20 from .common
import InfoExtractor
, SearchInfoExtractor
21 from .openload
import PhantomJSwrapper
22 from ..compat
import functools
23 from ..jsinterp
import JSInterpreter
68 # any clients starting with _ cannot be explicitly requested by the user
71 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
72 'INNERTUBE_CONTEXT': {
75 'clientVersion': '2.20220801.00.00',
78 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
84 'clientName': 'WEB_EMBEDDED_PLAYER',
85 'clientVersion': '1.20220731.00.00',
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
91 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
92 'INNERTUBE_HOST': 'music.youtube.com',
93 'INNERTUBE_CONTEXT': {
95 'clientName': 'WEB_REMIX',
96 'clientVersion': '1.20220727.01.00',
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
102 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
103 'INNERTUBE_CONTEXT': {
105 'clientName': 'WEB_CREATOR',
106 'clientVersion': '1.20220726.00.00',
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
112 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
113 'INNERTUBE_CONTEXT': {
115 'clientName': 'ANDROID',
116 'clientVersion': '17.31.35',
117 'androidSdkVersion': 30,
118 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
121 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
122 'REQUIRE_JS_PLAYER': False
124 'android_embedded': {
125 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
126 'INNERTUBE_CONTEXT': {
128 'clientName': 'ANDROID_EMBEDDED_PLAYER',
129 'clientVersion': '17.31.35',
130 'androidSdkVersion': 30,
131 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
134 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
135 'REQUIRE_JS_PLAYER': False
138 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
139 'INNERTUBE_CONTEXT': {
141 'clientName': 'ANDROID_MUSIC',
142 'clientVersion': '5.16.51',
143 'androidSdkVersion': 30,
144 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
147 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
148 'REQUIRE_JS_PLAYER': False
151 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
152 'INNERTUBE_CONTEXT': {
154 'clientName': 'ANDROID_CREATOR',
155 'clientVersion': '22.30.100',
156 'androidSdkVersion': 30,
157 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
167 'INNERTUBE_CONTEXT': {
170 'clientVersion': '17.33.2',
171 'deviceModel': 'iPhone14,3',
172 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
175 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
176 'REQUIRE_JS_PLAYER': False
179 'INNERTUBE_CONTEXT': {
181 'clientName': 'IOS_MESSAGES_EXTENSION',
182 'clientVersion': '17.33.2',
183 'deviceModel': 'iPhone14,3',
184 'userAgent': 'com.google.ios.youtube/17.33.2 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
192 'INNERTUBE_CONTEXT': {
194 'clientName': 'IOS_MUSIC',
195 'clientVersion': '5.21',
196 'deviceModel': 'iPhone14,3',
197 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
200 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
201 'REQUIRE_JS_PLAYER': False
204 'INNERTUBE_CONTEXT': {
206 'clientName': 'IOS_CREATOR',
207 'clientVersion': '22.33.101',
208 'deviceModel': 'iPhone14,3',
209 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
212 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
213 'REQUIRE_JS_PLAYER': False
215 # mweb has 'ultralow' formats
216 # See: https://github.com/yt-dlp/yt-dlp/pull/557
218 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
219 'INNERTUBE_CONTEXT': {
221 'clientName': 'MWEB',
222 'clientVersion': '2.20220801.00.00',
225 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
227 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
228 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
230 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
231 'INNERTUBE_CONTEXT': {
233 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
234 'clientVersion': '2.0',
237 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
242 def _split_innertube_client(client_name
):
243 variant
, *base
= client_name
.rsplit('.', 1)
245 return variant
, base
[0], variant
246 base
, *variant
= client_name
.split('_', 1)
247 return client_name
, base
, variant
[0] if variant
else None
250 def build_innertube_clients():
252 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
254 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
255 priority
= qualities(BASE_CLIENTS
[::-1])
257 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
258 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
259 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
260 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
261 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
263 _
, base_client
, variant
= _split_innertube_client(client
)
264 ytcfg
['priority'] = 10 * priority(base_client
)
267 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
268 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
269 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
270 embedscreen
['priority'] -= 3
271 elif variant
== 'embedded':
272 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
273 ytcfg
['priority'] -= 2
275 ytcfg
['priority'] -= 3
278 build_innertube_clients()
281 class BadgeType(enum
.Enum
):
282 AVAILABILITY_UNLISTED
= enum
.auto()
283 AVAILABILITY_PRIVATE
= enum
.auto()
284 AVAILABILITY_PUBLIC
= enum
.auto()
285 AVAILABILITY_PREMIUM
= enum
.auto()
286 AVAILABILITY_SUBSCRIPTION
= enum
.auto()
287 LIVE_NOW
= enum
.auto()
290 class YoutubeBaseInfoExtractor(InfoExtractor
):
291 """Provide base functions for Youtube extractors"""
294 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
295 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
296 r
'browse|oembed|get_video_info|iframe_api|s/player|source|'
297 r
'storefront|oops|index|account|t/terms|about|upload|signin|logout')
299 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
301 # _NETRC_MACHINE = 'youtube'
303 # If True it will raise an error if no login info is provided
304 _LOGIN_REQUIRED
= False
307 # invidious-redirect websites
308 r
'(?:www\.)?redirect\.invidious\.io',
309 r
'(?:(?:www|dev)\.)?invidio\.us',
310 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
311 r
'(?:www\.)?invidious\.pussthecat\.org',
312 r
'(?:www\.)?invidious\.zee\.li',
313 r
'(?:www\.)?invidious\.ethibox\.fr',
314 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
315 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
316 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
317 # youtube-dl invidious instances list
318 r
'(?:(?:www|no)\.)?invidiou\.sh',
319 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
320 r
'(?:www\.)?invidious\.kabi\.tk',
321 r
'(?:www\.)?invidious\.mastodon\.host',
322 r
'(?:www\.)?invidious\.zapashcanon\.fr',
323 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
324 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
325 r
'(?:www\.)?invidious\.himiko\.cloud',
326 r
'(?:www\.)?invidious\.reallyancient\.tech',
327 r
'(?:www\.)?invidious\.tube',
328 r
'(?:www\.)?invidiou\.site',
329 r
'(?:www\.)?invidious\.site',
330 r
'(?:www\.)?invidious\.xyz',
331 r
'(?:www\.)?invidious\.nixnet\.xyz',
332 r
'(?:www\.)?invidious\.048596\.xyz',
333 r
'(?:www\.)?invidious\.drycat\.fr',
334 r
'(?:www\.)?inv\.skyn3t\.in',
335 r
'(?:www\.)?tube\.poal\.co',
336 r
'(?:www\.)?tube\.connect\.cafe',
337 r
'(?:www\.)?vid\.wxzm\.sx',
338 r
'(?:www\.)?vid\.mint\.lgbt',
339 r
'(?:www\.)?vid\.puffyan\.us',
340 r
'(?:www\.)?yewtu\.be',
341 r
'(?:www\.)?yt\.elukerio\.org',
342 r
'(?:www\.)?yt\.lelux\.fi',
343 r
'(?:www\.)?invidious\.ggc-project\.de',
344 r
'(?:www\.)?yt\.maisputain\.ovh',
345 r
'(?:www\.)?ytprivate\.com',
346 r
'(?:www\.)?invidious\.13ad\.de',
347 r
'(?:www\.)?invidious\.toot\.koeln',
348 r
'(?:www\.)?invidious\.fdn\.fr',
349 r
'(?:www\.)?watch\.nettohikari\.com',
350 r
'(?:www\.)?invidious\.namazso\.eu',
351 r
'(?:www\.)?invidious\.silkky\.cloud',
352 r
'(?:www\.)?invidious\.exonip\.de',
353 r
'(?:www\.)?invidious\.riverside\.rocks',
354 r
'(?:www\.)?invidious\.blamefran\.net',
355 r
'(?:www\.)?invidious\.moomoo\.de',
356 r
'(?:www\.)?ytb\.trom\.tf',
357 r
'(?:www\.)?yt\.cyberhost\.uk',
358 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
359 r
'(?:www\.)?qklhadlycap4cnod\.onion',
360 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
361 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
362 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
363 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
364 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
365 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
366 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
367 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
368 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
369 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
370 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
371 r
'(?:www\.)?piped\.kavin\.rocks',
372 r
'(?:www\.)?piped\.tokhmi\.xyz',
373 r
'(?:www\.)?piped\.syncpundit\.io',
374 r
'(?:www\.)?piped\.mha\.fi',
375 r
'(?:www\.)?watch\.whatever\.social',
376 r
'(?:www\.)?piped\.garudalinux\.org',
377 r
'(?:www\.)?piped\.rivo\.lol',
378 r
'(?:www\.)?piped-libre\.kavin\.rocks',
379 r
'(?:www\.)?yt\.jae\.fi',
380 r
'(?:www\.)?piped\.mint\.lgbt',
382 r
'(?:www\.)?piped\.esmailelbob\.xyz',
383 r
'(?:www\.)?piped\.projectsegfau\.lt',
384 r
'(?:www\.)?piped\.privacydev\.net',
385 r
'(?:www\.)?piped\.palveluntarjoaja\.eu',
386 r
'(?:www\.)?piped\.smnz\.de',
387 r
'(?:www\.)?piped\.adminforge\.de',
388 r
'(?:www\.)?watch\.whatevertinfoil\.de',
389 r
'(?:www\.)?piped\.qdi\.fi',
392 # extracted from account/account_menu ep
393 # XXX: These are the supported YouTube UI and API languages,
394 # which is slightly different from languages supported for translation in YouTube studio
395 _SUPPORTED_LANG_CODES
= [
396 'af', 'az', 'id', 'ms', 'bs', 'ca', 'cs', 'da', 'de', 'et', 'en-IN', 'en-GB', 'en', 'es',
397 'es-419', 'es-US', 'eu', 'fil', 'fr', 'fr-CA', 'gl', 'hr', 'zu', 'is', 'it', 'sw', 'lv',
398 'lt', 'hu', 'nl', 'no', 'uz', 'pl', 'pt-PT', 'pt', 'ro', 'sq', 'sk', 'sl', 'sr-Latn', 'fi',
399 'sv', 'vi', 'tr', 'be', 'bg', 'ky', 'kk', 'mk', 'mn', 'ru', 'sr', 'uk', 'el', 'hy', 'iw',
400 'ur', 'ar', 'fa', 'ne', 'mr', 'hi', 'as', 'bn', 'pa', 'gu', 'or', 'ta', 'te', 'kn', 'ml',
401 'si', 'th', 'lo', 'my', 'ka', 'am', 'km', 'zh-CN', 'zh-TW', 'zh-HK', 'ja', 'ko'
404 _IGNORED_WARNINGS
= {'Unavailable videos will be hidden during playback'}
406 @functools.cached_property
407 def _preferred_lang(self
):
409 Returns a language code supported by YouTube for the user preferred language.
410 Returns None if no preferred language set.
412 preferred_lang
= self
._configuration
_arg
('lang', ie_key
='Youtube', casesense
=True, default
=[''])[0]
413 if not preferred_lang
:
415 if preferred_lang
not in self
._SUPPORTED
_LANG
_CODES
:
416 raise ExtractorError(
417 f
'Unsupported language code: {preferred_lang}. Supported language codes (case-sensitive): {join_nonempty(*self._SUPPORTED_LANG_CODES, delim=", ")}.',
419 elif preferred_lang
!= 'en':
421 f
'Preferring "{preferred_lang}" translated fields. Note that some metadata extraction may fail or be incorrect.')
422 return preferred_lang
424 def _initialize_consent(self
):
425 cookies
= self
._get
_cookies
('https://www.youtube.com/')
426 if cookies
.get('__Secure-3PSID'):
429 consent
= cookies
.get('CONSENT')
431 if 'YES' in consent
.value
:
433 consent_id
= self
._search
_regex
(
434 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
436 consent_id
= random
.randint(100, 999)
437 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
439 def _initialize_pref(self
):
440 cookies
= self
._get
_cookies
('https://www.youtube.com/')
441 pref_cookie
= cookies
.get('PREF')
445 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
447 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
448 pref
.update({'hl': self._preferred_lang or 'en', 'tz': 'UTC'}
)
449 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
451 def _real_initialize(self
):
452 self
._initialize
_pref
()
453 self
._initialize
_consent
()
454 self
._check
_login
_required
()
456 def _check_login_required(self
):
457 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
458 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
460 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
461 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
463 def _get_default_ytcfg(self, client='web'):
464 return copy.deepcopy(INNERTUBE_CLIENTS[client])
466 def _get_innertube_host(self, client='web'):
467 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
469 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
470 # try_get but with fallback to default ytcfg client values when present
471 _func = lambda y: try_get(y, getter, expected_type)
472 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
474 def _extract_client_name(self, ytcfg, default_client='web'):
475 return self._ytcfg_get_safe(
476 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
477 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
479 def _extract_client_version(self, ytcfg, default_client='web'):
480 return self._ytcfg_get_safe(
481 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
482 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
484 def _select_api_hostname(self, req_api_hostname, default_client=None):
485 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
486 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
488 def _extract_api_key(self, ytcfg=None, default_client='web'):
489 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
491 def _extract_context(self, ytcfg=None, default_client='web'):
493 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
494 # Enforce language and tz for extraction
495 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
496 client_context.update({'hl': self._preferred_lang or 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
501 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
502 time_now = round(time.time())
503 if self._SAPISID is None:
504 yt_cookies = self._get_cookies('https://www.youtube.com')
505 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
506 # See: https://github.com/yt-dlp/yt-dlp/issues/393
507 sapisid_cookie = dict_get(
508 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
509 if sapisid_cookie and sapisid_cookie.value:
510 self._SAPISID = sapisid_cookie.value
511 self.write_debug('Extracted SAPISID cookie')
512 # SAPISID cookie is required if not already present
513 if not yt_cookies.get('SAPISID'):
514 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
516 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
518 self._SAPISID = False
519 if not self._SAPISID:
521 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
522 sapisidhash = hashlib.sha1(
523 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
524 return f'SAPISIDHASH {time_now}_{sapisidhash}'
526 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
527 note='Downloading API JSON', errnote='Unable to download API page',
528 context=None, api_key=None, api_hostname=None, default_client='web'):
530 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
532 real_headers = self.generate_api_headers(default_client=default_client)
533 real_headers.update({'content-type': 'application/json'})
535 real_headers.update(headers)
536 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
537 or api_key or self._extract_api_key(default_client=default_client))
538 return self._download_json(
539 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
540 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
541 data=json.dumps(data).encode('utf8'), headers=real_headers,
542 query={'key': api_key, 'prettyPrint': 'false'})
544 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
545 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
548 def _extract_session_index(*data):
550 Index of current account in account list.
551 See: https://github.com/yt-dlp/yt-dlp/pull/519
554 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
555 if session_index is not None:
559 def _extract_identity_token(self, ytcfg=None, webpage=None):
561 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
565 return self._search_regex(
566 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
567 'identity token
', default=None, fatal=False)
570 def _extract_account_syncid(*args):
572 Extract syncId required to download private playlists of secondary channels
573 @params response and/or ytcfg
576 # ytcfg includes channel_syncid if on secondary channel
577 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
581 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
582 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
583 if len(sync_ids) >= 2 and sync_ids[1]:
584 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
585 # and just "user_syncid||" for primary channel. We only want the channel_syncid
589 def _extract_visitor_data(*args):
591 Extracts visitorData from an API response or ytcfg
592 Appears to be used to track session state
595 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
598 @functools.cached_property
599 def is_authenticated(self):
600 return bool(self._generate_sapisidhash_header())
602 def extract_ytcfg(self, video_id, webpage):
605 return self._parse_json(
607 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
608 default='{}'), video_id, fatal=False) or {}
610 def generate_api_headers(
611 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
612 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
614 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
616 'X-YouTube-Client-Name': str(
617 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
618 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
620 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
621 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
622 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
),
623 'User-Agent': self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT']['client']['userAgent'], default_client
=default_client
)
625 if session_index
is None:
626 session_index
= self
._extract
_session
_index
(ytcfg
)
627 if account_syncid
or session_index
is not None:
628 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
630 auth
= self
._generate
_sapisidhash
_header
(origin
)
632 headers
['Authorization'] = auth
633 headers
['X-Origin'] = origin
634 return filter_dict(headers
)
636 def _download_ytcfg(self
, client
, video_id
):
638 'web': 'https://www.youtube.com',
639 'web_music': 'https://music.youtube.com',
640 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
644 webpage
= self
._download
_webpage
(
645 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
646 return self
.extract_ytcfg(video_id
, webpage
) or {}
649 def _build_api_continuation_query(continuation
, ctp
=None):
651 'continuation': continuation
653 # TODO: Inconsistency with clickTrackingParams.
654 # Currently we have a fixed ctp contained within context (from ytcfg)
655 # and a ctp in root query for continuation.
657 query
['clickTracking'] = {'clickTrackingParams': ctp}
661 def _extract_next_continuation_data(cls
, renderer
):
662 next_continuation
= try_get(
663 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
664 lambda x
: x
['continuation']['reloadContinuationData']), dict)
665 if not next_continuation
:
667 continuation
= next_continuation
.get('continuation')
670 ctp
= next_continuation
.get('clickTrackingParams')
671 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
674 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
675 if isinstance(continuation_ep
, dict):
676 continuation
= try_get(
677 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
680 ctp
= continuation_ep
.get('clickTrackingParams')
681 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
684 def _extract_continuation(cls
, renderer
):
685 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
686 if next_continuation
:
687 return next_continuation
689 return traverse_obj(renderer
, (
690 ('contents', 'items', 'rows'), ..., 'continuationItemRenderer',
691 ('continuationEndpoint', ('button', 'buttonRenderer', 'command'))
692 ), get_all
=False, expected_type
=cls
._extract
_continuation
_ep
_data
)
695 def _extract_alerts(cls
, data
):
696 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
697 if not isinstance(alert_dict
, dict):
699 for alert
in alert_dict
.values():
700 alert_type
= alert
.get('type')
703 message
= cls
._get
_text
(alert
, 'text')
705 yield alert_type
, message
707 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
708 errors
, warnings
= [], []
709 for alert_type
, alert_message
in alerts
:
710 if alert_type
.lower() == 'error' and fatal
:
711 errors
.append([alert_type
, alert_message
])
712 elif alert_message
not in self
._IGNORED
_WARNINGS
:
713 warnings
.append([alert_type
, alert_message
])
715 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
716 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
718 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
720 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
721 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
723 def _extract_badges(self
, renderer
: dict):
725 'PRIVACY_UNLISTED': BadgeType
.AVAILABILITY_UNLISTED
,
726 'PRIVACY_PRIVATE': BadgeType
.AVAILABILITY_PRIVATE
,
727 'PRIVACY_PUBLIC': BadgeType
.AVAILABILITY_PUBLIC
731 'BADGE_STYLE_TYPE_MEMBERS_ONLY': BadgeType
.AVAILABILITY_SUBSCRIPTION
,
732 'BADGE_STYLE_TYPE_PREMIUM': BadgeType
.AVAILABILITY_PREMIUM
,
733 'BADGE_STYLE_TYPE_LIVE_NOW': BadgeType
.LIVE_NOW
737 'unlisted': BadgeType
.AVAILABILITY_UNLISTED
,
738 'private': BadgeType
.AVAILABILITY_PRIVATE
,
739 'members only': BadgeType
.AVAILABILITY_SUBSCRIPTION
,
740 'live': BadgeType
.LIVE_NOW
,
741 'premium': BadgeType
.AVAILABILITY_PREMIUM
745 for badge
in traverse_obj(renderer
, ('badges', ..., 'metadataBadgeRenderer'), default
=[]):
747 privacy_icon_map
.get(traverse_obj(badge
, ('icon', 'iconType'), expected_type
=str))
748 or badge_style_map
.get(traverse_obj(badge
, 'style'))
751 badges
.append({'type': badge_type}
)
754 # fallback, won't work in some languages
755 label
= traverse_obj(badge
, 'label', expected_type
=str, default
='')
756 for match
, label_badge_type
in label_map
.items():
757 if match
in label
.lower():
758 badges
.append({'type': badge_type}
)
764 def _has_badge(badges
, badge_type
):
765 return bool(traverse_obj(badges
, lambda _
, v
: v
['type'] == badge_type
))
768 def _get_text(data
, *path_list
, max_runs
=None):
769 for path
in path_list
or [None]:
773 obj
= traverse_obj(data
, path
, default
=[])
774 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
777 text
= try_get(item
, lambda x
: x
['simpleText'], str)
780 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
781 if not runs
and isinstance(item
, list):
784 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
785 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
789 def _get_count(self
, data
, *path_list
):
790 count_text
= self
._get
_text
(data
, *path_list
) or ''
791 count
= parse_count(count_text
)
794 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
798 def _extract_thumbnails(data
, *path_list
):
800 Extract thumbnails from thumbnails dict
801 @param path_list: path list to level that contains 'thumbnails' key
804 for path
in path_list
or [()]:
805 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
806 thumbnail_url
= url_or_none(thumbnail
.get('url'))
807 if not thumbnail_url
:
809 # Sometimes youtube gives a wrong thumbnail URL. See:
810 # https://github.com/yt-dlp/yt-dlp/issues/233
811 # https://github.com/ytdl-org/youtube-dl/issues/28023
812 if 'maxresdefault' in thumbnail_url
:
813 thumbnail_url
= thumbnail_url
.split('?')[0]
815 'url': thumbnail_url
,
816 'height': int_or_none(thumbnail
.get('height')),
817 'width': int_or_none(thumbnail
.get('width')),
822 def extract_relative_time(relative_time_text
):
824 Extracts a relative time from string and converts to dt object
825 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
827 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
)
829 start
= mobj
.group('start')
831 return datetime_from_str(start
)
833 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
837 def _parse_time_text(self
, text
):
840 dt
= self
.extract_relative_time(text
)
842 if isinstance(dt
, datetime
.datetime
):
843 timestamp
= calendar
.timegm(dt
.timetuple())
845 if timestamp
is None:
847 unified_timestamp(text
) or unified_timestamp(
849 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
850 text
.lower(), 'time text', default
=None)))
852 if text
and timestamp
is None and self
._preferred
_lang
in (None, 'en'):
854 f
'Cannot parse localized time text "{text}"', only_once
=True)
857 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
858 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
859 default_client
='web'):
860 for retry
in self
.RetryManager():
862 response
= self
._call
_api
(
863 ep
=ep
, fatal
=True, headers
=headers
,
864 video_id
=item_id
, query
=query
, note
=note
,
865 context
=self
._extract
_context
(ytcfg
, default_client
),
866 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
867 api_hostname
=api_hostname
, default_client
=default_client
)
868 except ExtractorError
as e
:
869 if not isinstance(e
.cause
, network_exceptions
):
870 return self
._error
_or
_warning
(e
, fatal
=fatal
)
871 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
875 first_bytes
= e
.cause
.read(512)
876 if not is_html(first_bytes
):
879 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
880 lambda x
: x
['error']['message'], str)
882 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
883 # Downloading page may result in intermittent 5xx HTTP error
884 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
885 # We also want to catch all other network exceptions since errors in later pages can be troublesome
886 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
887 if e
.cause
.code
not in (403, 429):
890 return self
._error
_or
_warning
(e
, fatal
=fatal
)
893 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
894 except ExtractorError
as e
:
895 # YouTube servers may return errors we want to retry on in a 200 OK response
896 # See: https://github.com/yt-dlp/yt-dlp/issues/839
897 if 'unknown error' in e
.msg
.lower():
900 return self
._error
_or
_warning
(e
, fatal
=fatal
)
901 # Youtube sometimes sends incomplete data
902 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
903 if not traverse_obj(response
, *variadic(check_get_keys
)):
904 retry
.error
= ExtractorError('Incomplete data received', expected
=True)
910 def is_music_url(url
):
911 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
913 def _extract_video(self
, renderer
):
914 video_id
= renderer
.get('videoId')
915 title
= self
._get
_text
(renderer
, 'title')
916 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
918 duration
= int_or_none(renderer
.get('lengthSeconds'))
920 duration
= parse_duration(self
._get
_text
(
921 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
923 duration
= parse_duration(self
._search
_regex
(
924 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
925 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
926 video_id
, default
=None, group
='duration'))
928 # videoInfo is a string like '50K views • 10 years ago'.
929 view_count
= self
._get
_count
(renderer
, 'viewCountText', 'shortViewCountText', 'videoInfo')
930 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
931 channel_id
= traverse_obj(
932 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
933 expected_type
=str, get_all
=False)
934 time_text
= self
._get
_text
(renderer
, 'publishedTimeText', 'videoInfo') or ''
935 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
936 overlay_style
= traverse_obj(
937 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
938 get_all
=False, expected_type
=str)
939 badges
= self
._extract
_badges
(renderer
)
940 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
941 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
942 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
943 expected_type
=str)) or ''
944 url
= f
'https://www.youtube.com/watch?v={video_id}'
945 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
946 url
= f
'https://www.youtube.com/shorts/{video_id}'
949 'is_upcoming' if scheduled_timestamp
is not None
950 else 'was_live' if 'streamed' in time_text
.lower()
951 else 'is_live' if overlay_style
== 'LIVE' or self
._has
_badge
(badges
, BadgeType
.LIVE_NOW
)
956 'ie_key': YoutubeIE
.ie_key(),
960 'description': description
,
961 'duration': duration
,
962 'uploader': uploader
,
963 'channel_id': channel_id
,
964 'thumbnails': thumbnails
,
965 'timestamp': (self
._parse
_time
_text
(time_text
)
966 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
)
968 'release_timestamp': scheduled_timestamp
,
970 'public' if self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
971 else self
._availability
(
972 is_private
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
) or None,
973 needs_premium
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
) or None,
974 needs_subscription
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
) or None,
975 is_unlisted
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
) or None),
976 'concurrent_view_count' if live_status
in ('is_live', 'is_upcoming') else 'view_count': view_count
,
977 'live_status': live_status
981 class YoutubeIE(YoutubeBaseInfoExtractor
):
983 _VALID_URL
= r
"""(?x)^
985 (?:https?://|//) # http(s):// or protocol-independent URL
986 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
987 (?:www\.)?deturl\.com/www\.youtube\.com|
988 (?:www\.)?pwnyoutube\.com|
989 (?:www\.)?hooktube\.com|
990 (?:www\.)?yourepeat\.com|
993 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
994 (?:.*?\#/)? # handle anchor (#/) redirect urls
995 (?: # the various things that can precede the ID:
996 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
997 |(?: # or the v= param in all its forms
998 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
999 (?:\?|\#!?) # the params delimiter ? or # or #!
1000 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
1005 youtu\.be| # just youtu.be/xxxx
1006 vid\.plus| # or vid.plus/xxxx
1007 zwearz\.com/watch| # or zwearz.com/watch/xxxx
1010 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
1012 )? # all until now is optional -> you can pass the naked ID
1013 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
1014 (?(1).+)? # if we found the ID, everything can follow
1016 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
1021 <(?:[0-9A-Za-z-]+?)?iframe[^>]+?src=|
1029 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1030 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1032 # https://wordpress.org/plugins/lazy-load-for-videos/
1034 <a\s
[^
>]*\bhref
="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"
1035 \s
[^
>]*\bclass
="[^"]*\blazy
-load
-youtube
''',
1039 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
1040 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$',
1041 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
1044 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1045 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
1046 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
1047 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
1048 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
1049 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1050 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1051 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1052 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
1053 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
1054 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1055 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
1056 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1057 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
1058 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1059 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
1060 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1061 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
1065 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1066 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
1067 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1068 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
1069 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
1070 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1071 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
1073 # Apple HTTP Live Streaming
1074 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1075 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1076 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1077 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
1078 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1079 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
1080 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
1081 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
1084 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
1085 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
1086 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1087 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
1088 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
1089 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
1090 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
1091 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
1092 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1093 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1094 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1095 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1098 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1099 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1100 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1101 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1102 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1103 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1104 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1107 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1108 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1109 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1110 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1111 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1112 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1113 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1114 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1115 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1116 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1117 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1118 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1119 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1120 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1121 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1122 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1123 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1124 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1125 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1126 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1127 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1128 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1131 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1132 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1134 # Dash webm audio with opus inside
1135 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1136 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1137 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1140 '_rtmp': {'protocol': 'rtmp'},
1142 # av01 video only formats sometimes served with "unknown" codecs
1143 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1144 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1145 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1146 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1147 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1148 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1149 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1150 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1152 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1159 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1161 'id': 'BaW_jenozKc',
1163 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1164 'uploader': 'Philipp Hagemeister',
1165 'uploader_id': 'phihag',
1166 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1167 'channel': 'Philipp Hagemeister',
1168 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1169 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1170 'upload_date': '20121002',
1171 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1172 'categories': ['Science & Technology'],
1173 'tags': ['youtube-dl'],
1177 'availability': 'public',
1178 'playable_in_embed': True,
1179 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1180 'live_status': 'not_live',
1184 'comment_count': int,
1185 'channel_follower_count': int
1189 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1190 'note': 'Embed-only video (#1746)',
1192 'id': 'yZIXLfi8CZQ',
1194 'upload_date': '20120608',
1195 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1196 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1197 'uploader': 'SET India',
1198 'uploader_id': 'setindia',
1199 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1202 'skip': 'Private video',
1205 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1206 'note': 'Use the first video ID in the URL',
1208 'id': 'BaW_jenozKc',
1210 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1211 'uploader': 'Philipp Hagemeister',
1212 'uploader_id': 'phihag',
1213 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1214 'channel': 'Philipp Hagemeister',
1215 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1216 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1217 'upload_date': '20121002',
1218 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1219 'categories': ['Science & Technology'],
1220 'tags': ['youtube-dl'],
1224 'availability': 'public',
1225 'playable_in_embed': True,
1226 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1227 'live_status': 'not_live',
1229 'comment_count': int,
1230 'channel_follower_count': int
1233 'skip_download': True,
1237 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1238 'note': '256k DASH audio (format 141) via DASH manifest',
1240 'id': 'a9LDPn-MO4I',
1242 'upload_date': '20121002',
1243 'uploader_id': '8KVIDEO',
1244 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1246 'uploader': '8KVIDEO',
1247 'title': 'UHDTV TEST 8K VIDEO.mp4'
1250 'youtube_include_dash_manifest': True,
1253 'skip': 'format 141 not served anymore',
1255 # DASH manifest with encrypted signature
1257 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1259 'id': 'IB3lcPjvWLA',
1261 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1262 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1264 'uploader': 'AfrojackVEVO',
1265 'uploader_id': 'AfrojackVEVO',
1266 'upload_date': '20131011',
1269 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1270 'playable_in_embed': True,
1271 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1273 'track': 'The Spark',
1274 'live_status': 'not_live',
1275 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1276 'channel': 'Afrojack',
1277 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1279 'availability': 'public',
1280 'categories': ['Music'],
1282 'alt_title': 'The Spark',
1283 'channel_follower_count': int
1286 'youtube_include_dash_manifest': True,
1287 'format': '141/bestaudio[ext=m4a]',
1290 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1292 'note': 'Embed allowed age-gate video',
1293 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1295 'id': 'HtVdAasjOgU',
1297 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1298 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1300 'uploader': 'The Witcher',
1301 'uploader_id': 'WitcherGame',
1302 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1303 'upload_date': '20140605',
1305 'categories': ['Gaming'],
1306 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1307 'availability': 'needs_auth',
1308 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1310 'channel': 'The Witcher',
1311 'live_status': 'not_live',
1313 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1314 'playable_in_embed': True,
1316 'channel_follower_count': int
1320 'note': 'Age-gate video with embed allowed in public site',
1321 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1323 'id': 'HsUATh_Nc2U',
1325 'title': 'Godzilla 2 (Official Video)',
1326 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1327 'upload_date': '20200408',
1328 'uploader_id': 'FlyingKitty900',
1329 'uploader': 'FlyingKitty',
1331 'availability': 'needs_auth',
1332 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1333 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1334 'channel': 'FlyingKitty',
1335 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1337 'categories': ['Entertainment'],
1338 'live_status': 'not_live',
1339 'tags': ['Flyingkitty', 'godzilla 2'],
1340 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1343 'playable_in_embed': True,
1344 'channel_follower_count': int
1348 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1349 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1351 'id': 'Tq92D6wQ1mg',
1352 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1354 'upload_date': '20191228',
1355 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1356 'uploader': 'Projekt Melody',
1357 'description': 'md5:17eccca93a786d51bc67646756894066',
1360 'availability': 'needs_auth',
1361 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1362 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1364 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1365 'channel': 'Projekt Melody',
1366 'live_status': 'not_live',
1367 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1368 'playable_in_embed': True,
1369 'categories': ['Entertainment'],
1371 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1372 'comment_count': int,
1373 'channel_follower_count': int
1377 'note': 'Non-Agegated non-embeddable video',
1378 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1380 'id': 'MeJVWBSsPAY',
1382 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1383 'uploader': 'Herr Lurik',
1384 'uploader_id': 'st3in234',
1385 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1386 'upload_date': '20130730',
1387 'track': 'Such mich find mich',
1389 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1391 'playable_in_embed': False,
1392 'creator': 'OOMPH!',
1393 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1395 'alt_title': 'Such mich find mich',
1397 'channel': 'Herr Lurik',
1398 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1399 'categories': ['Music'],
1400 'availability': 'public',
1401 'uploader_url': 'http://www.youtube.com/user/st3in234',
1402 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1403 'live_status': 'not_live',
1405 'channel_follower_count': int
1409 'note': 'Non-bypassable age-gated video',
1410 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1411 'only_matching': True,
1413 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1414 # YouTube Red ad is not captured for creator
1416 'url': '__2ABJjxzNo',
1418 'id': '__2ABJjxzNo',
1421 'upload_date': '20100430',
1422 'uploader_id': 'deadmau5',
1423 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1424 'creator': 'deadmau5',
1425 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1426 'uploader': 'deadmau5',
1427 'title': 'Deadmau5 - Some Chords (HD)',
1428 'alt_title': 'Some Chords',
1429 'availability': 'public',
1431 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1433 'live_status': 'not_live',
1434 'channel': 'deadmau5',
1435 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1437 'track': 'Some Chords',
1438 'artist': 'deadmau5',
1439 'playable_in_embed': True,
1441 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1442 'categories': ['Music'],
1443 'album': 'Some Chords',
1444 'channel_follower_count': int
1446 'expected_warnings': [
1447 'DASH manifest missing',
1450 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1452 'url': 'lqQg6PlCWgI',
1454 'id': 'lqQg6PlCWgI',
1457 'upload_date': '20150827',
1458 'uploader_id': 'olympic',
1459 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1460 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1461 'uploader': 'Olympics',
1462 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1464 'release_timestamp': 1343767800,
1465 'playable_in_embed': True,
1466 'categories': ['Sports'],
1467 'release_date': '20120731',
1468 'channel': 'Olympics',
1469 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1470 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1471 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1473 'availability': 'public',
1474 'live_status': 'was_live',
1476 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1477 'channel_follower_count': int
1480 'skip_download': 'requires avconv',
1485 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1487 'id': '_b-2C3KPAM0',
1489 'stretched_ratio': 16 / 9.,
1491 'upload_date': '20110310',
1492 'uploader_id': 'AllenMeow',
1493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1494 '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',
1496 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1497 'playable_in_embed': True,
1501 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1502 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1503 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1505 'categories': ['People & Blogs'],
1507 'live_status': 'not_live',
1508 'availability': 'unlisted',
1509 'comment_count': int,
1510 'channel_follower_count': int
1513 # url_encoded_fmt_stream_map is empty string
1515 'url': 'qEJwOuvDf7I',
1517 'id': 'qEJwOuvDf7I',
1519 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1521 'upload_date': '20150404',
1522 'uploader_id': 'spbelect',
1523 'uploader': 'Наблюдатели Петербурга',
1526 'skip_download': 'requires avconv',
1528 'skip': 'This live event has ended.',
1530 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1532 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1534 'id': 'FIl7x6_3R5Y',
1536 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1537 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1539 'upload_date': '20150625',
1540 'uploader_id': 'dorappi2000',
1541 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1542 'uploader': 'dorappi2000',
1543 'formats': 'mincount:31',
1545 'skip': 'not actual anymore',
1547 # DASH manifest with segment_list
1549 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1550 'md5': '8ce563a1d667b599d21064e982ab9e31',
1552 'id': 'CsmdDsKjzN8',
1554 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1555 'uploader': 'Airtek',
1556 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1557 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1558 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1561 'youtube_include_dash_manifest': True,
1562 'format': '135', # bestvideo
1564 'skip': 'This live event has ended.',
1567 # Multifeed videos (multiple cameras), URL is for Main Camera
1568 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1570 'id': 'jvGDaLqkpTg',
1571 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1572 'description': 'md5:e03b909557865076822aa169218d6a5d',
1576 'id': 'jvGDaLqkpTg',
1578 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1579 'description': 'md5:e03b909557865076822aa169218d6a5d',
1581 'upload_date': '20161111',
1582 'uploader': 'Team PGP',
1583 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1584 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1588 'id': '3AKt1R1aDnw',
1590 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1591 'description': 'md5:e03b909557865076822aa169218d6a5d',
1593 'upload_date': '20161111',
1594 'uploader': 'Team PGP',
1595 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1596 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1600 'id': 'RtAMM00gpVc',
1602 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1603 'description': 'md5:e03b909557865076822aa169218d6a5d',
1605 'upload_date': '20161111',
1606 'uploader': 'Team PGP',
1607 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1612 'id': '6N2fdlP3C5U',
1614 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1615 'description': 'md5:e03b909557865076822aa169218d6a5d',
1617 'upload_date': '20161111',
1618 'uploader': 'Team PGP',
1619 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1620 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1624 'skip_download': True,
1626 'skip': 'Not multifeed anymore',
1629 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1630 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1632 'id': 'gVfLd0zydlo',
1633 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1635 'playlist_count': 2,
1636 'skip': 'Not multifeed anymore',
1639 'url': 'https://vid.plus/FlRa-iH7PGw',
1640 'only_matching': True,
1643 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1644 'only_matching': True,
1647 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1648 # Also tests cut-off URL expansion in video description (see
1649 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1650 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1651 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1653 'id': 'lsguqyKfVQg',
1655 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1656 'alt_title': 'Dark Walk',
1657 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1659 'upload_date': '20151119',
1660 'uploader_id': 'IronSoulElf',
1661 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1662 'uploader': 'IronSoulElf',
1663 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1664 'track': 'Dark Walk',
1665 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1666 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1667 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1668 'categories': ['Film & Animation'],
1670 'live_status': 'not_live',
1671 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1672 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1674 'availability': 'public',
1675 'channel': 'IronSoulElf',
1676 'playable_in_embed': True,
1679 'channel_follower_count': int
1682 'skip_download': True,
1686 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1687 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1688 'only_matching': True,
1691 # Video with yt:stretch=17:0
1692 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1694 'id': 'Q39EVAstoRM',
1696 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1697 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1698 'upload_date': '20151107',
1699 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1700 'uploader': 'CH GAMER DROID',
1703 'skip_download': True,
1705 'skip': 'This video does not exist.',
1708 # Video with incomplete 'yt:stretch=16:'
1709 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1710 'only_matching': True,
1713 # Video licensed under Creative Commons
1714 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1716 'id': 'M4gD1WSo5mA',
1718 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1719 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1721 'upload_date': '20150128',
1722 'uploader_id': 'BerkmanCenter',
1723 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1724 'uploader': 'The Berkman Klein Center for Internet & Society',
1725 'license': 'Creative Commons Attribution license (reuse allowed)',
1726 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1727 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1730 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1731 'channel': 'The Berkman Klein Center for Internet & Society',
1732 'availability': 'public',
1734 'categories': ['Education'],
1735 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1736 'live_status': 'not_live',
1737 'playable_in_embed': True,
1738 'comment_count': int,
1739 'channel_follower_count': int,
1743 'skip_download': True,
1747 # Channel-like uploader_url
1748 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1750 'id': 'eQcmzGIKrzg',
1752 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1753 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1755 'upload_date': '20151120',
1756 'uploader': 'Bernie Sanders',
1757 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1758 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1759 'license': 'Creative Commons Attribution license (reuse allowed)',
1760 'playable_in_embed': True,
1763 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1765 'availability': 'public',
1766 'categories': ['News & Politics'],
1767 'channel': 'Bernie Sanders',
1768 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1770 'live_status': 'not_live',
1771 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1772 'comment_count': int,
1773 'channel_follower_count': int,
1777 'skip_download': True,
1781 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1782 'only_matching': True,
1785 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1786 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1787 'only_matching': True,
1790 # Rental video preview
1791 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1793 'id': 'uGpuVWrhIzE',
1795 'title': 'Piku - Trailer',
1796 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1797 'upload_date': '20150811',
1798 'uploader': 'FlixMatrix',
1799 'uploader_id': 'FlixMatrixKaravan',
1800 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1801 'license': 'Standard YouTube License',
1804 'skip_download': True,
1806 'skip': 'This video is not available.',
1809 # YouTube Red video with episode data
1810 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1812 'id': 'iqKdEhx-dD4',
1814 'title': 'Isolation - Mind Field (Ep 1)',
1815 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1817 'upload_date': '20170118',
1818 'uploader': 'Vsauce',
1819 'uploader_id': 'Vsauce',
1820 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1821 'series': 'Mind Field',
1823 'episode_number': 1,
1824 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1827 'availability': 'public',
1829 'channel': 'Vsauce',
1830 'episode': 'Episode 1',
1831 'categories': ['Entertainment'],
1832 'season': 'Season 1',
1833 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1834 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1836 'playable_in_embed': True,
1837 'live_status': 'not_live',
1838 'channel_follower_count': int
1841 'skip_download': True,
1843 'expected_warnings': [
1844 'Skipping DASH manifest',
1848 # The following content has been identified by the YouTube community
1849 # as inappropriate or offensive to some audiences.
1850 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1852 'id': '6SJNVb0GnPI',
1854 'title': 'Race Differences in Intelligence',
1855 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1857 'upload_date': '20140124',
1858 'uploader': 'New Century Foundation',
1859 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1860 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1863 'skip_download': True,
1865 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1869 'url': '1t24XAntNCY',
1870 'only_matching': True,
1873 # geo restricted to JP
1874 'url': 'sJL6WA-aGkQ',
1875 'only_matching': True,
1878 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1879 'only_matching': True,
1882 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1883 'only_matching': True,
1886 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1887 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1888 'only_matching': True,
1892 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1893 'only_matching': True,
1896 # Video with unsupported adaptive stream type formats
1897 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1899 'id': 'Z4Vy8R84T1U',
1901 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1902 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1904 'upload_date': '20130923',
1905 'uploader': 'Amelia Putri Harwita',
1906 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1907 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1908 'formats': 'maxcount:10',
1911 'skip_download': True,
1912 'youtube_include_dash_manifest': False,
1914 'skip': 'not actual anymore',
1917 # Youtube Music Auto-generated description
1918 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1920 'id': 'MgNrAu2pzNs',
1922 'title': 'Voyeur Girl',
1923 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1924 'upload_date': '20190312',
1925 'uploader': 'Stephen - Topic',
1926 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1927 'artist': 'Stephen',
1928 'track': 'Voyeur Girl',
1929 'album': 'it\'s too much love to know my dear',
1930 'release_date': '20190313',
1931 'release_year': 2019,
1932 'alt_title': 'Voyeur Girl',
1934 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1935 'playable_in_embed': True,
1937 'categories': ['Music'],
1938 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1939 'channel': 'Stephen',
1940 'availability': 'public',
1941 'creator': 'Stephen',
1943 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1945 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1947 'live_status': 'not_live',
1948 'channel_follower_count': int
1951 'skip_download': True,
1955 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1956 'only_matching': True,
1959 # invalid -> valid video id redirection
1960 'url': 'DJztXj2GPfl',
1962 'id': 'DJztXj2GPfk',
1964 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1965 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1966 'upload_date': '20090125',
1967 'uploader': 'Prochorowka',
1968 'uploader_id': 'Prochorowka',
1969 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1970 'artist': 'Panjabi MC',
1971 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1972 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1975 'skip_download': True,
1977 'skip': 'Video unavailable',
1980 # empty description results in an empty string
1981 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1983 'id': 'x41yOUIvK2k',
1985 'title': 'IMG 3456',
1987 'upload_date': '20170613',
1988 'uploader_id': 'ElevageOrVert',
1989 'uploader': 'ElevageOrVert',
1991 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1992 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1994 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1996 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1997 'availability': 'public',
1999 'categories': ['Pets & Animals'],
2001 'playable_in_embed': True,
2002 'live_status': 'not_live',
2003 'channel': 'ElevageOrVert',
2004 'channel_follower_count': int
2007 'skip_download': True,
2011 # with '};' inside yt initial data (see [1])
2012 # see [2] for an example with '};' inside ytInitialPlayerResponse
2013 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
2014 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
2015 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
2017 'id': 'CHqg6qOn4no',
2019 'title': 'Part 77 Sort a list of simple types in c#',
2020 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
2021 'upload_date': '20130831',
2022 'uploader_id': 'kudvenkat',
2023 'uploader': 'kudvenkat',
2024 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
2026 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
2027 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
2028 'live_status': 'not_live',
2029 'categories': ['Education'],
2030 'availability': 'public',
2031 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
2033 'playable_in_embed': True,
2037 'channel': 'kudvenkat',
2038 'comment_count': int,
2039 'channel_follower_count': int,
2043 'skip_download': True,
2047 # another example of '};' in ytInitialData
2048 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
2049 'only_matching': True,
2052 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
2053 'only_matching': True,
2056 # https://github.com/ytdl-org/youtube-dl/pull/28094
2057 'url': 'OtqTfy26tG0',
2059 'id': 'OtqTfy26tG0',
2061 'title': 'Burn Out',
2062 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
2063 'upload_date': '20141120',
2064 'uploader': 'The Cinematic Orchestra - Topic',
2065 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2066 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2067 'artist': 'The Cinematic Orchestra',
2068 'track': 'Burn Out',
2069 'album': 'Every Day',
2071 'live_status': 'not_live',
2072 'alt_title': 'Burn Out',
2076 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
2077 'creator': 'The Cinematic Orchestra',
2078 'channel': 'The Cinematic Orchestra',
2079 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
2080 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
2081 'availability': 'public',
2082 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
2083 'categories': ['Music'],
2084 'playable_in_embed': True,
2085 'channel_follower_count': int
2088 'skip_download': True,
2092 # controversial video, only works with bpctr when authenticated with cookies
2093 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
2094 'only_matching': True,
2097 # controversial video, requires bpctr/contentCheckOk
2098 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2100 'id': 'SZJvDhaSDnc',
2102 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2103 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2104 'uploader': 'CBS Mornings',
2105 'uploader_id': 'CBSThisMorning',
2106 'upload_date': '20140716',
2107 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2109 'categories': ['News & Politics'],
2110 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2112 'channel': 'CBS Mornings',
2113 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2114 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2116 'availability': 'needs_auth',
2117 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2119 'live_status': 'not_live',
2120 'playable_in_embed': True,
2121 'channel_follower_count': int
2125 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2126 'url': 'cBvYw8_A0vQ',
2128 'id': 'cBvYw8_A0vQ',
2130 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2131 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2132 'upload_date': '20201120',
2133 'uploader': 'Walk around Japan',
2134 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2135 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2137 'categories': ['Travel & Events'],
2138 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2140 'channel': 'Walk around Japan',
2141 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2142 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2144 'availability': 'public',
2145 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2146 'live_status': 'not_live',
2147 'playable_in_embed': True,
2148 'channel_follower_count': int
2151 'skip_download': True,
2154 # Has multiple audio streams
2155 'url': 'WaOKSUlf4TM',
2156 'only_matching': True
2158 # Requires Premium: has format 141 when requested using YTM url
2159 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2160 'only_matching': True
2162 # multiple subtitles with same lang_code
2163 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2164 'only_matching': True,
2166 # Force use android client fallback
2167 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2169 'id': 'YOelRv7fMxY',
2170 'title': 'DIGGING A SECRET TUNNEL Part 1',
2172 'upload_date': '20210624',
2173 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2174 'uploader': 'colinfurze',
2175 'uploader_id': 'colinfurze',
2176 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2177 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2179 'categories': ['Entertainment'],
2180 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2182 'channel': 'colinfurze',
2183 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2184 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2186 'availability': 'public',
2188 'live_status': 'not_live',
2189 'playable_in_embed': True,
2190 'channel_follower_count': int,
2194 'format': '17', # 3gp format available on android
2195 'extractor_args': {'youtube': {'player_client': ['android']}},
2199 # Skip download of additional client configs (remix client config in this case)
2200 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2201 'only_matching': True,
2203 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2207 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2208 'only_matching': True,
2210 'note': 'Storyboards',
2211 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2213 'id': '5KLPxDtMqe8',
2216 'title': 'Your Brain is Plastic',
2217 'uploader_id': 'scishow',
2218 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2219 'upload_date': '20140324',
2220 'uploader': 'SciShow',
2222 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2223 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2225 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2226 'playable_in_embed': True,
2228 'uploader_url': 'http://www.youtube.com/user/scishow',
2229 'availability': 'public',
2230 'channel': 'SciShow',
2231 'live_status': 'not_live',
2233 'categories': ['Education'],
2235 'channel_follower_count': int,
2237 }, 'params': {'format': 'mhtml', 'skip_download': True}
2239 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2240 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2242 'id': '2NUZ8W2llS4',
2244 'title': 'The NP that test your phone performance 🙂',
2245 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2246 'uploader': 'Leon Nguyen',
2247 'uploader_id': 'VNSXIII',
2248 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2249 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2250 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2254 'categories': ['Gaming'],
2256 'playable_in_embed': True,
2257 'live_status': 'not_live',
2258 'upload_date': '20220103',
2260 'availability': 'public',
2261 'channel': 'Leon Nguyen',
2262 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2263 'comment_count': int,
2264 'channel_follower_count': int
2267 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2268 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2270 'id': '2NUZ8W2llS4',
2272 'title': 'The NP that test your phone performance 🙂',
2273 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2274 'uploader': 'Leon Nguyen',
2275 'uploader_id': 'VNSXIII',
2276 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2277 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2278 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2282 'categories': ['Gaming'],
2284 'playable_in_embed': True,
2285 'live_status': 'not_live',
2286 'upload_date': '20220102',
2288 'availability': 'public',
2289 'channel': 'Leon Nguyen',
2290 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2291 'comment_count': int,
2292 'channel_follower_count': int
2294 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2296 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2297 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2299 'id': 'mzZzzBU6lrM',
2301 'title': 'I Met GeorgeNotFound In Real Life...',
2302 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2303 'uploader': 'Quackity',
2304 'uploader_id': 'QuackityHQ',
2305 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2306 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2307 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2311 'categories': ['Entertainment'],
2313 'playable_in_embed': True,
2314 'live_status': 'not_live',
2315 'release_timestamp': 1641172509,
2316 'release_date': '20220103',
2317 'upload_date': '20220103',
2319 'availability': 'public',
2320 'channel': 'Quackity',
2321 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2322 'channel_follower_count': int
2325 { # continuous livestream. Microformat upload date should be preferred.
2326 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2327 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2329 'id': 'kgx4WGK0oNU',
2330 '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}',
2332 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2333 'availability': 'public',
2335 'release_timestamp': 1637975704,
2336 'upload_date': '20210619',
2337 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2338 'live_status': 'is_live',
2339 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2340 'uploader': '阿鲍Abao',
2341 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2342 'channel': 'Abao in Tokyo',
2343 'channel_follower_count': int,
2344 'release_date': '20211127',
2346 'categories': ['People & Blogs'],
2348 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2350 'playable_in_embed': True,
2351 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2352 'concurrent_view_count': int,
2354 'params': {'skip_download': True}
2356 # Story. Requires specific player params to work.
2357 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2359 'id': 'vv8qTUWmulI',
2361 'availability': 'unlisted',
2363 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2364 'upload_date': '20220526',
2365 'categories': ['Education'],
2367 'channel': 'IT\'S HISTORY',
2369 'uploader_id': 'BlastfromthePast',
2371 'uploader': 'IT\'S HISTORY',
2372 'playable_in_embed': True,
2374 'live_status': 'not_live',
2376 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2377 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2378 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2380 'skip': 'stories get removed after some period of time',
2382 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2384 'id': 'tjjjtzRLHvA',
2386 'title': 'ハッシュタグ無し };if window.ytcsi',
2387 'upload_date': '20220323',
2389 'availability': 'unlisted',
2390 'channel': 'nao20010128nao',
2391 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2393 'uploader': 'nao20010128nao',
2394 'uploader_id': 'nao20010128nao',
2395 'categories': ['Music'],
2398 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2399 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2400 'live_status': 'not_live',
2401 'playable_in_embed': True,
2402 'channel_follower_count': int,
2405 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2408 # Prefer primary title+description language metadata by default
2409 # Do not prefer translated description if primary is empty
2410 'url': 'https://www.youtube.com/watch?v=el3E4MbxRqQ',
2412 'id': 'el3E4MbxRqQ',
2414 'title': 'dlp test video 2 - primary sv no desc',
2416 'channel': 'cole-dlp-test-acc',
2419 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2421 'playable_in_embed': True,
2422 'availability': 'unlisted',
2423 'thumbnail': 'https://i.ytimg.com/vi_webp/el3E4MbxRqQ/maxresdefault.webp',
2426 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2427 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2428 'live_status': 'not_live',
2429 'upload_date': '20220908',
2430 'categories': ['People & Blogs'],
2431 'uploader': 'cole-dlp-test-acc',
2432 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2434 'params': {'skip_download': True}
2436 # Extractor argument: prefer translated title+description
2437 'url': 'https://www.youtube.com/watch?v=gHKT4uU8Zng',
2439 'id': 'gHKT4uU8Zng',
2441 'channel': 'cole-dlp-test-acc',
2444 'live_status': 'not_live',
2445 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
2446 'upload_date': '20220728',
2447 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
2449 'categories': ['People & Blogs'],
2450 'thumbnail': 'https://i.ytimg.com/vi_webp/gHKT4uU8Zng/maxresdefault.webp',
2451 'title': 'dlp test video title translated (fr)',
2452 'availability': 'public',
2453 'uploader': 'cole-dlp-test-acc',
2455 'description': 'dlp test video description translated (fr)',
2456 'playable_in_embed': True,
2457 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2458 'uploader_url': 'http://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
2460 'params': {'skip_download': True, 'extractor_args': {'youtube': {'lang': ['fr']}}},
2461 'expected_warnings': [r'Preferring "fr" translated fields'],
2463 'note': '6 channel audio',
2464 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2465 'only_matching': True,
2470 # YouTube <object> embed
2472 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2473 'md5': '873c81d308b979f0e23ee7e620b312a3',
2475 'id': 'msN87y-iEx0',
2477 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2478 'upload_date': '20080526',
2479 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2480 'uploader': 'Christopher Sykes',
2481 'uploader_id': 'ChristopherJSykes',
2483 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2484 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2485 'playable_in_embed': True,
2486 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2488 'comment_count': int,
2489 'channel': 'Christopher Sykes',
2490 'live_status': 'not_live',
2491 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2492 'availability': 'public',
2495 'categories': ['Science & Technology'],
2496 'channel_follower_count': int,
2497 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2500 'skip_download': True,
2506 def suitable(cls, url):
2507 from ..utils import parse_qs
2510 if qs.get('list', [None])[0]:
2512 return super().suitable(url)
2514 def __init__(self, *args, **kwargs):
2515 super().__init__(*args, **kwargs)
2516 self._code_cache = {}
2517 self._player_cache = {}
2519 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data, is_live):
2520 lock = threading.Lock()
2521 start_time = time.time()
2522 formats = [f for f in formats if f.get('is_from_start')]
2524 def refetch_manifest(format_id, delay):
2525 nonlocal formats, start_time, is_live
2526 if time.time() <= start_time + delay:
2529 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2530 video_details = traverse_obj(
2531 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2532 microformats = traverse_obj(
2533 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2534 expected_type=dict, default=[])
2535 _, live_status, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2536 is_live = live_status == 'is_live'
2537 start_time = time.time()
2539 def mpd_feed(format_id, delay):
2541 @returns (manifest_url, manifest_stream_number, is_live) or None
2544 refetch_manifest(format_id, delay)
2546 f = next((f for f in formats if f['format_id'] == format_id), None)
2549 self.to_screen(f'{video_id}: Video is no longer live')
2551 self.report_warning(
2552 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2554 return f['manifest_url'], f['manifest_stream_number'], is_live
2557 f['is_live'] = is_live
2558 gen = functools.partial(self._live_dash_fragments, video_id, f['format_id'],
2559 live_start_time, mpd_feed, not is_live and f.copy())
2561 f['fragments'] = gen
2562 f['protocol'] = 'http_dash_segments_generator'
2564 f['fragments'] = LazyList(gen({}))
2565 del f['is_from_start']
2567 def _live_dash_fragments(self, video_id, format_id, live_start_time, mpd_feed, manifestless_orig_fmt, ctx):
2568 FETCH_SPAN, MAX_DURATION = 5, 432000
2570 mpd_url, stream_number, is_live = None, None, True
2573 download_start_time = ctx.get('start') or time.time()
2575 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2576 if lack_early_segments:
2577 self.report_warning(bug_reports_message(
2578 'Starting download from the last 120 hours of the live stream since '
2579 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2580 lack_early_segments = True
2582 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2583 fragments, fragment_base_url = None, None
2585 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2586 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2587 # Obtain from MPD's maximum seq value
2588 old_mpd_url = mpd_url
2589 last_error = ctx.pop('last_error', None)
2590 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2591 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2592 or (mpd_url, stream_number, False))
2593 if not refresh_sequence:
2594 if expire_fast and not is_live:
2595 return False, last_seq
2596 elif old_mpd_url == mpd_url:
2597 return True, last_seq
2598 if manifestless_orig_fmt:
2599 fmt_info = manifestless_orig_fmt
2602 fmts, _ = self._extract_mpd_formats_and_subtitles(
2603 mpd_url, None, note=False, errnote=False, fatal=False)
2604 except ExtractorError:
2607 no_fragment_score += 2
2608 return False, last_seq
2609 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2610 fragments = fmt_info['fragments']
2611 fragment_base_url = fmt_info['fragment_base_url']
2612 assert fragment_base_url
2614 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2615 return True, _last_seq
2617 self.write_debug(f'[{video_id}] Generating fragments for format {format_id}')
2619 fetch_time = time.time()
2620 if no_fragment_score > 30:
2622 if last_segment_url:
2623 # Obtain from "X-Head-Seqnum" header value from each segment
2625 urlh = self._request_webpage(
2626 last_segment_url, None, note=False, errnote=False, fatal=False)
2627 except ExtractorError:
2629 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2630 if last_seq is None:
2631 no_fragment_score += 2
2632 last_segment_url = None
2635 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2636 no_fragment_score += 2
2637 if not should_continue:
2640 if known_idx > last_seq:
2641 last_segment_url = None
2646 if begin_index < 0 and known_idx < 0:
2647 # skip from the start when it's negative value
2648 known_idx = last_seq + begin_index
2649 if lack_early_segments:
2650 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2652 for idx in range(known_idx, last_seq):
2653 # do not update sequence here or you'll get skipped some part of it
2654 should_continue, _ = _extract_sequence_from_mpd(False, False)
2655 if not should_continue:
2657 raise ExtractorError('breaking out of outer loop')
2658 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2660 'url': last_segment_url,
2661 'fragment_count': last_seq,
2663 if known_idx == last_seq:
2664 no_fragment_score += 5
2666 no_fragment_score = 0
2667 known_idx = last_seq
2668 except ExtractorError:
2671 if manifestless_orig_fmt:
2672 # Stop at the first iteration if running for post-live manifestless;
2673 # fragment count no longer increase since it starts
2676 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2678 def _extract_player_url(self, *ytcfgs, webpage=None):
2679 player_url = traverse_obj(
2680 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2681 get_all=False, expected_type=str)
2684 return urljoin('https://www.youtube.com', player_url)
2686 def _download_player_url(self, video_id, fatal=False):
2687 res = self._download_webpage(
2688 'https://www.youtube.com/iframe_api',
2689 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2691 player_version = self._search_regex(
2692 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2694 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2696 def _signature_cache_id(self, example_sig):
2697 """ Return a string representation of a signature """
2698 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2701 def _extract_player_info(cls, player_url):
2702 for player_re in cls._PLAYER_INFO_RE:
2703 id_m = re.search(player_re, player_url)
2707 raise ExtractorError('Cannot identify player %r' % player_url)
2708 return id_m.group('id')
2710 def _load_player(self, video_id, player_url, fatal=True):
2711 player_id = self._extract_player_info(player_url)
2712 if player_id not in self._code_cache:
2713 code = self._download_webpage(
2714 player_url, video_id, fatal=fatal,
2715 note='Downloading player ' + player_id,
2716 errnote='Download of %s failed' % player_url)
2718 self._code_cache[player_id] = code
2719 return self._code_cache.get(player_id)
2721 def _extract_signature_function(self, video_id, player_url, example_sig):
2722 player_id = self._extract_player_info(player_url)
2724 # Read from filesystem cache
2725 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2726 assert os.path.basename(func_id) == func_id
2728 self.write_debug(f'Extracting signature function {func_id}')
2729 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2732 code = self._load_player(video_id, player_url)
2734 res = self._parse_sig_js(code)
2735 test_string = ''.join(map(chr, range(len(example_sig))))
2736 cache_spec = [ord(c) for c in res(test_string)]
2737 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2739 return lambda s: ''.join(s[i] for i in cache_spec)
2741 def _print_sig_code(self, func, example_sig):
2742 if not self.get_param('youtube_print_sig_code'):
2745 def gen_sig_code(idxs):
2746 def _genslice(start, end, step):
2747 starts = '' if start == 0 else str(start)
2748 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2749 steps = '' if step == 1 else (':%d' % step)
2750 return f's[{starts}{ends}{steps}]'
2753 # Quelch pyflakes warnings - start will be set when step is set
2754 start = '(Never used)'
2755 for i, prev in zip(idxs[1:], idxs[:-1]):
2756 if step is not None:
2757 if i - prev == step:
2759 yield _genslice(start, prev, step)
2762 if i - prev in [-1, 1]:
2767 yield 's[%d]' % prev
2771 yield _genslice(start, i, step)
2773 test_string = ''.join(map(chr, range(len(example_sig))))
2774 cache_res = func(test_string)
2775 cache_spec = [ord(c) for c in cache_res]
2776 expr_code = ' + '.join(gen_sig_code(cache_spec))
2777 signature_id_tuple = '(%s)' % (
2778 ', '.join(str(len(p)) for p in example_sig.split('.')))
2779 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2780 ' return %s\n') % (signature_id_tuple, expr_code)
2781 self.to_screen('Extracted signature function:\n' + code)
2783 def _parse_sig_js(self, jscode):
2784 funcname = self._search_regex(
2785 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2786 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2787 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2788 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2789 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}\(a,\d+\)',
2790 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\(\s*""\s*\)',
2791 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2793 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2794 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2795 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2796 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2797 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2798 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2799 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2800 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2801 jscode, 'Initial JS player signature function name', group='sig')
2803 jsi = JSInterpreter(jscode)
2804 initial_function = jsi.extract_function(funcname)
2805 return lambda s: initial_function([s])
2807 def _cached(self, func, *cache_id):
2808 def inner(*args, **kwargs):
2809 if cache_id not in self._player_cache:
2811 self._player_cache[cache_id] = func(*args, **kwargs)
2812 except ExtractorError as e:
2813 self._player_cache[cache_id] = e
2814 except Exception as e:
2815 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2817 ret = self._player_cache[cache_id]
2818 if isinstance(ret, Exception):
2823 def _decrypt_signature(self, s, video_id, player_url):
2824 """Turn the encrypted s field into a working signature"""
2825 extract_sig = self._cached(
2826 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2827 func = extract_sig(video_id, player_url, s)
2828 self._print_sig_code(func, s)
2831 def _decrypt_nsig(self, s, video_id, player_url):
2832 """Turn the encrypted n field into a working signature"""
2833 if player_url is None:
2834 raise ExtractorError('Cannot decrypt nsig without player_url')
2835 player_url = urljoin('https://www.youtube.com', player_url)
2838 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2839 except ExtractorError as e:
2840 raise ExtractorError('Unable to extract nsig function code', cause=e)
2841 if self.get_param('youtube_print_sig_code'):
2842 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2845 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2846 ret = extract_nsig(jsi, func_code)(s)
2847 except JSInterpreter.Exception as e:
2849 jsi = PhantomJSwrapper(self, timeout=5000)
2850 except ExtractorError:
2852 self.report_warning(
2853 f'Native nsig extraction failed: Trying with PhantomJS\n'
2854 f' n = {s} ; player = {player_url}', video_id)
2855 self.write_debug(e, only_once=True)
2857 args, func_body = func_code
2859 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2860 video_id=video_id, note='Executing signature code').strip()
2862 self.write_debug(f'Decrypted nsig {s} => {ret}')
2865 def _extract_n_function_name(self, jscode):
2866 funcname, idx = self._search_regex(
2867 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2868 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2872 return json.loads(js_to_json(self._search_regex(
2873 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2874 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2876 def _extract_n_function_code(self, video_id, player_url):
2877 player_id = self._extract_player_info(player_url)
2878 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
2879 jscode = func_code or self._load_player(video_id, player_url)
2880 jsi = JSInterpreter(jscode)
2883 return jsi, player_id, func_code
2885 func_name = self._extract_n_function_name(jscode)
2888 func_code = self._search_regex(
2889 r'''(?xs
)%s\s
*=\s
*function\s
*\
((?P
<var
>[\w$
]+)\
)\s
*
2890 # NB: The end of the regex is intentionally kept strict
2891 {(?P<code>.+?}\s
*return\
[\w$
]+.join\
(""\
))};''' % func_name,
2892 jscode, 'nsig function', group=('var', 'code'), default=None)
2894 func_code = ([func_code[0]], func_code[1])
2896 self.write_debug('Extracting nsig function with jsinterp')
2897 func_code = jsi.extract_function_code(func_name)
2899 self.cache.store('youtube-nsig', player_id, func_code)
2900 return jsi, player_id, func_code
2902 def _extract_n_function_from_code(self, jsi, func_code):
2903 func = jsi.extract_function_from_code(*func_code)
2905 def extract_nsig(s):
2908 except JSInterpreter.Exception:
2910 except Exception as e:
2911 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2913 if ret.startswith('enhanced_except_'):
2914 raise JSInterpreter.Exception('Signature function returned an exception')
2919 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2921 Extract signatureTimestamp (sts)
2922 Required to tell API what sig/player version is in use.
2925 if isinstance(ytcfg, dict):
2926 sts = int_or_none(ytcfg.get('STS'))
2929 # Attempt to extract from player
2930 if player_url is None:
2931 error_msg = 'Cannot extract signature timestamp without player_url.'
2933 raise ExtractorError(error_msg)
2934 self.report_warning(error_msg)
2936 code = self._load_player(video_id, player_url, fatal=fatal)
2938 sts = int_or_none(self._search_regex(
2939 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2940 'JS player signature timestamp', group='sts', fatal=fatal))
2943 def _mark_watched(self, video_id, player_responses):
2944 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2945 label = 'fully ' if is_full else ''
2946 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2947 expected_type=url_or_none)
2949 self.report_warning(f'Unable to mark {label}watched')
2951 parsed_url = urllib.parse.urlparse(url)
2952 qs = urllib.parse.parse_qs(parsed_url.query)
2954 # cpn generation algorithm is reverse engineered from base.js.
2955 # In fact it works even with dummy cpn.
2956 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2957 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2959 # # more consistent results setting it to right before the end
2960 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2965 'cmt': video_length,
2966 'el': 'detailpage', # otherwise defaults to "shorts"
2970 # these seem to mark watchtime "history" in the real world
2971 # they're required, so send in a single value
2977 url = urllib.parse.urlunparse(
2978 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2980 self._download_webpage(
2981 url, video_id, f'Marking {label}watched',
2982 'Unable to mark watched', fatal=False)
2985 def _extract_from_webpage(cls, url, webpage):
2986 # Invidious Instances
2987 # https://github.com/yt-dlp/yt-dlp/issues/195
2988 # https://github.com/iv-org/invidious/pull/1730
2990 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2993 yield cls.url_result(mobj.group('url'), cls)
2994 raise cls.StopExtraction()
2996 yield from super()._extract_from_webpage(url, webpage)
2998 # lazyYT YouTube embed
2999 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
3000 yield cls.url_result(unescapeHTML(id_), cls, id_)
3002 # Wordpress "YouTube Video Importer" plugin
3003 for m in re.findall(r'''(?x
)<div
[^
>]+
3004 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
3005 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
3006 yield cls.url_result(m[-1], cls, m[-1])
3009 def extract_id(cls, url):
3010 video_id = cls.get_temp_id(url)
3012 raise ExtractorError(f'Invalid URL: {url}')
3015 def _extract_chapters_from_json(self, data, duration):
3016 chapter_list = traverse_obj(
3018 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
3019 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
3020 ), expected_type=list)
3022 return self._extract_chapters(
3024 chapter_time=lambda chapter: float_or_none(
3025 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
3026 chapter_title=lambda chapter: traverse_obj(
3027 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
3030 def _extract_chapters_from_engagement_panel(self, data, duration):
3031 content_list = traverse_obj(
3033 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
3034 expected_type=list, default=[])
3035 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
3036 chapter_title = lambda chapter: self._get_text(chapter, 'title')
3038 return next(filter(None, (
3039 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
3040 chapter_time, chapter_title, duration)
3041 for contents in content_list)), [])
3043 def _extract_chapters_from_description(self, description, duration):
3044 duration_re = r'(?:\d+:)?\d{1,2}:\d{2}'
3045 sep_re = r'(?m)^\s*(%s)\b\W*\s(%s)\s*$'
3046 return self._extract_chapters(
3047 re.findall(sep_re % (duration_re, r'.+?'), description or ''),
3048 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
3049 duration=duration, strict=False) or self._extract_chapters(
3050 re.findall(sep_re % (r'.+?', duration_re), description or ''),
3051 chapter_time=lambda x: parse_duration(x[1]), chapter_title=lambda x: x[0],
3052 duration=duration, strict=False)
3054 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
3058 'start_time': chapter_time(chapter),
3059 'title': chapter_title(chapter),
3060 } for chapter in chapter_list or []]
3062 chapter_list.sort(key=lambda c: c['start_time'] or 0)
3064 chapters = [{'start_time': 0}]
3065 for idx, chapter in enumerate(chapter_list):
3066 if chapter['start_time'] is None:
3067 self.report_warning(f'Incomplete chapter {idx}')
3068 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
3069 chapters.append(chapter)
3070 elif chapter not in chapters:
3071 self.report_warning(
3072 f'Invalid start time ({chapter["start_time"]} < {chapters[-1]["start_time"]}) for chapter "{chapter["title"]}
"')
3075 def _extract_comment(self, comment_renderer, parent=None):
3076 comment_id = comment_renderer.get('commentId')
3080 text = self._get_text(comment_renderer, 'contentText')
3082 # Timestamp is an estimate calculated from the current time and time_text
3083 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
3084 timestamp = self._parse_time_text(time_text)
3086 author = self._get_text(comment_renderer, 'authorText')
3087 author_id = try_get(comment_renderer,
3088 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
3090 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
3091 lambda x: x['likeCount']), str)) or 0
3092 author_thumbnail = try_get(comment_renderer,
3093 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
3095 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
3096 is_favorited = 'creatorHeart' in (try_get(
3097 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
3101 'timestamp': timestamp,
3102 'time_text': time_text,
3103 'like_count': votes,
3104 'is_favorited': is_favorited,
3106 'author_id': author_id,
3107 'author_thumbnail': author_thumbnail,
3108 'author_is_uploader': author_is_uploader,
3109 'parent': parent or 'root'
3112 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
3114 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
3116 def extract_header(contents):
3117 _continuation = None
3118 for content in contents:
3119 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
3120 expected_comment_count = self._get_count(
3121 comments_header_renderer, 'countText', 'commentsCount')
3123 if expected_comment_count:
3124 tracker['est_total'] = expected_comment_count
3125 self.to_screen(f'Downloading ~{expected_comment_count} comments')
3126 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
3128 sort_menu_item = try_get(
3129 comments_header_renderer,
3130 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
3131 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
3133 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
3134 if not _continuation:
3137 sort_text = str_or_none(sort_menu_item.get('title'))
3139 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
3140 self.to_screen('Sorting comments by %s' % sort_text.lower())
3142 return _continuation
3144 def extract_thread(contents):
3146 tracker['current_page_thread'] = 0
3147 for content in contents:
3148 if not parent and tracker['total_parent_comments'] >= max_parents:
3150 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
3151 comment_renderer = get_first(
3152 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
3153 expected_type=dict, default={})
3155 comment = self._extract_comment(comment_renderer, parent)
3159 tracker['running_total'] += 1
3160 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
3163 # Attempt to get the replies
3164 comment_replies_renderer = try_get(
3165 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
3167 if comment_replies_renderer:
3168 tracker['current_page_thread'] += 1
3169 comment_entries_iter = self._comment_entries(
3170 comment_replies_renderer, ytcfg, video_id,
3171 parent=comment.get('id'), tracker=tracker)
3172 yield from itertools.islice(comment_entries_iter, min(
3173 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
3175 # Keeps track of counts across recursive calls
3180 current_page_thread=0,
3181 total_parent_comments=0,
3182 total_reply_comments=0)
3185 # YouTube comments have a max depth of 2
3186 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3188 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3189 'Set max replies in the max-comments extractor argument instead')
3190 if max_depth == 1 and parent:
3193 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3194 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3196 continuation = self._extract_continuation(root_continuation_data)
3199 is_forced_continuation = False
3200 is_first_continuation = parent is None
3201 if is_first_continuation and not continuation:
3202 # Sometimes you can get comments by generating the continuation yourself,
3203 # even if YouTube initially reports them being disabled - e.g. stories comments.
3204 # Note: if the comment section is actually disabled, YouTube may return a response with
3205 # required check_get_keys missing. So we will disable that check initially in this case.
3206 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3207 is_forced_continuation = True
3209 for page_num in itertools.count(0):
3210 if not continuation:
3212 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3213 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
3215 if is_first_continuation:
3216 note_prefix = 'Downloading comment section API JSON'
3218 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3219 tracker['current_page_thread'], comment_prog_str)
3221 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3222 ' ' if parent else '', ' replies' if parent else '',
3223 page_num, comment_prog_str)
3225 response = self._extract_response(
3226 item_id=None, query=continuation,
3227 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3228 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3229 is_forced_continuation = False
3230 continuation_contents = traverse_obj(
3231 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3234 for continuation_section in continuation_contents:
3235 continuation_items = traverse_obj(
3236 continuation_section,
3237 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3238 get_all=False, expected_type=list) or []
3239 if is_first_continuation:
3240 continuation = extract_header(continuation_items)
3241 is_first_continuation = False
3246 for entry in extract_thread(continuation_items):
3250 continuation = self._extract_continuation({'contents': continuation_items})
3254 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3255 if message and not parent and tracker['running_total'] == 0:
3256 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3259 def _generate_comment_continuation(video_id):
3261 Generates initial comment section continuation token from given video id
3263 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3264 return base64.b64encode(token.encode()).decode()
3266 def _get_comments(self, ytcfg, video_id, contents, webpage):
3267 """Entry for comment extraction"""
3268 def _real_comment_extract(contents):
3270 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3271 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3272 yield from self._comment_entries(renderer, ytcfg, video_id)
3274 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3275 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3278 def _get_checkok_params():
3279 return {'contentCheckOk': True, 'racyCheckOk': True}
3282 def _generate_player_context(cls, sts=None):
3284 'html5Preference': 'HTML5_PREF_WANTS',
3287 context['signatureTimestamp'] = sts
3289 'playbackContext': {
3290 'contentPlaybackContext': context
3292 **cls._get_checkok_params()
3296 def _is_agegated(player_response):
3297 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3300 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3301 AGE_GATE_REASONS = (
3302 'confirm your age', 'age-restricted', 'inappropriate', # reason
3303 'age_verification_required', 'age_check_required', # status
3305 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3308 def _is_unplayable(player_response):
3309 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3311 _STORY_PLAYER_PARAMS = '8AEB'
3313 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3315 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3316 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3317 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3318 headers = self.generate_api_headers(
3319 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3322 'videoId': video_id,
3324 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3325 yt_query['params'] = self._STORY_PLAYER_PARAMS
3327 yt_query.update(self._generate_player_context(sts))
3328 return self._extract_response(
3329 item_id=video_id, ep='player', query=yt_query,
3330 ytcfg=player_ytcfg, headers=headers, fatal=True,
3331 default_client=client,
3332 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3335 def _get_requested_clients(self, url, smuggled_data):
3336 requested_clients = []
3337 default = ['android', 'web']
3338 allowed_clients = sorted(
3339 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3340 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3341 for client in self._configuration_arg('player_client'):
3342 if client in allowed_clients:
3343 requested_clients.append(client)
3344 elif client == 'default':
3345 requested_clients.extend(default)
3346 elif client == 'all':
3347 requested_clients.extend(allowed_clients)
3349 self.report_warning(f'Skipping unsupported client {client}')
3350 if not requested_clients:
3351 requested_clients = default
3353 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3354 requested_clients.extend(
3355 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3357 return orderedSet(requested_clients)
3359 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3362 initial_pr = self._search_json(
3363 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3365 all_clients = set(clients)
3366 clients = clients[::-1]
3369 def append_client(*client_names):
3370 """ Append the first client name that exists but not already used """
3371 for client_name in client_names:
3372 actual_client = _split_innertube_client(client_name)[0]
3373 if actual_client in INNERTUBE_CLIENTS:
3374 if actual_client not in all_clients:
3375 clients.append(client_name)
3376 all_clients.add(actual_client)
3379 # Android player_response does not have microFormats which are needed for
3380 # extraction of some data. So we return the initial_pr with formats
3381 # stripped out even if not requested by the user
3382 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3384 pr = dict(initial_pr)
3385 pr['streamingData'] = None
3389 tried_iframe_fallback = False
3392 client, base_client, variant = _split_innertube_client(clients.pop())
3393 player_ytcfg = master_ytcfg if client == 'web' else {}
3394 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3395 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3397 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3398 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3399 if 'js' in self._configuration_arg('player_skip'):
3400 require_js_player = False
3403 if not player_url and not tried_iframe_fallback and require_js_player:
3404 player_url = self._download_player_url(video_id)
3405 tried_iframe_fallback = True
3408 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3409 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3410 except ExtractorError as e:
3412 self.report_warning(last_error)
3417 # YouTube may return a different video player response than expected.
3418 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3419 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3420 if pr_video_id and pr_video_id != video_id:
3421 self.report_warning(
3422 f'Skipping player response from {client} client (got player response for video "{pr_video_id}
" instead of "{video_id}
")' + bug_reports_message())
3426 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3427 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3428 append_client(f'{base_client}_creator')
3429 elif self._is_agegated(pr):
3430 if variant == 'tv_embedded':
3431 append_client(f'{base_client}_embedded')
3433 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3438 self.report_warning(last_error)
3439 return prs, player_url
3441 def _needs_live_processing(self, live_status, duration):
3442 if (live_status == 'is_live' and self.get_param('live_from_start')
3443 or live_status == 'post_live' and (duration or 0) > 4 * 3600):
3446 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, live_status, duration):
3447 itags, stream_ids = {}, []
3448 itag_qualities, res_qualities = {}, {0: None}
3450 # Normally tiny is the smallest video-only formats. But
3451 # audio-only formats with unknown quality may get tagged as tiny
3453 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3454 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3456 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3458 for fmt in streaming_formats:
3459 if fmt.get('targetDurationSec'):
3462 itag = str_or_none(fmt.get('itag'))
3463 audio_track = fmt.get('audioTrack') or {}
3464 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3465 if stream_id in stream_ids:
3468 quality = fmt.get('quality')
3469 height = int_or_none(fmt.get('height'))
3470 if quality == 'tiny' or not quality:
3471 quality = fmt.get('audioQuality', '').lower() or quality
3472 # The 3gp format (17) in android client has a quality of "small
",
3473 # but is actually worse than other formats
3478 itag_qualities[itag] = quality
3480 res_qualities[height] = quality
3481 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3482 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3483 # number of fragment that would subsequently requested with (`&sq=N`)
3484 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3487 fmt_url = fmt.get('url')
3489 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3490 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3491 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3492 if not all((sc, fmt_url, player_url, encrypted_sig)):
3495 fmt_url += '&%s=%s' % (
3496 traverse_obj(sc, ('sp', -1)) or 'signature',
3497 self._decrypt_signature(encrypted_sig, video_id, player_url)
3499 except ExtractorError as e:
3500 self.report_warning('Signature extraction failed: Some formats may be missing',
3501 video_id=video_id, only_once=True)
3502 self.write_debug(e, only_once=True)
3505 query = parse_qs(fmt_url)
3509 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3510 fmt_url = update_url_query(fmt_url, {
3511 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3513 except ExtractorError as e:
3515 if isinstance(e, JSInterpreter.Exception):
3516 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3517 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3519 self.report_warning(
3520 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3521 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3522 self.write_debug(e, only_once=True)
3524 self.report_warning(
3525 'Cannot decrypt nsig without player_url: You may experience throttling for some formats',
3526 video_id=video_id, only_once=True)
3530 itags[itag] = 'https'
3531 stream_ids.append(stream_id)
3533 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3534 language_preference = (
3535 10 if audio_track.get('audioIsDefault') and 10
3536 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3538 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3539 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3540 # Make sure to avoid false positives with small duration differences.
3541 # E.g. __2ABJjxzNo, ySuUZEjARPY
3542 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3544 self.report_warning(
3545 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3547 'asr': int_or_none(fmt.get('audioSampleRate')),
3548 'filesize': int_or_none(fmt.get('contentLength')),
3550 'format_note': join_nonempty(
3551 '%s%s' % (audio_track.get('displayName') or '',
3552 ' (default)' if language_preference > 0 else ''),
3553 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3554 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3555 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3556 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3557 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3558 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3559 'fps': int_or_none(fmt.get('fps')) or None,
3560 'audio_channels': fmt.get('audioChannels'),
3562 'quality': q(quality),
3563 'has_drm': bool(fmt.get('drmFamilies')),
3566 'width': int_or_none(fmt.get('width')),
3567 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3568 'desc' if language_preference < -1 else ''),
3569 'language_preference': language_preference,
3570 # Strictly de-prioritize damaged and 3gp formats
3571 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3573 mime_mobj = re.match(
3574 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3576 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3577 dct.update(parse_codecs(mime_mobj.group(2)))
3578 no_audio = dct.get('acodec
') == 'none
'
3579 no_video = dct.get('vcodec
') == 'none
'
3584 if no_audio or no_video:
3585 dct['downloader_options
'] = {
3586 # Youtube throttles chunks >~10M
3587 'http_chunk_size
': 10485760,
3590 dct['container
'] = dct['ext
'] + '_dash
'
3593 needs_live_processing = self._needs_live_processing(live_status, duration)
3594 skip_bad_formats = not self._configuration_arg('include_incomplete_formats
')
3596 skip_manifests = set(self._configuration_arg('skip
'))
3597 if (not self.get_param('youtube_include_hls_manifest
', True)
3598 or needs_live_processing == 'is_live
' # These will be filtered out by YoutubeDL anyway
3599 or needs_live_processing and skip_bad_formats):
3600 skip_manifests.add('hls
')
3602 if not self.get_param('youtube_include_dash_manifest
', True):
3603 skip_manifests.add('dash
')
3604 if self._configuration_arg('include_live_dash
'):
3605 self._downloader.deprecated_feature('[youtube
] include_live_dash extractor argument
is deprecated
. '
3606 'Use include_incomplete_formats extractor argument instead
')
3607 elif skip_bad_formats and live_status == 'is_live
' and needs_live_processing != 'is_live
':
3608 skip_manifests.add('dash
')
3610 def process_manifest_format(f, proto, itag):
3612 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3614 itag = f'{itag}
-{proto}
'
3616 f['format_id
'] = itag
3619 f['quality
'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id
'].split('-')[0]), -1))
3620 if f['quality
'] == -1 and f.get('height
'):
3621 f['quality
'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height
']))])
3625 for sd in streaming_data:
3626 hls_manifest_url = 'hls
' not in skip_manifests and sd.get('hlsManifestUrl
')
3627 if hls_manifest_url:
3628 fmts, subs = self._extract_m3u8_formats_and_subtitles(
3629 hls_manifest_url, video_id, 'mp4
', fatal=False, live=live_status == 'is_live
')
3630 subtitles = self._merge_subtitles(subs, subtitles)
3632 if process_manifest_format(f, 'hls
', self._search_regex(
3633 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3636 dash_manifest_url = 'dash
' not in skip_manifests and sd.get('dashManifestUrl
')
3637 if dash_manifest_url:
3638 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3639 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3641 if process_manifest_format(f, 'dash
', f['format_id
']):
3642 f['filesize
'] = int_or_none(self._search_regex(
3643 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3644 if needs_live_processing:
3645 f['is_from_start
'] = True
3650 def _extract_storyboard(self, player_responses, duration):
3652 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3653 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3657 for i, args in enumerate(spec):
3658 args = args.split('#')
3659 counts
= list(map(int_or_none
, args
[:5]))
3660 if len(args
) != 8 or not all(counts
):
3661 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3663 width
, height
, frame_count
, cols
, rows
= counts
3666 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3667 fragment_count
= frame_count
/ (cols
* rows
)
3668 fragment_duration
= duration
/ fragment_count
3670 'format_id': f
'sb{i}',
3671 'format_note': 'storyboard',
3673 'protocol': 'mhtml',
3679 'fps': frame_count
/ duration
,
3683 'url': url
.replace('$M', str(j
)),
3684 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3685 } for j
in range(math
.ceil(fragment_count
))],
3688 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3690 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3691 query
= {'bpctr': '9999999999', 'has_verified': '1'}
3692 if smuggled_data
.get('is_story'):
3693 query
['pp'] = self
._STORY
_PLAYER
_PARAMS
3694 webpage
= self
._download
_webpage
(
3695 webpage_url
, video_id
, fatal
=False, query
=query
)
3697 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3699 player_responses
, player_url
= self
._extract
_player
_responses
(
3700 self
._get
_requested
_clients
(url
, smuggled_data
),
3701 video_id
, webpage
, master_ytcfg
, smuggled_data
)
3703 return webpage
, master_ytcfg
, player_responses
, player_url
3705 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3706 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3707 is_live
= get_first(video_details
, 'isLive')
3709 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3710 live_content
= get_first(video_details
, 'isLiveContent')
3711 is_upcoming
= get_first(video_details
, 'isUpcoming')
3712 post_live
= get_first(video_details
, 'isPostLiveDvr')
3713 live_status
= ('post_live' if post_live
3714 else 'is_live' if is_live
3715 else 'is_upcoming' if is_upcoming
3716 else 'was_live' if live_content
3717 else 'not_live' if False in (is_live
, live_content
)
3719 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3720 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, live_status
, duration
)
3722 return live_broadcast_details
, live_status
, streaming_data
, formats
, subtitles
3724 def _real_extract(self
, url
):
3725 url
, smuggled_data
= unsmuggle_url(url
, {})
3726 video_id
= self
._match
_id
(url
)
3728 base_url
= self
.http_scheme() + '//www.youtube.com/'
3729 webpage_url
= base_url
+ 'watch?v=' + video_id
3731 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3733 playability_statuses
= traverse_obj(
3734 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3736 trailer_video_id
= get_first(
3737 playability_statuses
,
3738 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3740 if trailer_video_id
:
3741 return self
.url_result(
3742 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3744 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3745 if webpage
else (lambda x
: None))
3747 video_details
= traverse_obj(
3748 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3749 microformats
= traverse_obj(
3750 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3751 expected_type
=dict, default
=[])
3753 translated_title
= self
._get
_text
(microformats
, (..., 'title'))
3754 video_title
= (self
._preferred
_lang
and translated_title
3755 or get_first(video_details
, 'title') # primary
3757 or search_meta(['og:title', 'twitter:title', 'title']))
3758 translated_description
= self
._get
_text
(microformats
, (..., 'description'))
3759 original_description
= get_first(video_details
, 'shortDescription')
3760 video_description
= (
3761 self
._preferred
_lang
and translated_description
3762 # If original description is blank, it will be an empty string.
3763 # Do not prefer translated description in this case.
3764 or original_description
if original_description
is not None else translated_description
)
3766 multifeed_metadata_list
= get_first(
3768 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3770 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3771 if self
.get_param('noplaylist'):
3772 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3776 for feed
in multifeed_metadata_list
.split(','):
3777 # Unquote should take place before split on comma (,) since textual
3778 # fields may contain comma as well (see
3779 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3780 feed_data
= urllib
.parse
.parse_qs(
3781 urllib
.parse
.unquote_plus(feed
))
3783 def feed_entry(name
):
3785 feed_data
, lambda x
: x
[name
][0], str)
3787 feed_id
= feed_entry('id')
3790 feed_title
= feed_entry('title')
3793 title
+= ' (%s)' % feed_title
3795 '_type': 'url_transparent',
3796 'ie_key': 'Youtube',
3798 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3799 {'force_singlefeed': True}
),
3802 feed_ids
.append(feed_id
)
3804 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3805 % (', '.join(feed_ids
), video_id
))
3806 return self
.playlist_result(
3807 entries
, video_id
, video_title
, video_description
)
3809 duration
= (int_or_none(get_first(video_details
, 'lengthSeconds'))
3810 or int_or_none(get_first(microformats
, 'lengthSeconds'))
3811 or parse_duration(search_meta('duration')) or None)
3813 live_broadcast_details
, live_status
, streaming_data
, formats
, automatic_captions
= \
3814 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
, duration
)
3815 if live_status
== 'post_live':
3816 self
.write_debug(f
'{video_id}: Video is in Post-Live Manifestless mode')
3819 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3820 self
.report_drm(video_id
)
3822 playability_statuses
,
3823 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3824 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3825 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3827 if subreason
== 'The uploader has not made this video available in your country.':
3828 countries
= get_first(microformats
, 'availableCountries')
3830 regions_allowed
= search_meta('regionsAllowed')
3831 countries
= regions_allowed
.split(',') if regions_allowed
else None
3832 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3833 reason
+= f
'. {subreason}'
3835 self
.raise_no_formats(reason
, expected
=True)
3837 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3838 if not keywords
and webpage
:
3840 unescapeHTML(m
.group('content'))
3841 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3842 for keyword
in keywords
:
3843 if keyword
.startswith('yt:stretch='):
3844 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3846 # NB: float is intentional for forcing float division
3847 w
, h
= (float(v
) for v
in mobj
.groups())
3851 if f
.get('vcodec') != 'none':
3852 f
['stretched_ratio'] = ratio
3854 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3855 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3858 'url': thumbnail_url
,
3860 original_thumbnails
= thumbnails
.copy()
3862 # The best resolution thumbnails sometimes does not appear in the webpage
3863 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3864 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3866 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3867 # in resolution, these are not the custom thumbnail. So de-prioritize them
3868 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3869 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3871 n_thumbnail_names
= len(thumbnail_names
)
3873 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3874 video_id
=video_id
, name
=name
, ext
=ext
,
3875 webp
='_webp' if ext
== 'webp' else '', live
='_live' if live_status
== 'is_live' else ''),
3876 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3877 for thumb
in thumbnails
:
3878 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3879 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3880 self
._remove
_duplicate
_formats
(thumbnails
)
3881 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3883 category
= get_first(microformats
, 'category') or search_meta('genre')
3884 channel_id
= str_or_none(
3885 get_first(video_details
, 'channelId')
3886 or get_first(microformats
, 'externalChannelId')
3887 or search_meta('channelId'))
3888 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3890 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3891 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3892 if not duration
and live_end_time
and live_start_time
:
3893 duration
= live_end_time
- live_start_time
3895 needs_live_processing
= self
._needs
_live
_processing
(live_status
, duration
)
3897 def is_bad_format(fmt
):
3898 if needs_live_processing
and not fmt
.get('is_from_start'):
3900 elif (live_status
== 'is_live' and needs_live_processing
!= 'is_live'
3901 and fmt
.get('protocol') == 'http_dash_segments'):
3904 for fmt
in filter(is_bad_format
, formats
):
3905 fmt
['preference'] = (fmt
.get('preference') or -1) - 10
3906 fmt
['format_note'] = join_nonempty(fmt
.get('format_note'), '(Last 4 hours)', delim
=' ')
3908 if needs_live_processing
:
3909 self
._prepare
_live
_from
_start
_formats
(
3910 formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
, live_status
== 'is_live')
3912 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3914 # source_preference is lower for throttled/potentially damaged formats
3915 self
._sort
_formats
(formats
, (
3916 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
3920 'title': video_title
,
3922 'thumbnails': thumbnails
,
3923 # The best thumbnail that we are sure exists. Prevents unnecessary
3924 # URL checking if user don't care about getting the best possible thumbnail
3925 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3926 'description': video_description
,
3927 'uploader': get_first(video_details
, 'author'),
3928 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3929 'uploader_url': owner_profile_url
,
3930 'channel_id': channel_id
,
3931 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3932 'duration': duration
,
3933 'view_count': int_or_none(
3934 get_first((video_details
, microformats
), (..., 'viewCount'))
3935 or search_meta('interactionCount')),
3936 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3937 'age_limit': 18 if (
3938 get_first(microformats
, 'isFamilySafe') is False
3939 or search_meta('isFamilyFriendly') == 'false'
3940 or search_meta('og:restrictions:age') == '18+') else 0,
3941 'webpage_url': webpage_url
,
3942 'categories': [category
] if category
else None,
3944 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3945 'live_status': live_status
,
3946 'release_timestamp': live_start_time
,
3950 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3952 def get_lang_code(track
):
3953 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3954 or track
.get('languageCode'))
3956 # Converted into dicts to remove duplicates
3958 get_lang_code(sub
): sub
3959 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3960 translation_languages
= {
3961 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3962 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3964 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3965 lang_subs
= container
.setdefault(lang_code
, [])
3966 for fmt
in self
._SUBTITLE
_FORMATS
:
3972 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3976 # NB: Constructing the full subtitle dictionary is slow
3977 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3978 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3979 for lang_code
, caption_track
in captions
.items():
3980 base_url
= caption_track
.get('baseUrl')
3981 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3984 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3985 if caption_track
.get('kind') != 'asr':
3989 subtitles
, base_url
, lang_code
, lang_name
, {})
3990 if not caption_track
.get('isTranslatable'):
3992 for trans_code
, trans_name
in translation_languages
.items():
3995 orig_trans_code
= trans_code
3996 if caption_track
.get('kind') != 'asr':
3997 if not get_translated_subs
:
3999 trans_code
+= f
'-{lang_code}'
4000 trans_name
+= format_field(lang_name
, None, ' from %s')
4001 # Add an "-orig" label to the original language so that it can be distinguished.
4002 # The subs are returned without "-orig" as well for compatibility
4003 if lang_code
== f
'a-{orig_trans_code}':
4005 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
4006 # Setting tlang=lang returns damaged subtitles.
4007 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
4008 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
4010 info
['automatic_captions'] = automatic_captions
4011 info
['subtitles'] = subtitles
4013 parsed_url
= urllib
.parse
.urlparse(url
)
4014 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
4015 query
= urllib
.parse
.parse_qs(component
)
4016 for k
, v
in query
.items():
4017 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
4019 if d_k
not in info
and k
in s_ks
:
4020 info
[d_k
] = parse_duration(query
[k
][0])
4022 # Youtube Music Auto-generated description
4023 if video_description
:
4026 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
4028 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
4029 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
4030 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
4031 .+\nAuto-generated\ by\ YouTube\.\s*$
4032 ''', video_description
)
4034 release_year
= mobj
.group('release_year')
4035 release_date
= mobj
.group('release_date')
4037 release_date
= release_date
.replace('-', '')
4038 if not release_year
:
4039 release_year
= release_date
[:4]
4041 'album': mobj
.group('album'.strip()),
4042 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
4043 'track': mobj
.group('track').strip(),
4044 'release_date': release_date
,
4045 'release_year': int_or_none(release_year
),
4050 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
4051 if not initial_data
:
4052 query
= {'videoId': video_id}
4053 query
.update(self
._get
_checkok
_params
())
4054 initial_data
= self
._extract
_response
(
4055 item_id
=video_id
, ep
='next', fatal
=False,
4056 ytcfg
=master_ytcfg
, query
=query
,
4057 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
4058 note
='Downloading initial data API JSON')
4060 info
['comment_count'] = traverse_obj(initial_data
, (
4061 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
4062 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
4064 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
4065 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
4066 ), expected_type
=int_or_none
, get_all
=False)
4068 try: # This will error if there is no livechat
4069 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
4070 except (KeyError, IndexError, TypeError):
4073 info
.setdefault('subtitles', {})['live_chat'] = [{
4074 # url is needed to set cookies
4075 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
4076 'video_id': video_id
,
4078 'protocol': ('youtube_live_chat' if live_status
in ('is_live', 'is_upcoming')
4079 else 'youtube_live_chat_replay'),
4083 info
['chapters'] = (
4084 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
4085 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
4086 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
4089 contents
= traverse_obj(
4090 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
4091 expected_type
=list, default
=[])
4093 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
4095 stl
= vpir
.get('superTitleLink')
4097 stl
= self
._get
_text
(stl
)
4100 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
4101 info
['location'] = stl
4103 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
4106 'series': mobj
.group(1),
4107 'season_number': int(mobj
.group(2)),
4108 'episode_number': int(mobj
.group(3)),
4110 for tlb
in (try_get(
4112 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
4116 tlb
, 'toggleButtonRenderer',
4117 ('segmentedLikeDislikeButtonRenderer', ..., 'toggleButtonRenderer'),
4120 for getter
, regex
in [(
4121 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
4122 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
4123 lambda x
: x
['accessibility'],
4124 lambda x
: x
['accessibilityData']['accessibilityData'],
4125 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
4126 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
4128 mobj
= re
.match(regex
, label
)
4130 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
4132 sbr_tooltip
= try_get(
4133 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
4135 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
4137 'like_count': str_to_int(like_count
),
4138 'dislike_count': str_to_int(dislike_count
),
4140 vcr
= traverse_obj(vpir
, ('viewCount', 'videoViewCountRenderer'))
4142 vc
= self
._get
_count
(vcr
, 'viewCount')
4143 # Upcoming premieres with waiting count are treated as live here
4144 if vcr
.get('isLive'):
4145 info
['concurrent_view_count'] = vc
4146 elif info
.get('view_count') is None:
4147 info
['view_count'] = vc
4149 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
4151 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
4153 'channel': self
._get
_text
(vor
, 'title'),
4154 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
4158 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
4160 multiple_songs
= False
4162 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
4163 multiple_songs
= True
4166 mrr
= row
.get('metadataRowRenderer') or {}
4167 mrr_title
= mrr
.get('title')
4170 mrr_title
= self
._get
_text
(mrr
, 'title')
4171 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
4172 if mrr_title
== 'License':
4173 info
['license'] = mrr_contents_text
4174 elif not multiple_songs
:
4175 if mrr_title
== 'Album':
4176 info
['album'] = mrr_contents_text
4177 elif mrr_title
== 'Artist':
4178 info
['artist'] = mrr_contents_text
4179 elif mrr_title
== 'Song':
4180 info
['track'] = mrr_contents_text
4183 'channel': 'uploader',
4184 'channel_id': 'uploader_id',
4185 'channel_url': 'uploader_url',
4188 # The upload date for scheduled, live and past live streams / premieres in microformats
4189 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
4190 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
4192 unified_strdate(get_first(microformats
, 'uploadDate'))
4193 or unified_strdate(search_meta('uploadDate')))
4194 if not upload_date
or (
4195 live_status
in ('not_live', None)
4196 and 'no-youtube-prefer-utc-upload-date' not in self
.get_param('compat_opts', [])
4198 upload_date
= strftime_or_none(
4199 self
._parse
_time
_text
(self
._get
_text
(vpir
, 'dateText')), '%Y%m%d') or upload_date
4200 info
['upload_date'] = upload_date
4202 for to
, frm
in fallbacks
.items():
4203 if not info
.get(to
):
4204 info
[to
] = info
.get(frm
)
4206 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
4211 badges
= self
._extract
_badges
(traverse_obj(contents
, (..., 'videoPrimaryInfoRenderer'), get_all
=False))
4213 is_private
= (self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
)
4214 or get_first(video_details
, 'isPrivate', expected_type
=bool))
4216 info
['availability'] = (
4217 'public' if self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
4218 else self
._availability
(
4219 is_private
=is_private
,
4221 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
)
4222 or False if initial_data
and is_private
is not None else None),
4223 needs_subscription
=(
4224 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
)
4225 or False if initial_data
and is_private
is not None else None),
4226 needs_auth
=info
['age_limit'] >= 18,
4227 is_unlisted
=None if is_private
is None else (
4228 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
)
4229 or get_first(microformats
, 'isUnlisted', expected_type
=bool))))
4231 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
4233 self
.mark_watched(video_id
, player_responses
)
4238 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
4241 def passthrough_smuggled_data(func
):
4242 def _smuggle(entries
, smuggled_data
):
4243 for entry
in entries
:
4244 # TODO: Convert URL to music.youtube instead.
4245 # Do we need to passthrough any other smuggled_data?
4246 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
4249 @functools.wraps(func
)
4250 def wrapper(self
, url
):
4251 url
, smuggled_data
= unsmuggle_url(url
, {})
4252 if self
.is_music_url(url
):
4253 smuggled_data
['is_music_url'] = True
4254 info_dict
= func(self
, url
, smuggled_data
)
4255 if smuggled_data
and info_dict
.get('entries'):
4256 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
4260 def _extract_channel_id(self
, webpage
):
4261 channel_id
= self
._html
_search
_meta
(
4262 'channelId', webpage
, 'channel id', default
=None)
4265 channel_url
= self
._html
_search
_meta
(
4266 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4267 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4268 'twitter:app:url:googleplay'), webpage
, 'channel url')
4269 return self
._search
_regex
(
4270 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4271 channel_url
, 'channel id')
4274 def _extract_basic_item_renderer(item
):
4275 # Modified from _extract_grid_item_renderer
4276 known_basic_renderers
= (
4277 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4279 for key
, renderer
in item
.items():
4280 if not isinstance(renderer
, dict):
4282 elif key
in known_basic_renderers
:
4284 elif key
.startswith('grid') and key
.endswith('Renderer'):
4287 def _grid_entries(self
, grid_renderer
):
4288 for item
in grid_renderer
['items']:
4289 if not isinstance(item
, dict):
4291 renderer
= self
._extract
_basic
_item
_renderer
(item
)
4292 if not isinstance(renderer
, dict):
4294 title
= self
._get
_text
(renderer
, 'title')
4297 playlist_id
= renderer
.get('playlistId')
4299 yield self
.url_result(
4300 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4301 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4305 video_id
= renderer
.get('videoId')
4307 yield self
._extract
_video
(renderer
)
4310 channel_id
= renderer
.get('channelId')
4312 yield self
.url_result(
4313 'https://www.youtube.com/channel/%s' % channel_id
,
4314 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
4316 # generic endpoint URL support
4317 ep_url
= urljoin('https://www.youtube.com/', try_get(
4318 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4321 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4322 if ie
.suitable(ep_url
):
4323 yield self
.url_result(
4324 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4327 def _music_reponsive_list_entry(self
, renderer
):
4328 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4330 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4331 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4332 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4334 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4336 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4337 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4338 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4339 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4340 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4342 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4343 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4345 def _shelf_entries_from_content(self
, shelf_renderer
):
4346 content
= shelf_renderer
.get('content')
4347 if not isinstance(content
, dict):
4349 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4351 # TODO: add support for nested playlists so each shelf is processed
4352 # as separate playlist
4353 # TODO: this includes only first N items
4354 yield from self
._grid
_entries
(renderer
)
4355 renderer
= content
.get('horizontalListRenderer')
4360 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4362 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4364 shelf_url
= urljoin('https://www.youtube.com', ep
)
4366 # Skipping links to another channels, note that checking for
4367 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4369 if skip_channels
and '/channels?' in shelf_url
:
4371 title
= self
._get
_text
(shelf_renderer
, 'title')
4372 yield self
.url_result(shelf_url
, video_title
=title
)
4373 # Shelf may not contain shelf URL, fallback to extraction from content
4374 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4376 def _playlist_entries(self
, video_list_renderer
):
4377 for content
in video_list_renderer
['contents']:
4378 if not isinstance(content
, dict):
4380 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4381 if not isinstance(renderer
, dict):
4383 video_id
= renderer
.get('videoId')
4386 yield self
._extract
_video
(renderer
)
4388 def _rich_entries(self
, rich_grid_renderer
):
4389 renderer
= traverse_obj(
4390 rich_grid_renderer
, ('content', ('videoRenderer', 'reelItemRenderer')), get_all
=False) or {}
4391 video_id
= renderer
.get('videoId')
4394 yield self
._extract
_video
(renderer
)
4396 def _video_entry(self
, video_renderer
):
4397 video_id
= video_renderer
.get('videoId')
4399 return self
._extract
_video
(video_renderer
)
4401 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4402 url
= urljoin('https://youtube.com', traverse_obj(
4403 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4405 return self
.url_result(
4406 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4408 def _post_thread_entries(self
, post_thread_renderer
):
4409 post_renderer
= try_get(
4410 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4411 if not post_renderer
:
4414 video_renderer
= try_get(
4415 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4416 video_id
= video_renderer
.get('videoId')
4418 entry
= self
._extract
_video
(video_renderer
)
4421 # playlist attachment
4422 playlist_id
= try_get(
4423 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4425 yield self
.url_result(
4426 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4427 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4428 # inline video links
4429 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4431 if not isinstance(run
, dict):
4434 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4437 if not YoutubeIE
.suitable(ep_url
):
4439 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4440 if video_id
== ep_video_id
:
4442 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4444 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4445 contents
= post_thread_continuation
.get('contents')
4446 if not isinstance(contents
, list):
4448 for content
in contents
:
4449 renderer
= content
.get('backstagePostThreadRenderer')
4450 if isinstance(renderer
, dict):
4451 yield from self
._post
_thread
_entries
(renderer
)
4453 renderer
= content
.get('videoRenderer')
4454 if isinstance(renderer
, dict):
4455 yield self
._video
_entry
(renderer
)
4458 def _rich_grid_entries(self, contents):
4459 for content in contents:
4460 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4462 entry = self._video_entry(video_renderer)
4467 def _report_history_entries(self
, renderer
):
4468 for url
in traverse_obj(renderer
, (
4469 'rows', ..., 'reportHistoryTableRowRenderer', 'cells', ...,
4470 'reportHistoryTableCellRenderer', 'cell', 'reportHistoryTableTextCellRenderer', 'text', 'runs', ...,
4471 'navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url')):
4472 yield self
.url_result(urljoin('https://www.youtube.com', url
), YoutubeIE
)
4474 def _extract_entries(self
, parent_renderer
, continuation_list
):
4475 # continuation_list is modified in-place with continuation_list = [continuation_token]
4476 continuation_list
[:] = [None]
4477 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4478 for content
in contents
:
4479 if not isinstance(content
, dict):
4481 is_renderer
= traverse_obj(
4482 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4485 if content
.get('richItemRenderer'):
4486 for entry
in self
._rich
_entries
(content
['richItemRenderer']):
4488 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4489 elif content
.get('reportHistorySectionRenderer'): # https://www.youtube.com/reporthistory
4490 table
= traverse_obj(content
, ('reportHistorySectionRenderer', 'table', 'tableRenderer'))
4491 yield from self
._report
_history
_entries
(table
)
4492 continuation_list
[0] = self
._extract
_continuation
(table
)
4495 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4496 for isr_content
in isr_contents
:
4497 if not isinstance(isr_content
, dict):
4501 'playlistVideoListRenderer': self
._playlist
_entries
,
4502 'gridRenderer': self
._grid
_entries
,
4503 'reelShelfRenderer': self
._grid
_entries
,
4504 'shelfRenderer': self
._shelf
_entries
,
4505 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4506 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4507 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4508 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4509 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4510 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4512 for key
, renderer
in isr_content
.items():
4513 if key
not in known_renderers
:
4515 for entry
in known_renderers
[key
](renderer
):
4518 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4521 if not continuation_list
[0]:
4522 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4524 if not continuation_list
[0]:
4525 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4527 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4528 continuation_list
= [None]
4529 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4530 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4534 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4535 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4536 yield from extract_entries(parent_renderer
)
4537 continuation
= continuation_list
[0]
4539 for page_num
in itertools
.count(1):
4540 if not continuation
:
4542 headers
= self
.generate_api_headers(
4543 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4544 response
= self
._extract
_response
(
4545 item_id
=f
'{item_id} page {page_num}',
4546 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4547 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4551 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4552 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4553 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4556 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4557 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4558 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4559 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4560 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4561 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4562 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4563 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents'),
4564 'reportHistoryTableRowRenderer': (self
._report
_history
_entries
, 'rows'),
4565 'playlistVideoListContinuation': (self
._playlist
_entries
, None),
4566 'gridContinuation': (self
._grid
_entries
, None),
4567 'itemSectionContinuation': (self
._post
_thread
_continuation
_entries
, None),
4568 'sectionListContinuation': (extract_entries
, None), # for feeds
4571 continuation_items
= traverse_obj(response
, (
4572 ('onResponseReceivedActions', 'onResponseReceivedEndpoints'), ...,
4573 'appendContinuationItemsAction', 'continuationItems'
4574 ), 'continuationContents', get_all
=False)
4575 continuation_item
= traverse_obj(continuation_items
, 0, None, expected_type
=dict, default
={})
4577 video_items_renderer
= None
4578 for key
in continuation_item
.keys():
4579 if key
not in known_renderers
:
4581 func
, parent_key
= known_renderers
[key
]
4582 video_items_renderer
= {parent_key: continuation_items}
if parent_key
else continuation_items
4583 continuation_list
= [None]
4584 yield from func(video_items_renderer
)
4585 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4587 if not video_items_renderer
:
4591 def _extract_selected_tab(tabs
, fatal
=True):
4592 for tab_renderer
in tabs
:
4593 if tab_renderer
.get('selected'):
4596 raise ExtractorError('Unable to find selected tab')
4599 def _extract_tab_renderers(response
):
4600 return traverse_obj(
4601 response
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs', ..., ('tabRenderer', 'expandableTabRenderer')), expected_type
=dict)
4603 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4604 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4607 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4608 # Deprecated - remove when layout discontinued
4609 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4610 playlist_header_renderer
= traverse_obj(data
, ('header', 'playlistHeaderRenderer'), expected_type
=dict)
4611 metadata_renderer
= try_get(
4612 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4613 if metadata_renderer
:
4614 channel_name
= metadata_renderer
.get('title')
4615 channel_url
= metadata_renderer
.get('channelUrl')
4616 channel_id
= metadata_renderer
.get('externalId')
4618 metadata_renderer
= try_get(
4619 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4621 if metadata_renderer
:
4622 title
= metadata_renderer
.get('title')
4623 description
= metadata_renderer
.get('description', '')
4624 playlist_id
= channel_id
4625 tags
= metadata_renderer
.get('keywords', '').split()
4627 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4628 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4629 def _get_uncropped(url
):
4630 return url_or_none((url
or '').split('=')[0] + '=s0')
4632 avatar_thumbnails
= self
._extract
_thumbnails
(metadata_renderer
, 'avatar')
4633 if avatar_thumbnails
:
4634 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4635 if uncropped_avatar
:
4636 avatar_thumbnails
.append({
4637 'url': uncropped_avatar
,
4638 'id': 'avatar_uncropped',
4642 channel_banners
= self
._extract
_thumbnails
(
4643 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4644 for banner
in channel_banners
:
4645 banner
['preference'] = -10
4648 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4649 if uncropped_banner
:
4650 channel_banners
.append({
4651 'url': uncropped_banner
,
4652 'id': 'banner_uncropped',
4656 # Deprecated - remove when old layout is discontinued
4657 primary_thumbnails
= self
._extract
_thumbnails
(
4658 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4660 playlist_thumbnails
= self
._extract
_thumbnails
(
4661 playlist_header_renderer
, ('playlistHeaderBanner', 'heroPlaylistThumbnailRenderer', 'thumbnail'))
4663 if playlist_id
is None:
4664 playlist_id
= item_id
4666 # Deprecated - remove primary_sidebar_renderer when old layout discontinued
4667 # Playlist stats is a text runs array containing [video count, view count, last updated].
4668 # last updated or (view count and last updated) may be missing.
4669 playlist_stats
= get_first(
4670 (primary_sidebar_renderer
, playlist_header_renderer
), (('stats', 'briefStats', 'numVideosText'),))
4671 last_updated_unix
= self
._parse
_time
_text
(
4672 self
._get
_text
(playlist_stats
, 2) # deprecated, remove when old layout discontinued
4673 or self
._get
_text
(playlist_header_renderer
, ('byline', 1, 'playlistBylineRenderer', 'text')))
4675 view_count
= self
._get
_count
(playlist_stats
, 1)
4676 if view_count
is None:
4677 view_count
= self
._get
_count
(playlist_header_renderer
, 'viewCountText')
4679 playlist_count
= self
._get
_count
(playlist_stats
, 0)
4680 if playlist_count
is None:
4681 playlist_count
= self
._get
_count
(playlist_header_renderer
, ('byline', 0, 'playlistBylineRenderer', 'text'))
4684 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4685 title
+= format_field(selected_tab
, 'title', ' - %s')
4686 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4689 'playlist_id': playlist_id
,
4690 'playlist_title': title
,
4691 'playlist_description': description
,
4692 'uploader': channel_name
,
4693 'uploader_id': channel_id
,
4694 'uploader_url': channel_url
,
4695 'thumbnails': (primary_thumbnails
or playlist_thumbnails
) + avatar_thumbnails
+ channel_banners
,
4697 'view_count': view_count
,
4698 'availability': self
._extract
_availability
(data
),
4699 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4700 'playlist_count': playlist_count
,
4701 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4704 owner
= traverse_obj(playlist_header_renderer
, 'ownerText')
4707 owner
= traverse_obj(
4708 self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer'),
4709 ('videoOwner', 'videoOwnerRenderer', 'title'))
4710 owner_text
= self
._get
_text
(owner
)
4711 browse_ep
= traverse_obj(owner
, ('runs', 0, 'navigationEndpoint', 'browseEndpoint')) or {}
4712 metadata
.update(filter_dict({
4713 'uploader': self
._search
_regex
(r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
),
4714 'uploader_id': browse_ep
.get('browseId'),
4715 'uploader_url': urljoin('https://www.youtube.com', browse_ep
.get('canonicalBaseUrl'))
4719 'channel': metadata
['uploader'],
4720 'channel_id': metadata
['uploader_id'],
4721 'channel_url': metadata
['uploader_url']})
4722 return self
.playlist_result(
4724 selected_tab
, playlist_id
, ytcfg
,
4725 self
._extract
_account
_syncid
(ytcfg
, data
),
4726 self
._extract
_visitor
_data
(data
, ytcfg
)),
4729 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4730 first_id
= last_id
= response
= None
4731 for page_num
in itertools
.count(1):
4732 videos
= list(self
._playlist
_entries
(playlist
))
4735 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4736 if start
>= len(videos
):
4738 yield from videos
[start
:]
4739 first_id
= first_id
or videos
[0]['id']
4740 last_id
= videos
[-1]['id']
4741 watch_endpoint
= try_get(
4742 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4743 headers
= self
.generate_api_headers(
4744 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4745 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4747 'playlistId': playlist_id
,
4748 'videoId': watch_endpoint
.get('videoId') or last_id
,
4749 'index': watch_endpoint
.get('index') or len(videos
),
4750 'params': watch_endpoint
.get('params') or 'OAE%3D'
4752 response
= self
._extract
_response
(
4753 item_id
='%s page %d' % (playlist_id
, page_num
),
4754 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4755 check_get_keys
='contents'
4758 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4760 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4761 title
= playlist
.get('title') or try_get(
4762 data
, lambda x
: x
['titleText']['simpleText'], str)
4763 playlist_id
= playlist
.get('playlistId') or item_id
4765 # Delegating everything except mix playlists to regular tab-based playlist URL
4766 playlist_url
= urljoin(url
, try_get(
4767 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4770 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4771 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4772 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4774 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4775 return self
.url_result(
4776 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4779 return self
.playlist_result(
4780 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4781 playlist_id
=playlist_id
, playlist_title
=title
)
4783 def _extract_availability(self
, data
):
4785 Gets the availability of a given playlist/tab.
4786 Note: Unless YouTube tells us explicitly, we do not assume it is public
4787 @param data: response
4789 sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4790 playlist_header_renderer
= traverse_obj(data
, ('header', 'playlistHeaderRenderer')) or {}
4791 player_header_privacy
= playlist_header_renderer
.get('privacy')
4793 badges
= self
._extract
_badges
(sidebar_renderer
)
4795 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4796 privacy_setting_icon
= get_first(
4797 (playlist_header_renderer
, sidebar_renderer
),
4798 ('privacyForm', 'dropdownFormFieldRenderer', 'dropdown', 'dropdownRenderer', 'entries',
4799 lambda _
, v
: v
['privacyDropdownItemRenderer']['isSelected'], 'privacyDropdownItemRenderer', 'icon', 'iconType'),
4802 microformats_is_unlisted
= traverse_obj(
4803 data
, ('microformat', 'microformatDataRenderer', 'unlisted'), expected_type
=bool)
4807 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PUBLIC
)
4808 or player_header_privacy
== 'PUBLIC'
4809 or privacy_setting_icon
== 'PRIVACY_PUBLIC')
4810 else self
._availability
(
4812 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PRIVATE
)
4813 or player_header_privacy
== 'PRIVATE' if player_header_privacy
is not None
4814 else privacy_setting_icon
== 'PRIVACY_PRIVATE' if privacy_setting_icon
is not None else None),
4816 self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_UNLISTED
)
4817 or player_header_privacy
== 'UNLISTED' if player_header_privacy
is not None
4818 else privacy_setting_icon
== 'PRIVACY_UNLISTED' if privacy_setting_icon
is not None
4819 else microformats_is_unlisted
if microformats_is_unlisted
is not None else None),
4820 needs_subscription
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_SUBSCRIPTION
) or None,
4821 needs_premium
=self
._has
_badge
(badges
, BadgeType
.AVAILABILITY_PREMIUM
) or None,
4825 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4826 sidebar_renderer
= try_get(
4827 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4828 for item
in sidebar_renderer
:
4829 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4833 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4835 Reload playlists with unavailable videos (e.g. private videos, region blocked, etc.)
4837 is_playlist
= bool(traverse_obj(
4838 data
, ('metadata', 'playlistMetadataRenderer'), ('header', 'playlistHeaderRenderer')))
4841 headers
= self
.generate_api_headers(
4842 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4843 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4845 'params': 'wgYCCAA=',
4846 'browseId': f
'VL{item_id}'
4848 return self
._extract
_response
(
4849 item_id
=item_id
, headers
=headers
, query
=query
,
4850 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4851 note
='Redownloading playlist API JSON with unavailable videos')
4853 @functools.cached_property
4854 def skip_webpage(self
):
4855 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4857 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4858 webpage
, data
= None, None
4859 for retry
in self
.RetryManager(fatal
=fatal
):
4861 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
4862 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4863 except ExtractorError
as e
:
4864 if isinstance(e
.cause
, network_exceptions
):
4865 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4868 self
._error
_or
_warning
(e
, fatal
=fatal
)
4872 self
._extract
_and
_report
_alerts
(data
)
4873 except ExtractorError
as e
:
4874 self
._error
_or
_warning
(e
, fatal
=fatal
)
4877 # Sometimes youtube returns a webpage with incomplete ytInitialData
4878 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4879 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4880 retry
.error
= ExtractorError('Incomplete yt initial data received')
4883 return webpage
, data
4885 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4886 """Use if failed to extract ytcfg (and data) from initial webpage"""
4887 if not ytcfg
and self
.is_authenticated
:
4888 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4889 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4890 raise ExtractorError(
4891 f
'{msg}. If you are not downloading private content, or '
4892 'your cookies are only for the first account and channel,'
4893 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4895 self
.report_warning(msg
, only_once
=True)
4897 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4899 if not self
.skip_webpage
:
4900 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4901 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4902 # Reject webpage data if redirected to home page without explicitly requesting
4903 selected_tab
= self
._extract
_selected
_tab
(self
._extract
_tab
_renderers
(data
), fatal
=False) or {}
4904 if (url
!= 'https://www.youtube.com/feed/recommended'
4905 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4906 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4907 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4909 raise ExtractorError(msg
, expected
=True)
4910 self
.report_warning(msg
, only_once
=True)
4912 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4913 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4916 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4917 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4918 resolve_response
= self
._extract
_response
(
4919 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4920 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4921 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4922 for ep_key
, ep
in endpoints
.items():
4923 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4925 return self
._extract
_response
(
4926 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4927 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4928 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4929 err_note
= 'Failed to resolve url (does the playlist exist?)'
4931 raise ExtractorError(err_note
, expected
=True)
4932 self
.report_warning(err_note
, item_id
)
4934 _SEARCH_PARAMS
= None
4936 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4937 data
= {'query': query}
4938 if params
is NO_DEFAULT
:
4939 params
= self
._SEARCH
_PARAMS
4941 data
['params'] = params
4944 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4945 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4947 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4948 ('continuationContents', ),
4950 display_id
= f
'query "{query}"'
4951 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4952 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4953 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4955 continuation_list
= [None]
4957 for page_num
in itertools
.count(1):
4958 data
.update(continuation_list
[0] or {})
4959 headers
= self
.generate_api_headers(
4960 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4961 search
= self
._extract
_response
(
4962 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4963 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4964 slr_contents
= traverse_obj(search
, *content_keys
)
4965 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4966 if not continuation_list
[0]:
4970 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4971 IE_DESC
= 'YouTube Tabs'
4972 _VALID_URL
= r
'''(?x:
4976 youtube(?:kids)?\.com|
4980 (?P<channel_type>channel|c|user|browse)/|
4983 (?:playlist|watch)\?.*?\blist=
4985 (?!(?:%(reserved_names)s)\b) # Direct URLs
4989 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4990 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4992 IE_NAME
= 'youtube:tab'
4995 'note': 'playlists, multipage',
4996 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4997 'playlist_mincount': 94,
4999 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5000 'title': 'Igor Kleiner - Playlists',
5001 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5002 'uploader': 'Igor Kleiner',
5003 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5004 'channel': 'Igor Kleiner',
5005 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5006 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5007 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5008 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5009 'channel_follower_count': int
5012 'note': 'playlists, multipage, different order',
5013 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
5014 'playlist_mincount': 94,
5016 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
5017 'title': 'Igor Kleiner - Playlists',
5018 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
5019 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5020 'uploader': 'Igor Kleiner',
5021 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5022 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
5023 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
5024 'channel': 'Igor Kleiner',
5025 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
5026 'channel_follower_count': int
5029 'note': 'playlists, series',
5030 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
5031 'playlist_mincount': 5,
5033 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5034 'title': '3Blue1Brown - Playlists',
5035 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5036 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5037 'uploader': '3Blue1Brown',
5038 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5039 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5040 'channel': '3Blue1Brown',
5041 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5042 'tags': ['Mathematics'],
5043 'channel_follower_count': int
5046 'note': 'playlists, singlepage',
5047 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
5048 'playlist_mincount': 4,
5050 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5051 'title': 'ThirstForScience - Playlists',
5052 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
5053 'uploader': 'ThirstForScience',
5054 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5055 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5056 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
5057 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
5059 'channel': 'ThirstForScience',
5060 'channel_follower_count': int
5063 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
5064 'only_matching': True,
5066 'note': 'basic, single video playlist',
5067 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5069 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5070 'uploader': 'Sergey M.',
5071 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5072 'title': 'youtube-dl public playlist',
5076 'modified_date': '20201130',
5077 'channel': 'Sergey M.',
5078 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5079 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5080 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5081 'availability': 'public',
5083 'playlist_count': 1,
5085 'note': 'empty playlist',
5086 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5088 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5089 'uploader': 'Sergey M.',
5090 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
5091 'title': 'youtube-dl empty playlist',
5093 'channel': 'Sergey M.',
5095 'modified_date': '20160902',
5096 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
5097 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5098 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5099 'availability': 'public',
5101 'playlist_count': 0,
5104 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
5106 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5107 'title': 'lex will - Home',
5108 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5109 'uploader': 'lex will',
5110 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5111 'channel': 'lex will',
5112 'tags': ['bible', 'history', 'prophesy'],
5113 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5114 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5115 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5116 'channel_follower_count': int
5118 'playlist_mincount': 2,
5120 'note': 'Videos tab',
5121 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
5123 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5124 'title': 'lex will - Videos',
5125 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5126 'uploader': 'lex will',
5127 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5128 'tags': ['bible', 'history', 'prophesy'],
5129 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5130 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5131 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5132 'channel': 'lex will',
5133 'channel_follower_count': int
5135 'playlist_mincount': 975,
5137 'note': 'Videos tab, sorted by popular',
5138 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
5140 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5141 'title': 'lex will - Videos',
5142 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5143 'uploader': 'lex will',
5144 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5145 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5146 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5147 'channel': 'lex will',
5148 'tags': ['bible', 'history', 'prophesy'],
5149 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5150 'channel_follower_count': int
5152 'playlist_mincount': 199,
5154 'note': 'Playlists tab',
5155 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
5157 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5158 'title': 'lex will - Playlists',
5159 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5160 'uploader': 'lex will',
5161 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5162 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5163 'channel': 'lex will',
5164 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5165 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5166 'tags': ['bible', 'history', 'prophesy'],
5167 'channel_follower_count': int
5169 'playlist_mincount': 17,
5171 'note': 'Community tab',
5172 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
5174 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5175 'title': 'lex will - Community',
5176 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5177 'uploader': 'lex will',
5178 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5179 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5180 'channel': 'lex will',
5181 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5182 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5183 'tags': ['bible', 'history', 'prophesy'],
5184 'channel_follower_count': int
5186 'playlist_mincount': 18,
5188 'note': 'Channels tab',
5189 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
5191 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5192 'title': 'lex will - Channels',
5193 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
5194 'uploader': 'lex will',
5195 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5196 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5197 'channel': 'lex will',
5198 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
5199 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
5200 'tags': ['bible', 'history', 'prophesy'],
5201 'channel_follower_count': int
5203 'playlist_mincount': 12,
5205 'note': 'Search tab',
5206 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
5207 'playlist_mincount': 40,
5209 'id': 'UCYO_jab_esuFRV4b17AJtAw',
5210 'title': '3Blue1Brown - Search - linear algebra',
5211 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
5212 'uploader': '3Blue1Brown',
5213 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
5214 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5215 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
5216 'tags': ['Mathematics'],
5217 'channel': '3Blue1Brown',
5218 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
5219 'channel_follower_count': int
5222 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5223 'only_matching': True,
5225 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5226 'only_matching': True,
5228 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
5229 'only_matching': True,
5231 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5232 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5234 'title': '29C3: Not my department',
5235 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5236 'uploader': 'Christiaan008',
5237 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5238 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5240 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5242 'modified_date': '20150605',
5243 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5244 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5245 'channel': 'Christiaan008',
5246 'availability': 'public',
5248 'playlist_count': 96,
5250 'note': 'Large playlist',
5251 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5253 'title': 'Uploads from Cauchemar',
5254 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5255 'uploader': 'Cauchemar',
5256 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5257 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5259 'modified_date': r
're:\d{8}',
5260 'channel': 'Cauchemar',
5261 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5264 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5265 'availability': 'public',
5267 'playlist_mincount': 1123,
5268 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5270 'note': 'even larger playlist, 8832 videos',
5271 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5272 'only_matching': True,
5274 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5275 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5277 'title': 'Uploads from Interstellar Movie',
5278 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5279 'uploader': 'Interstellar Movie',
5280 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5281 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5284 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5285 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5286 'channel': 'Interstellar Movie',
5288 'modified_date': r
're:\d{8}',
5289 'availability': 'public',
5291 'playlist_mincount': 21,
5293 'note': 'Playlist with "show unavailable videos" button',
5294 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5296 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5297 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5298 'uploader': 'Phim Siêu Nhân Nhật Bản',
5299 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5301 'channel': 'Phim Siêu Nhân Nhật Bản',
5303 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5305 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5306 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5307 'modified_date': r
're:\d{8}',
5308 'availability': 'public',
5310 'playlist_mincount': 200,
5311 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5313 'note': 'Playlist with unavailable videos in page 7',
5314 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5316 'title': 'Uploads from BlankTV',
5317 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5318 'uploader': 'BlankTV',
5319 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5320 'channel': 'BlankTV',
5321 'channel_url': 'https://www.youtube.com/c/blanktv',
5322 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5325 'uploader_url': 'https://www.youtube.com/c/blanktv',
5326 'modified_date': r
're:\d{8}',
5328 'availability': 'public',
5330 'playlist_mincount': 1000,
5331 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5333 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5334 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5336 'title': 'Data Analysis with Dr Mike Pound',
5337 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5338 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5339 'uploader': 'Computerphile',
5340 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5341 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5344 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5345 'channel_url': 'https://www.youtube.com/user/Computerphile',
5346 'channel': 'Computerphile',
5347 'availability': 'public',
5348 'modified_date': '20190712',
5350 'playlist_mincount': 11,
5352 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5353 'only_matching': True,
5355 'note': 'Playlist URL that does not actually serve a playlist',
5356 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5358 'id': 'FqZTN594JQw',
5360 'title': "Smiley's People 01 detective, Adventure Series, Action",
5361 'uploader': 'STREEM',
5362 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5363 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5364 'upload_date': '20150526',
5365 'license': 'Standard YouTube License',
5366 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5367 'categories': ['People & Blogs'],
5373 'skip_download': True,
5375 'skip': 'This video is not available.',
5376 'add_ie': [YoutubeIE
.ie_key()],
5378 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5379 'only_matching': True,
5381 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5382 'only_matching': True,
5384 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5386 'id': 'Wq15eF5vCbI', # This will keep changing
5389 'uploader': 'Sky News',
5390 'uploader_id': 'skynews',
5391 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5392 'upload_date': r
're:\d{8}',
5394 'categories': ['News & Politics'],
5397 'release_timestamp': int,
5398 'channel': 'Sky News',
5399 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5402 'thumbnail': r
're:https?://i\.ytimg\.com/vi/[^/]+/maxresdefault(?:_live)?\.jpg',
5403 'playable_in_embed': True,
5404 'release_date': r
're:\d+',
5405 'availability': 'public',
5406 'live_status': 'is_live',
5407 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5408 'channel_follower_count': int,
5409 'concurrent_view_count': int,
5412 'skip_download': True,
5414 'expected_warnings': ['Ignoring subtitle tracks found in '],
5416 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5418 'id': 'a48o2S1cPoo',
5420 'title': 'The Young Turks - Live Main Show',
5421 'uploader': 'The Young Turks',
5422 'uploader_id': 'TheYoungTurks',
5423 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5424 'upload_date': '20150715',
5425 'license': 'Standard YouTube License',
5426 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5427 'categories': ['News & Politics'],
5428 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5432 'skip_download': True,
5434 'only_matching': True,
5436 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5437 'only_matching': True,
5439 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5440 'only_matching': True,
5442 'note': 'A channel that is not live. Should raise error',
5443 'url': 'https://www.youtube.com/user/numberphile/live',
5444 'only_matching': True,
5446 'url': 'https://www.youtube.com/feed/trending',
5447 'only_matching': True,
5449 'url': 'https://www.youtube.com/feed/library',
5450 'only_matching': True,
5452 'url': 'https://www.youtube.com/feed/history',
5453 'only_matching': True,
5455 'url': 'https://www.youtube.com/feed/subscriptions',
5456 'only_matching': True,
5458 'url': 'https://www.youtube.com/feed/watch_later',
5459 'only_matching': True,
5461 'note': 'Recommended - redirects to home page.',
5462 'url': 'https://www.youtube.com/feed/recommended',
5463 'only_matching': True,
5465 'note': 'inline playlist with not always working continuations',
5466 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5467 'only_matching': True,
5469 'url': 'https://www.youtube.com/course',
5470 'only_matching': True,
5472 'url': 'https://www.youtube.com/zsecurity',
5473 'only_matching': True,
5475 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5476 'only_matching': True,
5478 'url': 'https://www.youtube.com/TheYoungTurks/live',
5479 'only_matching': True,
5481 'url': 'https://www.youtube.com/hashtag/cctv9',
5487 'playlist_mincount': 350,
5489 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5490 'only_matching': True,
5492 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5493 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5494 'only_matching': True
5496 'note': '/browse/ should redirect to /channel/',
5497 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5498 'only_matching': True
5500 'note': 'VLPL, should redirect to playlist?list=PL...',
5501 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5503 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5504 'uploader': 'NoCopyrightSounds',
5505 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5506 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5507 'title': 'NCS : All Releases 💿',
5508 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5509 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5510 'modified_date': r
're:\d{8}',
5512 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5514 'channel': 'NoCopyrightSounds',
5515 'availability': 'public',
5517 'playlist_mincount': 166,
5518 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5520 'note': 'Topic, should redirect to playlist?list=UU...',
5521 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5523 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5524 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5525 'title': 'Uploads from Royalty Free Music - Topic',
5526 'uploader': 'Royalty Free Music - Topic',
5528 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5529 'channel': 'Royalty Free Music - Topic',
5531 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5532 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5533 'modified_date': r
're:\d{8}',
5534 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5536 'availability': 'public',
5538 'expected_warnings': [
5539 'The URL does not have a videos tab',
5540 r
'[Uu]navailable videos (are|will be) hidden',
5542 'playlist_mincount': 101,
5544 # Destination channel with only a hidden self tab (tab id is UCtFRv9O2AHqOZjjynzrv-xg)
5545 # Treat as a general feed
5546 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5548 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5549 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5552 'playlist_mincount': 9,
5554 'note': 'Youtube music Album',
5555 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5557 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5558 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5562 'availability': 'unlisted',
5563 'modified_date': r
're:\d{8}',
5565 'playlist_count': 50,
5567 'note': 'unlisted single video playlist',
5568 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5570 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5571 'uploader': 'colethedj',
5572 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5573 'title': 'yt-dlp unlisted playlist test',
5574 'availability': 'unlisted',
5576 'modified_date': '20220418',
5577 'channel': 'colethedj',
5580 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5581 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5582 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5584 'playlist_count': 1,
5586 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5587 'url': 'https://www.youtube.com/feed/recommended',
5589 'id': 'recommended',
5590 'title': 'recommended',
5593 'playlist_mincount': 50,
5595 'skip_download': True,
5596 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5599 'note': 'API Fallback: /videos tab, sorted by oldest first',
5600 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5602 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5603 'title': 'Cody\'sLab - Videos',
5604 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5605 'uploader': 'Cody\'sLab',
5606 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5607 'channel': 'Cody\'sLab',
5608 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5610 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5611 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5612 'channel_follower_count': int
5614 'playlist_mincount': 650,
5616 'skip_download': True,
5617 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5619 'skip': 'Query for sorting no longer works',
5621 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5622 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5624 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5625 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5626 'title': 'Uploads from Royalty Free Music - Topic',
5627 'uploader': 'Royalty Free Music - Topic',
5628 'modified_date': r
're:\d{8}',
5629 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5631 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5633 'channel': 'Royalty Free Music - Topic',
5635 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5636 'availability': 'public',
5638 'playlist_mincount': 101,
5640 'skip_download': True,
5641 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5644 'note': 'non-standard redirect to regional channel',
5645 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5646 'only_matching': True
5648 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5649 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5651 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5652 'modified_date': '20220407',
5653 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5655 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5656 'uploader': 'pukkandan',
5657 'availability': 'unlisted',
5658 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5659 'channel': 'pukkandan',
5660 'description': 'Test for collaborative playlist',
5661 'title': 'yt-dlp test - collaborative playlist',
5663 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5665 'playlist_mincount': 2
5667 'note': 'translated tab name',
5668 'url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA/playlists',
5670 'id': 'UCiu-3thuViMebBjw_5nWYrA',
5672 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5673 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5675 'title': 'cole-dlp-test-acc - 再生リスト',
5676 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5677 'uploader': 'cole-dlp-test-acc',
5678 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5679 'channel': 'cole-dlp-test-acc',
5680 'channel_follower_count': int,
5682 'playlist_mincount': 1,
5683 'params': {'extractor_args': {'youtube': {'lang': ['ja']}
}},
5684 'expected_warnings': ['Preferring "ja"'],
5686 # XXX: this should really check flat playlist entries, but the test suite doesn't support that
5687 'note': 'preferred lang set with playlist with translated video titles',
5688 'url': 'https://www.youtube.com/playlist?list=PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5690 'id': 'PLt5yu3-wZAlQAaPZ5Z-rJoTdbT-45Q7c0',
5693 'channel_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5694 'uploader': 'cole-dlp-test-acc',
5695 'uploader_id': 'UCiu-3thuViMebBjw_5nWYrA',
5696 'channel': 'cole-dlp-test-acc',
5697 'channel_id': 'UCiu-3thuViMebBjw_5nWYrA',
5698 'description': 'test',
5699 'uploader_url': 'https://www.youtube.com/channel/UCiu-3thuViMebBjw_5nWYrA',
5700 'title': 'dlp test playlist',
5701 'availability': 'public',
5703 'playlist_mincount': 1,
5704 'params': {'extractor_args': {'youtube': {'lang': ['ja']}
}},
5705 'expected_warnings': ['Preferring "ja"'],
5707 # shorts audio pivot for 2GtVksBMYFM.
5708 'url': 'https://www.youtube.com/feed/sfv_audio_pivot?bp=8gUrCikSJwoLMkd0VmtzQk1ZRk0SCzJHdFZrc0JNWUZNGgsyR3RWa3NCTVlGTQ==',
5710 'id': 'sfv_audio_pivot',
5711 'title': 'sfv_audio_pivot',
5714 'playlist_mincount': 50,
5717 # Channel with a real live tab (not to be mistaken with streams tab)
5718 # Do not treat like it should redirect to live stream
5719 'url': 'https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live',
5721 'id': 'UCEH7P7kyJIkS_gJf93VYbmg',
5722 'title': 'UCEH7P7kyJIkS_gJf93VYbmg - Live',
5725 'playlist_mincount': 20,
5727 # Tab name is not the same as tab id
5728 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/letsplay',
5730 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5731 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Let\'s play',
5734 'playlist_mincount': 8,
5736 # Home tab id is literally home. Not to get mistaken with featured
5737 'url': 'https://www.youtube.com/channel/UCQvWX73GQygcwXOTSf_VDVg/home',
5739 'id': 'UCQvWX73GQygcwXOTSf_VDVg',
5740 'title': 'UCQvWX73GQygcwXOTSf_VDVg - Home',
5743 'playlist_mincount': 8,
5745 # Should get three playlists for videos, shorts and streams tabs
5746 'url': 'https://www.youtube.com/channel/UCK9V2B22uJYu3N7eR_BT9QA',
5748 'id': 'UCK9V2B22uJYu3N7eR_BT9QA',
5749 'title': 'Uploads for UCK9V2B22uJYu3N7eR_BT9QA'
5751 'playlist_count': 3,
5753 # Shorts tab with channel with handle
5754 'url': 'https://www.youtube.com/@NotJustBikes/shorts',
5756 'id': 'UC0intLFzLaudFG-xAvUEO-A',
5757 'title': 'Not Just Bikes - Shorts',
5759 'uploader': 'Not Just Bikes',
5760 'channel_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5761 'description': 'md5:7513148b1f02b924783157d84c4ea555',
5762 'channel_follower_count': int,
5763 'uploader_id': 'UC0intLFzLaudFG-xAvUEO-A',
5764 'channel_id': 'UC0intLFzLaudFG-xAvUEO-A',
5765 'uploader_url': 'https://www.youtube.com/channel/UC0intLFzLaudFG-xAvUEO-A',
5766 'channel': 'Not Just Bikes',
5768 'playlist_mincount': 10,
5771 'url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig/streams',
5773 'id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5774 'title': '中村悠一 - Live',
5776 'channel_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5777 'channel_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5778 'uploader_id': 'UC3eYAvjCVwNHgkaGbXX3sig',
5780 'uploader_url': 'https://www.youtube.com/channel/UC3eYAvjCVwNHgkaGbXX3sig',
5781 'channel_follower_count': int,
5783 'description': 'md5:e744f6c93dafa7a03c0c6deecb157300',
5785 'playlist_mincount': 60,
5787 # Channel with no uploads and hence no videos, streams, shorts tabs or uploads playlist. This should fail.
5788 # See test_youtube_lists
5789 'url': 'https://www.youtube.com/channel/UC2yXPzFejc422buOIzn_0CA',
5790 'only_matching': True,
5792 # No uploads and no UCID given. Should fail with no uploads error
5793 # See test_youtube_lists
5794 'url': 'https://www.youtube.com/news',
5795 'only_matching': True
5797 # No videos tab but has a shorts tab
5798 'url': 'https://www.youtube.com/c/TKFShorts',
5800 'id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5801 'title': 'Shorts Break - Shorts',
5803 'channel_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5804 'channel': 'Shorts Break',
5805 'description': 'md5:a6c234cf3d50d878ef8721e34457cd11',
5806 'uploader': 'Shorts Break',
5807 'channel_follower_count': int,
5808 'uploader_id': 'UCgJ5_1F6yJhYLnyMszUdmUg',
5809 'uploader_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5810 'channel_url': 'https://www.youtube.com/channel/UCgJ5_1F6yJhYLnyMszUdmUg',
5812 'playlist_mincount': 30,
5814 # Trending Now Tab. tab id is empty
5815 'url': 'https://www.youtube.com/feed/trending',
5818 'title': 'trending - Now',
5821 'playlist_mincount': 30,
5823 # Trending Gaming Tab. tab id is empty
5824 'url': 'https://www.youtube.com/feed/trending?bp=4gIcGhpnYW1pbmdfY29ycHVzX21vc3RfcG9wdWxhcg%3D%3D',
5827 'title': 'trending - Gaming',
5830 'playlist_mincount': 30,
5834 def suitable(cls
, url
):
5835 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5837 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/[^?#/]+))?(?P<post>.*)$')
5839 def _get_url_mobj(self
, url
):
5840 mobj
= self
._URL
_RE
.match(url
).groupdict()
5841 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5844 def _extract_tab_id_and_name(self
, tab
, base_url
='https://www.youtube.com'):
5845 tab_name
= (tab
.get('title') or '').lower()
5846 tab_url
= urljoin(base_url
, traverse_obj(
5847 tab
, ('endpoint', 'commandMetadata', 'webCommandMetadata', 'url')))
5849 tab_id
= (traverse_obj(tab
, 'tabIdentifier', expected_type
=str)
5850 or tab_url
and self
._get
_url
_mobj
(tab_url
)['tab'][1:])
5852 return tab_id
, tab_name
5854 # Fallback to tab name if we cannot get the tab id.
5855 # XXX: should we strip non-ascii letters? e.g. in case of 'let's play' tab example on special gaming channel
5856 # Note that in the case of translated tab name this may result in an empty string, which we don't want.
5857 self
.write_debug(f
'Falling back to selected tab name: {tab_name}')
5861 }.get(tab_name
, tab_name
), tab_name
5863 def _has_tab(self
, tabs
, tab_id
):
5864 return any(self
._extract
_tab
_id
_and
_name
(tab
)[0] == tab_id
for tab
in tabs
)
5866 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5867 def _real_extract(self
, url
, smuggled_data
):
5868 item_id
= self
._match
_id
(url
)
5869 url
= urllib
.parse
.urlunparse(
5870 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5871 compat_opts
= self
.get_param('compat_opts', [])
5873 mobj
= self
._get
_url
_mobj
(url
)
5874 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'], mobj
['post'], not mobj
['not_channel']
5876 if smuggled_data
.get('is_music_url'):
5877 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5878 item_id
= item_id
[2:]
5879 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5880 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5881 mdata
= self
._extract
_tab
_endpoint
(
5882 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5883 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5884 get_all
=False, expected_type
=str)
5886 raise ExtractorError('Failed to resolve album to playlist')
5887 return self
.url_result(murl
, YoutubeTabIE
)
5888 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5889 pre
= f
'https://www.youtube.com/channel/{item_id}'
5891 original_tab_id
= tab
[1:]
5892 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5895 url
= ''.join((pre
, tab
, post
))
5896 mobj
= self
._get
_url
_mobj
(url
)
5898 # Handle both video/playlist URLs
5900 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5902 if not video_id
and mobj
['not_channel'].startswith('watch'):
5904 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5905 raise ExtractorError('Unable to recognize tab page')
5906 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5907 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5908 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5909 mobj
= self
._get
_url
_mobj
(url
)
5911 if not self
._yes
_playlist
(playlist_id
, video_id
):
5912 return self
.url_result(
5913 f
'https://www.youtube.com/watch?v={video_id}', YoutubeIE
, video_id
)
5915 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5917 # YouTube may provide a non-standard redirect to the regional channel
5918 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5919 # https://support.google.com/youtube/answer/2976814#zippy=,conditional-redirects
5920 redirect_url
= traverse_obj(
5921 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5922 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5923 redirect_url
= ''.join((
5924 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5925 self
.to_screen(f
'This playlist is likely not available in your region. Following conditional redirect to {redirect_url}')
5926 return self
.url_result(redirect_url
, YoutubeTabIE
)
5929 tabs
= self
._extract
_tab
_renderers
(data
)
5930 if is_channel
and tabs
and 'no-youtube-channel-redirect' not in compat_opts
:
5931 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5932 selected_tab_id
, selected_tab_name
= self
._extract
_tab
_id
_and
_name
(selected_tab
, url
) # NB: Name may be translated
5933 self
.write_debug(f
'Selected tab: {selected_tab_id!r} ({selected_tab_name}), Requested tab: {original_tab_id!r}')
5935 if not original_tab_id
and selected_tab_name
:
5936 self
.to_screen('Channel URLs download all uploads of the channel. '
5937 'To download only the videos in a specific tab, pass the tab\'s URL')
5938 if self
._has
_tab
(tabs
, 'streams'):
5939 tab_results
.append(self
.url_result(''.join((pre
, '/streams', post
))))
5940 if self
._has
_tab
(tabs
, 'shorts'):
5941 tab_results
.append(self
.url_result(''.join((pre
, '/shorts', post
))))
5942 # XXX: Members-only tab should also be extracted
5944 if not tab_results
and selected_tab_id
!= 'videos':
5945 # Channel does not have streams, shorts or videos tabs
5946 if item_id
[:2] != 'UC':
5947 raise ExtractorError('This channel has no uploads', expected
=True)
5949 # Topic channels don't have /videos. Use the equivalent playlist instead
5950 pl_id
= f
'UU{item_id[2:]}'
5951 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5953 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5954 except ExtractorError
:
5955 raise ExtractorError('This channel has no uploads', expected
=True)
5957 item_id
, url
= pl_id
, pl_url
5959 f
'The channel does not have a videos, shorts, or live tab. Redirecting to playlist {pl_id} instead')
5961 elif tab_results
and selected_tab_id
!= 'videos':
5962 # When there are shorts/live tabs but not videos tab
5963 url
, data
= ''.join((pre
, post
)), None
5965 elif (original_tab_id
or 'videos') != selected_tab_id
:
5966 if original_tab_id
== 'live':
5967 # Live tab should have redirected to the video
5968 # Except in the case the channel has an actual live tab
5969 # Example: https://www.youtube.com/channel/UCEH7P7kyJIkS_gJf93VYbmg/live
5970 raise UserNotLive(video_id
=mobj
['id'])
5971 elif selected_tab_name
:
5972 raise ExtractorError(f
'This channel does not have a {original_tab_id} tab', expected
=True)
5974 # For channels such as https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg
5975 url
= f
'{pre}{post}'
5977 self
.write_debug(f
'Final URL: {url}')
5979 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5980 if 'no-youtube-unavailable-videos' not in compat_opts
:
5981 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5982 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5984 tabs
= self
._extract
_tab
_renderers
(data
)
5986 tab_results
[:0] = [self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)]
5987 tab_results
[0].update({
5988 'extractor_key': YoutubeTabIE
.ie_key(),
5989 'extractor': YoutubeTabIE
.IE_NAME
,
5993 if len(tab_results
) == 1:
5994 return tab_results
[0]
5995 elif len(tab_results
) > 1:
5996 return self
.playlist_result(tab_results
, item_id
, title
=f
'Uploads for {item_id}')
5998 playlist
= traverse_obj(
5999 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
6001 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
6003 video_id
= traverse_obj(
6004 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
6006 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
6007 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
6008 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}', YoutubeIE
, video_id
)
6010 raise ExtractorError('Unable to recognize tab page')
6013 class YoutubePlaylistIE(InfoExtractor
):
6014 IE_DESC
= 'YouTube playlists'
6015 _VALID_URL
= r
'''(?x)(?:
6020 youtube(?:kids)?\.com|
6025 (?P<id>%(playlist_id)s)
6027 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
6028 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
6030 IE_NAME
= 'youtube:playlist'
6032 'note': 'issue #673',
6033 'url': 'PLBB231211A4F62143',
6035 'title': '[OLD]Team Fortress 2 (Class-based LP)',
6036 'id': 'PLBB231211A4F62143',
6037 'uploader': 'Wickman',
6038 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6039 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
6041 'uploader_url': 'https://www.youtube.com/c/WickmanVT',
6042 'modified_date': r
're:\d{8}',
6043 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
6044 'channel': 'Wickman',
6046 'channel_url': 'https://www.youtube.com/c/WickmanVT',
6047 'availability': 'public',
6049 'playlist_mincount': 29,
6051 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6053 'title': 'YDL_safe_search',
6054 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
6056 'playlist_count': 2,
6057 'skip': 'This playlist is private',
6060 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6061 'playlist_count': 4,
6064 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
6065 'uploader': 'milan',
6066 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6068 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6070 'modified_date': '20140919',
6073 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
6074 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
6075 'availability': 'public',
6077 'expected_warnings': [r
'[Uu]navailable videos? (is|are|will be) hidden'],
6079 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6080 'playlist_mincount': 455,
6082 'title': '2018 Chinese New Singles (11/6 updated)',
6083 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
6085 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6086 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
6089 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
6091 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
6092 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
6093 'modified_date': r
're:\d{8}',
6094 'availability': 'public',
6096 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
6098 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
6099 'only_matching': True,
6101 # music album playlist
6102 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
6103 'only_matching': True,
6107 def suitable(cls
, url
):
6108 if YoutubeTabIE
.suitable(url
):
6110 from ..utils
import parse_qs
6112 if qs
.get('v', [None])[0]:
6114 return super().suitable(url
)
6116 def _real_extract(self
, url
):
6117 playlist_id
= self
._match
_id
(url
)
6118 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
6119 url
= update_url_query(
6120 'https://www.youtube.com/playlist',
6121 parse_qs(url
) or {'list': playlist_id}
)
6123 url
= smuggle_url(url
, {'is_music_url': True}
)
6124 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
6127 class YoutubeYtBeIE(InfoExtractor
):
6128 IE_DESC
= 'youtu.be'
6129 _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}
6131 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
6133 'id': 'yeWKywCrFtk',
6135 'title': 'Small Scale Baler and Braiding Rugs',
6136 'uploader': 'Backus-Page House Museum',
6137 'uploader_id': 'backuspagemuseum',
6138 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
6139 'upload_date': '20161008',
6140 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
6141 'categories': ['Nonprofits & Activism'],
6145 'playable_in_embed': True,
6146 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
6147 'channel': 'Backus-Page House Museum',
6148 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
6149 'live_status': 'not_live',
6151 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
6152 'availability': 'public',
6154 'comment_count': int,
6155 'channel_follower_count': int
6159 'skip_download': True,
6162 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
6163 'only_matching': True,
6166 def _real_extract(self
, url
):
6167 mobj
= self
._match
_valid
_url
(url
)
6168 video_id
= mobj
.group('id')
6169 playlist_id
= mobj
.group('playlist_id')
6170 return self
.url_result(
6171 update_url_query('https://www.youtube.com/watch', {
6173 'list': playlist_id
,
6174 'feature': 'youtu.be',
6175 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
6178 class YoutubeLivestreamEmbedIE(InfoExtractor
):
6179 IE_DESC
= 'YouTube livestream embeds'
6180 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
6182 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
6183 'only_matching': True,
6186 def _real_extract(self
, url
):
6187 channel_id
= self
._match
_id
(url
)
6188 return self
.url_result(
6189 f
'https://www.youtube.com/channel/{channel_id}/live',
6190 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
6193 class YoutubeYtUserIE(InfoExtractor
):
6194 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
6195 IE_NAME
= 'youtube:user'
6196 _VALID_URL
= r
'ytuser:(?P<id>.+)'
6198 'url': 'ytuser:phihag',
6199 'only_matching': True,
6202 def _real_extract(self
, url
):
6203 user_id
= self
._match
_id
(url
)
6204 return self
.url_result(
6205 'https://www.youtube.com/user/%s/videos' % user_id
,
6206 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
6209 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
6210 IE_NAME
= 'youtube:favorites'
6211 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
6212 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
6213 _LOGIN_REQUIRED
= True
6216 'only_matching': True,
6218 'url': ':ytfavorites',
6219 'only_matching': True,
6222 def _real_extract(self
, url
):
6223 return self
.url_result(
6224 'https://www.youtube.com/playlist?list=LL',
6225 ie
=YoutubeTabIE
.ie_key())
6228 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
6229 IE_NAME
= 'youtube:notif'
6230 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
6231 _VALID_URL
= r
':ytnotif(?:ication)?s?'
6232 _LOGIN_REQUIRED
= True
6235 'only_matching': True,
6237 'url': ':ytnotifications',
6238 'only_matching': True,
6241 def _extract_notification_menu(self
, response
, continuation_list
):
6242 notification_list
= traverse_obj(
6244 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
6245 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
6246 expected_type
=list) or []
6247 continuation_list
[0] = None
6248 for item
in notification_list
:
6249 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
6252 continuation
= item
.get('continuationItemRenderer')
6254 continuation_list
[0] = continuation
6256 def _extract_notification_renderer(self
, notification
):
6257 video_id
= traverse_obj(
6258 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
6259 url
= f
'https://www.youtube.com/watch?v={video_id}'
6262 browse_ep
= traverse_obj(
6263 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
6264 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
6265 post_id
= self
._search
_regex
(
6266 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
6267 'post id', default
=None)
6268 if not channel_id
or not post_id
:
6270 # The direct /post url redirects to this in the browser
6271 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
6273 channel
= traverse_obj(
6274 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
6276 notification_title
= self
._get
_text
(notification
, 'shortMessage')
6277 if notification_title
:
6278 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
6279 # TODO: handle recommended videos
6280 title
= self
._search
_regex
(
6281 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
6282 'video title', default
=None)
6283 timestamp
= (self
._parse
_time
_text
(self
._get
_text
(notification
, 'sentTimeText'))
6284 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
)
6289 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
6290 'video_id': video_id
,
6292 'channel_id': channel_id
,
6294 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
6295 'timestamp': timestamp
,
6298 def _notification_menu_entries(self
, ytcfg
):
6299 continuation_list
= [None]
6301 for page
in itertools
.count(1):
6302 ctoken
= traverse_obj(
6303 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
6304 response
= self
._extract
_response
(
6305 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
6306 ep
='notification/get_notification_menu', check_get_keys
='actions',
6307 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
6308 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
6309 if not continuation_list
[0]:
6312 def _real_extract(self
, url
):
6313 display_id
= 'notifications'
6314 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
6315 self
._report
_playlist
_authcheck
(ytcfg
)
6316 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
6319 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
6320 IE_DESC
= 'YouTube search'
6321 IE_NAME
= 'youtube:search'
6322 _SEARCH_KEY
= 'ytsearch'
6323 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
6325 'url': 'ytsearch5:youtube-dl test video',
6326 'playlist_count': 5,
6328 'id': 'youtube-dl test video',
6329 'title': 'youtube-dl test video',
6334 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
6335 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
6336 _SEARCH_KEY
= 'ytsearchdate'
6337 IE_DESC
= 'YouTube search, newest videos first'
6338 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
6340 'url': 'ytsearchdate5:youtube-dl test video',
6341 'playlist_count': 5,
6343 'id': 'youtube-dl test video',
6344 'title': 'youtube-dl test video',
6349 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
6350 IE_DESC
= 'YouTube search URLs with sorting and filter support'
6351 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
6352 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6354 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
6355 'playlist_mincount': 5,
6357 'id': 'youtube-dl test video',
6358 'title': 'youtube-dl test video',
6361 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
6362 'playlist_mincount': 5,
6368 'url': 'https://www.youtube.com/results?search_query=%23cats',
6369 'playlist_mincount': 1,
6373 # The test suite does not have support for nested playlists
6375 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
6380 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
6381 'only_matching': True,
6384 def _real_extract(self
, url
):
6386 query
= (qs
.get('search_query') or qs
.get('q'))[0]
6387 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
6390 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
6391 IE_DESC
= 'YouTube music search URLs with selectable sections, e.g. #songs'
6392 IE_NAME
= 'youtube:music:search_url'
6393 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
6395 'url': 'https://music.youtube.com/search?q=royalty+free+music',
6396 'playlist_count': 16,
6398 'id': 'royalty free music',
6399 'title': 'royalty free music',
6402 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
6403 'playlist_mincount': 30,
6405 'id': 'royalty free music - songs',
6406 'title': 'royalty free music - songs',
6408 'params': {'extract_flat': 'in_playlist'}
6410 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
6411 'playlist_mincount': 30,
6413 'id': 'royalty free music - community playlists',
6414 'title': 'royalty free music - community playlists',
6416 'params': {'extract_flat': 'in_playlist'}
6420 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
6421 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
6422 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
6423 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
6424 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
6425 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
6428 def _real_extract(self
, url
):
6430 query
= (qs
.get('search_query') or qs
.get('q'))[0]
6431 params
= qs
.get('sp', (None,))[0]
6433 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
6435 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
6436 params
= self
._SECTIONS
.get(section
)
6439 title
= join_nonempty(query
, section
, delim
=' - ')
6440 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
6443 class YoutubeFeedsInfoExtractor(InfoExtractor
):
6445 Base class for feed extractors
6446 Subclasses must re-define the _FEED_NAME property.
6448 _LOGIN_REQUIRED
= True
6449 _FEED_NAME
= 'feeds'
6451 def _real_initialize(self
):
6452 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
6456 return f
'youtube:{self._FEED_NAME}'
6458 def _real_extract(self
, url
):
6459 return self
.url_result(
6460 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
6463 class YoutubeWatchLaterIE(InfoExtractor
):
6464 IE_NAME
= 'youtube:watchlater'
6465 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6466 _VALID_URL
= r
':ytwatchlater'
6468 'url': ':ytwatchlater',
6469 'only_matching': True,
6472 def _real_extract(self
, url
):
6473 return self
.url_result(
6474 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
6477 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
6478 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
6479 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6480 _FEED_NAME
= 'recommended'
6481 _LOGIN_REQUIRED
= False
6484 'only_matching': True,
6486 'url': ':ytrecommended',
6487 'only_matching': True,
6489 'url': 'https://youtube.com',
6490 'only_matching': True,
6494 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
6495 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6496 _VALID_URL
= r
':ytsub(?:scription)?s?'
6497 _FEED_NAME
= 'subscriptions'
6500 'only_matching': True,
6502 'url': ':ytsubscriptions',
6503 'only_matching': True,
6507 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
6508 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
6509 _VALID_URL
= r
':ythis(?:tory)?'
6510 _FEED_NAME
= 'history'
6512 'url': ':ythistory',
6513 'only_matching': True,
6517 class YoutubeStoriesIE(InfoExtractor
):
6518 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
6519 IE_NAME
= 'youtube:stories'
6520 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6522 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6523 'only_matching': True,
6526 def _real_extract(self
, url
):
6527 playlist_id
= f
'RLTD{self._match_id(url)}'
6528 return self
.url_result(
6529 smuggle_url(f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}
),
6530 ie
=YoutubeTabIE
, video_id
=playlist_id
)
6533 class YoutubeShortsAudioPivotIE(InfoExtractor
):
6534 IE_DESC
= 'YouTube Shorts audio pivot (Shorts using audio of a given video)'
6535 IE_NAME
= 'youtube:shorts:pivot:audio'
6536 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/source/(?P<id>[\w-]{11})/shorts'
6538 'url': 'https://www.youtube.com/source/Lyj-MZSAA9o/shorts',
6539 'only_matching': True,
6543 def _generate_audio_pivot_params(video_id
):
6545 Generates sfv_audio_pivot browse params for this video id
6547 pb_params
= b
'\xf2\x05+\n)\x12\'\n\x0b%b\x12\x0b%b\x1a\x0b%b' % ((video_id
.encode(),) * 3)
6548 return urllib
.parse
.quote(base64
.b64encode(pb_params
).decode())
6550 def _real_extract(self
, url
):
6551 video_id
= self
._match
_id
(url
)
6552 return self
.url_result(
6553 f
'https://www.youtube.com/feed/sfv_audio_pivot?bp={self._generate_audio_pivot_params(video_id)}',
6557 class YoutubeTruncatedURLIE(InfoExtractor
):
6558 IE_NAME
= 'youtube:truncated_url'
6559 IE_DESC
= False # Do not list
6560 _VALID_URL
= r
'''(?x)
6562 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6565 annotation_id=annotation_[^&]+|
6571 attribution_link\?a=[^&]+
6577 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6578 'only_matching': True,
6580 'url': 'https://www.youtube.com/watch?',
6581 'only_matching': True,
6583 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6584 'only_matching': True,
6586 'url': 'https://www.youtube.com/watch?feature=foo',
6587 'only_matching': True,
6589 'url': 'https://www.youtube.com/watch?hl=en-GB',
6590 'only_matching': True,
6592 'url': 'https://www.youtube.com/watch?t=2372',
6593 'only_matching': True,
6596 def _real_extract(self
, url
):
6597 raise ExtractorError(
6598 'Did you forget to quote the URL? Remember that & is a meta '
6599 'character in most shells, so you want to put the URL in quotes, '
6601 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6602 ' or simply youtube-dl BaW_jenozKc .',
6606 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6607 IE_NAME
= 'youtube:clip'
6608 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6610 # FIXME: Other metadata should be extracted from the clip, not from the base video
6611 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6613 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6615 'section_start': 29.0,
6616 'section_end': 39.7,
6619 'availability': 'public',
6620 'categories': ['Gaming'],
6621 'channel': 'Scott The Woz',
6622 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6623 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6624 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6626 'playable_in_embed': True,
6628 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6629 'title': 'Mobile Games on Console - Scott The Woz',
6630 'upload_date': '20210920',
6631 'uploader': 'Scott The Woz',
6632 'uploader_id': 'scottthewoz',
6633 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6635 'live_status': 'not_live',
6636 'channel_follower_count': int
6640 def _real_extract(self
, url
):
6641 clip_id
= self
._match
_id
(url
)
6642 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6644 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6646 raise ExtractorError('Unable to find video ID')
6648 clip_data
= traverse_obj(data
, (
6649 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6650 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6651 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6652 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6655 '_type': 'url_transparent',
6656 'url': f
'https://www.youtube.com/watch?v={video_id}',
6657 'ie_key': YoutubeIE
.ie_key(),
6659 'section_start': int(clip_data
['startTimeMs']) / 1000,
6660 'section_end': int(clip_data
['endTimeMs']) / 1000,
6664 class YoutubeTruncatedIDIE(InfoExtractor
):
6665 IE_NAME
= 'youtube:truncated_id'
6666 IE_DESC
= False # Do not list
6667 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6670 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6671 'only_matching': True,
6674 def _real_extract(self
, url
):
6675 video_id
= self
._match
_id
(url
)
6676 raise ExtractorError(
6677 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',