19 from .common
import InfoExtractor
, SearchInfoExtractor
20 from ..compat
import functools
21 from ..jsinterp
import JSInterpreter
66 # any clients starting with _ cannot be explicitly requested by the user
69 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
70 'INNERTUBE_CONTEXT': {
73 'clientVersion': '2.20211221.00.00',
76 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
82 'clientName': 'WEB_EMBEDDED_PLAYER',
83 'clientVersion': '1.20211215.00.01',
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
89 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
90 'INNERTUBE_HOST': 'music.youtube.com',
91 'INNERTUBE_CONTEXT': {
93 'clientName': 'WEB_REMIX',
94 'clientVersion': '1.20211213.00.00',
97 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
100 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
101 'INNERTUBE_CONTEXT': {
103 'clientName': 'WEB_CREATOR',
104 'clientVersion': '1.20211220.02.00',
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
110 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
111 'INNERTUBE_CONTEXT': {
113 'clientName': 'ANDROID',
114 'clientVersion': '16.49',
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
118 'REQUIRE_JS_PLAYER': False
120 'android_embedded': {
121 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
122 'INNERTUBE_CONTEXT': {
124 'clientName': 'ANDROID_EMBEDDED_PLAYER',
125 'clientVersion': '16.49',
128 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
129 'REQUIRE_JS_PLAYER': False
132 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
133 'INNERTUBE_CONTEXT': {
135 'clientName': 'ANDROID_MUSIC',
136 'clientVersion': '4.57',
139 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
140 'REQUIRE_JS_PLAYER': False
143 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
144 'INNERTUBE_CONTEXT': {
146 'clientName': 'ANDROID_CREATOR',
147 'clientVersion': '21.47',
150 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
151 'REQUIRE_JS_PLAYER': False
153 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
154 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
156 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
157 'INNERTUBE_CONTEXT': {
160 'clientVersion': '16.46',
161 'deviceModel': 'iPhone14,3',
164 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
165 'REQUIRE_JS_PLAYER': False
168 'INNERTUBE_CONTEXT': {
170 'clientName': 'IOS_MESSAGES_EXTENSION',
171 'clientVersion': '16.46',
172 'deviceModel': 'iPhone14,3',
175 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
176 'REQUIRE_JS_PLAYER': False
179 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
180 'INNERTUBE_CONTEXT': {
182 'clientName': 'IOS_MUSIC',
183 'clientVersion': '4.57',
186 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
187 'REQUIRE_JS_PLAYER': False
190 'INNERTUBE_CONTEXT': {
192 'clientName': 'IOS_CREATOR',
193 'clientVersion': '21.47',
196 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
197 'REQUIRE_JS_PLAYER': False
199 # mweb has 'ultralow' formats
200 # See: https://github.com/yt-dlp/yt-dlp/pull/557
202 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
203 'INNERTUBE_CONTEXT': {
205 'clientName': 'MWEB',
206 'clientVersion': '2.20211221.01.00',
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
211 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
212 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
215 'INNERTUBE_CONTEXT': {
217 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
218 'clientVersion': '2.0',
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
226 def _split_innertube_client(client_name
):
227 variant
, *base
= client_name
.rsplit('.', 1)
229 return variant
, base
[0], variant
230 base
, *variant
= client_name
.split('_', 1)
231 return client_name
, base
, variant
[0] if variant
else None
234 def build_innertube_clients():
236 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
238 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
239 priority
= qualities(BASE_CLIENTS
[::-1])
241 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
242 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
243 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
244 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
245 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
247 _
, base_client
, variant
= _split_innertube_client(client
)
248 ytcfg
['priority'] = 10 * priority(base_client
)
251 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
252 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
253 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
254 embedscreen
['priority'] -= 3
255 elif variant
== 'embedded':
256 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
257 ytcfg
['priority'] -= 2
259 ytcfg
['priority'] -= 3
262 build_innertube_clients()
265 class YoutubeBaseInfoExtractor(InfoExtractor
):
266 """Provide base functions for Youtube extractors"""
269 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
270 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
271 r
'browse|oembed|get_video_info|iframe_api|s/player|'
272 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
274 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
276 # _NETRC_MACHINE = 'youtube'
278 # If True it will raise an error if no login info is provided
279 _LOGIN_REQUIRED
= False
282 # invidious-redirect websites
283 r
'(?:www\.)?redirect\.invidious\.io',
284 r
'(?:(?:www|dev)\.)?invidio\.us',
285 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
286 r
'(?:www\.)?invidious\.pussthecat\.org',
287 r
'(?:www\.)?invidious\.zee\.li',
288 r
'(?:www\.)?invidious\.ethibox\.fr',
289 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
290 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
291 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
292 # youtube-dl invidious instances list
293 r
'(?:(?:www|no)\.)?invidiou\.sh',
294 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
295 r
'(?:www\.)?invidious\.kabi\.tk',
296 r
'(?:www\.)?invidious\.mastodon\.host',
297 r
'(?:www\.)?invidious\.zapashcanon\.fr',
298 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
299 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
300 r
'(?:www\.)?invidious\.himiko\.cloud',
301 r
'(?:www\.)?invidious\.reallyancient\.tech',
302 r
'(?:www\.)?invidious\.tube',
303 r
'(?:www\.)?invidiou\.site',
304 r
'(?:www\.)?invidious\.site',
305 r
'(?:www\.)?invidious\.xyz',
306 r
'(?:www\.)?invidious\.nixnet\.xyz',
307 r
'(?:www\.)?invidious\.048596\.xyz',
308 r
'(?:www\.)?invidious\.drycat\.fr',
309 r
'(?:www\.)?inv\.skyn3t\.in',
310 r
'(?:www\.)?tube\.poal\.co',
311 r
'(?:www\.)?tube\.connect\.cafe',
312 r
'(?:www\.)?vid\.wxzm\.sx',
313 r
'(?:www\.)?vid\.mint\.lgbt',
314 r
'(?:www\.)?vid\.puffyan\.us',
315 r
'(?:www\.)?yewtu\.be',
316 r
'(?:www\.)?yt\.elukerio\.org',
317 r
'(?:www\.)?yt\.lelux\.fi',
318 r
'(?:www\.)?invidious\.ggc-project\.de',
319 r
'(?:www\.)?yt\.maisputain\.ovh',
320 r
'(?:www\.)?ytprivate\.com',
321 r
'(?:www\.)?invidious\.13ad\.de',
322 r
'(?:www\.)?invidious\.toot\.koeln',
323 r
'(?:www\.)?invidious\.fdn\.fr',
324 r
'(?:www\.)?watch\.nettohikari\.com',
325 r
'(?:www\.)?invidious\.namazso\.eu',
326 r
'(?:www\.)?invidious\.silkky\.cloud',
327 r
'(?:www\.)?invidious\.exonip\.de',
328 r
'(?:www\.)?invidious\.riverside\.rocks',
329 r
'(?:www\.)?invidious\.blamefran\.net',
330 r
'(?:www\.)?invidious\.moomoo\.de',
331 r
'(?:www\.)?ytb\.trom\.tf',
332 r
'(?:www\.)?yt\.cyberhost\.uk',
333 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
334 r
'(?:www\.)?qklhadlycap4cnod\.onion',
335 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
336 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
337 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
338 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
339 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
340 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
341 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
342 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
343 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
344 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
345 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
346 r
'(?:www\.)?piped\.kavin\.rocks',
347 r
'(?:www\.)?piped\.silkky\.cloud',
348 r
'(?:www\.)?piped\.tokhmi\.xyz',
349 r
'(?:www\.)?piped\.moomoo\.me',
351 r
'(?:www\.)?piped\.syncpundit\.com',
352 r
'(?:www\.)?piped\.mha\.fi',
353 r
'(?:www\.)?piped\.mint\.lgbt',
354 r
'(?:www\.)?piped\.privacy\.com\.de',
357 def _initialize_consent(self
):
358 cookies
= self
._get
_cookies
('https://www.youtube.com/')
359 if cookies
.get('__Secure-3PSID'):
362 consent
= cookies
.get('CONSENT')
364 if 'YES' in consent
.value
:
366 consent_id
= self
._search
_regex
(
367 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
369 consent_id
= random
.randint(100, 999)
370 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
372 def _initialize_pref(self
):
373 cookies
= self
._get
_cookies
('https://www.youtube.com/')
374 pref_cookie
= cookies
.get('PREF')
378 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
380 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
381 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
382 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
384 def _real_initialize(self
):
385 self
._initialize
_pref
()
386 self
._initialize
_consent
()
387 self
._check
_login
_required
()
389 def _check_login_required(self
):
390 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
391 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
393 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
394 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
396 def _get_default_ytcfg(self, client='web'):
397 return copy.deepcopy(INNERTUBE_CLIENTS[client])
399 def _get_innertube_host(self, client='web'):
400 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
402 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
403 # try_get but with fallback to default ytcfg client values when present
404 _func = lambda y: try_get(y, getter, expected_type)
405 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
407 def _extract_client_name(self, ytcfg, default_client='web'):
408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
412 def _extract_client_version(self, ytcfg, default_client='web'):
413 return self._ytcfg_get_safe(
414 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
415 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
417 def _select_api_hostname(self, req_api_hostname, default_client=None):
418 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
419 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
421 def _extract_api_key(self, ytcfg=None, default_client='web'):
422 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
424 def _extract_context(self, ytcfg=None, default_client='web'):
426 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
427 # Enforce language and tz for extraction
428 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
429 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
434 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
435 time_now = round(time.time())
436 if self._SAPISID is None:
437 yt_cookies = self._get_cookies('https://www.youtube.com')
438 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
439 # See: https://github.com/yt-dlp/yt-dlp/issues/393
440 sapisid_cookie = dict_get(
441 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
442 if sapisid_cookie and sapisid_cookie.value:
443 self._SAPISID = sapisid_cookie.value
444 self.write_debug('Extracted SAPISID cookie')
445 # SAPISID cookie is required if not already present
446 if not yt_cookies.get('SAPISID'):
447 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
449 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
451 self._SAPISID = False
452 if not self._SAPISID:
454 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
455 sapisidhash = hashlib.sha1(
456 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
457 return f'SAPISIDHASH {time_now}_{sapisidhash}'
459 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
460 note='Downloading API JSON', errnote='Unable to download API page',
461 context=None, api_key=None, api_hostname=None, default_client='web'):
463 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
465 real_headers = self.generate_api_headers(default_client=default_client)
466 real_headers.update({'content-type': 'application/json'})
468 real_headers.update(headers)
469 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
470 or api_key or self._extract_api_key(default_client=default_client))
471 return self._download_json(
472 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
473 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
474 data=json.dumps(data).encode('utf8'), headers=real_headers,
475 query={'key': api_key, 'prettyPrint': 'false'})
477 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
478 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
481 def _extract_session_index(*data):
483 Index of current account in account list.
484 See: https://github.com/yt-dlp/yt-dlp/pull/519
487 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
488 if session_index is not None:
492 def _extract_identity_token(self, ytcfg=None, webpage=None):
494 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
498 return self._search_regex(
499 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
500 'identity token
', default=None, fatal=False)
503 def _extract_account_syncid(*args):
505 Extract syncId required to download private playlists of secondary channels
506 @params response and/or ytcfg
509 # ytcfg includes channel_syncid if on secondary channel
510 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
514 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
515 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
516 if len(sync_ids) >= 2 and sync_ids[1]:
517 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
518 # and just "user_syncid||" for primary channel. We only want the channel_syncid
522 def _extract_visitor_data(*args):
524 Extracts visitorData from an API response or ytcfg
525 Appears to be used to track session state
528 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
531 @functools.cached_property
532 def is_authenticated(self):
533 return bool(self._generate_sapisidhash_header())
535 def extract_ytcfg(self, video_id, webpage):
538 return self._parse_json(
540 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
541 default='{}'), video_id, fatal=False) or {}
543 def generate_api_headers(
544 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
545 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
547 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
549 'X-YouTube-Client-Name': str(
550 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
551 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
553 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
554 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
555 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
557 if session_index
is None:
558 session_index
= self
._extract
_session
_index
(ytcfg
)
559 if account_syncid
or session_index
is not None:
560 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
562 auth
= self
._generate
_sapisidhash
_header
(origin
)
564 headers
['Authorization'] = auth
565 headers
['X-Origin'] = origin
566 return {h: v for h, v in headers.items() if v is not None}
568 def _download_ytcfg(self
, client
, video_id
):
570 'web': 'https://www.youtube.com',
571 'web_music': 'https://music.youtube.com',
572 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
576 webpage
= self
._download
_webpage
(
577 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
578 return self
.extract_ytcfg(video_id
, webpage
) or {}
581 def _build_api_continuation_query(continuation
, ctp
=None):
583 'continuation': continuation
585 # TODO: Inconsistency with clickTrackingParams.
586 # Currently we have a fixed ctp contained within context (from ytcfg)
587 # and a ctp in root query for continuation.
589 query
['clickTracking'] = {'clickTrackingParams': ctp}
593 def _extract_next_continuation_data(cls
, renderer
):
594 next_continuation
= try_get(
595 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
596 lambda x
: x
['continuation']['reloadContinuationData']), dict)
597 if not next_continuation
:
599 continuation
= next_continuation
.get('continuation')
602 ctp
= next_continuation
.get('clickTrackingParams')
603 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
606 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
607 if isinstance(continuation_ep
, dict):
608 continuation
= try_get(
609 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
612 ctp
= continuation_ep
.get('clickTrackingParams')
613 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
616 def _extract_continuation(cls
, renderer
):
617 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
618 if next_continuation
:
619 return next_continuation
622 for key
in ('contents', 'items'):
623 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
625 for content
in contents
:
626 if not isinstance(content
, dict):
628 continuation_ep
= try_get(
629 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
630 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
632 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
637 def _extract_alerts(cls
, data
):
638 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
639 if not isinstance(alert_dict
, dict):
641 for alert
in alert_dict
.values():
642 alert_type
= alert
.get('type')
645 message
= cls
._get
_text
(alert
, 'text')
647 yield alert_type
, message
649 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
652 for alert_type
, alert_message
in alerts
:
653 if alert_type
.lower() == 'error' and fatal
:
654 errors
.append([alert_type
, alert_message
])
656 warnings
.append([alert_type
, alert_message
])
658 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
659 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
661 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
663 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
664 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
666 def _extract_badges(self
, renderer
: dict):
668 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
669 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], str)
671 badges
.add(label
.lower())
675 def _get_text(data
, *path_list
, max_runs
=None):
676 for path
in path_list
or [None]:
680 obj
= traverse_obj(data
, path
, default
=[])
681 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
684 text
= try_get(item
, lambda x
: x
['simpleText'], str)
687 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
688 if not runs
and isinstance(item
, list):
691 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
692 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
696 def _get_count(self
, data
, *path_list
):
697 count_text
= self
._get
_text
(data
, *path_list
) or ''
698 count
= parse_count(count_text
)
701 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
705 def _extract_thumbnails(data
, *path_list
):
707 Extract thumbnails from thumbnails dict
708 @param path_list: path list to level that contains 'thumbnails' key
711 for path
in path_list
or [()]:
712 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
713 thumbnail_url
= url_or_none(thumbnail
.get('url'))
714 if not thumbnail_url
:
716 # Sometimes youtube gives a wrong thumbnail URL. See:
717 # https://github.com/yt-dlp/yt-dlp/issues/233
718 # https://github.com/ytdl-org/youtube-dl/issues/28023
719 if 'maxresdefault' in thumbnail_url
:
720 thumbnail_url
= thumbnail_url
.split('?')[0]
722 'url': thumbnail_url
,
723 'height': int_or_none(thumbnail
.get('height')),
724 'width': int_or_none(thumbnail
.get('width')),
729 def extract_relative_time(relative_time_text
):
731 Extracts a relative time from string and converts to dt object
732 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
734 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
)
736 start
= mobj
.group('start')
738 return datetime_from_str(start
)
740 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
744 def _extract_time_text(self
, renderer
, *path_list
):
745 """@returns (timestamp, time_text)"""
746 text
= self
._get
_text
(renderer
, *path_list
) or ''
747 dt
= self
.extract_relative_time(text
)
749 if isinstance(dt
, datetime
.datetime
):
750 timestamp
= calendar
.timegm(dt
.timetuple())
752 if timestamp
is None:
754 unified_timestamp(text
) or unified_timestamp(
756 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
757 text
.lower(), 'time text', default
=None)))
759 if text
and timestamp
is None:
760 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
761 return timestamp
, text
763 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
764 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
765 default_client
='web'):
769 retries
= self
.get_param('extractor_retries', 3)
770 if check_get_keys
is None:
772 while count
< retries
:
775 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
777 response
= self
._call
_api
(
778 ep
=ep
, fatal
=True, headers
=headers
,
779 video_id
=item_id
, query
=query
,
780 context
=self
._extract
_context
(ytcfg
, default_client
),
781 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
782 api_hostname
=api_hostname
, default_client
=default_client
,
783 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
784 except ExtractorError
as e
:
785 if isinstance(e
.cause
, network_exceptions
):
786 if isinstance(e
.cause
, urllib
.error
.HTTPError
):
787 first_bytes
= e
.cause
.read(512)
788 if not is_html(first_bytes
):
791 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
792 lambda x
: x
['error']['message'], str)
794 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
795 # Downloading page may result in intermittent 5xx HTTP error
796 # Sometimes a 404 is also received. See: https://github.com/ytdl-org/youtube-dl/issues/28289
797 # We also want to catch all other network exceptions since errors in later pages can be troublesome
798 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
799 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
800 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
806 self
.report_warning(error_to_compat_str(e
))
811 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
812 except ExtractorError
as e
:
813 # YouTube servers may return errors we want to retry on in a 200 OK response
814 # See: https://github.com/yt-dlp/yt-dlp/issues/839
815 if 'unknown error' in e
.msg
.lower():
820 self
.report_warning(error_to_compat_str(e
))
822 if not check_get_keys
or dict_get(response
, check_get_keys
):
824 # Youtube sometimes sends incomplete data
825 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
826 last_error
= 'Incomplete data received'
829 raise ExtractorError(last_error
)
831 self
.report_warning(last_error
)
836 def is_music_url(url
):
837 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
839 def _extract_video(self
, renderer
):
840 video_id
= renderer
.get('videoId')
841 title
= self
._get
_text
(renderer
, 'title')
842 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
843 duration
= parse_duration(self
._get
_text
(
844 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
846 duration
= parse_duration(self
._search
_regex
(
847 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
848 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
849 video_id
, default
=None, group
='duration'))
851 view_count
= self
._get
_count
(renderer
, 'viewCountText')
853 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
854 channel_id
= traverse_obj(
855 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
856 expected_type
=str, get_all
=False)
857 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
858 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
859 overlay_style
= traverse_obj(
860 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
861 get_all
=False, expected_type
=str)
862 badges
= self
._extract
_badges
(renderer
)
863 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
864 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
865 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
866 expected_type
=str)) or ''
867 url
= f
'https://www.youtube.com/watch?v={video_id}'
868 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
869 url
= f
'https://www.youtube.com/shorts/{video_id}'
873 'ie_key': YoutubeIE
.ie_key(),
877 'description': description
,
878 'duration': duration
,
879 'view_count': view_count
,
880 'uploader': uploader
,
881 'channel_id': channel_id
,
882 'thumbnails': thumbnails
,
883 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
884 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
886 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
887 else 'was_live' if 'streamed' in time_text
.lower()
888 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
890 'release_timestamp': scheduled_timestamp
,
891 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
895 class YoutubeIE(YoutubeBaseInfoExtractor
):
897 _VALID_URL
= r
"""(?x)^
899 (?:https?://|//) # http(s):// or protocol-independent URL
900 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
901 (?:www\.)?deturl\.com/www\.youtube\.com|
902 (?:www\.)?pwnyoutube\.com|
903 (?:www\.)?hooktube\.com|
904 (?:www\.)?yourepeat\.com|
907 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
908 (?:.*?\#/)? # handle anchor (#/) redirect urls
909 (?: # the various things that can precede the ID:
910 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
911 |(?: # or the v= param in all its forms
912 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
913 (?:\?|\#!?) # the params delimiter ? or # or #!
914 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
919 youtu\.be| # just youtu.be/xxxx
920 vid\.plus| # or vid.plus/xxxx
921 zwearz\.com/watch| # or zwearz.com/watch/xxxx
924 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
926 )? # all until now is optional -> you can pass the naked ID
927 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
928 (?(1).+)? # if we found the ID, everything can follow
930 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
932 _EMBED_REGEX
= [r
'''(?x)
942 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
943 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
946 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
947 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$',
948 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
951 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
952 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
953 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
954 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
955 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
956 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
957 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
958 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
959 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
960 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
961 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
962 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
963 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
964 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
965 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
966 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
967 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
968 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
972 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
973 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
974 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
975 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
976 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
977 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
978 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
980 # Apple HTTP Live Streaming
981 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
982 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
983 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
984 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
985 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
986 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
987 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
988 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
991 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
992 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
994 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
995 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
996 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
997 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
998 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
999 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
1000 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1001 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
1002 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
1005 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1006 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1007 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1008 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1009 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1010 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1011 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1014 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1015 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1016 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1017 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1018 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1019 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1020 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1021 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1023 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1024 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1025 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1026 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1027 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1028 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1029 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1030 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1031 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1032 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1033 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1034 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1035 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1038 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1039 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1041 # Dash webm audio with opus inside
1042 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1043 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1044 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1047 '_rtmp': {'protocol': 'rtmp'},
1049 # av01 video only formats sometimes served with "unknown" codecs
1050 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1051 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1052 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1053 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1054 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1055 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1056 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1057 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1059 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1066 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1068 'id': 'BaW_jenozKc',
1070 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1071 'uploader': 'Philipp Hagemeister',
1072 'uploader_id': 'phihag',
1073 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1074 'channel': 'Philipp Hagemeister',
1075 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1076 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1077 'upload_date': '20121002',
1078 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1079 'categories': ['Science & Technology'],
1080 'tags': ['youtube-dl'],
1084 'availability': 'public',
1085 'playable_in_embed': True,
1086 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1087 'live_status': 'not_live',
1091 'comment_count': int,
1092 'channel_follower_count': int
1096 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1097 'note': 'Embed-only video (#1746)',
1099 'id': 'yZIXLfi8CZQ',
1101 'upload_date': '20120608',
1102 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1103 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1104 'uploader': 'SET India',
1105 'uploader_id': 'setindia',
1106 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1109 'skip': 'Private video',
1112 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1113 'note': 'Use the first video ID in the URL',
1115 'id': 'BaW_jenozKc',
1117 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1118 'uploader': 'Philipp Hagemeister',
1119 'uploader_id': 'phihag',
1120 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1121 'channel': 'Philipp Hagemeister',
1122 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1123 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1124 'upload_date': '20121002',
1125 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1126 'categories': ['Science & Technology'],
1127 'tags': ['youtube-dl'],
1131 'availability': 'public',
1132 'playable_in_embed': True,
1133 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1134 'live_status': 'not_live',
1136 'comment_count': int,
1137 'channel_follower_count': int
1140 'skip_download': True,
1144 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1145 'note': '256k DASH audio (format 141) via DASH manifest',
1147 'id': 'a9LDPn-MO4I',
1149 'upload_date': '20121002',
1150 'uploader_id': '8KVIDEO',
1151 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1153 'uploader': '8KVIDEO',
1154 'title': 'UHDTV TEST 8K VIDEO.mp4'
1157 'youtube_include_dash_manifest': True,
1160 'skip': 'format 141 not served anymore',
1162 # DASH manifest with encrypted signature
1164 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1166 'id': 'IB3lcPjvWLA',
1168 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1169 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1171 'uploader': 'AfrojackVEVO',
1172 'uploader_id': 'AfrojackVEVO',
1173 'upload_date': '20131011',
1176 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1177 'playable_in_embed': True,
1178 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1180 'track': 'The Spark',
1181 'live_status': 'not_live',
1182 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1183 'channel': 'Afrojack',
1184 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1186 'availability': 'public',
1187 'categories': ['Music'],
1189 'alt_title': 'The Spark',
1190 'channel_follower_count': int
1193 'youtube_include_dash_manifest': True,
1194 'format': '141/bestaudio[ext=m4a]',
1197 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1199 'note': 'Embed allowed age-gate video',
1200 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1202 'id': 'HtVdAasjOgU',
1204 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1205 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1207 'uploader': 'The Witcher',
1208 'uploader_id': 'WitcherGame',
1209 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1210 'upload_date': '20140605',
1212 'categories': ['Gaming'],
1213 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1214 'availability': 'needs_auth',
1215 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1217 'channel': 'The Witcher',
1218 'live_status': 'not_live',
1220 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1221 'playable_in_embed': True,
1223 'channel_follower_count': int
1227 'note': 'Age-gate video with embed allowed in public site',
1228 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1230 'id': 'HsUATh_Nc2U',
1232 'title': 'Godzilla 2 (Official Video)',
1233 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1234 'upload_date': '20200408',
1235 'uploader_id': 'FlyingKitty900',
1236 'uploader': 'FlyingKitty',
1238 'availability': 'needs_auth',
1239 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1240 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1241 'channel': 'FlyingKitty',
1242 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1244 'categories': ['Entertainment'],
1245 'live_status': 'not_live',
1246 'tags': ['Flyingkitty', 'godzilla 2'],
1247 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1250 'playable_in_embed': True,
1251 'channel_follower_count': int
1255 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1256 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1258 'id': 'Tq92D6wQ1mg',
1259 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1261 'upload_date': '20191228',
1262 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1263 'uploader': 'Projekt Melody',
1264 'description': 'md5:17eccca93a786d51bc67646756894066',
1267 'availability': 'needs_auth',
1268 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1269 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1271 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1272 'channel': 'Projekt Melody',
1273 'live_status': 'not_live',
1274 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1275 'playable_in_embed': True,
1276 'categories': ['Entertainment'],
1278 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1279 'comment_count': int,
1280 'channel_follower_count': int
1284 'note': 'Non-Agegated non-embeddable video',
1285 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1287 'id': 'MeJVWBSsPAY',
1289 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1290 'uploader': 'Herr Lurik',
1291 'uploader_id': 'st3in234',
1292 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1293 'upload_date': '20130730',
1294 'track': 'Such mich find mich',
1296 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1298 'playable_in_embed': False,
1299 'creator': 'OOMPH!',
1300 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1302 'alt_title': 'Such mich find mich',
1304 'channel': 'Herr Lurik',
1305 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1306 'categories': ['Music'],
1307 'availability': 'public',
1308 'uploader_url': 'http://www.youtube.com/user/st3in234',
1309 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1310 'live_status': 'not_live',
1312 'channel_follower_count': int
1316 'note': 'Non-bypassable age-gated video',
1317 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1318 'only_matching': True,
1320 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1321 # YouTube Red ad is not captured for creator
1323 'url': '__2ABJjxzNo',
1325 'id': '__2ABJjxzNo',
1328 'upload_date': '20100430',
1329 'uploader_id': 'deadmau5',
1330 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1331 'creator': 'deadmau5',
1332 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1333 'uploader': 'deadmau5',
1334 'title': 'Deadmau5 - Some Chords (HD)',
1335 'alt_title': 'Some Chords',
1336 'availability': 'public',
1338 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1340 'live_status': 'not_live',
1341 'channel': 'deadmau5',
1342 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1344 'track': 'Some Chords',
1345 'artist': 'deadmau5',
1346 'playable_in_embed': True,
1348 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1349 'categories': ['Music'],
1350 'album': 'Some Chords',
1351 'channel_follower_count': int
1353 'expected_warnings': [
1354 'DASH manifest missing',
1357 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1359 'url': 'lqQg6PlCWgI',
1361 'id': 'lqQg6PlCWgI',
1364 'upload_date': '20150827',
1365 'uploader_id': 'olympic',
1366 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1367 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1368 'uploader': 'Olympics',
1369 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1371 'release_timestamp': 1343767800,
1372 'playable_in_embed': True,
1373 'categories': ['Sports'],
1374 'release_date': '20120731',
1375 'channel': 'Olympics',
1376 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1377 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1378 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1380 'availability': 'public',
1381 'live_status': 'was_live',
1383 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1384 'channel_follower_count': int
1387 'skip_download': 'requires avconv',
1392 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1394 'id': '_b-2C3KPAM0',
1396 'stretched_ratio': 16 / 9.,
1398 'upload_date': '20110310',
1399 'uploader_id': 'AllenMeow',
1400 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1401 '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',
1403 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1404 'playable_in_embed': True,
1408 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1409 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1410 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1412 'categories': ['People & Blogs'],
1414 'live_status': 'not_live',
1415 'availability': 'unlisted',
1416 'comment_count': int,
1417 'channel_follower_count': int
1420 # url_encoded_fmt_stream_map is empty string
1422 'url': 'qEJwOuvDf7I',
1424 'id': 'qEJwOuvDf7I',
1426 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1428 'upload_date': '20150404',
1429 'uploader_id': 'spbelect',
1430 'uploader': 'Наблюдатели Петербурга',
1433 'skip_download': 'requires avconv',
1435 'skip': 'This live event has ended.',
1437 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1439 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1441 'id': 'FIl7x6_3R5Y',
1443 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1444 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1446 'upload_date': '20150625',
1447 'uploader_id': 'dorappi2000',
1448 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1449 'uploader': 'dorappi2000',
1450 'formats': 'mincount:31',
1452 'skip': 'not actual anymore',
1454 # DASH manifest with segment_list
1456 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1457 'md5': '8ce563a1d667b599d21064e982ab9e31',
1459 'id': 'CsmdDsKjzN8',
1461 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1462 'uploader': 'Airtek',
1463 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1464 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1465 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1468 'youtube_include_dash_manifest': True,
1469 'format': '135', # bestvideo
1471 'skip': 'This live event has ended.',
1474 # Multifeed videos (multiple cameras), URL is for Main Camera
1475 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1477 'id': 'jvGDaLqkpTg',
1478 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1479 'description': 'md5:e03b909557865076822aa169218d6a5d',
1483 'id': 'jvGDaLqkpTg',
1485 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1486 'description': 'md5:e03b909557865076822aa169218d6a5d',
1488 'upload_date': '20161111',
1489 'uploader': 'Team PGP',
1490 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1491 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1495 'id': '3AKt1R1aDnw',
1497 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1498 'description': 'md5:e03b909557865076822aa169218d6a5d',
1500 'upload_date': '20161111',
1501 'uploader': 'Team PGP',
1502 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1503 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1507 'id': 'RtAMM00gpVc',
1509 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1510 'description': 'md5:e03b909557865076822aa169218d6a5d',
1512 'upload_date': '20161111',
1513 'uploader': 'Team PGP',
1514 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1515 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1519 'id': '6N2fdlP3C5U',
1521 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1522 'description': 'md5:e03b909557865076822aa169218d6a5d',
1524 'upload_date': '20161111',
1525 'uploader': 'Team PGP',
1526 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1527 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1531 'skip_download': True,
1533 'skip': 'Not multifeed anymore',
1536 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1537 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1539 'id': 'gVfLd0zydlo',
1540 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1542 'playlist_count': 2,
1543 'skip': 'Not multifeed anymore',
1546 'url': 'https://vid.plus/FlRa-iH7PGw',
1547 'only_matching': True,
1550 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1551 'only_matching': True,
1554 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1555 # Also tests cut-off URL expansion in video description (see
1556 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1557 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1558 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1560 'id': 'lsguqyKfVQg',
1562 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1563 'alt_title': 'Dark Walk',
1564 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1566 'upload_date': '20151119',
1567 'uploader_id': 'IronSoulElf',
1568 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1569 'uploader': 'IronSoulElf',
1570 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1571 'track': 'Dark Walk',
1572 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1573 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1574 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1575 'categories': ['Film & Animation'],
1577 'live_status': 'not_live',
1578 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1579 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1581 'availability': 'public',
1582 'channel': 'IronSoulElf',
1583 'playable_in_embed': True,
1586 'channel_follower_count': int
1589 'skip_download': True,
1593 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1594 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1595 'only_matching': True,
1598 # Video with yt:stretch=17:0
1599 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1601 'id': 'Q39EVAstoRM',
1603 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1604 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1605 'upload_date': '20151107',
1606 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1607 'uploader': 'CH GAMER DROID',
1610 'skip_download': True,
1612 'skip': 'This video does not exist.',
1615 # Video with incomplete 'yt:stretch=16:'
1616 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1617 'only_matching': True,
1620 # Video licensed under Creative Commons
1621 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1623 'id': 'M4gD1WSo5mA',
1625 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1626 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1628 'upload_date': '20150128',
1629 'uploader_id': 'BerkmanCenter',
1630 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1631 'uploader': 'The Berkman Klein Center for Internet & Society',
1632 'license': 'Creative Commons Attribution license (reuse allowed)',
1633 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1634 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1637 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1638 'channel': 'The Berkman Klein Center for Internet & Society',
1639 'availability': 'public',
1641 'categories': ['Education'],
1642 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1643 'live_status': 'not_live',
1644 'playable_in_embed': True,
1645 'comment_count': int,
1646 'channel_follower_count': int
1649 'skip_download': True,
1653 # Channel-like uploader_url
1654 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1656 'id': 'eQcmzGIKrzg',
1658 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1659 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1661 'upload_date': '20151120',
1662 'uploader': 'Bernie Sanders',
1663 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1664 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1665 'license': 'Creative Commons Attribution license (reuse allowed)',
1666 'playable_in_embed': True,
1669 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1671 'availability': 'public',
1672 'categories': ['News & Politics'],
1673 'channel': 'Bernie Sanders',
1674 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1676 'live_status': 'not_live',
1677 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1678 'comment_count': int,
1679 'channel_follower_count': int
1682 'skip_download': True,
1686 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1687 'only_matching': True,
1690 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1691 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1692 'only_matching': True,
1695 # Rental video preview
1696 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1698 'id': 'uGpuVWrhIzE',
1700 'title': 'Piku - Trailer',
1701 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1702 'upload_date': '20150811',
1703 'uploader': 'FlixMatrix',
1704 'uploader_id': 'FlixMatrixKaravan',
1705 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1706 'license': 'Standard YouTube License',
1709 'skip_download': True,
1711 'skip': 'This video is not available.',
1714 # YouTube Red video with episode data
1715 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1717 'id': 'iqKdEhx-dD4',
1719 'title': 'Isolation - Mind Field (Ep 1)',
1720 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1722 'upload_date': '20170118',
1723 'uploader': 'Vsauce',
1724 'uploader_id': 'Vsauce',
1725 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1726 'series': 'Mind Field',
1728 'episode_number': 1,
1729 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1732 'availability': 'public',
1734 'channel': 'Vsauce',
1735 'episode': 'Episode 1',
1736 'categories': ['Entertainment'],
1737 'season': 'Season 1',
1738 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1739 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1741 'playable_in_embed': True,
1742 'live_status': 'not_live',
1743 'channel_follower_count': int
1746 'skip_download': True,
1748 'expected_warnings': [
1749 'Skipping DASH manifest',
1753 # The following content has been identified by the YouTube community
1754 # as inappropriate or offensive to some audiences.
1755 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1757 'id': '6SJNVb0GnPI',
1759 'title': 'Race Differences in Intelligence',
1760 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1762 'upload_date': '20140124',
1763 'uploader': 'New Century Foundation',
1764 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1765 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1768 'skip_download': True,
1770 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1774 'url': '1t24XAntNCY',
1775 'only_matching': True,
1778 # geo restricted to JP
1779 'url': 'sJL6WA-aGkQ',
1780 'only_matching': True,
1783 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1784 'only_matching': True,
1787 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1788 'only_matching': True,
1791 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1792 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1793 'only_matching': True,
1797 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1798 'only_matching': True,
1801 # Video with unsupported adaptive stream type formats
1802 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1804 'id': 'Z4Vy8R84T1U',
1806 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1807 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1809 'upload_date': '20130923',
1810 'uploader': 'Amelia Putri Harwita',
1811 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1812 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1813 'formats': 'maxcount:10',
1816 'skip_download': True,
1817 'youtube_include_dash_manifest': False,
1819 'skip': 'not actual anymore',
1822 # Youtube Music Auto-generated description
1823 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1825 'id': 'MgNrAu2pzNs',
1827 'title': 'Voyeur Girl',
1828 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1829 'upload_date': '20190312',
1830 'uploader': 'Stephen - Topic',
1831 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1832 'artist': 'Stephen',
1833 'track': 'Voyeur Girl',
1834 'album': 'it\'s too much love to know my dear',
1835 'release_date': '20190313',
1836 'release_year': 2019,
1837 'alt_title': 'Voyeur Girl',
1839 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1840 'playable_in_embed': True,
1842 'categories': ['Music'],
1843 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1844 'channel': 'Stephen',
1845 'availability': 'public',
1846 'creator': 'Stephen',
1848 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1850 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1852 'live_status': 'not_live',
1853 'channel_follower_count': int
1856 'skip_download': True,
1860 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1861 'only_matching': True,
1864 # invalid -> valid video id redirection
1865 'url': 'DJztXj2GPfl',
1867 'id': 'DJztXj2GPfk',
1869 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1870 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1871 'upload_date': '20090125',
1872 'uploader': 'Prochorowka',
1873 'uploader_id': 'Prochorowka',
1874 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1875 'artist': 'Panjabi MC',
1876 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1877 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1880 'skip_download': True,
1882 'skip': 'Video unavailable',
1885 # empty description results in an empty string
1886 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1888 'id': 'x41yOUIvK2k',
1890 'title': 'IMG 3456',
1892 'upload_date': '20170613',
1893 'uploader_id': 'ElevageOrVert',
1894 'uploader': 'ElevageOrVert',
1896 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1897 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1899 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1901 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1902 'availability': 'public',
1904 'categories': ['Pets & Animals'],
1906 'playable_in_embed': True,
1907 'live_status': 'not_live',
1908 'channel': 'ElevageOrVert',
1909 'channel_follower_count': int
1912 'skip_download': True,
1916 # with '};' inside yt initial data (see [1])
1917 # see [2] for an example with '};' inside ytInitialPlayerResponse
1918 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1919 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1920 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1922 'id': 'CHqg6qOn4no',
1924 'title': 'Part 77 Sort a list of simple types in c#',
1925 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1926 'upload_date': '20130831',
1927 'uploader_id': 'kudvenkat',
1928 'uploader': 'kudvenkat',
1929 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1931 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1932 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1933 'live_status': 'not_live',
1934 'categories': ['Education'],
1935 'availability': 'public',
1936 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1938 'playable_in_embed': True,
1942 'channel': 'kudvenkat',
1943 'comment_count': int,
1944 'channel_follower_count': int
1947 'skip_download': True,
1951 # another example of '};' in ytInitialData
1952 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1953 'only_matching': True,
1956 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1957 'only_matching': True,
1960 # https://github.com/ytdl-org/youtube-dl/pull/28094
1961 'url': 'OtqTfy26tG0',
1963 'id': 'OtqTfy26tG0',
1965 'title': 'Burn Out',
1966 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1967 'upload_date': '20141120',
1968 'uploader': 'The Cinematic Orchestra - Topic',
1969 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1970 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1971 'artist': 'The Cinematic Orchestra',
1972 'track': 'Burn Out',
1973 'album': 'Every Day',
1975 'live_status': 'not_live',
1976 'alt_title': 'Burn Out',
1980 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1981 'creator': 'The Cinematic Orchestra',
1982 'channel': 'The Cinematic Orchestra',
1983 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1984 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1985 'availability': 'public',
1986 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1987 'categories': ['Music'],
1988 'playable_in_embed': True,
1989 'channel_follower_count': int
1992 'skip_download': True,
1996 # controversial video, only works with bpctr when authenticated with cookies
1997 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1998 'only_matching': True,
2001 # controversial video, requires bpctr/contentCheckOk
2002 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
2004 'id': 'SZJvDhaSDnc',
2006 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2007 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2008 'uploader': 'CBS Mornings',
2009 'uploader_id': 'CBSThisMorning',
2010 'upload_date': '20140716',
2011 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2013 'categories': ['News & Politics'],
2014 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2016 'channel': 'CBS Mornings',
2017 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2018 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2020 'availability': 'needs_auth',
2021 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2023 'live_status': 'not_live',
2024 'playable_in_embed': True,
2025 'channel_follower_count': int
2029 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2030 'url': 'cBvYw8_A0vQ',
2032 'id': 'cBvYw8_A0vQ',
2034 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2035 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2036 'upload_date': '20201120',
2037 'uploader': 'Walk around Japan',
2038 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2039 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2041 'categories': ['Travel & Events'],
2042 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2044 'channel': 'Walk around Japan',
2045 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2046 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2048 'availability': 'public',
2049 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2050 'live_status': 'not_live',
2051 'playable_in_embed': True,
2052 'channel_follower_count': int
2055 'skip_download': True,
2058 # Has multiple audio streams
2059 'url': 'WaOKSUlf4TM',
2060 'only_matching': True
2062 # Requires Premium: has format 141 when requested using YTM url
2063 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2064 'only_matching': True
2066 # multiple subtitles with same lang_code
2067 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2068 'only_matching': True,
2070 # Force use android client fallback
2071 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2073 'id': 'YOelRv7fMxY',
2074 'title': 'DIGGING A SECRET TUNNEL Part 1',
2076 'upload_date': '20210624',
2077 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2078 'uploader': 'colinfurze',
2079 'uploader_id': 'colinfurze',
2080 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2081 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2083 'categories': ['Entertainment'],
2084 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2086 'channel': 'colinfurze',
2087 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2088 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2090 'availability': 'public',
2092 'live_status': 'not_live',
2093 'playable_in_embed': True,
2094 'channel_follower_count': int
2097 'format': '17', # 3gp format available on android
2098 'extractor_args': {'youtube': {'player_client': ['android']}},
2102 # Skip download of additional client configs (remix client config in this case)
2103 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2104 'only_matching': True,
2106 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2110 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2111 'only_matching': True,
2113 'note': 'Storyboards',
2114 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2116 'id': '5KLPxDtMqe8',
2119 'title': 'Your Brain is Plastic',
2120 'uploader_id': 'scishow',
2121 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2122 'upload_date': '20140324',
2123 'uploader': 'SciShow',
2125 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2126 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2128 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2129 'playable_in_embed': True,
2131 'uploader_url': 'http://www.youtube.com/user/scishow',
2132 'availability': 'public',
2133 'channel': 'SciShow',
2134 'live_status': 'not_live',
2136 'categories': ['Education'],
2138 'channel_follower_count': int
2139 }, 'params': {'format': 'mhtml', 'skip_download': True}
2141 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2142 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2144 'id': '2NUZ8W2llS4',
2146 'title': 'The NP that test your phone performance 🙂',
2147 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2148 'uploader': 'Leon Nguyen',
2149 'uploader_id': 'VNSXIII',
2150 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2151 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2152 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2156 'categories': ['Gaming'],
2158 'playable_in_embed': True,
2159 'live_status': 'not_live',
2160 'upload_date': '20220103',
2162 'availability': 'public',
2163 'channel': 'Leon Nguyen',
2164 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2165 'comment_count': int,
2166 'channel_follower_count': int
2169 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2170 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2172 'id': 'mzZzzBU6lrM',
2174 'title': 'I Met GeorgeNotFound In Real Life...',
2175 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2176 'uploader': 'Quackity',
2177 'uploader_id': 'QuackityHQ',
2178 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2179 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2180 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2184 'categories': ['Entertainment'],
2186 'playable_in_embed': True,
2187 'live_status': 'not_live',
2188 'release_timestamp': 1641172509,
2189 'release_date': '20220103',
2190 'upload_date': '20220103',
2192 'availability': 'public',
2193 'channel': 'Quackity',
2194 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2195 'channel_follower_count': int
2198 { # continuous livestream. Microformat upload date should be preferred.
2199 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2200 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2202 'id': 'kgx4WGK0oNU',
2203 '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}',
2205 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2206 'availability': 'public',
2208 'release_timestamp': 1637975704,
2209 'upload_date': '20210619',
2210 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2211 'live_status': 'is_live',
2212 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2213 'uploader': '阿鲍Abao',
2214 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2215 'channel': 'Abao in Tokyo',
2216 'channel_follower_count': int,
2217 'release_date': '20211127',
2219 'categories': ['People & Blogs'],
2221 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2223 'playable_in_embed': True,
2224 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2226 'params': {'skip_download': True}
2228 # Story. Requires specific player params to work.
2229 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2231 'id': 'vv8qTUWmulI',
2233 'availability': 'unlisted',
2235 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2236 'upload_date': '20220526',
2237 'categories': ['Education'],
2239 'channel': 'IT\'S HISTORY',
2241 'uploader_id': 'BlastfromthePast',
2243 'uploader': 'IT\'S HISTORY',
2244 'playable_in_embed': True,
2246 'live_status': 'not_live',
2248 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2249 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2250 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2252 'skip': 'stories get removed after some period of time',
2254 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2256 'id': 'tjjjtzRLHvA',
2258 'title': 'ハッシュタグ無し };if window.ytcsi',
2259 'upload_date': '20220323',
2261 'availability': 'unlisted',
2262 'channel': 'nao20010128nao',
2263 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2265 'uploader': 'nao20010128nao',
2266 'uploader_id': 'nao20010128nao',
2267 'categories': ['Music'],
2270 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2271 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2272 'live_status': 'not_live',
2273 'playable_in_embed': True,
2274 'channel_follower_count': int,
2277 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2283 # YouTube <object> embed
2285 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2286 'md5': '873c81d308b979f0e23ee7e620b312a3',
2288 'id': 'msN87y-iEx0',
2290 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2291 'upload_date': '20080526',
2292 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2293 'uploader': 'Christopher Sykes',
2294 'uploader_id': 'ChristopherJSykes',
2296 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2297 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2298 'playable_in_embed': True,
2299 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2301 'comment_count': int,
2302 'channel': 'Christopher Sykes',
2303 'live_status': 'not_live',
2304 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2305 'availability': 'public',
2308 'categories': ['Science & Technology'],
2309 'channel_follower_count': int,
2310 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2313 'skip_download': True,
2319 def suitable(cls, url):
2320 from ..utils import parse_qs
2323 if qs.get('list', [None])[0]:
2325 return super().suitable(url)
2327 def __init__(self, *args, **kwargs):
2328 super().__init__(*args, **kwargs)
2329 self._code_cache = {}
2330 self._player_cache = {}
2332 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2333 lock = threading.Lock()
2336 start_time = time.time()
2337 formats = [f for f in formats if f.get('is_from_start')]
2339 def refetch_manifest(format_id, delay):
2340 nonlocal formats, start_time, is_live
2341 if time.time() <= start_time + delay:
2344 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2345 video_details = traverse_obj(
2346 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2347 microformats = traverse_obj(
2348 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2349 expected_type=dict, default=[])
2350 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2351 start_time = time.time()
2353 def mpd_feed(format_id, delay):
2355 @returns (manifest_url, manifest_stream_number, is_live) or None
2358 refetch_manifest(format_id, delay)
2360 f = next((f for f in formats if f['format_id'] == format_id), None)
2363 self.to_screen(f'{video_id}: Video is no longer live')
2365 self.report_warning(
2366 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2368 return f['manifest_url'], f['manifest_stream_number'], is_live
2372 f['protocol'] = 'http_dash_segments_generator'
2373 f['fragments'] = functools.partial(
2374 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2376 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2377 FETCH_SPAN, MAX_DURATION = 5, 432000
2379 mpd_url, stream_number, is_live = None, None, True
2382 download_start_time = ctx.get('start') or time.time()
2384 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2385 if lack_early_segments:
2386 self.report_warning(bug_reports_message(
2387 'Starting download from the last 120 hours of the live stream since '
2388 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2389 lack_early_segments = True
2391 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2392 fragments, fragment_base_url = None, None
2394 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2395 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2396 # Obtain from MPD's maximum seq value
2397 old_mpd_url = mpd_url
2398 last_error = ctx.pop('last_error', None)
2399 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2400 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2401 or (mpd_url, stream_number, False))
2402 if not refresh_sequence:
2403 if expire_fast and not is_live:
2404 return False, last_seq
2405 elif old_mpd_url == mpd_url:
2406 return True, last_seq
2408 fmts, _ = self._extract_mpd_formats_and_subtitles(
2409 mpd_url, None, note=False, errnote=False, fatal=False)
2410 except ExtractorError:
2413 no_fragment_score += 2
2414 return False, last_seq
2415 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2416 fragments = fmt_info['fragments']
2417 fragment_base_url = fmt_info['fragment_base_url']
2418 assert fragment_base_url
2420 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2421 return True, _last_seq
2424 fetch_time = time.time()
2425 if no_fragment_score > 30:
2427 if last_segment_url:
2428 # Obtain from "X-Head-Seqnum" header value from each segment
2430 urlh = self._request_webpage(
2431 last_segment_url, None, note=False, errnote=False, fatal=False)
2432 except ExtractorError:
2434 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2435 if last_seq is None:
2436 no_fragment_score += 2
2437 last_segment_url = None
2440 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2441 no_fragment_score += 2
2442 if not should_continue:
2445 if known_idx > last_seq:
2446 last_segment_url = None
2451 if begin_index < 0 and known_idx < 0:
2452 # skip from the start when it's negative value
2453 known_idx = last_seq + begin_index
2454 if lack_early_segments:
2455 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2457 for idx in range(known_idx, last_seq):
2458 # do not update sequence here or you'll get skipped some part of it
2459 should_continue, _ = _extract_sequence_from_mpd(False, False)
2460 if not should_continue:
2462 raise ExtractorError('breaking out of outer loop')
2463 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2465 'url': last_segment_url,
2466 'fragment_count': last_seq,
2468 if known_idx == last_seq:
2469 no_fragment_score += 5
2471 no_fragment_score = 0
2472 known_idx = last_seq
2473 except ExtractorError:
2476 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2478 def _extract_player_url(self, *ytcfgs, webpage=None):
2479 player_url = traverse_obj(
2480 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2481 get_all=False, expected_type=str)
2484 return urljoin('https://www.youtube.com', player_url)
2486 def _download_player_url(self, video_id, fatal=False):
2487 res = self._download_webpage(
2488 'https://www.youtube.com/iframe_api',
2489 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2491 player_version = self._search_regex(
2492 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2494 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2496 def _signature_cache_id(self, example_sig):
2497 """ Return a string representation of a signature """
2498 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2501 def _extract_player_info(cls, player_url):
2502 for player_re in cls._PLAYER_INFO_RE:
2503 id_m = re.search(player_re, player_url)
2507 raise ExtractorError('Cannot identify player %r' % player_url)
2508 return id_m.group('id')
2510 def _load_player(self, video_id, player_url, fatal=True):
2511 player_id = self._extract_player_info(player_url)
2512 if player_id not in self._code_cache:
2513 code = self._download_webpage(
2514 player_url, video_id, fatal=fatal,
2515 note='Downloading player ' + player_id,
2516 errnote='Download of %s failed' % player_url)
2518 self._code_cache[player_id] = code
2519 return self._code_cache.get(player_id)
2521 def _extract_signature_function(self, video_id, player_url, example_sig):
2522 player_id = self._extract_player_info(player_url)
2524 # Read from filesystem cache
2525 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2526 assert os.path.basename(func_id) == func_id
2528 self.write_debug(f'Extracting signature function {func_id}')
2529 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
2530 if cache_spec is not None:
2531 return lambda s: ''.join(s[i] for i in cache_spec)
2533 code = self._load_player(video_id, player_url)
2535 res = self._parse_sig_js(code)
2537 test_string = ''.join(map(chr, range(len(example_sig))))
2538 cache_res = res(test_string)
2539 cache_spec = [ord(c) for c in cache_res]
2541 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2544 def _print_sig_code(self, func, example_sig):
2545 if not self.get_param('youtube_print_sig_code'):
2548 def gen_sig_code(idxs):
2549 def _genslice(start, end, step):
2550 starts = '' if start == 0 else str(start)
2551 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2552 steps = '' if step == 1 else (':%d' % step)
2553 return f's[{starts}{ends}{steps}]'
2556 # Quelch pyflakes warnings - start will be set when step is set
2557 start = '(Never used)'
2558 for i, prev in zip(idxs[1:], idxs[:-1]):
2559 if step is not None:
2560 if i - prev == step:
2562 yield _genslice(start, prev, step)
2565 if i - prev in [-1, 1]:
2570 yield 's[%d]' % prev
2574 yield _genslice(start, i, step)
2576 test_string = ''.join(map(chr, range(len(example_sig))))
2577 cache_res = func(test_string)
2578 cache_spec = [ord(c) for c in cache_res]
2579 expr_code = ' + '.join(gen_sig_code(cache_spec))
2580 signature_id_tuple = '(%s)' % (
2581 ', '.join(str(len(p)) for p in example_sig.split('.')))
2582 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2583 ' return %s\n') % (signature_id_tuple, expr_code)
2584 self.to_screen('Extracted signature function:\n' + code)
2586 def _parse_sig_js(self, jscode):
2587 funcname = self._search_regex(
2588 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2589 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2590 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2591 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2592 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}\(a,\d+\)',
2593 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\(\s*""\s*\)',
2594 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2596 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2597 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2598 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2599 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2600 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2601 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2602 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2603 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2604 jscode, 'Initial JS player signature function name', group='sig')
2606 jsi = JSInterpreter(jscode)
2607 initial_function = jsi.extract_function(funcname)
2608 return lambda s: initial_function([s])
2610 def _decrypt_signature(self, s, video_id, player_url):
2611 """Turn the encrypted s field into a working signature"""
2613 player_id = (player_url, self._signature_cache_id(s))
2614 if player_id not in self._player_cache:
2615 func = self._extract_signature_function(video_id, player_url, s)
2616 self._player_cache[player_id] = func
2617 func = self._player_cache[player_id]
2618 self._print_sig_code(func, s)
2620 except Exception as e:
2621 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2623 def _decrypt_nsig(self, s, video_id, player_url):
2624 """Turn the encrypted n field into a working signature"""
2625 if player_url is None:
2626 raise ExtractorError('Cannot decrypt nsig without player_url')
2627 player_url = urljoin('https://www.youtube.com', player_url)
2629 sig_id = ('nsig_value', s)
2630 if sig_id in self._player_cache:
2631 return self._player_cache[sig_id]
2634 player_id = ('nsig', player_url)
2635 if player_id not in self._player_cache:
2636 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2637 func = self._player_cache[player_id]
2638 self._player_cache[sig_id] = func(s)
2639 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2640 return self._player_cache[sig_id]
2641 except Exception as e:
2642 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2644 def _extract_n_function_name(self, jscode):
2645 nfunc, idx = self._search_regex(
2646 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2647 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2650 return json.loads(js_to_json(self._search_regex(
2651 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2652 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2654 def _extract_n_function(self, video_id, player_url):
2655 player_id = self._extract_player_info(player_url)
2656 func_code = self.cache.load('youtube-nsig', player_id)
2659 jsi = JSInterpreter(func_code)
2661 jscode = self._load_player(video_id, player_url)
2662 funcname = self._extract_n_function_name(jscode)
2663 jsi = JSInterpreter(jscode)
2664 func_code = jsi.extract_function_code(funcname)
2665 self.cache.store('youtube-nsig', player_id, func_code)
2667 if self.get_param('youtube_print_sig_code'):
2668 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2670 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2672 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2674 Extract signatureTimestamp (sts)
2675 Required to tell API what sig/player version is in use.
2678 if isinstance(ytcfg, dict):
2679 sts = int_or_none(ytcfg.get('STS'))
2682 # Attempt to extract from player
2683 if player_url is None:
2684 error_msg = 'Cannot extract signature timestamp without player_url.'
2686 raise ExtractorError(error_msg)
2687 self.report_warning(error_msg)
2689 code = self._load_player(video_id, player_url, fatal=fatal)
2691 sts = int_or_none(self._search_regex(
2692 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2693 'JS player signature timestamp', group='sts', fatal=fatal))
2696 def _mark_watched(self, video_id, player_responses):
2697 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2698 label = 'fully ' if is_full else ''
2699 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2700 expected_type=url_or_none)
2702 self.report_warning(f'Unable to mark {label}watched')
2704 parsed_url = urllib.parse.urlparse(url)
2705 qs = urllib.parse.parse_qs(parsed_url.query)
2707 # cpn generation algorithm is reverse engineered from base.js.
2708 # In fact it works even with dummy cpn.
2709 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2710 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2712 # # more consistent results setting it to right before the end
2713 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2718 'cmt': video_length,
2719 'el': 'detailpage', # otherwise defaults to "shorts"
2723 # these seem to mark watchtime "history" in the real world
2724 # they're required, so send in a single value
2730 url = urllib.parse.urlunparse(
2731 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2733 self._download_webpage(
2734 url, video_id, f'Marking {label}watched',
2735 'Unable to mark watched', fatal=False)
2738 def _extract_from_webpage(cls, url, webpage):
2739 # Invidious Instances
2740 # https://github.com/yt-dlp/yt-dlp/issues/195
2741 # https://github.com/iv-org/invidious/pull/1730
2743 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2746 yield cls.url_result(mobj.group('url'), cls)
2747 raise cls.StopExtraction()
2749 yield from super()._extract_from_webpage(url, webpage)
2751 # lazyYT YouTube embed
2752 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2753 yield cls.url_result(unescapeHTML(id_), cls, id_)
2755 # Wordpress "YouTube Video Importer" plugin
2756 for m in re.findall(r'''(?x
)<div
[^
>]+
2757 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2758 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
2759 yield cls.url_result(m[-1], cls, m[-1])
2762 def extract_id(cls, url):
2763 video_id = cls.get_temp_id(url)
2765 raise ExtractorError(f'Invalid URL: {url}')
2768 def _extract_chapters_from_json(self, data, duration):
2769 chapter_list = traverse_obj(
2771 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2772 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2773 ), expected_type=list)
2775 return self._extract_chapters(
2777 chapter_time=lambda chapter: float_or_none(
2778 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2779 chapter_title=lambda chapter: traverse_obj(
2780 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2783 def _extract_chapters_from_engagement_panel(self, data, duration):
2784 content_list = traverse_obj(
2786 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2787 expected_type=list, default=[])
2788 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2789 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2791 return next(filter(None, (
2792 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2793 chapter_time, chapter_title, duration)
2794 for contents in content_list)), [])
2796 def _extract_chapters_from_description(self, description, duration):
2797 return self._extract_chapters(
2798 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2799 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2800 duration=duration, strict=False)
2802 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2806 'start_time': chapter_time(chapter),
2807 'title': chapter_title(chapter),
2808 } for chapter in chapter_list or []]
2810 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2812 chapters = [{'start_time': 0}]
2813 for idx, chapter in enumerate(chapter_list):
2814 if chapter['start_time'] is None:
2815 self.report_warning(f'Incomplete chapter {idx}')
2816 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2817 chapters.append(chapter)
2819 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2822 def _extract_comment(self, comment_renderer, parent=None):
2823 comment_id = comment_renderer.get('commentId')
2827 text = self._get_text(comment_renderer, 'contentText')
2829 # note: timestamp is an estimate calculated from the current time and time_text
2830 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2831 author = self._get_text(comment_renderer, 'authorText')
2832 author_id = try_get(comment_renderer,
2833 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2835 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2836 lambda x: x['likeCount']), str)) or 0
2837 author_thumbnail = try_get(comment_renderer,
2838 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2840 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2841 is_favorited = 'creatorHeart' in (try_get(
2842 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2846 'timestamp': timestamp,
2847 'time_text': time_text,
2848 'like_count': votes,
2849 'is_favorited': is_favorited,
2851 'author_id': author_id,
2852 'author_thumbnail': author_thumbnail,
2853 'author_is_uploader': author_is_uploader,
2854 'parent': parent or 'root'
2857 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2859 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2861 def extract_header(contents):
2862 _continuation = None
2863 for content in contents:
2864 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2865 expected_comment_count = self._get_count(
2866 comments_header_renderer, 'countText', 'commentsCount')
2868 if expected_comment_count:
2869 tracker['est_total'] = expected_comment_count
2870 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2871 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2873 sort_menu_item = try_get(
2874 comments_header_renderer,
2875 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2876 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2878 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2879 if not _continuation:
2882 sort_text = str_or_none(sort_menu_item.get('title'))
2884 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2885 self.to_screen('Sorting comments by %s' % sort_text.lower())
2887 return _continuation
2889 def extract_thread(contents):
2891 tracker['current_page_thread'] = 0
2892 for content in contents:
2893 if not parent and tracker['total_parent_comments'] >= max_parents:
2895 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2896 comment_renderer = get_first(
2897 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2898 expected_type=dict, default={})
2900 comment = self._extract_comment(comment_renderer, parent)
2904 tracker['running_total'] += 1
2905 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2908 # Attempt to get the replies
2909 comment_replies_renderer = try_get(
2910 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2912 if comment_replies_renderer:
2913 tracker['current_page_thread'] += 1
2914 comment_entries_iter = self._comment_entries(
2915 comment_replies_renderer, ytcfg, video_id,
2916 parent=comment.get('id'), tracker=tracker)
2917 yield from itertools.islice(comment_entries_iter, min(
2918 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2920 # Keeps track of counts across recursive calls
2925 current_page_thread=0,
2926 total_parent_comments=0,
2927 total_reply_comments=0)
2930 # YouTube comments have a max depth of 2
2931 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2933 self._downloader.deprecation_warning(
2934 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2935 if max_depth == 1 and parent:
2938 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2939 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2941 continuation = self._extract_continuation(root_continuation_data)
2944 is_forced_continuation = False
2945 is_first_continuation = parent is None
2946 if is_first_continuation and not continuation:
2947 # Sometimes you can get comments by generating the continuation yourself,
2948 # even if YouTube initially reports them being disabled - e.g. stories comments.
2949 # Note: if the comment section is actually disabled, YouTube may return a response with
2950 # required check_get_keys missing. So we will disable that check initially in this case.
2951 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2952 is_forced_continuation = True
2954 for page_num in itertools.count(0):
2955 if not continuation:
2957 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2958 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
2960 if is_first_continuation:
2961 note_prefix = 'Downloading comment section API JSON'
2963 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2964 tracker['current_page_thread'], comment_prog_str)
2966 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2967 ' ' if parent else '', ' replies' if parent else '',
2968 page_num, comment_prog_str)
2970 response = self._extract_response(
2971 item_id=None, query=continuation,
2972 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2973 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2974 is_forced_continuation = False
2975 continuation_contents = traverse_obj(
2976 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2979 for continuation_section in continuation_contents:
2980 continuation_items = traverse_obj(
2981 continuation_section,
2982 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2983 get_all=False, expected_type=list) or []
2984 if is_first_continuation:
2985 continuation = extract_header(continuation_items)
2986 is_first_continuation = False
2991 for entry in extract_thread(continuation_items):
2995 continuation = self._extract_continuation({'contents': continuation_items})
2999 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3000 if message and not parent and tracker['running_total'] == 0:
3001 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3004 def _generate_comment_continuation(video_id):
3006 Generates initial comment section continuation token from given video id
3008 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3009 return base64.b64encode(token.encode()).decode()
3011 def _get_comments(self, ytcfg, video_id, contents, webpage):
3012 """Entry for comment extraction"""
3013 def _real_comment_extract(contents):
3015 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3016 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3017 yield from self._comment_entries(renderer, ytcfg, video_id)
3019 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3020 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3023 def _get_checkok_params():
3024 return {'contentCheckOk': True, 'racyCheckOk': True}
3027 def _generate_player_context(cls, sts=None):
3029 'html5Preference': 'HTML5_PREF_WANTS',
3032 context['signatureTimestamp'] = sts
3034 'playbackContext': {
3035 'contentPlaybackContext': context
3037 **cls._get_checkok_params()
3041 def _is_agegated(player_response):
3042 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3045 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3046 AGE_GATE_REASONS = (
3047 'confirm your age', 'age-restricted', 'inappropriate', # reason
3048 'age_verification_required', 'age_check_required', # status
3050 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3053 def _is_unplayable(player_response):
3054 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3056 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
3058 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3059 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3060 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3061 headers = self.generate_api_headers(
3062 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3065 'videoId': video_id,
3066 'params': '8AEB' # enable stories
3068 yt_query.update(self._generate_player_context(sts))
3069 return self._extract_response(
3070 item_id=video_id, ep='player', query=yt_query,
3071 ytcfg=player_ytcfg, headers=headers, fatal=True,
3072 default_client=client,
3073 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3076 def _get_requested_clients(self, url, smuggled_data):
3077 requested_clients = []
3078 default = ['android', 'web']
3079 allowed_clients = sorted(
3080 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3081 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3082 for client in self._configuration_arg('player_client'):
3083 if client in allowed_clients:
3084 requested_clients.append(client)
3085 elif client == 'default':
3086 requested_clients.extend(default)
3087 elif client == 'all':
3088 requested_clients.extend(allowed_clients)
3090 self.report_warning(f'Skipping unsupported client {client}')
3091 if not requested_clients:
3092 requested_clients = default
3094 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3095 requested_clients.extend(
3096 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3098 return orderedSet(requested_clients)
3100 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
3103 initial_pr = self._search_json(
3104 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3106 all_clients = set(clients)
3107 clients = clients[::-1]
3110 def append_client(*client_names):
3111 """ Append the first client name that exists but not already used """
3112 for client_name in client_names:
3113 actual_client = _split_innertube_client(client_name)[0]
3114 if actual_client in INNERTUBE_CLIENTS:
3115 if actual_client not in all_clients:
3116 clients.append(client_name)
3117 all_clients.add(actual_client)
3120 # Android player_response does not have microFormats which are needed for
3121 # extraction of some data. So we return the initial_pr with formats
3122 # stripped out even if not requested by the user
3123 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3125 pr = dict(initial_pr)
3126 pr['streamingData'] = None
3130 tried_iframe_fallback = False
3133 client, base_client, variant = _split_innertube_client(clients.pop())
3134 player_ytcfg = master_ytcfg if client == 'web' else {}
3135 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3136 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3138 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3139 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3140 if 'js' in self._configuration_arg('player_skip'):
3141 require_js_player = False
3144 if not player_url and not tried_iframe_fallback and require_js_player:
3145 player_url = self._download_player_url(video_id)
3146 tried_iframe_fallback = True
3149 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3150 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3151 except ExtractorError as e:
3153 self.report_warning(last_error)
3160 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3161 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3162 append_client(f'{base_client}_creator')
3163 elif self._is_agegated(pr):
3164 if variant == 'tv_embedded':
3165 append_client(f'{base_client}_embedded')
3167 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3172 self.report_warning(last_error)
3173 return prs, player_url
3175 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
3176 itags, stream_ids = {}, []
3177 itag_qualities, res_qualities = {}, {}
3179 # Normally tiny is the smallest video-only formats. But
3180 # audio-only formats with unknown quality may get tagged as tiny
3182 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3183 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3185 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3187 for fmt in streaming_formats:
3188 if fmt.get('targetDurationSec'):
3191 itag = str_or_none(fmt.get('itag'))
3192 audio_track = fmt.get('audioTrack') or {}
3193 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3194 if stream_id in stream_ids:
3197 quality = fmt.get('quality')
3198 height = int_or_none(fmt.get('height'))
3199 if quality == 'tiny' or not quality:
3200 quality = fmt.get('audioQuality', '').lower() or quality
3201 # The 3gp format (17) in android client has a quality of "small
",
3202 # but is actually worse than other formats
3207 itag_qualities[itag] = quality
3209 res_qualities[height] = quality
3210 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3211 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3212 # number of fragment that would subsequently requested with (`&sq=N`)
3213 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3216 fmt_url = fmt.get('url')
3218 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3219 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3220 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3221 if not all((sc, fmt_url, player_url, encrypted_sig)):
3224 fmt_url += '&%s=%s' % (
3225 traverse_obj(sc, ('sp', -1)) or 'signature',
3226 self._decrypt_signature(encrypted_sig, video_id, player_url)
3228 except ExtractorError as e:
3229 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3230 self.write_debug(e, only_once=True)
3233 query = parse_qs(fmt_url)
3237 fmt_url = update_url_query(fmt_url, {
3238 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3239 except ExtractorError as e:
3240 self.report_warning(
3241 'nsig extraction failed: You may experience throttling for some formats\n'
3242 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3243 self.write_debug(e, only_once=True)
3247 itags[itag] = 'https'
3248 stream_ids.append(stream_id)
3250 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3251 language_preference = (
3252 10 if audio_track.get('audioIsDefault') and 10
3253 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3255 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3256 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3257 # Make sure to avoid false positives with small duration differences.
3258 # Eg: __2ABJjxzNo, ySuUZEjARPY
3259 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3261 self.report_warning(
3262 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3264 'asr': int_or_none(fmt.get('audioSampleRate')),
3265 'filesize': int_or_none(fmt.get('contentLength')),
3267 'format_note': join_nonempty(
3268 '%s%s' % (audio_track.get('displayName') or '',
3269 ' (default)' if language_preference > 0 else ''),
3270 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3271 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3272 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3273 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3274 'fps': int_or_none(fmt.get('fps')) or None,
3276 'quality': q(quality),
3277 'has_drm': bool(fmt.get('drmFamilies')),
3280 'width': int_or_none(fmt.get('width')),
3281 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3282 'desc' if language_preference < -1 else ''),
3283 'language_preference': language_preference,
3284 # Strictly de-prioritize damaged and 3gp formats
3285 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3287 mime_mobj = re.match(
3288 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3290 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3291 dct.update(parse_codecs(mime_mobj.group(2)))
3292 no_audio = dct.get('acodec
') == 'none
'
3293 no_video = dct.get('vcodec
') == 'none
'
3298 if no_audio or no_video:
3299 dct['downloader_options
'] = {
3300 # Youtube throttles chunks >~10M
3301 'http_chunk_size
': 10485760,
3304 dct['container
'] = dct['ext
'] + '_dash
'
3307 live_from_start = is_live and self.get_param('live_from_start
')
3308 skip_manifests = self._configuration_arg('skip
')
3309 if not self.get_param('youtube_include_hls_manifest
', True):
3310 skip_manifests.append('hls
')
3311 if not self.get_param('youtube_include_dash_manifest
', True):
3312 skip_manifests.append('dash
')
3313 get_dash = 'dash
' not in skip_manifests and (
3314 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3315 get_hls = not live_from_start and 'hls
' not in skip_manifests
3317 def process_manifest_format(f, proto, itag):
3319 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3321 itag = f'{itag}
-{proto}
'
3323 f['format_id
'] = itag
3326 f['quality
'] = next((
3328 for val, qdict in ((f.get('format_id
', '').split('-')[0], itag_qualities), (f.get('height
'), res_qualities))
3329 if val in qdict), -1)
3333 for sd in streaming_data:
3334 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3335 if hls_manifest_url:
3336 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4
', fatal=False, live=is_live)
3337 subtitles = self._merge_subtitles(subs, subtitles)
3339 if process_manifest_format(f, 'hls
', self._search_regex(
3340 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3343 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3344 if dash_manifest_url:
3345 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3346 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3348 if process_manifest_format(f, 'dash
', f['format_id
']):
3349 f['filesize
'] = int_or_none(self._search_regex(
3350 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3352 f['is_from_start
'] = True
3357 def _extract_storyboard(self, player_responses, duration):
3359 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3360 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3364 for i, args in enumerate(spec):
3365 args = args.split('#')
3366 counts
= list(map(int_or_none
, args
[:5]))
3367 if len(args
) != 8 or not all(counts
):
3368 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3370 width
, height
, frame_count
, cols
, rows
= counts
3373 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3374 fragment_count
= frame_count
/ (cols
* rows
)
3375 fragment_duration
= duration
/ fragment_count
3377 'format_id': f
'sb{i}',
3378 'format_note': 'storyboard',
3380 'protocol': 'mhtml',
3386 'fps': frame_count
/ duration
,
3390 'url': url
.replace('$M', str(j
)),
3391 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3392 } for j
in range(math
.ceil(fragment_count
))],
3395 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3397 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3398 webpage
= self
._download
_webpage
(
3399 webpage_url
+ '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id
, fatal
=False)
3401 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3403 player_responses
, player_url
= self
._extract
_player
_responses
(
3404 self
._get
_requested
_clients
(url
, smuggled_data
),
3405 video_id
, webpage
, master_ytcfg
)
3407 return webpage
, master_ytcfg
, player_responses
, player_url
3409 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3410 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3411 is_live
= get_first(video_details
, 'isLive')
3413 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3415 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3416 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, is_live
, duration
)
3418 return live_broadcast_details
, is_live
, streaming_data
, formats
, subtitles
3420 def _real_extract(self
, url
):
3421 url
, smuggled_data
= unsmuggle_url(url
, {})
3422 video_id
= self
._match
_id
(url
)
3424 base_url
= self
.http_scheme() + '//www.youtube.com/'
3425 webpage_url
= base_url
+ 'watch?v=' + video_id
3427 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3429 playability_statuses
= traverse_obj(
3430 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3432 trailer_video_id
= get_first(
3433 playability_statuses
,
3434 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3436 if trailer_video_id
:
3437 return self
.url_result(
3438 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3440 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3441 if webpage
else (lambda x
: None))
3443 video_details
= traverse_obj(
3444 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3445 microformats
= traverse_obj(
3446 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3447 expected_type
=dict, default
=[])
3449 get_first(video_details
, 'title')
3450 or self
._get
_text
(microformats
, (..., 'title'))
3451 or search_meta(['og:title', 'twitter:title', 'title']))
3452 video_description
= get_first(video_details
, 'shortDescription')
3454 multifeed_metadata_list
= get_first(
3456 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3458 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3459 if self
.get_param('noplaylist'):
3460 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3464 for feed
in multifeed_metadata_list
.split(','):
3465 # Unquote should take place before split on comma (,) since textual
3466 # fields may contain comma as well (see
3467 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3468 feed_data
= urllib
.parse
.parse_qs(
3469 urllib
.parse
.unquote_plus(feed
))
3471 def feed_entry(name
):
3473 feed_data
, lambda x
: x
[name
][0], str)
3475 feed_id
= feed_entry('id')
3478 feed_title
= feed_entry('title')
3481 title
+= ' (%s)' % feed_title
3483 '_type': 'url_transparent',
3484 'ie_key': 'Youtube',
3486 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3487 {'force_singlefeed': True}
),
3490 feed_ids
.append(feed_id
)
3492 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3493 % (', '.join(feed_ids
), video_id
))
3494 return self
.playlist_result(
3495 entries
, video_id
, video_title
, video_description
)
3497 duration
= int_or_none(
3498 get_first(video_details
, 'lengthSeconds')
3499 or get_first(microformats
, 'lengthSeconds')
3500 or parse_duration(search_meta('duration'))) or None
3502 live_broadcast_details
, is_live
, streaming_data
, formats
, automatic_captions
= \
3503 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
)
3506 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3507 self
.report_drm(video_id
)
3509 playability_statuses
,
3510 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3511 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3512 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3514 if subreason
== 'The uploader has not made this video available in your country.':
3515 countries
= get_first(microformats
, 'availableCountries')
3517 regions_allowed
= search_meta('regionsAllowed')
3518 countries
= regions_allowed
.split(',') if regions_allowed
else None
3519 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3520 reason
+= f
'. {subreason}'
3522 self
.raise_no_formats(reason
, expected
=True)
3524 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3525 if not keywords
and webpage
:
3527 unescapeHTML(m
.group('content'))
3528 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3529 for keyword
in keywords
:
3530 if keyword
.startswith('yt:stretch='):
3531 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3533 # NB: float is intentional for forcing float division
3534 w
, h
= (float(v
) for v
in mobj
.groups())
3538 if f
.get('vcodec') != 'none':
3539 f
['stretched_ratio'] = ratio
3541 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3542 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3545 'url': thumbnail_url
,
3547 original_thumbnails
= thumbnails
.copy()
3549 # The best resolution thumbnails sometimes does not appear in the webpage
3550 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3551 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3553 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3554 # in resolution, these are not the custom thumbnail. So de-prioritize them
3555 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3556 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3558 n_thumbnail_names
= len(thumbnail_names
)
3560 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3561 video_id
=video_id
, name
=name
, ext
=ext
,
3562 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3563 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3564 for thumb
in thumbnails
:
3565 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3566 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3567 self
._remove
_duplicate
_formats
(thumbnails
)
3568 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3570 category
= get_first(microformats
, 'category') or search_meta('genre')
3571 channel_id
= str_or_none(
3572 get_first(video_details
, 'channelId')
3573 or get_first(microformats
, 'externalChannelId')
3574 or search_meta('channelId'))
3575 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3577 live_content
= get_first(video_details
, 'isLiveContent')
3578 is_upcoming
= get_first(video_details
, 'isUpcoming')
3580 if is_upcoming
or live_content
is False:
3582 if is_upcoming
is None and (live_content
or is_live
):
3584 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3585 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3586 if not duration
and live_end_time
and live_start_time
:
3587 duration
= live_end_time
- live_start_time
3589 if is_live
and self
.get_param('live_from_start'):
3590 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3592 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3594 # source_preference is lower for throttled/potentially damaged formats
3595 self
._sort
_formats
(formats
, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3599 'title': video_title
,
3601 'thumbnails': thumbnails
,
3602 # The best thumbnail that we are sure exists. Prevents unnecessary
3603 # URL checking if user don't care about getting the best possible thumbnail
3604 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3605 'description': video_description
,
3606 'uploader': get_first(video_details
, 'author'),
3607 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3608 'uploader_url': owner_profile_url
,
3609 'channel_id': channel_id
,
3610 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3611 'duration': duration
,
3612 'view_count': int_or_none(
3613 get_first((video_details
, microformats
), (..., 'viewCount'))
3614 or search_meta('interactionCount')),
3615 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3616 'age_limit': 18 if (
3617 get_first(microformats
, 'isFamilySafe') is False
3618 or search_meta('isFamilyFriendly') == 'false'
3619 or search_meta('og:restrictions:age') == '18+') else 0,
3620 'webpage_url': webpage_url
,
3621 'categories': [category
] if category
else None,
3623 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3625 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3626 else None if is_live
is None or is_upcoming
is None
3628 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3629 'release_timestamp': live_start_time
,
3632 if get_first(video_details
, 'isPostLiveDvr'):
3633 self
.write_debug('Video is in Post-Live Manifestless mode')
3634 info
['live_status'] = 'post_live'
3635 if (duration
or 0) > 4 * 3600:
3636 self
.report_warning(
3637 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3638 'This is a known issue and patches are welcome')
3641 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3643 def get_lang_code(track
):
3644 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3645 or track
.get('languageCode'))
3647 # Converted into dicts to remove duplicates
3649 get_lang_code(sub
): sub
3650 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3651 translation_languages
= {
3652 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3653 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3655 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3656 lang_subs
= container
.setdefault(lang_code
, [])
3657 for fmt
in self
._SUBTITLE
_FORMATS
:
3663 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3667 # NB: Constructing the full subtitle dictionary is slow
3668 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3669 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3670 for lang_code
, caption_track
in captions
.items():
3671 base_url
= caption_track
.get('baseUrl')
3672 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3675 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3676 if caption_track
.get('kind') != 'asr':
3680 subtitles
, base_url
, lang_code
, lang_name
, {})
3681 if not caption_track
.get('isTranslatable'):
3683 for trans_code
, trans_name
in translation_languages
.items():
3686 orig_trans_code
= trans_code
3687 if caption_track
.get('kind') != 'asr':
3688 if not get_translated_subs
:
3690 trans_code
+= f
'-{lang_code}'
3691 trans_name
+= format_field(lang_name
, None, ' from %s')
3692 # Add an "-orig" label to the original language so that it can be distinguished.
3693 # The subs are returned without "-orig" as well for compatibility
3694 if lang_code
== f
'a-{orig_trans_code}':
3696 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3697 # Setting tlang=lang returns damaged subtitles.
3698 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3699 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3701 info
['automatic_captions'] = automatic_captions
3702 info
['subtitles'] = subtitles
3704 parsed_url
= urllib
.parse
.urlparse(url
)
3705 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3706 query
= urllib
.parse
.parse_qs(component
)
3707 for k
, v
in query
.items():
3708 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3710 if d_k
not in info
and k
in s_ks
:
3711 info
[d_k
] = parse_duration(query
[k
][0])
3713 # Youtube Music Auto-generated description
3714 if video_description
:
3717 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3719 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3720 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3721 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3722 .+\nAuto-generated\ by\ YouTube\.\s*$
3723 ''', video_description
)
3725 release_year
= mobj
.group('release_year')
3726 release_date
= mobj
.group('release_date')
3728 release_date
= release_date
.replace('-', '')
3729 if not release_year
:
3730 release_year
= release_date
[:4]
3732 'album': mobj
.group('album'.strip()),
3733 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3734 'track': mobj
.group('track').strip(),
3735 'release_date': release_date
,
3736 'release_year': int_or_none(release_year
),
3741 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3742 if not initial_data
:
3743 query
= {'videoId': video_id}
3744 query
.update(self
._get
_checkok
_params
())
3745 initial_data
= self
._extract
_response
(
3746 item_id
=video_id
, ep
='next', fatal
=False,
3747 ytcfg
=master_ytcfg
, query
=query
,
3748 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3749 note
='Downloading initial data API JSON')
3751 info
['comment_count'] = traverse_obj(initial_data
, (
3752 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3753 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3755 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3756 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3757 ), expected_type
=int_or_none
, get_all
=False)
3759 try: # This will error if there is no livechat
3760 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3761 except (KeyError, IndexError, TypeError):
3764 info
.setdefault('subtitles', {})['live_chat'] = [{
3765 # url is needed to set cookies
3766 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3767 'video_id': video_id
,
3769 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3773 info
['chapters'] = (
3774 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3775 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3776 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3779 contents
= traverse_obj(
3780 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3781 expected_type
=list, default
=[])
3783 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3785 stl
= vpir
.get('superTitleLink')
3787 stl
= self
._get
_text
(stl
)
3790 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3791 info
['location'] = stl
3793 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3796 'series': mobj
.group(1),
3797 'season_number': int(mobj
.group(2)),
3798 'episode_number': int(mobj
.group(3)),
3800 for tlb
in (try_get(
3802 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3804 tbr
= tlb
.get('toggleButtonRenderer') or {}
3805 for getter
, regex
in [(
3806 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3807 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3808 lambda x
: x
['accessibility'],
3809 lambda x
: x
['accessibilityData']['accessibilityData'],
3810 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3811 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3813 mobj
= re
.match(regex
, label
)
3815 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3817 sbr_tooltip
= try_get(
3818 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3820 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3822 'like_count': str_to_int(like_count
),
3823 'dislike_count': str_to_int(dislike_count
),
3825 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3827 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3829 'channel': self
._get
_text
(vor
, 'title'),
3830 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3834 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3836 multiple_songs
= False
3838 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3839 multiple_songs
= True
3842 mrr
= row
.get('metadataRowRenderer') or {}
3843 mrr_title
= mrr
.get('title')
3846 mrr_title
= self
._get
_text
(mrr
, 'title')
3847 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3848 if mrr_title
== 'License':
3849 info
['license'] = mrr_contents_text
3850 elif not multiple_songs
:
3851 if mrr_title
== 'Album':
3852 info
['album'] = mrr_contents_text
3853 elif mrr_title
== 'Artist':
3854 info
['artist'] = mrr_contents_text
3855 elif mrr_title
== 'Song':
3856 info
['track'] = mrr_contents_text
3859 'channel': 'uploader',
3860 'channel_id': 'uploader_id',
3861 'channel_url': 'uploader_url',
3864 # The upload date for scheduled, live and past live streams / premieres in microformats
3865 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3866 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3868 unified_strdate(get_first(microformats
, 'uploadDate'))
3869 or unified_strdate(search_meta('uploadDate')))
3870 if not upload_date
or (not info
.get('is_live') and not info
.get('was_live') and info
.get('live_status') != 'is_upcoming'):
3871 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3872 info
['upload_date'] = upload_date
3874 for to
, frm
in fallbacks
.items():
3875 if not info
.get(to
):
3876 info
[to
] = info
.get(frm
)
3878 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3883 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3884 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3885 is_membersonly
= None
3887 if initial_data
and is_private
is not None:
3888 is_membersonly
= False
3890 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3891 badge_labels
= set()
3892 for content
in contents
:
3893 if not isinstance(content
, dict):
3895 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3896 for badge_label
in badge_labels
:
3897 if badge_label
.lower() == 'members only':
3898 is_membersonly
= True
3899 elif badge_label
.lower() == 'premium':
3901 elif badge_label
.lower() == 'unlisted':
3904 info
['availability'] = self
._availability
(
3905 is_private
=is_private
,
3906 needs_premium
=is_premium
,
3907 needs_subscription
=is_membersonly
,
3908 needs_auth
=info
['age_limit'] >= 18,
3909 is_unlisted
=None if is_private
is None else is_unlisted
)
3911 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
3913 self
.mark_watched(video_id
, player_responses
)
3918 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
3921 def passthrough_smuggled_data(func
):
3922 def _smuggle(entries
, smuggled_data
):
3923 for entry
in entries
:
3924 # TODO: Convert URL to music.youtube instead.
3925 # Do we need to passthrough any other smuggled_data?
3926 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
3929 @functools.wraps(func
)
3930 def wrapper(self
, url
):
3931 url
, smuggled_data
= unsmuggle_url(url
, {})
3932 if self
.is_music_url(url
):
3933 smuggled_data
['is_music_url'] = True
3934 info_dict
= func(self
, url
, smuggled_data
)
3935 if smuggled_data
and info_dict
.get('entries'):
3936 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
3940 def _extract_channel_id(self
, webpage
):
3941 channel_id
= self
._html
_search
_meta
(
3942 'channelId', webpage
, 'channel id', default
=None)
3945 channel_url
= self
._html
_search
_meta
(
3946 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3947 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3948 'twitter:app:url:googleplay'), webpage
, 'channel url')
3949 return self
._search
_regex
(
3950 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3951 channel_url
, 'channel id')
3954 def _extract_basic_item_renderer(item
):
3955 # Modified from _extract_grid_item_renderer
3956 known_basic_renderers
= (
3957 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3959 for key
, renderer
in item
.items():
3960 if not isinstance(renderer
, dict):
3962 elif key
in known_basic_renderers
:
3964 elif key
.startswith('grid') and key
.endswith('Renderer'):
3967 def _grid_entries(self
, grid_renderer
):
3968 for item
in grid_renderer
['items']:
3969 if not isinstance(item
, dict):
3971 renderer
= self
._extract
_basic
_item
_renderer
(item
)
3972 if not isinstance(renderer
, dict):
3974 title
= self
._get
_text
(renderer
, 'title')
3977 playlist_id
= renderer
.get('playlistId')
3979 yield self
.url_result(
3980 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
3981 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
3985 video_id
= renderer
.get('videoId')
3987 yield self
._extract
_video
(renderer
)
3990 channel_id
= renderer
.get('channelId')
3992 yield self
.url_result(
3993 'https://www.youtube.com/channel/%s' % channel_id
,
3994 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
3996 # generic endpoint URL support
3997 ep_url
= urljoin('https://www.youtube.com/', try_get(
3998 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4001 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4002 if ie
.suitable(ep_url
):
4003 yield self
.url_result(
4004 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4007 def _music_reponsive_list_entry(self
, renderer
):
4008 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4010 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4011 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4012 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4014 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4016 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4017 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4018 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4019 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4020 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4022 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4023 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4025 def _shelf_entries_from_content(self
, shelf_renderer
):
4026 content
= shelf_renderer
.get('content')
4027 if not isinstance(content
, dict):
4029 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4031 # TODO: add support for nested playlists so each shelf is processed
4032 # as separate playlist
4033 # TODO: this includes only first N items
4034 yield from self
._grid
_entries
(renderer
)
4035 renderer
= content
.get('horizontalListRenderer')
4040 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4042 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4044 shelf_url
= urljoin('https://www.youtube.com', ep
)
4046 # Skipping links to another channels, note that checking for
4047 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4049 if skip_channels
and '/channels?' in shelf_url
:
4051 title
= self
._get
_text
(shelf_renderer
, 'title')
4052 yield self
.url_result(shelf_url
, video_title
=title
)
4053 # Shelf may not contain shelf URL, fallback to extraction from content
4054 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4056 def _playlist_entries(self
, video_list_renderer
):
4057 for content
in video_list_renderer
['contents']:
4058 if not isinstance(content
, dict):
4060 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4061 if not isinstance(renderer
, dict):
4063 video_id
= renderer
.get('videoId')
4066 yield self
._extract
_video
(renderer
)
4068 def _rich_entries(self
, rich_grid_renderer
):
4070 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4071 video_id
= renderer
.get('videoId')
4074 yield self
._extract
_video
(renderer
)
4076 def _video_entry(self
, video_renderer
):
4077 video_id
= video_renderer
.get('videoId')
4079 return self
._extract
_video
(video_renderer
)
4081 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4082 url
= urljoin('https://youtube.com', traverse_obj(
4083 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4085 return self
.url_result(
4086 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4088 def _post_thread_entries(self
, post_thread_renderer
):
4089 post_renderer
= try_get(
4090 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4091 if not post_renderer
:
4094 video_renderer
= try_get(
4095 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4096 video_id
= video_renderer
.get('videoId')
4098 entry
= self
._extract
_video
(video_renderer
)
4101 # playlist attachment
4102 playlist_id
= try_get(
4103 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4105 yield self
.url_result(
4106 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4107 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4108 # inline video links
4109 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4111 if not isinstance(run
, dict):
4114 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4117 if not YoutubeIE
.suitable(ep_url
):
4119 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4120 if video_id
== ep_video_id
:
4122 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4124 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4125 contents
= post_thread_continuation
.get('contents')
4126 if not isinstance(contents
, list):
4128 for content
in contents
:
4129 renderer
= content
.get('backstagePostThreadRenderer')
4130 if isinstance(renderer
, dict):
4131 yield from self
._post
_thread
_entries
(renderer
)
4133 renderer
= content
.get('videoRenderer')
4134 if isinstance(renderer
, dict):
4135 yield self
._video
_entry
(renderer
)
4138 def _rich_grid_entries(self, contents):
4139 for content in contents:
4140 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4142 entry = self._video_entry(video_renderer)
4147 def _extract_entries(self
, parent_renderer
, continuation_list
):
4148 # continuation_list is modified in-place with continuation_list = [continuation_token]
4149 continuation_list
[:] = [None]
4150 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4151 for content
in contents
:
4152 if not isinstance(content
, dict):
4154 is_renderer
= traverse_obj(
4155 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4158 renderer
= content
.get('richItemRenderer')
4160 for entry
in self
._rich
_entries
(renderer
):
4162 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4164 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4165 for isr_content
in isr_contents
:
4166 if not isinstance(isr_content
, dict):
4170 'playlistVideoListRenderer': self
._playlist
_entries
,
4171 'gridRenderer': self
._grid
_entries
,
4172 'reelShelfRenderer': self
._grid
_entries
,
4173 'shelfRenderer': self
._shelf
_entries
,
4174 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4175 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4176 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4177 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4178 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4179 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4181 for key
, renderer
in isr_content
.items():
4182 if key
not in known_renderers
:
4184 for entry
in known_renderers
[key
](renderer
):
4187 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4190 if not continuation_list
[0]:
4191 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4193 if not continuation_list
[0]:
4194 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4196 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4197 continuation_list
= [None]
4198 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4199 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4203 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4204 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4205 yield from extract_entries(parent_renderer
)
4206 continuation
= continuation_list
[0]
4208 for page_num
in itertools
.count(1):
4209 if not continuation
:
4211 headers
= self
.generate_api_headers(
4212 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4213 response
= self
._extract
_response
(
4214 item_id
=f
'{item_id} page {page_num}',
4215 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4216 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4220 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4221 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4222 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4224 known_continuation_renderers
= {
4225 'playlistVideoListContinuation': self
._playlist
_entries
,
4226 'gridContinuation': self
._grid
_entries
,
4227 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4228 'sectionListContinuation': extract_entries
, # for feeds
4230 continuation_contents
= try_get(
4231 response
, lambda x
: x
['continuationContents'], dict) or {}
4232 continuation_renderer
= None
4233 for key
, value
in continuation_contents
.items():
4234 if key
not in known_continuation_renderers
:
4236 continuation_renderer
= value
4237 continuation_list
= [None]
4238 yield from known_continuation_renderers
[key
](continuation_renderer
)
4239 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4241 if continuation_renderer
:
4245 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4246 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4247 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4248 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4249 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4250 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4251 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4252 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4254 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4255 continuation_items
= try_get(
4256 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4257 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4258 video_items_renderer
= None
4259 for key
, value
in continuation_item
.items():
4260 if key
not in known_renderers
:
4262 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4263 continuation_list
= [None]
4264 yield from known_renderers
[key
][0](video_items_renderer
)
4265 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4267 if video_items_renderer
:
4272 def _extract_selected_tab(tabs
, fatal
=True):
4274 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4275 if renderer
.get('selected') is True:
4279 raise ExtractorError('Unable to find selected tab')
4281 def _extract_uploader(self
, data
):
4283 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4285 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4287 owner_text
= owner
.get('text')
4288 uploader
['uploader'] = self
._search
_regex
(
4289 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4290 uploader
['uploader_id'] = try_get(
4291 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], str)
4292 uploader
['uploader_url'] = urljoin(
4293 'https://www.youtube.com/',
4294 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4295 return {k: v for k, v in uploader.items() if v is not None}
4297 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4298 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4301 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4302 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4304 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4306 channel_name
= renderer
.get('title')
4307 channel_url
= renderer
.get('channelUrl')
4308 channel_id
= renderer
.get('externalId')
4311 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4314 title
= renderer
.get('title')
4315 description
= renderer
.get('description', '')
4316 playlist_id
= channel_id
4317 tags
= renderer
.get('keywords', '').split()
4319 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4320 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4321 def _get_uncropped(url
):
4322 return url_or_none((url
or '').split('=')[0] + '=s0')
4324 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4325 if avatar_thumbnails
:
4326 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4327 if uncropped_avatar
:
4328 avatar_thumbnails
.append({
4329 'url': uncropped_avatar
,
4330 'id': 'avatar_uncropped',
4334 channel_banners
= self
._extract
_thumbnails
(
4335 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4336 for banner
in channel_banners
:
4337 banner
['preference'] = -10
4340 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4341 if uncropped_banner
:
4342 channel_banners
.append({
4343 'url': uncropped_banner
,
4344 'id': 'banner_uncropped',
4348 primary_thumbnails
= self
._extract
_thumbnails
(
4349 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4351 if playlist_id
is None:
4352 playlist_id
= item_id
4354 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4355 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4357 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4358 title
+= format_field(selected_tab
, 'title', ' - %s')
4359 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4362 'playlist_id': playlist_id
,
4363 'playlist_title': title
,
4364 'playlist_description': description
,
4365 'uploader': channel_name
,
4366 'uploader_id': channel_id
,
4367 'uploader_url': channel_url
,
4368 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4370 'view_count': self
._get
_count
(playlist_stats
, 1),
4371 'availability': self
._extract
_availability
(data
),
4372 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4373 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4374 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4377 metadata
.update(self
._extract
_uploader
(data
))
4379 'channel': metadata
['uploader'],
4380 'channel_id': metadata
['uploader_id'],
4381 'channel_url': metadata
['uploader_url']})
4382 return self
.playlist_result(
4384 selected_tab
, playlist_id
, ytcfg
,
4385 self
._extract
_account
_syncid
(ytcfg
, data
),
4386 self
._extract
_visitor
_data
(data
, ytcfg
)),
4389 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4390 first_id
= last_id
= response
= None
4391 for page_num
in itertools
.count(1):
4392 videos
= list(self
._playlist
_entries
(playlist
))
4395 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4396 if start
>= len(videos
):
4398 yield from videos
[start
:]
4399 first_id
= first_id
or videos
[0]['id']
4400 last_id
= videos
[-1]['id']
4401 watch_endpoint
= try_get(
4402 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4403 headers
= self
.generate_api_headers(
4404 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4405 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4407 'playlistId': playlist_id
,
4408 'videoId': watch_endpoint
.get('videoId') or last_id
,
4409 'index': watch_endpoint
.get('index') or len(videos
),
4410 'params': watch_endpoint
.get('params') or 'OAE%3D'
4412 response
= self
._extract
_response
(
4413 item_id
='%s page %d' % (playlist_id
, page_num
),
4414 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4415 check_get_keys
='contents'
4418 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4420 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4421 title
= playlist
.get('title') or try_get(
4422 data
, lambda x
: x
['titleText']['simpleText'], str)
4423 playlist_id
= playlist
.get('playlistId') or item_id
4425 # Delegating everything except mix playlists to regular tab-based playlist URL
4426 playlist_url
= urljoin(url
, try_get(
4427 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4430 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4431 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4432 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4434 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4435 return self
.url_result(
4436 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4439 return self
.playlist_result(
4440 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4441 playlist_id
=playlist_id
, playlist_title
=title
)
4443 def _extract_availability(self
, data
):
4445 Gets the availability of a given playlist/tab.
4446 Note: Unless YouTube tells us explicitly, we do not assume it is public
4447 @param data: response
4449 is_private
= is_unlisted
= None
4450 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4451 badge_labels
= self
._extract
_badges
(renderer
)
4453 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4454 privacy_dropdown_entries
= try_get(
4455 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4456 for renderer_dict
in privacy_dropdown_entries
:
4457 is_selected
= try_get(
4458 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4461 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4463 badge_labels
.add(label
.lower())
4466 for badge_label
in badge_labels
:
4467 if badge_label
== 'unlisted':
4469 elif badge_label
== 'private':
4471 elif badge_label
== 'public':
4472 is_unlisted
= is_private
= False
4473 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4476 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4477 sidebar_renderer
= try_get(
4478 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4479 for item
in sidebar_renderer
:
4480 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4484 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4486 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4488 browse_id
= params
= None
4489 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4492 menu_renderer
= try_get(
4493 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4494 for menu_item
in menu_renderer
:
4495 if not isinstance(menu_item
, dict):
4497 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4499 nav_item_renderer
, lambda x
: x
['text']['simpleText'], str)
4500 if not text
or text
.lower() != 'show unavailable videos':
4502 browse_endpoint
= try_get(
4503 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4504 browse_id
= browse_endpoint
.get('browseId')
4505 params
= browse_endpoint
.get('params')
4508 headers
= self
.generate_api_headers(
4509 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4510 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4512 'params': params
or 'wgYCCAA=',
4513 'browseId': browse_id
or 'VL%s' % item_id
4515 return self
._extract
_response
(
4516 item_id
=item_id
, headers
=headers
, query
=query
,
4517 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4518 note
='Downloading API JSON with unavailable videos')
4520 @functools.cached_property
4521 def skip_webpage(self
):
4522 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4524 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4525 retries
= self
.get_param('extractor_retries', 3)
4527 webpage
= data
= last_error
= None
4528 while count
< retries
:
4530 # Sometimes youtube returns a webpage with incomplete ytInitialData
4531 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4533 self
.report_warning('%s. Retrying ...' % last_error
)
4535 webpage
= self
._download
_webpage
(
4537 note
='Downloading webpage%s' % (' (retry #%d)' % count
if count
else '',))
4538 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4539 except ExtractorError
as e
:
4540 if isinstance(e
.cause
, network_exceptions
):
4541 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4542 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
4547 self
.report_warning(error_to_compat_str(e
))
4551 self
._extract
_and
_report
_alerts
(data
)
4552 except ExtractorError
as e
:
4555 self
.report_warning(error_to_compat_str(e
))
4558 if dict_get(data
, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4561 last_error
= 'Incomplete yt initial data received'
4562 if count
>= retries
:
4564 raise ExtractorError(last_error
)
4565 self
.report_warning(last_error
)
4568 return webpage
, data
4570 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4571 """Use if failed to extract ytcfg (and data) from initial webpage"""
4572 if not ytcfg
and self
.is_authenticated
:
4573 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4574 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4575 raise ExtractorError(
4576 f
'{msg}. If you are not downloading private content, or '
4577 'your cookies are only for the first account and channel,'
4578 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4580 self
.report_warning(msg
, only_once
=True)
4582 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4584 if not self
.skip_webpage
:
4585 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4586 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4587 # Reject webpage data if redirected to home page without explicitly requesting
4588 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4589 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4590 if (url
!= 'https://www.youtube.com/feed/recommended'
4591 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4592 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4593 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4595 raise ExtractorError(msg
, expected
=True)
4596 self
.report_warning(msg
, only_once
=True)
4598 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4599 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4602 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4603 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4604 resolve_response
= self
._extract
_response
(
4605 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4606 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4607 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4608 for ep_key
, ep
in endpoints
.items():
4609 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4611 return self
._extract
_response
(
4612 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4613 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4614 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4615 err_note
= 'Failed to resolve url (does the playlist exist?)'
4617 raise ExtractorError(err_note
, expected
=True)
4618 self
.report_warning(err_note
, item_id
)
4620 _SEARCH_PARAMS
= None
4622 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4623 data
= {'query': query}
4624 if params
is NO_DEFAULT
:
4625 params
= self
._SEARCH
_PARAMS
4627 data
['params'] = params
4630 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4631 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4633 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4634 ('continuationContents', ),
4636 display_id
= f
'query "{query}"'
4637 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4638 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4639 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4641 continuation_list
= [None]
4643 for page_num
in itertools
.count(1):
4644 data
.update(continuation_list
[0] or {})
4645 headers
= self
.generate_api_headers(
4646 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4647 search
= self
._extract
_response
(
4648 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4649 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4650 slr_contents
= traverse_obj(search
, *content_keys
)
4651 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4652 if not continuation_list
[0]:
4656 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4657 IE_DESC
= 'YouTube Tabs'
4658 _VALID_URL
= r
'''(?x:
4662 youtube(?:kids)?\.com|
4666 (?P<channel_type>channel|c|user|browse)/|
4669 (?:playlist|watch)\?.*?\blist=
4671 (?!(?:%(reserved_names)s)\b) # Direct URLs
4675 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4676 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4678 IE_NAME
= 'youtube:tab'
4681 'note': 'playlists, multipage',
4682 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4683 'playlist_mincount': 94,
4685 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4686 'title': 'Igor Kleiner - Playlists',
4687 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4688 'uploader': 'Igor Kleiner',
4689 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4690 'channel': 'Igor Kleiner',
4691 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4692 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4693 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4694 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4695 'channel_follower_count': int
4698 'note': 'playlists, multipage, different order',
4699 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4700 'playlist_mincount': 94,
4702 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4703 'title': 'Igor Kleiner - Playlists',
4704 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4705 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4706 'uploader': 'Igor Kleiner',
4707 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4708 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4709 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4710 'channel': 'Igor Kleiner',
4711 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4712 'channel_follower_count': int
4715 'note': 'playlists, series',
4716 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4717 'playlist_mincount': 5,
4719 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4720 'title': '3Blue1Brown - Playlists',
4721 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4722 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4723 'uploader': '3Blue1Brown',
4724 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4725 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4726 'channel': '3Blue1Brown',
4727 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4728 'tags': ['Mathematics'],
4729 'channel_follower_count': int
4732 'note': 'playlists, singlepage',
4733 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4734 'playlist_mincount': 4,
4736 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4737 'title': 'ThirstForScience - Playlists',
4738 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4739 'uploader': 'ThirstForScience',
4740 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4741 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4742 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4743 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4745 'channel': 'ThirstForScience',
4746 'channel_follower_count': int
4749 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4750 'only_matching': True,
4752 'note': 'basic, single video playlist',
4753 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4755 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4756 'uploader': 'Sergey M.',
4757 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4758 'title': 'youtube-dl public playlist',
4762 'modified_date': '20201130',
4763 'channel': 'Sergey M.',
4764 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4765 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4766 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4768 'playlist_count': 1,
4770 'note': 'empty playlist',
4771 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4773 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4774 'uploader': 'Sergey M.',
4775 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4776 'title': 'youtube-dl empty playlist',
4778 'channel': 'Sergey M.',
4780 'modified_date': '20160902',
4781 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4782 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4783 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4785 'playlist_count': 0,
4788 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4790 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4791 'title': 'lex will - Home',
4792 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4793 'uploader': 'lex will',
4794 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4795 'channel': 'lex will',
4796 'tags': ['bible', 'history', 'prophesy'],
4797 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4799 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'channel_follower_count': int
4802 'playlist_mincount': 2,
4804 'note': 'Videos tab',
4805 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4807 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4808 'title': 'lex will - Videos',
4809 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4810 'uploader': 'lex will',
4811 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4812 'tags': ['bible', 'history', 'prophesy'],
4813 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4815 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4816 'channel': 'lex will',
4817 'channel_follower_count': int
4819 'playlist_mincount': 975,
4821 'note': 'Videos tab, sorted by popular',
4822 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4824 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4825 'title': 'lex will - Videos',
4826 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4827 'uploader': 'lex will',
4828 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4829 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'channel': 'lex will',
4832 'tags': ['bible', 'history', 'prophesy'],
4833 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'channel_follower_count': int
4836 'playlist_mincount': 199,
4838 'note': 'Playlists tab',
4839 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4841 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4842 'title': 'lex will - Playlists',
4843 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4844 'uploader': 'lex will',
4845 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4846 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'channel': 'lex will',
4848 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4849 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4850 'tags': ['bible', 'history', 'prophesy'],
4851 'channel_follower_count': int
4853 'playlist_mincount': 17,
4855 'note': 'Community tab',
4856 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4858 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4859 'title': 'lex will - Community',
4860 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4861 'uploader': 'lex will',
4862 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4863 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4864 'channel': 'lex will',
4865 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4866 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4867 'tags': ['bible', 'history', 'prophesy'],
4868 'channel_follower_count': int
4870 'playlist_mincount': 18,
4872 'note': 'Channels tab',
4873 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4875 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4876 'title': 'lex will - Channels',
4877 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4878 'uploader': 'lex will',
4879 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4880 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4881 'channel': 'lex will',
4882 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4883 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4884 'tags': ['bible', 'history', 'prophesy'],
4885 'channel_follower_count': int
4887 'playlist_mincount': 12,
4889 'note': 'Search tab',
4890 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4891 'playlist_mincount': 40,
4893 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4894 'title': '3Blue1Brown - Search - linear algebra',
4895 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4896 'uploader': '3Blue1Brown',
4897 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4898 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4899 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4900 'tags': ['Mathematics'],
4901 'channel': '3Blue1Brown',
4902 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4903 'channel_follower_count': int
4906 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4907 'only_matching': True,
4909 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4910 'only_matching': True,
4912 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4913 'only_matching': True,
4915 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4916 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4918 'title': '29C3: Not my department',
4919 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4920 'uploader': 'Christiaan008',
4921 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4922 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4924 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4926 'modified_date': '20150605',
4927 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4928 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4929 'channel': 'Christiaan008',
4931 'playlist_count': 96,
4933 'note': 'Large playlist',
4934 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4936 'title': 'Uploads from Cauchemar',
4937 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4938 'uploader': 'Cauchemar',
4939 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4940 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4942 'modified_date': r
're:\d{8}',
4943 'channel': 'Cauchemar',
4944 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4947 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4949 'playlist_mincount': 1123,
4950 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4952 'note': 'even larger playlist, 8832 videos',
4953 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4954 'only_matching': True,
4956 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4957 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4959 'title': 'Uploads from Interstellar Movie',
4960 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4961 'uploader': 'Interstellar Movie',
4962 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4963 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4966 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4967 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4968 'channel': 'Interstellar Movie',
4970 'modified_date': r
're:\d{8}',
4972 'playlist_mincount': 21,
4974 'note': 'Playlist with "show unavailable videos" button',
4975 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4977 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4978 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4979 'uploader': 'Phim Siêu Nhân Nhật Bản',
4980 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4982 'channel': 'Phim Siêu Nhân Nhật Bản',
4984 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4986 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4987 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4988 'modified_date': r
're:\d{8}',
4990 'playlist_mincount': 200,
4991 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4993 'note': 'Playlist with unavailable videos in page 7',
4994 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4996 'title': 'Uploads from BlankTV',
4997 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4998 'uploader': 'BlankTV',
4999 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5000 'channel': 'BlankTV',
5001 'channel_url': 'https://www.youtube.com/c/blanktv',
5002 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5005 'uploader_url': 'https://www.youtube.com/c/blanktv',
5006 'modified_date': r
're:\d{8}',
5009 'playlist_mincount': 1000,
5010 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5012 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5013 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5015 'title': 'Data Analysis with Dr Mike Pound',
5016 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5017 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5018 'uploader': 'Computerphile',
5019 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5020 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5023 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5024 'channel_url': 'https://www.youtube.com/user/Computerphile',
5025 'channel': 'Computerphile',
5027 'playlist_mincount': 11,
5029 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5030 'only_matching': True,
5032 'note': 'Playlist URL that does not actually serve a playlist',
5033 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5035 'id': 'FqZTN594JQw',
5037 'title': "Smiley's People 01 detective, Adventure Series, Action",
5038 'uploader': 'STREEM',
5039 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5040 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5041 'upload_date': '20150526',
5042 'license': 'Standard YouTube License',
5043 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5044 'categories': ['People & Blogs'],
5050 'skip_download': True,
5052 'skip': 'This video is not available.',
5053 'add_ie': [YoutubeIE
.ie_key()],
5055 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5056 'only_matching': True,
5058 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5059 'only_matching': True,
5061 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5063 'id': 'Wq15eF5vCbI', # This will keep changing
5066 'uploader': 'Sky News',
5067 'uploader_id': 'skynews',
5068 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5069 'upload_date': r
're:\d{8}',
5071 'categories': ['News & Politics'],
5074 'release_timestamp': 1642502819,
5075 'channel': 'Sky News',
5076 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5079 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5080 'playable_in_embed': True,
5081 'release_date': '20220118',
5082 'availability': 'public',
5083 'live_status': 'is_live',
5084 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5085 'channel_follower_count': int
5088 'skip_download': True,
5090 'expected_warnings': ['Ignoring subtitle tracks found in '],
5092 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5094 'id': 'a48o2S1cPoo',
5096 'title': 'The Young Turks - Live Main Show',
5097 'uploader': 'The Young Turks',
5098 'uploader_id': 'TheYoungTurks',
5099 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5100 'upload_date': '20150715',
5101 'license': 'Standard YouTube License',
5102 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5103 'categories': ['News & Politics'],
5104 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5108 'skip_download': True,
5110 'only_matching': True,
5112 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5113 'only_matching': True,
5115 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5116 'only_matching': True,
5118 'note': 'A channel that is not live. Should raise error',
5119 'url': 'https://www.youtube.com/user/numberphile/live',
5120 'only_matching': True,
5122 'url': 'https://www.youtube.com/feed/trending',
5123 'only_matching': True,
5125 'url': 'https://www.youtube.com/feed/library',
5126 'only_matching': True,
5128 'url': 'https://www.youtube.com/feed/history',
5129 'only_matching': True,
5131 'url': 'https://www.youtube.com/feed/subscriptions',
5132 'only_matching': True,
5134 'url': 'https://www.youtube.com/feed/watch_later',
5135 'only_matching': True,
5137 'note': 'Recommended - redirects to home page.',
5138 'url': 'https://www.youtube.com/feed/recommended',
5139 'only_matching': True,
5141 'note': 'inline playlist with not always working continuations',
5142 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5143 'only_matching': True,
5145 'url': 'https://www.youtube.com/course',
5146 'only_matching': True,
5148 'url': 'https://www.youtube.com/zsecurity',
5149 'only_matching': True,
5151 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5152 'only_matching': True,
5154 'url': 'https://www.youtube.com/TheYoungTurks/live',
5155 'only_matching': True,
5157 'url': 'https://www.youtube.com/hashtag/cctv9',
5163 'playlist_mincount': 350,
5165 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5166 'only_matching': True,
5168 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5169 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5170 'only_matching': True
5172 'note': '/browse/ should redirect to /channel/',
5173 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5174 'only_matching': True
5176 'note': 'VLPL, should redirect to playlist?list=PL...',
5177 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5179 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5180 'uploader': 'NoCopyrightSounds',
5181 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5182 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5183 'title': 'NCS : All Releases 💿',
5184 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5185 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5186 'modified_date': r
're:\d{8}',
5188 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5190 'channel': 'NoCopyrightSounds',
5192 'playlist_mincount': 166,
5193 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5195 'note': 'Topic, should redirect to playlist?list=UU...',
5196 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5198 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5199 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5200 'title': 'Uploads from Royalty Free Music - Topic',
5201 'uploader': 'Royalty Free Music - Topic',
5203 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5204 'channel': 'Royalty Free Music - Topic',
5206 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5207 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5208 'modified_date': r
're:\d{8}',
5209 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5212 'expected_warnings': [
5213 'The URL does not have a videos tab',
5214 r
'[Uu]navailable videos (are|will be) hidden',
5216 'playlist_mincount': 101,
5218 'note': 'Topic without a UU playlist',
5219 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5221 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5222 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5225 'expected_warnings': [
5226 'the playlist redirect gave error',
5228 'playlist_mincount': 9,
5230 'note': 'Youtube music Album',
5231 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5233 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5234 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5238 'availability': 'unlisted',
5239 'modified_date': r
're:\d{8}',
5241 'playlist_count': 50,
5243 'note': 'unlisted single video playlist',
5244 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5246 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5247 'uploader': 'colethedj',
5248 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5249 'title': 'yt-dlp unlisted playlist test',
5250 'availability': 'unlisted',
5252 'modified_date': '20220418',
5253 'channel': 'colethedj',
5256 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5257 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5258 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5260 'playlist_count': 1,
5262 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5263 'url': 'https://www.youtube.com/feed/recommended',
5265 'id': 'recommended',
5266 'title': 'recommended',
5269 'playlist_mincount': 50,
5271 'skip_download': True,
5272 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5275 'note': 'API Fallback: /videos tab, sorted by oldest first',
5276 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5278 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5279 'title': 'Cody\'sLab - Videos',
5280 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5281 'uploader': 'Cody\'sLab',
5282 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5283 'channel': 'Cody\'sLab',
5284 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5286 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5287 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5288 'channel_follower_count': int
5290 'playlist_mincount': 650,
5292 'skip_download': True,
5293 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5296 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5297 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5299 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5300 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5301 'title': 'Uploads from Royalty Free Music - Topic',
5302 'uploader': 'Royalty Free Music - Topic',
5303 'modified_date': r
're:\d{8}',
5304 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5306 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5308 'channel': 'Royalty Free Music - Topic',
5310 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5312 'expected_warnings': [
5313 'does not have a videos tab',
5314 r
'[Uu]navailable videos (are|will be) hidden',
5316 'playlist_mincount': 101,
5318 'skip_download': True,
5319 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5322 'note': 'non-standard redirect to regional channel',
5323 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5324 'only_matching': True
5326 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5327 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5329 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5330 'modified_date': '20220407',
5331 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5333 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5334 'uploader': 'pukkandan',
5335 'availability': 'unlisted',
5336 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5337 'channel': 'pukkandan',
5338 'description': 'Test for collaborative playlist',
5339 'title': 'yt-dlp test - collaborative playlist',
5341 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5343 'playlist_mincount': 2
5347 def suitable(cls
, url
):
5348 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5350 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5352 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5353 def _real_extract(self
, url
, smuggled_data
):
5354 item_id
= self
._match
_id
(url
)
5355 url
= urllib
.parse
.urlunparse(
5356 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5357 compat_opts
= self
.get_param('compat_opts', [])
5360 mobj
= self
._URL
_RE
.match(url
).groupdict()
5361 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5364 mobj
, redirect_warning
= get_mobj(url
), None
5365 # Youtube returns incomplete data if tabname is not lower case
5366 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5368 if smuggled_data
.get('is_music_url'):
5369 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5370 item_id
= item_id
[2:]
5371 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5372 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5373 mdata
= self
._extract
_tab
_endpoint
(
5374 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5375 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5376 get_all
=False, expected_type
=str)
5378 raise ExtractorError('Failed to resolve album to playlist')
5379 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5380 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5381 pre
= f
'https://www.youtube.com/channel/{item_id}'
5383 original_tab_name
= tab
5384 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5385 # Home URLs should redirect to /videos/
5386 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5387 'To download only the videos in the home page, add a "/featured" to the URL')
5390 url
= ''.join((pre
, tab
, post
))
5391 mobj
= get_mobj(url
)
5393 # Handle both video/playlist URLs
5395 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5397 if not video_id
and mobj
['not_channel'].startswith('watch'):
5399 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5400 raise ExtractorError('Unable to recognize tab page')
5401 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5402 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5403 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5404 mobj
= get_mobj(url
)
5406 if video_id
and playlist_id
:
5407 if self
.get_param('noplaylist'):
5408 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5409 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5410 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5411 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5413 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5415 # YouTube may provide a non-standard redirect to the regional channel
5416 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5417 redirect_url
= traverse_obj(
5418 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5419 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5420 redirect_url
= ''.join((
5421 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5422 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5423 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5425 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5427 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5428 selected_tab_name
= selected_tab
.get('title', '').lower()
5429 if selected_tab_name
== 'home':
5430 selected_tab_name
= 'featured'
5431 requested_tab_name
= mobj
['tab'][1:]
5432 if 'no-youtube-channel-redirect' not in compat_opts
:
5433 if requested_tab_name
== 'live': # Live tab should have redirected to the video
5434 raise UserNotLive(video_id
=mobj
['id'])
5435 if requested_tab_name
not in ('', selected_tab_name
):
5436 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5437 if not original_tab_name
:
5438 if item_id
[:2] == 'UC':
5439 # Topic channels don't have /videos. Use the equivalent playlist instead
5440 pl_id
= f
'UU{item_id[2:]}'
5441 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5443 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5444 except ExtractorError
:
5445 redirect_warning
+= ' and the playlist redirect gave error'
5447 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5448 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5449 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5450 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5452 raise ExtractorError(redirect_warning
, expected
=True)
5454 if redirect_warning
:
5455 self
.to_screen(redirect_warning
)
5456 self
.write_debug(f
'Final URL: {url}')
5458 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5459 if 'no-youtube-unavailable-videos' not in compat_opts
:
5460 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5461 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5462 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5464 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5466 playlist
= traverse_obj(
5467 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5469 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5471 video_id
= traverse_obj(
5472 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5474 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5475 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5476 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5477 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5479 raise ExtractorError('Unable to recognize tab page')
5482 class YoutubePlaylistIE(InfoExtractor
):
5483 IE_DESC
= 'YouTube playlists'
5484 _VALID_URL
= r
'''(?x)(?:
5489 youtube(?:kids)?\.com|
5494 (?P<id>%(playlist_id)s)
5496 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5497 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5499 IE_NAME
= 'youtube:playlist'
5501 'note': 'issue #673',
5502 'url': 'PLBB231211A4F62143',
5504 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5505 'id': 'PLBB231211A4F62143',
5506 'uploader': 'Wickman',
5507 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5508 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5510 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5511 'modified_date': r
're:\d{8}',
5512 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5513 'channel': 'Wickman',
5515 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5517 'playlist_mincount': 29,
5519 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5521 'title': 'YDL_safe_search',
5522 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5524 'playlist_count': 2,
5525 'skip': 'This playlist is private',
5528 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5529 'playlist_count': 4,
5532 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5533 'uploader': 'milan',
5534 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5536 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5538 'modified_date': '20140919',
5541 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5542 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5544 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5546 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5547 'playlist_mincount': 455,
5549 'title': '2018 Chinese New Singles (11/6 updated)',
5550 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5552 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5553 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5556 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5558 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5559 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5560 'modified_date': r
're:\d{8}',
5562 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5564 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5565 'only_matching': True,
5567 # music album playlist
5568 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5569 'only_matching': True,
5573 def suitable(cls
, url
):
5574 if YoutubeTabIE
.suitable(url
):
5576 from ..utils
import parse_qs
5578 if qs
.get('v', [None])[0]:
5580 return super().suitable(url
)
5582 def _real_extract(self
, url
):
5583 playlist_id
= self
._match
_id
(url
)
5584 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5585 url
= update_url_query(
5586 'https://www.youtube.com/playlist',
5587 parse_qs(url
) or {'list': playlist_id}
)
5589 url
= smuggle_url(url
, {'is_music_url': True}
)
5590 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5593 class YoutubeYtBeIE(InfoExtractor
):
5594 IE_DESC
= 'youtu.be'
5595 _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}
5597 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5599 'id': 'yeWKywCrFtk',
5601 'title': 'Small Scale Baler and Braiding Rugs',
5602 'uploader': 'Backus-Page House Museum',
5603 'uploader_id': 'backuspagemuseum',
5604 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5605 'upload_date': '20161008',
5606 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5607 'categories': ['Nonprofits & Activism'],
5611 'playable_in_embed': True,
5612 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5613 'channel': 'Backus-Page House Museum',
5614 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5615 'live_status': 'not_live',
5617 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5618 'availability': 'public',
5620 'comment_count': int,
5621 'channel_follower_count': int
5625 'skip_download': True,
5628 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5629 'only_matching': True,
5632 def _real_extract(self
, url
):
5633 mobj
= self
._match
_valid
_url
(url
)
5634 video_id
= mobj
.group('id')
5635 playlist_id
= mobj
.group('playlist_id')
5636 return self
.url_result(
5637 update_url_query('https://www.youtube.com/watch', {
5639 'list': playlist_id
,
5640 'feature': 'youtu.be',
5641 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5644 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5645 IE_DESC
= 'YouTube livestream embeds'
5646 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5648 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5649 'only_matching': True,
5652 def _real_extract(self
, url
):
5653 channel_id
= self
._match
_id
(url
)
5654 return self
.url_result(
5655 f
'https://www.youtube.com/channel/{channel_id}/live',
5656 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5659 class YoutubeYtUserIE(InfoExtractor
):
5660 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5661 IE_NAME
= 'youtube:user'
5662 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5664 'url': 'ytuser:phihag',
5665 'only_matching': True,
5668 def _real_extract(self
, url
):
5669 user_id
= self
._match
_id
(url
)
5670 return self
.url_result(
5671 'https://www.youtube.com/user/%s/videos' % user_id
,
5672 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5675 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5676 IE_NAME
= 'youtube:favorites'
5677 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5678 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5679 _LOGIN_REQUIRED
= True
5682 'only_matching': True,
5684 'url': ':ytfavorites',
5685 'only_matching': True,
5688 def _real_extract(self
, url
):
5689 return self
.url_result(
5690 'https://www.youtube.com/playlist?list=LL',
5691 ie
=YoutubeTabIE
.ie_key())
5694 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5695 IE_NAME
= 'youtube:notif'
5696 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5697 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5698 _LOGIN_REQUIRED
= True
5701 'only_matching': True,
5703 'url': ':ytnotifications',
5704 'only_matching': True,
5707 def _extract_notification_menu(self
, response
, continuation_list
):
5708 notification_list
= traverse_obj(
5710 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5711 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5712 expected_type
=list) or []
5713 continuation_list
[0] = None
5714 for item
in notification_list
:
5715 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5718 continuation
= item
.get('continuationItemRenderer')
5720 continuation_list
[0] = continuation
5722 def _extract_notification_renderer(self
, notification
):
5723 video_id
= traverse_obj(
5724 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5725 url
= f
'https://www.youtube.com/watch?v={video_id}'
5728 browse_ep
= traverse_obj(
5729 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5730 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5731 post_id
= self
._search
_regex
(
5732 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5733 'post id', default
=None)
5734 if not channel_id
or not post_id
:
5736 # The direct /post url redirects to this in the browser
5737 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5739 channel
= traverse_obj(
5740 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5742 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5743 if notification_title
:
5744 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5745 # TODO: handle recommended videos
5746 title
= self
._search
_regex
(
5747 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5748 'video title', default
=None)
5749 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5750 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5755 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5756 'video_id': video_id
,
5758 'channel_id': channel_id
,
5760 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5761 'upload_date': upload_date
,
5764 def _notification_menu_entries(self
, ytcfg
):
5765 continuation_list
= [None]
5767 for page
in itertools
.count(1):
5768 ctoken
= traverse_obj(
5769 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5770 response
= self
._extract
_response
(
5771 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5772 ep
='notification/get_notification_menu', check_get_keys
='actions',
5773 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5774 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5775 if not continuation_list
[0]:
5778 def _real_extract(self
, url
):
5779 display_id
= 'notifications'
5780 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5781 self
._report
_playlist
_authcheck
(ytcfg
)
5782 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5785 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5786 IE_DESC
= 'YouTube search'
5787 IE_NAME
= 'youtube:search'
5788 _SEARCH_KEY
= 'ytsearch'
5789 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5791 'url': 'ytsearch5:youtube-dl test video',
5792 'playlist_count': 5,
5794 'id': 'youtube-dl test video',
5795 'title': 'youtube-dl test video',
5800 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5801 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5802 _SEARCH_KEY
= 'ytsearchdate'
5803 IE_DESC
= 'YouTube search, newest videos first'
5804 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5806 'url': 'ytsearchdate5:youtube-dl test video',
5807 'playlist_count': 5,
5809 'id': 'youtube-dl test video',
5810 'title': 'youtube-dl test video',
5815 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5816 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5817 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5818 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5820 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5821 'playlist_mincount': 5,
5823 'id': 'youtube-dl test video',
5824 'title': 'youtube-dl test video',
5827 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5828 'playlist_mincount': 5,
5834 'url': 'https://www.youtube.com/results?search_query=%23cats',
5835 'playlist_mincount': 1,
5839 # The test suite does not have support for nested playlists
5841 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5846 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5847 'only_matching': True,
5850 def _real_extract(self
, url
):
5852 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5853 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5856 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5857 IE_DESC
= 'YouTube music search URLs with selectable sections (Eg: #songs)'
5858 IE_NAME
= 'youtube:music:search_url'
5859 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5861 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5862 'playlist_count': 16,
5864 'id': 'royalty free music',
5865 'title': 'royalty free music',
5868 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5869 'playlist_mincount': 30,
5871 'id': 'royalty free music - songs',
5872 'title': 'royalty free music - songs',
5874 'params': {'extract_flat': 'in_playlist'}
5876 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5877 'playlist_mincount': 30,
5879 'id': 'royalty free music - community playlists',
5880 'title': 'royalty free music - community playlists',
5882 'params': {'extract_flat': 'in_playlist'}
5886 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5887 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5888 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5889 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5890 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5891 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5894 def _real_extract(self
, url
):
5896 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5897 params
= qs
.get('sp', (None,))[0]
5899 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5901 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
5902 params
= self
._SECTIONS
.get(section
)
5905 title
= join_nonempty(query
, section
, delim
=' - ')
5906 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5909 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5911 Base class for feed extractors
5912 Subclasses must re-define the _FEED_NAME property.
5914 _LOGIN_REQUIRED
= True
5915 _FEED_NAME
= 'feeds'
5917 def _real_initialize(self
):
5918 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
5922 return f
'youtube:{self._FEED_NAME}'
5924 def _real_extract(self
, url
):
5925 return self
.url_result(
5926 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
5929 class YoutubeWatchLaterIE(InfoExtractor
):
5930 IE_NAME
= 'youtube:watchlater'
5931 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5932 _VALID_URL
= r
':ytwatchlater'
5934 'url': ':ytwatchlater',
5935 'only_matching': True,
5938 def _real_extract(self
, url
):
5939 return self
.url_result(
5940 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
5943 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
5944 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
5945 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5946 _FEED_NAME
= 'recommended'
5947 _LOGIN_REQUIRED
= False
5950 'only_matching': True,
5952 'url': ':ytrecommended',
5953 'only_matching': True,
5955 'url': 'https://youtube.com',
5956 'only_matching': True,
5960 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
5961 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5962 _VALID_URL
= r
':ytsub(?:scription)?s?'
5963 _FEED_NAME
= 'subscriptions'
5966 'only_matching': True,
5968 'url': ':ytsubscriptions',
5969 'only_matching': True,
5973 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
5974 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
5975 _VALID_URL
= r
':ythis(?:tory)?'
5976 _FEED_NAME
= 'history'
5978 'url': ':ythistory',
5979 'only_matching': True,
5983 class YoutubeStoriesIE(InfoExtractor
):
5984 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
5985 IE_NAME
= 'youtube:stories'
5986 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5988 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5989 'only_matching': True,
5992 def _real_extract(self
, url
):
5993 playlist_id
= f
'RLTD{self._match_id(url)}'
5994 return self
.url_result(
5995 f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5996 ie
=YoutubeTabIE
, video_id
=playlist_id
)
5999 class YoutubeTruncatedURLIE(InfoExtractor
):
6000 IE_NAME
= 'youtube:truncated_url'
6001 IE_DESC
= False # Do not list
6002 _VALID_URL
= r
'''(?x)
6004 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6007 annotation_id=annotation_[^&]+|
6013 attribution_link\?a=[^&]+
6019 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6020 'only_matching': True,
6022 'url': 'https://www.youtube.com/watch?',
6023 'only_matching': True,
6025 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6026 'only_matching': True,
6028 'url': 'https://www.youtube.com/watch?feature=foo',
6029 'only_matching': True,
6031 'url': 'https://www.youtube.com/watch?hl=en-GB',
6032 'only_matching': True,
6034 'url': 'https://www.youtube.com/watch?t=2372',
6035 'only_matching': True,
6038 def _real_extract(self
, url
):
6039 raise ExtractorError(
6040 'Did you forget to quote the URL? Remember that & is a meta '
6041 'character in most shells, so you want to put the URL in quotes, '
6043 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6044 ' or simply youtube-dl BaW_jenozKc .',
6048 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6049 IE_NAME
= 'youtube:clip'
6050 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6052 # FIXME: Other metadata should be extracted from the clip, not from the base video
6053 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6055 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6057 'section_start': 29.0,
6058 'section_end': 39.7,
6061 'availability': 'public',
6062 'categories': ['Gaming'],
6063 'channel': 'Scott The Woz',
6064 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6065 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6066 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6068 'playable_in_embed': True,
6070 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6071 'title': 'Mobile Games on Console - Scott The Woz',
6072 'upload_date': '20210920',
6073 'uploader': 'Scott The Woz',
6074 'uploader_id': 'scottthewoz',
6075 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6077 'live_status': 'not_live',
6078 'channel_follower_count': int
6082 def _real_extract(self
, url
):
6083 clip_id
= self
._match
_id
(url
)
6084 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6086 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6088 raise ExtractorError('Unable to find video ID')
6090 clip_data
= traverse_obj(data
, (
6091 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6092 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6093 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6094 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6097 '_type': 'url_transparent',
6098 'url': f
'https://www.youtube.com/watch?v={video_id}',
6099 'ie_key': YoutubeIE
.ie_key(),
6101 'section_start': int(clip_data
['startTimeMs']) / 1000,
6102 'section_end': int(clip_data
['endTimeMs']) / 1000,
6106 class YoutubeTruncatedIDIE(InfoExtractor
):
6107 IE_NAME
= 'youtube:truncated_id'
6108 IE_DESC
= False # Do not list
6109 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6112 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6113 'only_matching': True,
6116 def _real_extract(self
, url
):
6117 video_id
= self
._match
_id
(url
)
6118 raise ExtractorError(
6119 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',