extra_tabs
and selected_tab_id
!= 'videos':
6249 # When there are shorts/live tabs but not videos tab
6250 url
, data
= f
'{pre}{post}', None
6252 elif (original_tab_id
or 'videos') != selected_tab_id
:
6253 if original_tab_id
== 'live':
6254 # Live tab should have redirected to the video
6255 # Except in the case the channel has an actual live tab
6256 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
6257 raise UserNotLive(video_id
=item_id
)
6258 elif selected_tab_name
:
6259 raise ExtractorError(f
'This channel does not have a {original_tab_id} tab', expected
=True)
6261 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
6262 url
= f
'{pre}{post}'
6264 # YouTube sometimes provides a button to reload playlist with unavailable videos.
6265 if 'no-youtube-unavailable-videos' not in compat_opts
:
6266 data
= self
._reload
_with
_unavailable
_videos
(display_id
, data
, ytcfg
) or data
6267 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
6269 tabs
, entries
= self
._extract
_tab
_renderers
(data
), []
6271 entries
= [self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)]
6273 'extractor_key': YoutubeTabIE
.ie_key(),
6274 'extractor': YoutubeTabIE
.IE_NAME
,
6277 if self
.get_param('playlist_items') == '0':
6278 entries
.extend(self
.url_result(u
, YoutubeTabIE
) for u
in extra_tabs
)
6279 else: # Users expect to get all `video_id`s even with `--flat-playlist`. So don't return `url_result`
6280 entries
.extend(map(self
._real
_extract
, extra_tabs
))
6282 if len(entries
) == 1:
6285 metadata
= self
._extract
_metadata
_from
_tabs
(item_id
, data
)
6286 uploads_url
= 'the Uploads (UU) playlist URL'
6287 if try_get(metadata
, lambda x
: x
['channel_id'].startswith('UC')):
6288 uploads_url
= f
'https://www.youtube.com/playlist?list=UU{metadata["channel_id"][2:]}'
6290 'Downloading as multiple playlists, separated by tabs. '
6291 f
'To download as a single playlist instead, pass {uploads_url}')
6292 return self
.playlist_result(entries
, item_id
, **metadata
)
6295 playlist
= traverse_obj(
6296 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
6298 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
6300 video_id
= traverse_obj(
6301 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
6303 if tab
!= '/live': # live tab is expected to redirect to video
6304 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
6305 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}', YoutubeIE
, video_id
)
6307 raise ExtractorError('Unable to recognize tab page')
6310 class YoutubePlaylistIE(InfoExtractor
):
6311 IE_DESC
= 'YouTube playlists'
6312 _VALID_URL
= r
'''(?x)(?:
6317 youtube(?:kids)?\.com|
6322 (?P<id>%(playlist_id)s)
6324 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
6325 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
6327 IE_NAME
= 'youtube:playlist'
6329 'note': 'issue #673',
6330 'url': 'PLBB231211A4F62143',
6332 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6333 'id': 'PLBB231211A4F62143',
6334 'uploader': 'Wickman',
6335 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6336 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6338 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6339 'modified_date': r
're:\d{8}',
6340 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6341 'channel': 'Wickman',
6343 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6344 'availability': 'public',
6346 'playlist_mincount': 29,
6348 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6350 'title': 'YDL_safe_search',
6351 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6353 'playlist_count': 2,
6354 'skip': 'This playlist is private',
6357 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6358 'playlist_count': 4,
6361 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6362 'uploader': 'milan',
6363 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6365 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6367 'modified_date': '20140919',
6370 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6371 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6372 'availability': 'public',
6374 'expected_warnings': [r
'[Uu]navailable videos? (is|are|will be) hidden'],
6376 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6377 'playlist_mincount': 455,
6379 'title': '2018 Chinese New Singles (11/6 updated)',
6380 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6382 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6383 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6386 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6388 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6389 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6390 'modified_date': r
're:\d{8}',
6391 'availability': 'public',
6393 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
6395 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6396 'only_matching': True,
6398 # music album playlist
6399 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6400 'only_matching': True,
6404 def suitable(cls
, url
):
6405 if YoutubeTabIE
.suitable(url
):
6407 from ..utils
import parse_qs
6409 if qs
.get('v', [None])[0]:
6411 return super().suitable(url
)
6413 def _real_extract(self
, url
):
6414 playlist_id
= self
._match
_id
(url
)
6415 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
6416 url
= update_url_query(
6417 'https://www.youtube.com/playlist',
6418 parse_qs(url
) or {'list': playlist_id}
)
6420 url
= smuggle_url(url
, {'is_music_url': True}
)
6421 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
6424 class YoutubeYtBeIE(InfoExtractor
):
6425 IE_DESC
= 'youtu.be'
6426 _VALID_URL
= r
'https?://youtu\.be/(?P<id>[0-9A-Za-z_-]{11})/*?.*?\blist=(?P<playlist_id>%(playlist_id)s)' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
6428 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6430 'id': 'yeWKywCrFtk',
6432 'title': 'Small Scale Baler and Braiding Rugs',
6433 'uploader': 'Backus-Page House Museum',
6434 'uploader_id': 'backuspagemuseum',
6435 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6436 'upload_date': '20161008',
6437 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6438 'categories': ['Nonprofits & Activism'],
6442 'playable_in_embed': True,
6443 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6444 'channel': 'Backus-Page House Museum',
6445 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6446 'live_status': 'not_live',
6448 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6449 'availability': 'public',
6451 'comment_count': int,
6452 'channel_follower_count': int
6456 'skip_download': True,
6459 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6460 'only_matching': True,
6463 def _real_extract(self
, url
):
6464 mobj
= self
._match
_valid
_url
(url
)
6465 video_id
= mobj
.group('id')
6466 playlist_id
= mobj
.group('playlist_id')
6467 return self
.url_result(
6468 update_url_query('https://www.youtube.com/watch', {
6470 'list': playlist_id
,
6471 'feature': 'youtu.be',
6472 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
6475 class YoutubeLivestreamEmbedIE(InfoExtractor
):
6476 IE_DESC
= 'YouTube livestream embeds'
6477 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6479 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6480 'only_matching': True,
6483 def _real_extract(self
, url
):
6484 channel_id
= self
._match
_id
(url
)
6485 return self
.url_result(
6486 f
'https://www.youtube.com/channel/{channel_id}/live',
6487 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
6490 class YoutubeYtUserIE(InfoExtractor
):
6491 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
6492 IE_NAME
= 'youtube:user'
6493 _VALID_URL
= r
'ytuser:(?P<id>.+)'
6495 'url': 'ytuser:phihag',
6496 'only_matching': True,
6499 def _real_extract(self
, url
):
6500 user_id
= self
._match
_id
(url
)
6501 return self
.url_result(f
'https://www.youtube.com/user/{user_id}', YoutubeTabIE
, user_id
)
6504 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
6505 IE_NAME
= 'youtube:favorites'
6506 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6507 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
6508 _LOGIN_REQUIRED
= True
6511 'only_matching': True,
6513 'url': ':ytfavorites',
6514 'only_matching': True,
6517 def _real_extract(self
, url
):
6518 return self
.url_result(
6519 'https://www.youtube.com/playlist?list=LL',
6520 ie
=YoutubeTabIE
.ie_key())
6523 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
6524 IE_NAME
= 'youtube:notif'
6525 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6526 _VALID_URL
= r
':ytnotif(?:ication)?s?'
6527 _LOGIN_REQUIRED
= True
6530 'only_matching': True,
6532 'url': ':ytnotifications',
6533 'only_matching': True,
6536 def _extract_notification_menu(self
, response
, continuation_list
):
6537 notification_list
= traverse_obj(
6539 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6540 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6541 expected_type
=list) or []
6542 continuation_list
[0] = None
6543 for item
in notification_list
:
6544 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
6547 continuation
= item
.get('continuationItemRenderer')
6549 continuation_list
[0] = continuation
6551 def _extract_notification_renderer(self
, notification
):
6552 video_id
= traverse_obj(
6553 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
6554 url
= f
'https://www.youtube.com/watch?v={video_id}'
6557 browse_ep
= traverse_obj(
6558 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
6559 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
6560 post_id
= self
._search
_regex
(
6561 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
6562 'post id', default
=None)
6563 if not channel_id
or not post_id
:
6565 # The direct /post url redirects to this in the browser
6566 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6568 channel
= traverse_obj(
6569 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6571 notification_title
= self
._get
_text
(notification
, 'shortMessage')
6572 if notification_title
:
6573 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
6574 # TODO: handle recommended videos
6575 title
= self
._search
_regex
(
6576 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
6577 'video title', default
=None)
6578 timestamp
= (self
._parse
_time
_text
(self
._get
_text
(notification
, 'sentTimeText'))
6579 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
)
6584 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
6585 'video_id': video_id
,
6587 'channel_id': channel_id
,
6589 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
6590 'timestamp': timestamp
,
6593 def _notification_menu_entries(self
, ytcfg
):
6594 continuation_list
= [None]
6596 for page
in itertools
.count(1):
6597 ctoken
= traverse_obj(
6598 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
6599 response
= self
._extract
_response
(
6600 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
6601 ep
='notification/get_notification_menu', check_get_keys
='actions',
6602 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
6603 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
6604 if not continuation_list
[0]:
6607 def _real_extract(self
, url
):
6608 display_id
= 'notifications'
6609 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
6610 self
._report
_playlist
_authcheck
(ytcfg
)
6611 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
6614 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
6615 IE_DESC
= 'YouTube search'
6616 IE_NAME
= 'youtube:search'
6617 _SEARCH_KEY
= 'ytsearch'
6618 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
6620 'url': 'ytsearch5:youtube-dl test video',
6621 'playlist_count': 5,
6623 'id': 'youtube-dl test video',
6624 'title': 'youtube-dl test video',
6629 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
6630 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
6631 _SEARCH_KEY
= 'ytsearchdate'
6632 IE_DESC
= 'YouTube search, newest videos first'
6633 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
6635 'url': 'ytsearchdate5:youtube-dl test video',
6636 'playlist_count': 5,
6638 'id': 'youtube-dl test video',
6639 'title': 'youtube-dl test video',
6644 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
6645 IE_DESC
= 'YouTube search URLs with sorting and filter support'
6646 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
6647 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6649 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6650 'playlist_mincount': 5,
6652 'id': 'youtube-dl test video',
6653 'title': 'youtube-dl test video',
6656 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6657 'playlist_mincount': 5,
6663 'url': 'https://www.youtube.com/results?search_query=%23cats',
6664 'playlist_mincount': 1,
6668 # The test suite does not have support for nested playlists
6670 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6676 'url': 'https://www.youtube.com/results?search_query=kurzgesagt&sp=EgIQAg%253D%253D',
6679 'title': 'kurzgesagt',
6684 'id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6685 'url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6686 'ie_key': 'YoutubeTab',
6687 'channel': 'Kurzgesagt – In a Nutshell',
6688 'description': 'md5:4ae48dfa9505ffc307dad26342d06bfc',
6689 'title': 'Kurzgesagt – In a Nutshell',
6690 'channel_id': 'UCsXVk37bltHxD1rDPwtNM8Q',
6691 'playlist_count': int, # XXX: should have a way of saying > 1
6692 'channel_url': 'https://www.youtube.com/channel/UCsXVk37bltHxD1rDPwtNM8Q',
6696 'params': {'extract_flat': True, 'playlist_items': '1'}
,
6697 'playlist_mincount': 1,
6699 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6700 'only_matching': True,
6703 def _real_extract(self
, url
):
6705 query
= (qs
.get('search_query') or qs
.get('q'))[0]
6706 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
6709 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
6710 IE_DESC
= 'YouTube music search URLs with selectable sections, e.g. #songs'
6711 IE_NAME
= 'youtube:music:search_url'
6712 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6714 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6715 'playlist_count': 16,
6717 'id': 'royalty free music',
6718 'title': 'royalty free music',
6721 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6722 'playlist_mincount': 30,
6724 'id': 'royalty free music - songs',
6725 'title': 'royalty free music - songs',
6727 'params': {'extract_flat': 'in_playlist'}
6729 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6730 'playlist_mincount': 30,
6732 'id': 'royalty free music - community playlists',
6733 'title': 'royalty free music - community playlists',
6735 'params': {'extract_flat': 'in_playlist'}
6739 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6740 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6741 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6742 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6743 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6744 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6747 def _real_extract(self
, url
):
6749 query
= (qs
.get('search_query') or qs
.get('q'))[0]
6750 params
= qs
.get('sp', (None,))[0]
6752 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
6754 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
6755 params
= self
._SECTIONS
.get(section
)
6758 title
= join_nonempty(query
, section
, delim
=' - ')
6759 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
6762 class YoutubeFeedsInfoExtractor(InfoExtractor
):
6764 Base class for feed extractors
6765 Subclasses must re-define the _FEED_NAME property.
6767 _LOGIN_REQUIRED
= True
6768 _FEED_NAME
= 'feeds'
6770 def _real_initialize(self
):
6771 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
6775 return f
'youtube:{self._FEED_NAME}'
6777 def _real_extract(self
, url
):
6778 return self
.url_result(
6779 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
6782 class YoutubeWatchLaterIE(InfoExtractor
):
6783 IE_NAME
= 'youtube:watchlater'
6784 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6785 _VALID_URL
= r
':ytwatchlater'
6787 'url': ':ytwatchlater',
6788 'only_matching': True,
6791 def _real_extract(self
, url
):
6792 return self
.url_result(
6793 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
6796 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
6797 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
6798 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6799 _FEED_NAME
= 'recommended'
6800 _LOGIN_REQUIRED
= False
6803 'only_matching': True,
6805 'url': ':ytrecommended',
6806 'only_matching': True,
6808 'url': 'https://youtube.com',
6809 'only_matching': True,
6813 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
6814 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6815 _VALID_URL
= r
':ytsub(?:scription)?s?'
6816 _FEED_NAME
= 'subscriptions'
6819 'only_matching': True,
6821 'url': ':ytsubscriptions',
6822 'only_matching': True,
6826 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
6827 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
6828 _VALID_URL
= r
':ythis(?:tory)?'
6829 _FEED_NAME
= 'history'
6831 'url': ':ythistory',
6832 'only_matching': True,
6836 class YoutubeStoriesIE(InfoExtractor
):
6837 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
6838 IE_NAME
= 'youtube:stories'
6839 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6841 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6842 'only_matching': True,
6845 def _real_extract(self
, url
):
6846 playlist_id
= f
'RLTD{self._match_id(url)}'
6847 return self
.url_result(
6848 smuggle_url(f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}
),
6849 ie
=YoutubeTabIE
, video_id
=playlist_id
)
6852 class YoutubeShortsAudioPivotIE(InfoExtractor
):
6853 IE_DESC
= 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6854 IE_NAME
= 'youtube:shorts:pivot:audio'
6855 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6857 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6858 'only_matching': True,
6862 def _generate_audio_pivot_params(video_id
):
6864 Generates sfv_audio_pivot browse params for this video id
6866 pb_params
= b
'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id
.encode(),) * 3)
6867 return urllib
.parse
.quote(base64
.b64encode(pb_params
).decode())
6869 def _real_extract(self
, url
):
6870 video_id
= self
._match
_id
(url
)
6871 return self
.url_result(
6872 f
'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6876 class YoutubeTruncatedURLIE(InfoExtractor
):
6877 IE_NAME
= 'youtube:truncated_url'
6878 IE_DESC
= False # Do not list
6879 _VALID_URL
= r
'''(?x)
6881 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6884 annotation_id=annotation_[^&]+|
6890 attribution_link\?a=[^&]+
6896 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6897 'only_matching': True,
6899 'url': 'https://www.youtube.com/watch?',
6900 'only_matching': True,
6902 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6903 'only_matching': True,
6905 'url': 'https://www.youtube.com/watch?feature=foo',
6906 'only_matching': True,
6908 'url': 'https://www.youtube.com/watch?hl=en-GB',
6909 'only_matching': True,
6911 'url': 'https://www.youtube.com/watch?t=2372',
6912 'only_matching': True,
6915 def _real_extract(self
, url
):
6916 raise ExtractorError(
6917 'Did you forget to quote the URL? Remember that & is a meta '
6918 'character in most shells, so you want to put the URL in quotes, '
6920 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6921 ' or simply youtube-dl BaW_jenozKc .',
6925 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6926 IE_NAME
= 'youtube:clip'
6927 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6929 # FIXME: Other metadata should be extracted from the clip, not from the base video
6930 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6932 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6934 'section_start': 29.0,
6935 'section_end': 39.7,
6938 'availability': 'public',
6939 'categories': ['Gaming'],
6940 'channel': 'Scott The Woz',
6941 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6942 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6943 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6945 'playable_in_embed': True,
6947 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6948 'title': 'Mobile Games on Console - Scott The Woz',
6949 'upload_date': '20210920',
6950 'uploader': 'Scott The Woz',
6951 'uploader_id': 'scottthewoz',
6952 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6954 'live_status': 'not_live',
6955 'channel_follower_count': int
6959 def _real_extract(self
, url
):
6960 clip_id
= self
._match
_id
(url
)
6961 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6963 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6965 raise ExtractorError('Unable to find video ID')
6967 clip_data
= traverse_obj(data
, (
6968 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6969 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6970 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6971 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6974 '_type': 'url_transparent',
6975 'url': f
'https://www.youtube.com/watch?v={video_id}',
6976 'ie_key': YoutubeIE
.ie_key(),
6978 'section_start': int(clip_data
['startTimeMs']) / 1000,
6979 'section_end': int(clip_data
['endTimeMs']) / 1000,
6983 class YoutubeConsentRedirectIE(YoutubeBaseInfoExtractor
):
6984 IE_NAME
= 'youtube:consent'
6985 IE_DESC
= False # Do not list
6986 _VALID_URL
= r
'https?://consent\.youtube\.com/m\?'
6988 'url': 'https://consent.youtube.com/m?continue=https%3A%2F%2Fwww.youtube.com%2Flive%2FqVv6vCqciTM%3Fcbrd%3D1&gl=NL&m=0&pc=yt&hl=en&src=1',
6990 'id': 'qVv6vCqciTM',
6993 'uploader_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
6994 'comment_count': int,
6995 'chapters': 'count:13',
6996 'upload_date': '20221223',
6997 'thumbnail': 'https://i.ytimg.com/vi/qVv6vCqciTM/maxresdefault.jpg',
6998 'channel_url': 'https://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
6999 'uploader_url': 'http://www.youtube.com/channel/UCIdEIHpS0TdkqRkHL5OkLtA',
7001 'release_date': '20221223',
7002 'tags': ['Vtuber', '月ノ美兎', '名取さな', 'にじさんじ', 'クリスマス', '3D配信'],
7003 'title': '【 #インターネット女クリスマス 】3Dで歌ってはしゃぐインターネットの女たち【月ノ美兎/名取さな】',
7005 'playable_in_embed': True,
7007 'availability': 'public',
7008 'channel_follower_count': int,
7009 'channel_id': 'UCIdEIHpS0TdkqRkHL5OkLtA',
7010 'categories': ['Entertainment'],
7011 'live_status': 'was_live',
7012 'release_timestamp': 1671793345,
7013 'channel': 'さなちゃんねる',
7014 'description': 'md5:6aebf95cc4a1d731aebc01ad6cc9806d',
7015 'uploader': 'さなちゃんねる',
7017 'add_ie': ['Youtube'],
7018 'params': {'skip_download': 'Youtube'}
,
7021 def _real_extract(self
, url
):
7022 redirect_url
= url_or_none(parse_qs(url
).get('continue', [None])[-1])
7023 if not redirect_url
:
7024 raise ExtractorError('Invalid cookie consent redirect URL', expected
=True)
7025 return self
.url_result(redirect_url
)
7028 class YoutubeTruncatedIDIE(InfoExtractor
):
7029 IE_NAME
= 'youtube:truncated_id'
7030 IE_DESC
= False # Do not list
7031 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
7034 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
7035 'only_matching': True,
7038 def _real_extract(self
, url
):
7039 video_id
= self
._match
_id
(url
)
7040 raise ExtractorError(
7041 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',