19 from .common
import InfoExtractor
, SearchInfoExtractor
20 from ..compat
import functools
21 from ..jsinterp
import JSInterpreter
64 # any clients starting with _ cannot be explicitly requested by the user
67 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
68 'INNERTUBE_CONTEXT': {
71 'clientVersion': '2.20220801.00.00',
74 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
77 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
78 'INNERTUBE_CONTEXT': {
80 'clientName': 'WEB_EMBEDDED_PLAYER',
81 'clientVersion': '1.20220731.00.00',
84 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
87 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
88 'INNERTUBE_HOST': 'music.youtube.com',
89 'INNERTUBE_CONTEXT': {
91 'clientName': 'WEB_REMIX',
92 'clientVersion': '1.20220727.01.00',
95 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
98 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
99 'INNERTUBE_CONTEXT': {
101 'clientName': 'WEB_CREATOR',
102 'clientVersion': '1.20220726.00.00',
105 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
108 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
109 'INNERTUBE_CONTEXT': {
111 'clientName': 'ANDROID',
112 'clientVersion': '17.28.34',
115 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
116 'REQUIRE_JS_PLAYER': False
118 'android_embedded': {
119 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
120 'INNERTUBE_CONTEXT': {
122 'clientName': 'ANDROID_EMBEDDED_PLAYER',
123 'clientVersion': '17.28.34',
126 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
127 'REQUIRE_JS_PLAYER': False
130 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
131 'INNERTUBE_CONTEXT': {
133 'clientName': 'ANDROID_MUSIC',
134 'clientVersion': '5.16.51',
137 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
138 'REQUIRE_JS_PLAYER': False
141 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
142 'INNERTUBE_CONTEXT': {
144 'clientName': 'ANDROID_CREATOR',
145 'clientVersion': '22.28.100',
148 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
149 'REQUIRE_JS_PLAYER': False
151 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
152 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
154 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
155 'INNERTUBE_CONTEXT': {
158 'clientVersion': '17.30.1',
159 'deviceModel': 'iPhone14,3',
162 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
163 'REQUIRE_JS_PLAYER': False
166 'INNERTUBE_CONTEXT': {
168 'clientName': 'IOS_MESSAGES_EXTENSION',
169 'clientVersion': '17.30.1',
170 'deviceModel': 'iPhone14,3',
173 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
174 'REQUIRE_JS_PLAYER': False
177 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
178 'INNERTUBE_CONTEXT': {
180 'clientName': 'IOS_MUSIC',
181 'clientVersion': '5.18',
184 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
185 'REQUIRE_JS_PLAYER': False
188 'INNERTUBE_CONTEXT': {
190 'clientName': 'IOS_CREATOR',
191 'clientVersion': '22.29.101',
194 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
195 'REQUIRE_JS_PLAYER': False
197 # mweb has 'ultralow' formats
198 # See: https://github.com/yt-dlp/yt-dlp/pull/557
200 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
201 'INNERTUBE_CONTEXT': {
203 'clientName': 'MWEB',
204 'clientVersion': '2.20220801.00.00',
207 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
209 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
210 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
213 'INNERTUBE_CONTEXT': {
215 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
216 'clientVersion': '2.0',
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
224 def _split_innertube_client(client_name
):
225 variant
, *base
= client_name
.rsplit('.', 1)
227 return variant
, base
[0], variant
228 base
, *variant
= client_name
.split('_', 1)
229 return client_name
, base
, variant
[0] if variant
else None
232 def build_innertube_clients():
234 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
236 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
237 priority
= qualities(BASE_CLIENTS
[::-1])
239 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
240 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
241 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
242 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
243 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
245 _
, base_client
, variant
= _split_innertube_client(client
)
246 ytcfg
['priority'] = 10 * priority(base_client
)
249 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
250 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
251 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
252 embedscreen
['priority'] -= 3
253 elif variant
== 'embedded':
254 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
255 ytcfg
['priority'] -= 2
257 ytcfg
['priority'] -= 3
260 build_innertube_clients()
263 class YoutubeBaseInfoExtractor(InfoExtractor
):
264 """Provide base functions for Youtube extractors"""
267 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
268 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
269 r
'browse|oembed|get_video_info|iframe_api|s/player|'
270 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
272 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
274 # _NETRC_MACHINE = 'youtube'
276 # If True it will raise an error if no login info is provided
277 _LOGIN_REQUIRED
= False
280 # invidious-redirect websites
281 r
'(?:www\.)?redirect\.invidious\.io',
282 r
'(?:(?:www|dev)\.)?invidio\.us',
283 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
284 r
'(?:www\.)?invidious\.pussthecat\.org',
285 r
'(?:www\.)?invidious\.zee\.li',
286 r
'(?:www\.)?invidious\.ethibox\.fr',
287 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
288 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
289 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
290 # youtube-dl invidious instances list
291 r
'(?:(?:www|no)\.)?invidiou\.sh',
292 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
293 r
'(?:www\.)?invidious\.kabi\.tk',
294 r
'(?:www\.)?invidious\.mastodon\.host',
295 r
'(?:www\.)?invidious\.zapashcanon\.fr',
296 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
297 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
298 r
'(?:www\.)?invidious\.himiko\.cloud',
299 r
'(?:www\.)?invidious\.reallyancient\.tech',
300 r
'(?:www\.)?invidious\.tube',
301 r
'(?:www\.)?invidiou\.site',
302 r
'(?:www\.)?invidious\.site',
303 r
'(?:www\.)?invidious\.xyz',
304 r
'(?:www\.)?invidious\.nixnet\.xyz',
305 r
'(?:www\.)?invidious\.048596\.xyz',
306 r
'(?:www\.)?invidious\.drycat\.fr',
307 r
'(?:www\.)?inv\.skyn3t\.in',
308 r
'(?:www\.)?tube\.poal\.co',
309 r
'(?:www\.)?tube\.connect\.cafe',
310 r
'(?:www\.)?vid\.wxzm\.sx',
311 r
'(?:www\.)?vid\.mint\.lgbt',
312 r
'(?:www\.)?vid\.puffyan\.us',
313 r
'(?:www\.)?yewtu\.be',
314 r
'(?:www\.)?yt\.elukerio\.org',
315 r
'(?:www\.)?yt\.lelux\.fi',
316 r
'(?:www\.)?invidious\.ggc-project\.de',
317 r
'(?:www\.)?yt\.maisputain\.ovh',
318 r
'(?:www\.)?ytprivate\.com',
319 r
'(?:www\.)?invidious\.13ad\.de',
320 r
'(?:www\.)?invidious\.toot\.koeln',
321 r
'(?:www\.)?invidious\.fdn\.fr',
322 r
'(?:www\.)?watch\.nettohikari\.com',
323 r
'(?:www\.)?invidious\.namazso\.eu',
324 r
'(?:www\.)?invidious\.silkky\.cloud',
325 r
'(?:www\.)?invidious\.exonip\.de',
326 r
'(?:www\.)?invidious\.riverside\.rocks',
327 r
'(?:www\.)?invidious\.blamefran\.net',
328 r
'(?:www\.)?invidious\.moomoo\.de',
329 r
'(?:www\.)?ytb\.trom\.tf',
330 r
'(?:www\.)?yt\.cyberhost\.uk',
331 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
332 r
'(?:www\.)?qklhadlycap4cnod\.onion',
333 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
334 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
335 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
336 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
337 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
338 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
339 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
340 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
341 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
342 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
343 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
344 r
'(?:www\.)?piped\.kavin\.rocks',
345 r
'(?:www\.)?piped\.silkky\.cloud',
346 r
'(?:www\.)?piped\.tokhmi\.xyz',
347 r
'(?:www\.)?piped\.moomoo\.me',
349 r
'(?:www\.)?piped\.syncpundit\.com',
350 r
'(?:www\.)?piped\.mha\.fi',
351 r
'(?:www\.)?piped\.mint\.lgbt',
352 r
'(?:www\.)?piped\.privacy\.com\.de',
355 def _initialize_consent(self
):
356 cookies
= self
._get
_cookies
('https://www.youtube.com/')
357 if cookies
.get('__Secure-3PSID'):
360 consent
= cookies
.get('CONSENT')
362 if 'YES' in consent
.value
:
364 consent_id
= self
._search
_regex
(
365 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
367 consent_id
= random
.randint(100, 999)
368 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
370 def _initialize_pref(self
):
371 cookies
= self
._get
_cookies
('https://www.youtube.com/')
372 pref_cookie
= cookies
.get('PREF')
376 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
378 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
379 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
380 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
382 def _real_initialize(self
):
383 self
._initialize
_pref
()
384 self
._initialize
_consent
()
385 self
._check
_login
_required
()
387 def _check_login_required(self
):
388 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
389 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
391 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
392 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
394 def _get_default_ytcfg(self, client='web'):
395 return copy.deepcopy(INNERTUBE_CLIENTS[client])
397 def _get_innertube_host(self, client='web'):
398 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
400 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
401 # try_get but with fallback to default ytcfg client values when present
402 _func = lambda y: try_get(y, getter, expected_type)
403 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
405 def _extract_client_name(self, ytcfg, default_client='web'):
406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
410 def _extract_client_version(self, ytcfg, default_client='web'):
411 return self._ytcfg_get_safe(
412 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
413 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
415 def _select_api_hostname(self, req_api_hostname, default_client=None):
416 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
417 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
419 def _extract_api_key(self, ytcfg=None, default_client='web'):
420 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
422 def _extract_context(self, ytcfg=None, default_client='web'):
424 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
425 # Enforce language and tz for extraction
426 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
427 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
432 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
433 time_now = round(time.time())
434 if self._SAPISID is None:
435 yt_cookies = self._get_cookies('https://www.youtube.com')
436 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
437 # See: https://github.com/yt-dlp/yt-dlp/issues/393
438 sapisid_cookie = dict_get(
439 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
440 if sapisid_cookie and sapisid_cookie.value:
441 self._SAPISID = sapisid_cookie.value
442 self.write_debug('Extracted SAPISID cookie')
443 # SAPISID cookie is required if not already present
444 if not yt_cookies.get('SAPISID'):
445 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
447 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
449 self._SAPISID = False
450 if not self._SAPISID:
452 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
453 sapisidhash = hashlib.sha1(
454 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
455 return f'SAPISIDHASH {time_now}_{sapisidhash}'
457 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
458 note='Downloading API JSON', errnote='Unable to download API page',
459 context=None, api_key=None, api_hostname=None, default_client='web'):
461 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
463 real_headers = self.generate_api_headers(default_client=default_client)
464 real_headers.update({'content-type': 'application/json'})
466 real_headers.update(headers)
467 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
468 or api_key or self._extract_api_key(default_client=default_client))
469 return self._download_json(
470 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
471 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
472 data=json.dumps(data).encode('utf8'), headers=real_headers,
473 query={'key': api_key, 'prettyPrint': 'false'})
475 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
476 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
479 def _extract_session_index(*data):
481 Index of current account in account list.
482 See: https://github.com/yt-dlp/yt-dlp/pull/519
485 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
486 if session_index is not None:
490 def _extract_identity_token(self, ytcfg=None, webpage=None):
492 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
496 return self._search_regex(
497 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
498 'identity token
', default=None, fatal=False)
501 def _extract_account_syncid(*args):
503 Extract syncId required to download private playlists of secondary channels
504 @params response and/or ytcfg
507 # ytcfg includes channel_syncid if on secondary channel
508 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
512 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
513 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
514 if len(sync_ids) >= 2 and sync_ids[1]:
515 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
516 # and just "user_syncid||" for primary channel. We only want the channel_syncid
520 def _extract_visitor_data(*args):
522 Extracts visitorData from an API response or ytcfg
523 Appears to be used to track session state
526 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
529 @functools.cached_property
530 def is_authenticated(self):
531 return bool(self._generate_sapisidhash_header())
533 def extract_ytcfg(self, video_id, webpage):
536 return self._parse_json(
538 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
539 default='{}'), video_id, fatal=False) or {}
541 def generate_api_headers(
542 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
543 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
545 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
547 'X-YouTube-Client-Name': str(
548 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
549 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
551 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
552 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
553 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
555 if session_index
is None:
556 session_index
= self
._extract
_session
_index
(ytcfg
)
557 if account_syncid
or session_index
is not None:
558 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
560 auth
= self
._generate
_sapisidhash
_header
(origin
)
562 headers
['Authorization'] = auth
563 headers
['X-Origin'] = origin
564 return {h: v for h, v in headers.items() if v is not None}
566 def _download_ytcfg(self
, client
, video_id
):
568 'web': 'https://www.youtube.com',
569 'web_music': 'https://music.youtube.com',
570 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
574 webpage
= self
._download
_webpage
(
575 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
576 return self
.extract_ytcfg(video_id
, webpage
) or {}
579 def _build_api_continuation_query(continuation
, ctp
=None):
581 'continuation': continuation
583 # TODO: Inconsistency with clickTrackingParams.
584 # Currently we have a fixed ctp contained within context (from ytcfg)
585 # and a ctp in root query for continuation.
587 query
['clickTracking'] = {'clickTrackingParams': ctp}
591 def _extract_next_continuation_data(cls
, renderer
):
592 next_continuation
= try_get(
593 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
594 lambda x
: x
['continuation']['reloadContinuationData']), dict)
595 if not next_continuation
:
597 continuation
= next_continuation
.get('continuation')
600 ctp
= next_continuation
.get('clickTrackingParams')
601 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
604 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
605 if isinstance(continuation_ep
, dict):
606 continuation
= try_get(
607 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
610 ctp
= continuation_ep
.get('clickTrackingParams')
611 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
614 def _extract_continuation(cls
, renderer
):
615 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
616 if next_continuation
:
617 return next_continuation
620 for key
in ('contents', 'items'):
621 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
623 for content
in contents
:
624 if not isinstance(content
, dict):
626 continuation_ep
= try_get(
627 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
628 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
630 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
635 def _extract_alerts(cls
, data
):
636 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
637 if not isinstance(alert_dict
, dict):
639 for alert
in alert_dict
.values():
640 alert_type
= alert
.get('type')
643 message
= cls
._get
_text
(alert
, 'text')
645 yield alert_type
, message
647 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
650 for alert_type
, alert_message
in alerts
:
651 if alert_type
.lower() == 'error' and fatal
:
652 errors
.append([alert_type
, alert_message
])
654 warnings
.append([alert_type
, alert_message
])
656 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
657 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
659 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
661 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
662 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
664 def _extract_badges(self
, renderer
: dict):
666 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
667 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], str)
669 badges
.add(label
.lower())
673 def _get_text(data
, *path_list
, max_runs
=None):
674 for path
in path_list
or [None]:
678 obj
= traverse_obj(data
, path
, default
=[])
679 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
682 text
= try_get(item
, lambda x
: x
['simpleText'], str)
685 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
686 if not runs
and isinstance(item
, list):
689 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
690 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
694 def _get_count(self
, data
, *path_list
):
695 count_text
= self
._get
_text
(data
, *path_list
) or ''
696 count
= parse_count(count_text
)
699 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
703 def _extract_thumbnails(data
, *path_list
):
705 Extract thumbnails from thumbnails dict
706 @param path_list: path list to level that contains 'thumbnails' key
709 for path
in path_list
or [()]:
710 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
711 thumbnail_url
= url_or_none(thumbnail
.get('url'))
712 if not thumbnail_url
:
714 # Sometimes youtube gives a wrong thumbnail URL. See:
715 # https://github.com/yt-dlp/yt-dlp/issues/233
716 # https://github.com/ytdl-org/youtube-dl/issues/28023
717 if 'maxresdefault' in thumbnail_url
:
718 thumbnail_url
= thumbnail_url
.split('?')[0]
720 'url': thumbnail_url
,
721 'height': int_or_none(thumbnail
.get('height')),
722 'width': int_or_none(thumbnail
.get('width')),
727 def extract_relative_time(relative_time_text
):
729 Extracts a relative time from string and converts to dt object
730 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
732 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
)
734 start
= mobj
.group('start')
736 return datetime_from_str(start
)
738 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
742 def _extract_time_text(self
, renderer
, *path_list
):
743 """@returns (timestamp, time_text)"""
744 text
= self
._get
_text
(renderer
, *path_list
) or ''
745 dt
= self
.extract_relative_time(text
)
747 if isinstance(dt
, datetime
.datetime
):
748 timestamp
= calendar
.timegm(dt
.timetuple())
750 if timestamp
is None:
752 unified_timestamp(text
) or unified_timestamp(
754 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
755 text
.lower(), 'time text', default
=None)))
757 if text
and timestamp
is None:
758 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
759 return timestamp
, text
761 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
762 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
763 default_client
='web'):
764 for retry
in self
.RetryManager():
766 response
= self
._call
_api
(
767 ep
=ep
, fatal
=True, headers
=headers
,
768 video_id
=item_id
, query
=query
, note
=note
,
769 context
=self
._extract
_context
(ytcfg
, default_client
),
770 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
771 api_hostname
=api_hostname
, default_client
=default_client
)
772 except ExtractorError
as e
:
773 if not isinstance(e
.cause
, network_exceptions
):
774 return self
._error
_or
_warning
(e
, fatal
=fatal
)
775 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
779 first_bytes
= e
.cause
.read(512)
780 if not is_html(first_bytes
):
783 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
784 lambda x
: x
['error']['message'], str)
786 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
787 # Downloading page may result in intermittent 5xx HTTP error
788 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
789 # We also want to catch all other network exceptions since errors in later pages can be troublesome
790 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
791 if e
.cause
.code
not in (403, 429):
794 return self
._error
_or
_warning
(e
, fatal
=fatal
)
797 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
798 except ExtractorError
as e
:
799 # YouTube servers may return errors we want to retry on in a 200 OK response
800 # See: https://github.com/yt-dlp/yt-dlp/issues/839
801 if 'unknown error' in e
.msg
.lower():
804 return self
._error
_or
_warning
(e
, fatal
=fatal
)
805 # Youtube sometimes sends incomplete data
806 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
807 if not traverse_obj(response
, *variadic(check_get_keys
)):
808 retry
.error
= ExtractorError('Incomplete data received')
814 def is_music_url(url
):
815 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
817 def _extract_video(self
, renderer
):
818 video_id
= renderer
.get('videoId')
819 title
= self
._get
_text
(renderer
, 'title')
820 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
821 duration
= parse_duration(self
._get
_text
(
822 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
824 duration
= parse_duration(self
._search
_regex
(
825 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
826 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
827 video_id
, default
=None, group
='duration'))
829 view_count
= self
._get
_count
(renderer
, 'viewCountText')
831 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
832 channel_id
= traverse_obj(
833 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
834 expected_type
=str, get_all
=False)
835 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
836 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
837 overlay_style
= traverse_obj(
838 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
839 get_all
=False, expected_type
=str)
840 badges
= self
._extract
_badges
(renderer
)
841 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
842 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
843 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
844 expected_type
=str)) or ''
845 url
= f
'https://www.youtube.com/watch?v={video_id}'
846 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
847 url
= f
'https://www.youtube.com/shorts/{video_id}'
851 'ie_key': YoutubeIE
.ie_key(),
855 'description': description
,
856 'duration': duration
,
857 'view_count': view_count
,
858 'uploader': uploader
,
859 'channel_id': channel_id
,
860 'thumbnails': thumbnails
,
861 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
862 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
864 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
865 else 'was_live' if 'streamed' in time_text
.lower()
866 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
868 'release_timestamp': scheduled_timestamp
,
869 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
873 class YoutubeIE(YoutubeBaseInfoExtractor
):
875 _VALID_URL
= r
"""(?x)^
877 (?:https?://|//) # http(s):// or protocol-independent URL
878 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
879 (?:www\.)?deturl\.com/www\.youtube\.com|
880 (?:www\.)?pwnyoutube\.com|
881 (?:www\.)?hooktube\.com|
882 (?:www\.)?yourepeat\.com|
885 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
886 (?:.*?\#/)? # handle anchor (#/) redirect urls
887 (?: # the various things that can precede the ID:
888 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
889 |(?: # or the v= param in all its forms
890 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
891 (?:\?|\#!?) # the params delimiter ? or # or #!
892 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
897 youtu\.be| # just youtu.be/xxxx
898 vid\.plus| # or vid.plus/xxxx
899 zwearz\.com/watch| # or zwearz.com/watch/xxxx
902 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
904 )? # all until now is optional -> you can pass the naked ID
905 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
906 (?(1).+)? # if we found the ID, everything can follow
908 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
910 _EMBED_REGEX
= [r
'''(?x)
920 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
921 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
924 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
925 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$',
926 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
929 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
930 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
931 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
932 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
933 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
934 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
935 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
936 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
937 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
938 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
939 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
940 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
941 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
942 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
943 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
944 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
945 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
946 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
950 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
951 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
952 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
953 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
954 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
955 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
956 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
958 # Apple HTTP Live Streaming
959 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
960 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
961 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
962 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
963 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
964 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
965 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
966 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
969 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
970 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
971 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
972 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
973 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
974 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
975 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
979 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
980 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
984 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
985 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
986 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
987 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
988 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
989 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
992 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
993 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
994 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
995 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
996 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
997 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
999 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1000 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1001 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1002 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1003 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1004 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1008 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1010 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1011 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1012 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1017 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1019 # Dash webm audio with opus inside
1020 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1021 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1022 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1025 '_rtmp': {'protocol': 'rtmp'},
1027 # av01 video only formats sometimes served with "unknown" codecs
1028 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1029 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1030 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1031 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1032 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1033 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1034 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1035 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1037 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1044 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1046 'id': 'BaW_jenozKc',
1048 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1049 'uploader': 'Philipp Hagemeister',
1050 'uploader_id': 'phihag',
1051 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1052 'channel': 'Philipp Hagemeister',
1053 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1054 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1055 'upload_date': '20121002',
1056 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1057 'categories': ['Science & Technology'],
1058 'tags': ['youtube-dl'],
1062 'availability': 'public',
1063 'playable_in_embed': True,
1064 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1065 'live_status': 'not_live',
1069 'comment_count': int,
1070 'channel_follower_count': int
1074 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1075 'note': 'Embed-only video (#1746)',
1077 'id': 'yZIXLfi8CZQ',
1079 'upload_date': '20120608',
1080 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1081 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1082 'uploader': 'SET India',
1083 'uploader_id': 'setindia',
1084 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1087 'skip': 'Private video',
1090 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1091 'note': 'Use the first video ID in the URL',
1093 'id': 'BaW_jenozKc',
1095 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1096 'uploader': 'Philipp Hagemeister',
1097 'uploader_id': 'phihag',
1098 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1099 'channel': 'Philipp Hagemeister',
1100 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1101 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1102 'upload_date': '20121002',
1103 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1104 'categories': ['Science & Technology'],
1105 'tags': ['youtube-dl'],
1109 'availability': 'public',
1110 'playable_in_embed': True,
1111 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1112 'live_status': 'not_live',
1114 'comment_count': int,
1115 'channel_follower_count': int
1118 'skip_download': True,
1122 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1123 'note': '256k DASH audio (format 141) via DASH manifest',
1125 'id': 'a9LDPn-MO4I',
1127 'upload_date': '20121002',
1128 'uploader_id': '8KVIDEO',
1129 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1131 'uploader': '8KVIDEO',
1132 'title': 'UHDTV TEST 8K VIDEO.mp4'
1135 'youtube_include_dash_manifest': True,
1138 'skip': 'format 141 not served anymore',
1140 # DASH manifest with encrypted signature
1142 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1144 'id': 'IB3lcPjvWLA',
1146 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1147 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1149 'uploader': 'AfrojackVEVO',
1150 'uploader_id': 'AfrojackVEVO',
1151 'upload_date': '20131011',
1154 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1155 'playable_in_embed': True,
1156 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1158 'track': 'The Spark',
1159 'live_status': 'not_live',
1160 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1161 'channel': 'Afrojack',
1162 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1164 'availability': 'public',
1165 'categories': ['Music'],
1167 'alt_title': 'The Spark',
1168 'channel_follower_count': int
1171 'youtube_include_dash_manifest': True,
1172 'format': '141/bestaudio[ext=m4a]',
1175 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1177 'note': 'Embed allowed age-gate video',
1178 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1180 'id': 'HtVdAasjOgU',
1182 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1183 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1185 'uploader': 'The Witcher',
1186 'uploader_id': 'WitcherGame',
1187 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1188 'upload_date': '20140605',
1190 'categories': ['Gaming'],
1191 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1192 'availability': 'needs_auth',
1193 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1195 'channel': 'The Witcher',
1196 'live_status': 'not_live',
1198 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1199 'playable_in_embed': True,
1201 'channel_follower_count': int
1205 'note': 'Age-gate video with embed allowed in public site',
1206 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1208 'id': 'HsUATh_Nc2U',
1210 'title': 'Godzilla 2 (Official Video)',
1211 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1212 'upload_date': '20200408',
1213 'uploader_id': 'FlyingKitty900',
1214 'uploader': 'FlyingKitty',
1216 'availability': 'needs_auth',
1217 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1218 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1219 'channel': 'FlyingKitty',
1220 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1222 'categories': ['Entertainment'],
1223 'live_status': 'not_live',
1224 'tags': ['Flyingkitty', 'godzilla 2'],
1225 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1228 'playable_in_embed': True,
1229 'channel_follower_count': int
1233 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1234 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1236 'id': 'Tq92D6wQ1mg',
1237 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1239 'upload_date': '20191228',
1240 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1241 'uploader': 'Projekt Melody',
1242 'description': 'md5:17eccca93a786d51bc67646756894066',
1245 'availability': 'needs_auth',
1246 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1247 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1249 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1250 'channel': 'Projekt Melody',
1251 'live_status': 'not_live',
1252 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1253 'playable_in_embed': True,
1254 'categories': ['Entertainment'],
1256 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'comment_count': int,
1258 'channel_follower_count': int
1262 'note': 'Non-Agegated non-embeddable video',
1263 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1265 'id': 'MeJVWBSsPAY',
1267 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1268 'uploader': 'Herr Lurik',
1269 'uploader_id': 'st3in234',
1270 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1271 'upload_date': '20130730',
1272 'track': 'Such mich find mich',
1274 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1276 'playable_in_embed': False,
1277 'creator': 'OOMPH!',
1278 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1280 'alt_title': 'Such mich find mich',
1282 'channel': 'Herr Lurik',
1283 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1284 'categories': ['Music'],
1285 'availability': 'public',
1286 'uploader_url': 'http://www.youtube.com/user/st3in234',
1287 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1288 'live_status': 'not_live',
1290 'channel_follower_count': int
1294 'note': 'Non-bypassable age-gated video',
1295 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1296 'only_matching': True,
1298 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1299 # YouTube Red ad is not captured for creator
1301 'url': '__2ABJjxzNo',
1303 'id': '__2ABJjxzNo',
1306 'upload_date': '20100430',
1307 'uploader_id': 'deadmau5',
1308 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1309 'creator': 'deadmau5',
1310 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1311 'uploader': 'deadmau5',
1312 'title': 'Deadmau5 - Some Chords (HD)',
1313 'alt_title': 'Some Chords',
1314 'availability': 'public',
1316 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1318 'live_status': 'not_live',
1319 'channel': 'deadmau5',
1320 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1322 'track': 'Some Chords',
1323 'artist': 'deadmau5',
1324 'playable_in_embed': True,
1326 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1327 'categories': ['Music'],
1328 'album': 'Some Chords',
1329 'channel_follower_count': int
1331 'expected_warnings': [
1332 'DASH manifest missing',
1335 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1337 'url': 'lqQg6PlCWgI',
1339 'id': 'lqQg6PlCWgI',
1342 'upload_date': '20150827',
1343 'uploader_id': 'olympic',
1344 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1345 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1346 'uploader': 'Olympics',
1347 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1349 'release_timestamp': 1343767800,
1350 'playable_in_embed': True,
1351 'categories': ['Sports'],
1352 'release_date': '20120731',
1353 'channel': 'Olympics',
1354 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1355 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1356 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1358 'availability': 'public',
1359 'live_status': 'was_live',
1361 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1362 'channel_follower_count': int
1365 'skip_download': 'requires avconv',
1370 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1372 'id': '_b-2C3KPAM0',
1374 'stretched_ratio': 16 / 9.,
1376 'upload_date': '20110310',
1377 'uploader_id': 'AllenMeow',
1378 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1379 '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',
1381 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1382 'playable_in_embed': True,
1386 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1387 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1388 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1390 'categories': ['People & Blogs'],
1392 'live_status': 'not_live',
1393 'availability': 'unlisted',
1394 'comment_count': int,
1395 'channel_follower_count': int
1398 # url_encoded_fmt_stream_map is empty string
1400 'url': 'qEJwOuvDf7I',
1402 'id': 'qEJwOuvDf7I',
1404 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1406 'upload_date': '20150404',
1407 'uploader_id': 'spbelect',
1408 'uploader': 'Наблюдатели Петербурга',
1411 'skip_download': 'requires avconv',
1413 'skip': 'This live event has ended.',
1415 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1417 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1419 'id': 'FIl7x6_3R5Y',
1421 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1422 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1424 'upload_date': '20150625',
1425 'uploader_id': 'dorappi2000',
1426 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1427 'uploader': 'dorappi2000',
1428 'formats': 'mincount:31',
1430 'skip': 'not actual anymore',
1432 # DASH manifest with segment_list
1434 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1435 'md5': '8ce563a1d667b599d21064e982ab9e31',
1437 'id': 'CsmdDsKjzN8',
1439 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1440 'uploader': 'Airtek',
1441 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1442 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1443 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1446 'youtube_include_dash_manifest': True,
1447 'format': '135', # bestvideo
1449 'skip': 'This live event has ended.',
1452 # Multifeed videos (multiple cameras), URL is for Main Camera
1453 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1455 'id': 'jvGDaLqkpTg',
1456 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1457 'description': 'md5:e03b909557865076822aa169218d6a5d',
1461 'id': 'jvGDaLqkpTg',
1463 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1464 'description': 'md5:e03b909557865076822aa169218d6a5d',
1466 'upload_date': '20161111',
1467 'uploader': 'Team PGP',
1468 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1469 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1473 'id': '3AKt1R1aDnw',
1475 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1476 'description': 'md5:e03b909557865076822aa169218d6a5d',
1478 'upload_date': '20161111',
1479 'uploader': 'Team PGP',
1480 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1485 'id': 'RtAMM00gpVc',
1487 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1488 'description': 'md5:e03b909557865076822aa169218d6a5d',
1490 'upload_date': '20161111',
1491 'uploader': 'Team PGP',
1492 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1497 'id': '6N2fdlP3C5U',
1499 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1500 'description': 'md5:e03b909557865076822aa169218d6a5d',
1502 'upload_date': '20161111',
1503 'uploader': 'Team PGP',
1504 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1509 'skip_download': True,
1511 'skip': 'Not multifeed anymore',
1514 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1515 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1517 'id': 'gVfLd0zydlo',
1518 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1520 'playlist_count': 2,
1521 'skip': 'Not multifeed anymore',
1524 'url': 'https://vid.plus/FlRa-iH7PGw',
1525 'only_matching': True,
1528 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1529 'only_matching': True,
1532 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1533 # Also tests cut-off URL expansion in video description (see
1534 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1535 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1536 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1538 'id': 'lsguqyKfVQg',
1540 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1541 'alt_title': 'Dark Walk',
1542 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1544 'upload_date': '20151119',
1545 'uploader_id': 'IronSoulElf',
1546 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1547 'uploader': 'IronSoulElf',
1548 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1549 'track': 'Dark Walk',
1550 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1551 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1552 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1553 'categories': ['Film & Animation'],
1555 'live_status': 'not_live',
1556 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1557 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1559 'availability': 'public',
1560 'channel': 'IronSoulElf',
1561 'playable_in_embed': True,
1564 'channel_follower_count': int
1567 'skip_download': True,
1571 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1572 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1573 'only_matching': True,
1576 # Video with yt:stretch=17:0
1577 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1579 'id': 'Q39EVAstoRM',
1581 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1582 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1583 'upload_date': '20151107',
1584 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1585 'uploader': 'CH GAMER DROID',
1588 'skip_download': True,
1590 'skip': 'This video does not exist.',
1593 # Video with incomplete 'yt:stretch=16:'
1594 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1595 'only_matching': True,
1598 # Video licensed under Creative Commons
1599 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1601 'id': 'M4gD1WSo5mA',
1603 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1604 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1606 'upload_date': '20150128',
1607 'uploader_id': 'BerkmanCenter',
1608 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1609 'uploader': 'The Berkman Klein Center for Internet & Society',
1610 'license': 'Creative Commons Attribution license (reuse allowed)',
1611 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1612 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1615 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1616 'channel': 'The Berkman Klein Center for Internet & Society',
1617 'availability': 'public',
1619 'categories': ['Education'],
1620 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1621 'live_status': 'not_live',
1622 'playable_in_embed': True,
1623 'comment_count': int,
1624 'channel_follower_count': int
1627 'skip_download': True,
1631 # Channel-like uploader_url
1632 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1634 'id': 'eQcmzGIKrzg',
1636 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1637 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1639 'upload_date': '20151120',
1640 'uploader': 'Bernie Sanders',
1641 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1642 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1643 'license': 'Creative Commons Attribution license (reuse allowed)',
1644 'playable_in_embed': True,
1647 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1649 'availability': 'public',
1650 'categories': ['News & Politics'],
1651 'channel': 'Bernie Sanders',
1652 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1654 'live_status': 'not_live',
1655 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1656 'comment_count': int,
1657 'channel_follower_count': int
1660 'skip_download': True,
1664 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1665 'only_matching': True,
1668 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1669 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1670 'only_matching': True,
1673 # Rental video preview
1674 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1676 'id': 'uGpuVWrhIzE',
1678 'title': 'Piku - Trailer',
1679 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1680 'upload_date': '20150811',
1681 'uploader': 'FlixMatrix',
1682 'uploader_id': 'FlixMatrixKaravan',
1683 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1684 'license': 'Standard YouTube License',
1687 'skip_download': True,
1689 'skip': 'This video is not available.',
1692 # YouTube Red video with episode data
1693 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1695 'id': 'iqKdEhx-dD4',
1697 'title': 'Isolation - Mind Field (Ep 1)',
1698 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1700 'upload_date': '20170118',
1701 'uploader': 'Vsauce',
1702 'uploader_id': 'Vsauce',
1703 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1704 'series': 'Mind Field',
1706 'episode_number': 1,
1707 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1710 'availability': 'public',
1712 'channel': 'Vsauce',
1713 'episode': 'Episode 1',
1714 'categories': ['Entertainment'],
1715 'season': 'Season 1',
1716 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1717 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1719 'playable_in_embed': True,
1720 'live_status': 'not_live',
1721 'channel_follower_count': int
1724 'skip_download': True,
1726 'expected_warnings': [
1727 'Skipping DASH manifest',
1731 # The following content has been identified by the YouTube community
1732 # as inappropriate or offensive to some audiences.
1733 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1735 'id': '6SJNVb0GnPI',
1737 'title': 'Race Differences in Intelligence',
1738 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1740 'upload_date': '20140124',
1741 'uploader': 'New Century Foundation',
1742 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1743 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1746 'skip_download': True,
1748 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1752 'url': '1t24XAntNCY',
1753 'only_matching': True,
1756 # geo restricted to JP
1757 'url': 'sJL6WA-aGkQ',
1758 'only_matching': True,
1761 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1762 'only_matching': True,
1765 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1769 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1770 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1771 'only_matching': True,
1775 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1776 'only_matching': True,
1779 # Video with unsupported adaptive stream type formats
1780 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1782 'id': 'Z4Vy8R84T1U',
1784 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1785 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1787 'upload_date': '20130923',
1788 'uploader': 'Amelia Putri Harwita',
1789 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1790 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1791 'formats': 'maxcount:10',
1794 'skip_download': True,
1795 'youtube_include_dash_manifest': False,
1797 'skip': 'not actual anymore',
1800 # Youtube Music Auto-generated description
1801 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1803 'id': 'MgNrAu2pzNs',
1805 'title': 'Voyeur Girl',
1806 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1807 'upload_date': '20190312',
1808 'uploader': 'Stephen - Topic',
1809 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1810 'artist': 'Stephen',
1811 'track': 'Voyeur Girl',
1812 'album': 'it\'s too much love to know my dear',
1813 'release_date': '20190313',
1814 'release_year': 2019,
1815 'alt_title': 'Voyeur Girl',
1817 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1818 'playable_in_embed': True,
1820 'categories': ['Music'],
1821 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'channel': 'Stephen',
1823 'availability': 'public',
1824 'creator': 'Stephen',
1826 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1828 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1830 'live_status': 'not_live',
1831 'channel_follower_count': int
1834 'skip_download': True,
1838 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1839 'only_matching': True,
1842 # invalid -> valid video id redirection
1843 'url': 'DJztXj2GPfl',
1845 'id': 'DJztXj2GPfk',
1847 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1848 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1849 'upload_date': '20090125',
1850 'uploader': 'Prochorowka',
1851 'uploader_id': 'Prochorowka',
1852 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1853 'artist': 'Panjabi MC',
1854 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1855 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1858 'skip_download': True,
1860 'skip': 'Video unavailable',
1863 # empty description results in an empty string
1864 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1866 'id': 'x41yOUIvK2k',
1868 'title': 'IMG 3456',
1870 'upload_date': '20170613',
1871 'uploader_id': 'ElevageOrVert',
1872 'uploader': 'ElevageOrVert',
1874 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1875 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1877 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1879 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1880 'availability': 'public',
1882 'categories': ['Pets & Animals'],
1884 'playable_in_embed': True,
1885 'live_status': 'not_live',
1886 'channel': 'ElevageOrVert',
1887 'channel_follower_count': int
1890 'skip_download': True,
1894 # with '};' inside yt initial data (see [1])
1895 # see [2] for an example with '};' inside ytInitialPlayerResponse
1896 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1897 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1898 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1900 'id': 'CHqg6qOn4no',
1902 'title': 'Part 77 Sort a list of simple types in c#',
1903 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1904 'upload_date': '20130831',
1905 'uploader_id': 'kudvenkat',
1906 'uploader': 'kudvenkat',
1907 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1909 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1910 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1911 'live_status': 'not_live',
1912 'categories': ['Education'],
1913 'availability': 'public',
1914 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1916 'playable_in_embed': True,
1920 'channel': 'kudvenkat',
1921 'comment_count': int,
1922 'channel_follower_count': int
1925 'skip_download': True,
1929 # another example of '};' in ytInitialData
1930 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1931 'only_matching': True,
1934 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1935 'only_matching': True,
1938 # https://github.com/ytdl-org/youtube-dl/pull/28094
1939 'url': 'OtqTfy26tG0',
1941 'id': 'OtqTfy26tG0',
1943 'title': 'Burn Out',
1944 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1945 'upload_date': '20141120',
1946 'uploader': 'The Cinematic Orchestra - Topic',
1947 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1948 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1949 'artist': 'The Cinematic Orchestra',
1950 'track': 'Burn Out',
1951 'album': 'Every Day',
1953 'live_status': 'not_live',
1954 'alt_title': 'Burn Out',
1958 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1959 'creator': 'The Cinematic Orchestra',
1960 'channel': 'The Cinematic Orchestra',
1961 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1962 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1963 'availability': 'public',
1964 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1965 'categories': ['Music'],
1966 'playable_in_embed': True,
1967 'channel_follower_count': int
1970 'skip_download': True,
1974 # controversial video, only works with bpctr when authenticated with cookies
1975 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1976 'only_matching': True,
1979 # controversial video, requires bpctr/contentCheckOk
1980 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1982 'id': 'SZJvDhaSDnc',
1984 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1985 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1986 'uploader': 'CBS Mornings',
1987 'uploader_id': 'CBSThisMorning',
1988 'upload_date': '20140716',
1989 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1991 'categories': ['News & Politics'],
1992 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1994 'channel': 'CBS Mornings',
1995 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1996 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1998 'availability': 'needs_auth',
1999 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2001 'live_status': 'not_live',
2002 'playable_in_embed': True,
2003 'channel_follower_count': int
2007 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2008 'url': 'cBvYw8_A0vQ',
2010 'id': 'cBvYw8_A0vQ',
2012 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2013 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2014 'upload_date': '20201120',
2015 'uploader': 'Walk around Japan',
2016 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2017 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2019 'categories': ['Travel & Events'],
2020 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2022 'channel': 'Walk around Japan',
2023 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2024 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2026 'availability': 'public',
2027 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2028 'live_status': 'not_live',
2029 'playable_in_embed': True,
2030 'channel_follower_count': int
2033 'skip_download': True,
2036 # Has multiple audio streams
2037 'url': 'WaOKSUlf4TM',
2038 'only_matching': True
2040 # Requires Premium: has format 141 when requested using YTM url
2041 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2042 'only_matching': True
2044 # multiple subtitles with same lang_code
2045 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2046 'only_matching': True,
2048 # Force use android client fallback
2049 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2051 'id': 'YOelRv7fMxY',
2052 'title': 'DIGGING A SECRET TUNNEL Part 1',
2054 'upload_date': '20210624',
2055 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2056 'uploader': 'colinfurze',
2057 'uploader_id': 'colinfurze',
2058 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2059 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2061 'categories': ['Entertainment'],
2062 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2064 'channel': 'colinfurze',
2065 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2066 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2068 'availability': 'public',
2070 'live_status': 'not_live',
2071 'playable_in_embed': True,
2072 'channel_follower_count': int
2075 'format': '17', # 3gp format available on android
2076 'extractor_args': {'youtube': {'player_client': ['android']}},
2080 # Skip download of additional client configs (remix client config in this case)
2081 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2082 'only_matching': True,
2084 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2088 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2089 'only_matching': True,
2091 'note': 'Storyboards',
2092 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2094 'id': '5KLPxDtMqe8',
2097 'title': 'Your Brain is Plastic',
2098 'uploader_id': 'scishow',
2099 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2100 'upload_date': '20140324',
2101 'uploader': 'SciShow',
2103 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2104 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2106 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2107 'playable_in_embed': True,
2109 'uploader_url': 'http://www.youtube.com/user/scishow',
2110 'availability': 'public',
2111 'channel': 'SciShow',
2112 'live_status': 'not_live',
2114 'categories': ['Education'],
2116 'channel_follower_count': int
2117 }, 'params': {'format': 'mhtml', 'skip_download': True}
2119 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2120 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2122 'id': '2NUZ8W2llS4',
2124 'title': 'The NP that test your phone performance 🙂',
2125 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2126 'uploader': 'Leon Nguyen',
2127 'uploader_id': 'VNSXIII',
2128 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2129 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2130 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2134 'categories': ['Gaming'],
2136 'playable_in_embed': True,
2137 'live_status': 'not_live',
2138 'upload_date': '20220103',
2140 'availability': 'public',
2141 'channel': 'Leon Nguyen',
2142 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2143 'comment_count': int,
2144 'channel_follower_count': int
2147 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2148 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2150 'id': 'mzZzzBU6lrM',
2152 'title': 'I Met GeorgeNotFound In Real Life...',
2153 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2154 'uploader': 'Quackity',
2155 'uploader_id': 'QuackityHQ',
2156 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2157 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2158 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2162 'categories': ['Entertainment'],
2164 'playable_in_embed': True,
2165 'live_status': 'not_live',
2166 'release_timestamp': 1641172509,
2167 'release_date': '20220103',
2168 'upload_date': '20220103',
2170 'availability': 'public',
2171 'channel': 'Quackity',
2172 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2173 'channel_follower_count': int
2176 { # continuous livestream. Microformat upload date should be preferred.
2177 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2178 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2180 'id': 'kgx4WGK0oNU',
2181 '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}',
2183 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2184 'availability': 'public',
2186 'release_timestamp': 1637975704,
2187 'upload_date': '20210619',
2188 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2189 'live_status': 'is_live',
2190 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2191 'uploader': '阿鲍Abao',
2192 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2193 'channel': 'Abao in Tokyo',
2194 'channel_follower_count': int,
2195 'release_date': '20211127',
2197 'categories': ['People & Blogs'],
2199 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2201 'playable_in_embed': True,
2202 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2204 'params': {'skip_download': True}
2206 # Story. Requires specific player params to work.
2207 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2209 'id': 'vv8qTUWmulI',
2211 'availability': 'unlisted',
2213 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2214 'upload_date': '20220526',
2215 'categories': ['Education'],
2217 'channel': 'IT\'S HISTORY',
2219 'uploader_id': 'BlastfromthePast',
2221 'uploader': 'IT\'S HISTORY',
2222 'playable_in_embed': True,
2224 'live_status': 'not_live',
2226 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2227 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2228 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2230 'skip': 'stories get removed after some period of time',
2232 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2234 'id': 'tjjjtzRLHvA',
2236 'title': 'ハッシュタグ無し };if window.ytcsi',
2237 'upload_date': '20220323',
2239 'availability': 'unlisted',
2240 'channel': 'nao20010128nao',
2241 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2243 'uploader': 'nao20010128nao',
2244 'uploader_id': 'nao20010128nao',
2245 'categories': ['Music'],
2248 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2249 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2250 'live_status': 'not_live',
2251 'playable_in_embed': True,
2252 'channel_follower_count': int,
2255 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2261 # YouTube <object> embed
2263 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2264 'md5': '873c81d308b979f0e23ee7e620b312a3',
2266 'id': 'msN87y-iEx0',
2268 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2269 'upload_date': '20080526',
2270 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2271 'uploader': 'Christopher Sykes',
2272 'uploader_id': 'ChristopherJSykes',
2274 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2275 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2276 'playable_in_embed': True,
2277 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2279 'comment_count': int,
2280 'channel': 'Christopher Sykes',
2281 'live_status': 'not_live',
2282 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2283 'availability': 'public',
2286 'categories': ['Science & Technology'],
2287 'channel_follower_count': int,
2288 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2291 'skip_download': True,
2297 def suitable(cls, url):
2298 from ..utils import parse_qs
2301 if qs.get('list', [None])[0]:
2303 return super().suitable(url)
2305 def __init__(self, *args, **kwargs):
2306 super().__init__(*args, **kwargs)
2307 self._code_cache = {}
2308 self._player_cache = {}
2310 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2311 lock = threading.Lock()
2314 start_time = time.time()
2315 formats = [f for f in formats if f.get('is_from_start')]
2317 def refetch_manifest(format_id, delay):
2318 nonlocal formats, start_time, is_live
2319 if time.time() <= start_time + delay:
2322 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2323 video_details = traverse_obj(
2324 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2325 microformats = traverse_obj(
2326 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2327 expected_type=dict, default=[])
2328 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2329 start_time = time.time()
2331 def mpd_feed(format_id, delay):
2333 @returns (manifest_url, manifest_stream_number, is_live) or None
2336 refetch_manifest(format_id, delay)
2338 f = next((f for f in formats if f['format_id'] == format_id), None)
2341 self.to_screen(f'{video_id}: Video is no longer live')
2343 self.report_warning(
2344 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2346 return f['manifest_url'], f['manifest_stream_number'], is_live
2350 f['protocol'] = 'http_dash_segments_generator'
2351 f['fragments'] = functools.partial(
2352 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2354 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2355 FETCH_SPAN, MAX_DURATION = 5, 432000
2357 mpd_url, stream_number, is_live = None, None, True
2360 download_start_time = ctx.get('start') or time.time()
2362 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2363 if lack_early_segments:
2364 self.report_warning(bug_reports_message(
2365 'Starting download from the last 120 hours of the live stream since '
2366 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2367 lack_early_segments = True
2369 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2370 fragments, fragment_base_url = None, None
2372 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2373 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2374 # Obtain from MPD's maximum seq value
2375 old_mpd_url = mpd_url
2376 last_error = ctx.pop('last_error', None)
2377 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2378 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2379 or (mpd_url, stream_number, False))
2380 if not refresh_sequence:
2381 if expire_fast and not is_live:
2382 return False, last_seq
2383 elif old_mpd_url == mpd_url:
2384 return True, last_seq
2386 fmts, _ = self._extract_mpd_formats_and_subtitles(
2387 mpd_url, None, note=False, errnote=False, fatal=False)
2388 except ExtractorError:
2391 no_fragment_score += 2
2392 return False, last_seq
2393 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2394 fragments = fmt_info['fragments']
2395 fragment_base_url = fmt_info['fragment_base_url']
2396 assert fragment_base_url
2398 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2399 return True, _last_seq
2402 fetch_time = time.time()
2403 if no_fragment_score > 30:
2405 if last_segment_url:
2406 # Obtain from "X-Head-Seqnum" header value from each segment
2408 urlh = self._request_webpage(
2409 last_segment_url, None, note=False, errnote=False, fatal=False)
2410 except ExtractorError:
2412 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2413 if last_seq is None:
2414 no_fragment_score += 2
2415 last_segment_url = None
2418 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2419 no_fragment_score += 2
2420 if not should_continue:
2423 if known_idx > last_seq:
2424 last_segment_url = None
2429 if begin_index < 0 and known_idx < 0:
2430 # skip from the start when it's negative value
2431 known_idx = last_seq + begin_index
2432 if lack_early_segments:
2433 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2435 for idx in range(known_idx, last_seq):
2436 # do not update sequence here or you'll get skipped some part of it
2437 should_continue, _ = _extract_sequence_from_mpd(False, False)
2438 if not should_continue:
2440 raise ExtractorError('breaking out of outer loop')
2441 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2443 'url': last_segment_url,
2444 'fragment_count': last_seq,
2446 if known_idx == last_seq:
2447 no_fragment_score += 5
2449 no_fragment_score = 0
2450 known_idx = last_seq
2451 except ExtractorError:
2454 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2456 def _extract_player_url(self, *ytcfgs, webpage=None):
2457 player_url = traverse_obj(
2458 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2459 get_all=False, expected_type=str)
2462 return urljoin('https://www.youtube.com', player_url)
2464 def _download_player_url(self, video_id, fatal=False):
2465 res = self._download_webpage(
2466 'https://www.youtube.com/iframe_api',
2467 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2469 player_version = self._search_regex(
2470 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2472 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2474 def _signature_cache_id(self, example_sig):
2475 """ Return a string representation of a signature """
2476 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2479 def _extract_player_info(cls, player_url):
2480 for player_re in cls._PLAYER_INFO_RE:
2481 id_m = re.search(player_re, player_url)
2485 raise ExtractorError('Cannot identify player %r' % player_url)
2486 return id_m.group('id')
2488 def _load_player(self, video_id, player_url, fatal=True):
2489 player_id = self._extract_player_info(player_url)
2490 if player_id not in self._code_cache:
2491 code = self._download_webpage(
2492 player_url, video_id, fatal=fatal,
2493 note='Downloading player ' + player_id,
2494 errnote='Download of %s failed' % player_url)
2496 self._code_cache[player_id] = code
2497 return self._code_cache.get(player_id)
2499 def _extract_signature_function(self, video_id, player_url, example_sig):
2500 player_id = self._extract_player_info(player_url)
2502 # Read from filesystem cache
2503 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2504 assert os.path.basename(func_id) == func_id
2506 self.write_debug(f'Extracting signature function {func_id}')
2507 cache_spec = self.cache.load('youtube-sigfuncs', func_id)
2508 if cache_spec is not None:
2509 return lambda s: ''.join(s[i] for i in cache_spec)
2511 code = self._load_player(video_id, player_url)
2513 res = self._parse_sig_js(code)
2515 test_string = ''.join(map(chr, range(len(example_sig))))
2516 cache_res = res(test_string)
2517 cache_spec = [ord(c) for c in cache_res]
2519 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2522 def _print_sig_code(self, func, example_sig):
2523 if not self.get_param('youtube_print_sig_code'):
2526 def gen_sig_code(idxs):
2527 def _genslice(start, end, step):
2528 starts = '' if start == 0 else str(start)
2529 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2530 steps = '' if step == 1 else (':%d' % step)
2531 return f's[{starts}{ends}{steps}]'
2534 # Quelch pyflakes warnings - start will be set when step is set
2535 start = '(Never used)'
2536 for i, prev in zip(idxs[1:], idxs[:-1]):
2537 if step is not None:
2538 if i - prev == step:
2540 yield _genslice(start, prev, step)
2543 if i - prev in [-1, 1]:
2548 yield 's[%d]' % prev
2552 yield _genslice(start, i, step)
2554 test_string = ''.join(map(chr, range(len(example_sig))))
2555 cache_res = func(test_string)
2556 cache_spec = [ord(c) for c in cache_res]
2557 expr_code = ' + '.join(gen_sig_code(cache_spec))
2558 signature_id_tuple = '(%s)' % (
2559 ', '.join(str(len(p)) for p in example_sig.split('.')))
2560 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2561 ' return %s\n') % (signature_id_tuple, expr_code)
2562 self.to_screen('Extracted signature function:\n' + code)
2564 def _parse_sig_js(self, jscode):
2565 funcname = self._search_regex(
2566 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2567 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2568 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2569 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2570 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}\(a,\d+\)',
2571 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\(\s*""\s*\)',
2572 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2574 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2575 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2576 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2577 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2578 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2579 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2580 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2581 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2582 jscode, 'Initial JS player signature function name', group='sig')
2584 jsi = JSInterpreter(jscode)
2585 initial_function = jsi.extract_function(funcname)
2586 return lambda s: initial_function([s])
2588 def _decrypt_signature(self, s, video_id, player_url):
2589 """Turn the encrypted s field into a working signature"""
2591 player_id = (player_url, self._signature_cache_id(s))
2592 if player_id not in self._player_cache:
2593 func = self._extract_signature_function(video_id, player_url, s)
2594 self._player_cache[player_id] = func
2595 func = self._player_cache[player_id]
2596 self._print_sig_code(func, s)
2598 except Exception as e:
2599 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2601 def _decrypt_nsig(self, s, video_id, player_url):
2602 """Turn the encrypted n field into a working signature"""
2603 if player_url is None:
2604 raise ExtractorError('Cannot decrypt nsig without player_url')
2605 player_url = urljoin('https://www.youtube.com', player_url)
2607 sig_id = ('nsig_value', s)
2608 if sig_id in self._player_cache:
2609 return self._player_cache[sig_id]
2612 player_id = ('nsig', player_url)
2613 if player_id not in self._player_cache:
2614 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2615 func = self._player_cache[player_id]
2616 self._player_cache[sig_id] = func(s)
2617 self.write_debug(f'Decrypted nsig {s} => {self._player_cache[sig_id]}')
2618 return self._player_cache[sig_id]
2619 except Exception as e:
2620 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2622 def _extract_n_function_name(self, jscode):
2623 nfunc, idx = self._search_regex(
2624 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2625 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2628 return json.loads(js_to_json(self._search_regex(
2629 rf'var {re.escape(nfunc)}\s*=\s*(\[.+?\]);', jscode,
2630 f'Initial JS player n function list ({nfunc}.{idx})')))[int(idx)]
2632 def _extract_n_function(self, video_id, player_url):
2633 player_id = self._extract_player_info(player_url)
2634 func_code = self.cache.load('youtube-nsig', player_id)
2637 jsi = JSInterpreter(func_code)
2639 jscode = self._load_player(video_id, player_url)
2640 funcname = self._extract_n_function_name(jscode)
2641 jsi = JSInterpreter(jscode)
2642 func_code = jsi.extract_function_code(funcname)
2643 self.cache.store('youtube-nsig', player_id, func_code)
2645 if self.get_param('youtube_print_sig_code'):
2646 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2648 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2650 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2652 Extract signatureTimestamp (sts)
2653 Required to tell API what sig/player version is in use.
2656 if isinstance(ytcfg, dict):
2657 sts = int_or_none(ytcfg.get('STS'))
2660 # Attempt to extract from player
2661 if player_url is None:
2662 error_msg = 'Cannot extract signature timestamp without player_url.'
2664 raise ExtractorError(error_msg)
2665 self.report_warning(error_msg)
2667 code = self._load_player(video_id, player_url, fatal=fatal)
2669 sts = int_or_none(self._search_regex(
2670 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2671 'JS player signature timestamp', group='sts', fatal=fatal))
2674 def _mark_watched(self, video_id, player_responses):
2675 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2676 label = 'fully ' if is_full else ''
2677 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2678 expected_type=url_or_none)
2680 self.report_warning(f'Unable to mark {label}watched')
2682 parsed_url = urllib.parse.urlparse(url)
2683 qs = urllib.parse.parse_qs(parsed_url.query)
2685 # cpn generation algorithm is reverse engineered from base.js.
2686 # In fact it works even with dummy cpn.
2687 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2688 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2690 # # more consistent results setting it to right before the end
2691 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2696 'cmt': video_length,
2697 'el': 'detailpage', # otherwise defaults to "shorts"
2701 # these seem to mark watchtime "history" in the real world
2702 # they're required, so send in a single value
2708 url = urllib.parse.urlunparse(
2709 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2711 self._download_webpage(
2712 url, video_id, f'Marking {label}watched',
2713 'Unable to mark watched', fatal=False)
2716 def _extract_from_webpage(cls, url, webpage):
2717 # Invidious Instances
2718 # https://github.com/yt-dlp/yt-dlp/issues/195
2719 # https://github.com/iv-org/invidious/pull/1730
2721 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2724 yield cls.url_result(mobj.group('url'), cls)
2725 raise cls.StopExtraction()
2727 yield from super()._extract_from_webpage(url, webpage)
2729 # lazyYT YouTube embed
2730 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2731 yield cls.url_result(unescapeHTML(id_), cls, id_)
2733 # Wordpress "YouTube Video Importer" plugin
2734 for m in re.findall(r'''(?x
)<div
[^
>]+
2735 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2736 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
2737 yield cls.url_result(m[-1], cls, m[-1])
2740 def extract_id(cls, url):
2741 video_id = cls.get_temp_id(url)
2743 raise ExtractorError(f'Invalid URL: {url}')
2746 def _extract_chapters_from_json(self, data, duration):
2747 chapter_list = traverse_obj(
2749 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2750 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2751 ), expected_type=list)
2753 return self._extract_chapters(
2755 chapter_time=lambda chapter: float_or_none(
2756 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2757 chapter_title=lambda chapter: traverse_obj(
2758 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2761 def _extract_chapters_from_engagement_panel(self, data, duration):
2762 content_list = traverse_obj(
2764 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2765 expected_type=list, default=[])
2766 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2767 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2769 return next(filter(None, (
2770 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2771 chapter_time, chapter_title, duration)
2772 for contents in content_list)), [])
2774 def _extract_chapters_from_description(self, description, duration):
2775 return self._extract_chapters(
2776 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2777 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2778 duration=duration, strict=False)
2780 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2784 'start_time': chapter_time(chapter),
2785 'title': chapter_title(chapter),
2786 } for chapter in chapter_list or []]
2788 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2790 chapters = [{'start_time': 0}]
2791 for idx, chapter in enumerate(chapter_list):
2792 if chapter['start_time'] is None:
2793 self.report_warning(f'Incomplete chapter {idx}')
2794 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2795 chapters.append(chapter)
2797 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2800 def _extract_comment(self, comment_renderer, parent=None):
2801 comment_id = comment_renderer.get('commentId')
2805 text = self._get_text(comment_renderer, 'contentText')
2807 # note: timestamp is an estimate calculated from the current time and time_text
2808 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2809 author = self._get_text(comment_renderer, 'authorText')
2810 author_id = try_get(comment_renderer,
2811 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2813 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2814 lambda x: x['likeCount']), str)) or 0
2815 author_thumbnail = try_get(comment_renderer,
2816 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2818 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2819 is_favorited = 'creatorHeart' in (try_get(
2820 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2824 'timestamp': timestamp,
2825 'time_text': time_text,
2826 'like_count': votes,
2827 'is_favorited': is_favorited,
2829 'author_id': author_id,
2830 'author_thumbnail': author_thumbnail,
2831 'author_is_uploader': author_is_uploader,
2832 'parent': parent or 'root'
2835 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2837 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2839 def extract_header(contents):
2840 _continuation = None
2841 for content in contents:
2842 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2843 expected_comment_count = self._get_count(
2844 comments_header_renderer, 'countText', 'commentsCount')
2846 if expected_comment_count:
2847 tracker['est_total'] = expected_comment_count
2848 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2849 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2851 sort_menu_item = try_get(
2852 comments_header_renderer,
2853 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2854 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2856 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2857 if not _continuation:
2860 sort_text = str_or_none(sort_menu_item.get('title'))
2862 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2863 self.to_screen('Sorting comments by %s' % sort_text.lower())
2865 return _continuation
2867 def extract_thread(contents):
2869 tracker['current_page_thread'] = 0
2870 for content in contents:
2871 if not parent and tracker['total_parent_comments'] >= max_parents:
2873 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2874 comment_renderer = get_first(
2875 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2876 expected_type=dict, default={})
2878 comment = self._extract_comment(comment_renderer, parent)
2882 tracker['running_total'] += 1
2883 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2886 # Attempt to get the replies
2887 comment_replies_renderer = try_get(
2888 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2890 if comment_replies_renderer:
2891 tracker['current_page_thread'] += 1
2892 comment_entries_iter = self._comment_entries(
2893 comment_replies_renderer, ytcfg, video_id,
2894 parent=comment.get('id'), tracker=tracker)
2895 yield from itertools.islice(comment_entries_iter, min(
2896 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2898 # Keeps track of counts across recursive calls
2903 current_page_thread=0,
2904 total_parent_comments=0,
2905 total_reply_comments=0)
2908 # YouTube comments have a max depth of 2
2909 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2911 self._downloader.deprecation_warning(
2912 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2913 if max_depth == 1 and parent:
2916 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2917 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2919 continuation = self._extract_continuation(root_continuation_data)
2922 is_forced_continuation = False
2923 is_first_continuation = parent is None
2924 if is_first_continuation and not continuation:
2925 # Sometimes you can get comments by generating the continuation yourself,
2926 # even if YouTube initially reports them being disabled - e.g. stories comments.
2927 # Note: if the comment section is actually disabled, YouTube may return a response with
2928 # required check_get_keys missing. So we will disable that check initially in this case.
2929 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2930 is_forced_continuation = True
2932 for page_num in itertools.count(0):
2933 if not continuation:
2935 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2936 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
2938 if is_first_continuation:
2939 note_prefix = 'Downloading comment section API JSON'
2941 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2942 tracker['current_page_thread'], comment_prog_str)
2944 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2945 ' ' if parent else '', ' replies' if parent else '',
2946 page_num, comment_prog_str)
2948 response = self._extract_response(
2949 item_id=None, query=continuation,
2950 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2951 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2952 is_forced_continuation = False
2953 continuation_contents = traverse_obj(
2954 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2957 for continuation_section in continuation_contents:
2958 continuation_items = traverse_obj(
2959 continuation_section,
2960 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2961 get_all=False, expected_type=list) or []
2962 if is_first_continuation:
2963 continuation = extract_header(continuation_items)
2964 is_first_continuation = False
2969 for entry in extract_thread(continuation_items):
2973 continuation = self._extract_continuation({'contents': continuation_items})
2977 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2978 if message and not parent and tracker['running_total'] == 0:
2979 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2982 def _generate_comment_continuation(video_id):
2984 Generates initial comment section continuation token from given video id
2986 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2987 return base64.b64encode(token.encode()).decode()
2989 def _get_comments(self, ytcfg, video_id, contents, webpage):
2990 """Entry for comment extraction"""
2991 def _real_comment_extract(contents):
2993 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2994 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2995 yield from self._comment_entries(renderer, ytcfg, video_id)
2997 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2998 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3001 def _get_checkok_params():
3002 return {'contentCheckOk': True, 'racyCheckOk': True}
3005 def _generate_player_context(cls, sts=None):
3007 'html5Preference': 'HTML5_PREF_WANTS',
3010 context['signatureTimestamp'] = sts
3012 'playbackContext': {
3013 'contentPlaybackContext': context
3015 **cls._get_checkok_params()
3019 def _is_agegated(player_response):
3020 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3023 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3024 AGE_GATE_REASONS = (
3025 'confirm your age', 'age-restricted', 'inappropriate', # reason
3026 'age_verification_required', 'age_check_required', # status
3028 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3031 def _is_unplayable(player_response):
3032 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3034 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
3036 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3037 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3038 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3039 headers = self.generate_api_headers(
3040 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3043 'videoId': video_id,
3044 'params': '8AEB' # enable stories
3046 yt_query.update(self._generate_player_context(sts))
3047 return self._extract_response(
3048 item_id=video_id, ep='player', query=yt_query,
3049 ytcfg=player_ytcfg, headers=headers, fatal=True,
3050 default_client=client,
3051 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3054 def _get_requested_clients(self, url, smuggled_data):
3055 requested_clients = []
3056 default = ['android', 'web']
3057 allowed_clients = sorted(
3058 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3059 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3060 for client in self._configuration_arg('player_client'):
3061 if client in allowed_clients:
3062 requested_clients.append(client)
3063 elif client == 'default':
3064 requested_clients.extend(default)
3065 elif client == 'all':
3066 requested_clients.extend(allowed_clients)
3068 self.report_warning(f'Skipping unsupported client {client}')
3069 if not requested_clients:
3070 requested_clients = default
3072 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3073 requested_clients.extend(
3074 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3076 return orderedSet(requested_clients)
3078 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
3081 initial_pr = self._search_json(
3082 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3084 all_clients = set(clients)
3085 clients = clients[::-1]
3088 def append_client(*client_names):
3089 """ Append the first client name that exists but not already used """
3090 for client_name in client_names:
3091 actual_client = _split_innertube_client(client_name)[0]
3092 if actual_client in INNERTUBE_CLIENTS:
3093 if actual_client not in all_clients:
3094 clients.append(client_name)
3095 all_clients.add(actual_client)
3098 # Android player_response does not have microFormats which are needed for
3099 # extraction of some data. So we return the initial_pr with formats
3100 # stripped out even if not requested by the user
3101 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3103 pr = dict(initial_pr)
3104 pr['streamingData'] = None
3108 tried_iframe_fallback = False
3111 client, base_client, variant = _split_innertube_client(clients.pop())
3112 player_ytcfg = master_ytcfg if client == 'web' else {}
3113 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3114 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3116 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3117 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3118 if 'js' in self._configuration_arg('player_skip'):
3119 require_js_player = False
3122 if not player_url and not tried_iframe_fallback and require_js_player:
3123 player_url = self._download_player_url(video_id)
3124 tried_iframe_fallback = True
3127 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3128 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3129 except ExtractorError as e:
3131 self.report_warning(last_error)
3136 # YouTube may return a different video player response than expected.
3137 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3138 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3139 if pr_video_id and pr_video_id != video_id:
3140 self.report_warning(
3141 f'{client} client returned a player response for "{pr_video_id}
" instead of "{video_id}
"' + bug_reports_message())
3145 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3146 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3147 append_client(f'{base_client}_creator')
3148 elif self._is_agegated(pr):
3149 if variant == 'tv_embedded':
3150 append_client(f'{base_client}_embedded')
3152 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3157 self.report_warning(last_error)
3158 return prs, player_url
3160 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
3161 itags, stream_ids = {}, []
3162 itag_qualities, res_qualities = {}, {}
3164 # Normally tiny is the smallest video-only formats. But
3165 # audio-only formats with unknown quality may get tagged as tiny
3167 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3168 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3170 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3172 for fmt in streaming_formats:
3173 if fmt.get('targetDurationSec'):
3176 itag = str_or_none(fmt.get('itag'))
3177 audio_track = fmt.get('audioTrack') or {}
3178 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3179 if stream_id in stream_ids:
3182 quality = fmt.get('quality')
3183 height = int_or_none(fmt.get('height'))
3184 if quality == 'tiny' or not quality:
3185 quality = fmt.get('audioQuality', '').lower() or quality
3186 # The 3gp format (17) in android client has a quality of "small
",
3187 # but is actually worse than other formats
3192 itag_qualities[itag] = quality
3194 res_qualities[height] = quality
3195 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3196 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3197 # number of fragment that would subsequently requested with (`&sq=N`)
3198 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3201 fmt_url = fmt.get('url')
3203 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3204 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3205 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3206 if not all((sc, fmt_url, player_url, encrypted_sig)):
3209 fmt_url += '&%s=%s' % (
3210 traverse_obj(sc, ('sp', -1)) or 'signature',
3211 self._decrypt_signature(encrypted_sig, video_id, player_url)
3213 except ExtractorError as e:
3214 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3215 self.write_debug(e, only_once=True)
3218 query = parse_qs(fmt_url)
3222 fmt_url = update_url_query(fmt_url, {
3223 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3224 except ExtractorError as e:
3225 self.report_warning(
3226 'nsig extraction failed: You may experience throttling for some formats\n'
3227 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3228 self.write_debug(e, only_once=True)
3232 itags[itag] = 'https'
3233 stream_ids.append(stream_id)
3235 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3236 language_preference = (
3237 10 if audio_track.get('audioIsDefault') and 10
3238 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3240 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3241 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3242 # Make sure to avoid false positives with small duration differences.
3243 # Eg: __2ABJjxzNo, ySuUZEjARPY
3244 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3246 self.report_warning(
3247 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3249 'asr': int_or_none(fmt.get('audioSampleRate')),
3250 'filesize': int_or_none(fmt.get('contentLength')),
3252 'format_note': join_nonempty(
3253 '%s%s' % (audio_track.get('displayName') or '',
3254 ' (default)' if language_preference > 0 else ''),
3255 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3256 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3257 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3258 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3259 'fps': int_or_none(fmt.get('fps')) or None,
3261 'quality': q(quality),
3262 'has_drm': bool(fmt.get('drmFamilies')),
3265 'width': int_or_none(fmt.get('width')),
3266 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3267 'desc' if language_preference < -1 else ''),
3268 'language_preference': language_preference,
3269 # Strictly de-prioritize damaged and 3gp formats
3270 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3272 mime_mobj = re.match(
3273 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3275 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3276 dct.update(parse_codecs(mime_mobj.group(2)))
3277 no_audio = dct.get('acodec
') == 'none
'
3278 no_video = dct.get('vcodec
') == 'none
'
3283 if no_audio or no_video:
3284 dct['downloader_options
'] = {
3285 # Youtube throttles chunks >~10M
3286 'http_chunk_size
': 10485760,
3289 dct['container
'] = dct['ext
'] + '_dash
'
3292 live_from_start = is_live and self.get_param('live_from_start
')
3293 skip_manifests = self._configuration_arg('skip
')
3294 if not self.get_param('youtube_include_hls_manifest
', True):
3295 skip_manifests.append('hls
')
3296 if not self.get_param('youtube_include_dash_manifest
', True):
3297 skip_manifests.append('dash
')
3298 get_dash = 'dash
' not in skip_manifests and (
3299 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3300 get_hls = not live_from_start and 'hls
' not in skip_manifests
3302 def process_manifest_format(f, proto, itag):
3304 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3306 itag = f'{itag}
-{proto}
'
3308 f['format_id
'] = itag
3311 f['quality
'] = next((
3313 for val, qdict in ((f.get('format_id
', '').split('-')[0], itag_qualities), (f.get('height
'), res_qualities))
3314 if val in qdict), -1)
3318 for sd in streaming_data:
3319 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3320 if hls_manifest_url:
3321 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4
', fatal=False, live=is_live)
3322 subtitles = self._merge_subtitles(subs, subtitles)
3324 if process_manifest_format(f, 'hls
', self._search_regex(
3325 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3328 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3329 if dash_manifest_url:
3330 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3331 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3333 if process_manifest_format(f, 'dash
', f['format_id
']):
3334 f['filesize
'] = int_or_none(self._search_regex(
3335 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3337 f['is_from_start
'] = True
3342 def _extract_storyboard(self, player_responses, duration):
3344 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3345 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3349 for i, args in enumerate(spec):
3350 args = args.split('#')
3351 counts
= list(map(int_or_none
, args
[:5]))
3352 if len(args
) != 8 or not all(counts
):
3353 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3355 width
, height
, frame_count
, cols
, rows
= counts
3358 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3359 fragment_count
= frame_count
/ (cols
* rows
)
3360 fragment_duration
= duration
/ fragment_count
3362 'format_id': f
'sb{i}',
3363 'format_note': 'storyboard',
3365 'protocol': 'mhtml',
3371 'fps': frame_count
/ duration
,
3375 'url': url
.replace('$M', str(j
)),
3376 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3377 } for j
in range(math
.ceil(fragment_count
))],
3380 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3382 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3383 webpage
= self
._download
_webpage
(
3384 webpage_url
+ '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id
, fatal
=False)
3386 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3388 player_responses
, player_url
= self
._extract
_player
_responses
(
3389 self
._get
_requested
_clients
(url
, smuggled_data
),
3390 video_id
, webpage
, master_ytcfg
)
3392 return webpage
, master_ytcfg
, player_responses
, player_url
3394 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3395 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3396 is_live
= get_first(video_details
, 'isLive')
3398 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3400 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3401 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, is_live
, duration
)
3403 return live_broadcast_details
, is_live
, streaming_data
, formats
, subtitles
3405 def _real_extract(self
, url
):
3406 url
, smuggled_data
= unsmuggle_url(url
, {})
3407 video_id
= self
._match
_id
(url
)
3409 base_url
= self
.http_scheme() + '//www.youtube.com/'
3410 webpage_url
= base_url
+ 'watch?v=' + video_id
3412 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3414 playability_statuses
= traverse_obj(
3415 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3417 trailer_video_id
= get_first(
3418 playability_statuses
,
3419 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3421 if trailer_video_id
:
3422 return self
.url_result(
3423 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3425 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3426 if webpage
else (lambda x
: None))
3428 video_details
= traverse_obj(
3429 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3430 microformats
= traverse_obj(
3431 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3432 expected_type
=dict, default
=[])
3434 get_first(video_details
, 'title')
3435 or self
._get
_text
(microformats
, (..., 'title'))
3436 or search_meta(['og:title', 'twitter:title', 'title']))
3437 video_description
= get_first(video_details
, 'shortDescription')
3439 multifeed_metadata_list
= get_first(
3441 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3443 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3444 if self
.get_param('noplaylist'):
3445 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3449 for feed
in multifeed_metadata_list
.split(','):
3450 # Unquote should take place before split on comma (,) since textual
3451 # fields may contain comma as well (see
3452 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3453 feed_data
= urllib
.parse
.parse_qs(
3454 urllib
.parse
.unquote_plus(feed
))
3456 def feed_entry(name
):
3458 feed_data
, lambda x
: x
[name
][0], str)
3460 feed_id
= feed_entry('id')
3463 feed_title
= feed_entry('title')
3466 title
+= ' (%s)' % feed_title
3468 '_type': 'url_transparent',
3469 'ie_key': 'Youtube',
3471 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3472 {'force_singlefeed': True}
),
3475 feed_ids
.append(feed_id
)
3477 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3478 % (', '.join(feed_ids
), video_id
))
3479 return self
.playlist_result(
3480 entries
, video_id
, video_title
, video_description
)
3482 duration
= int_or_none(
3483 get_first(video_details
, 'lengthSeconds')
3484 or get_first(microformats
, 'lengthSeconds')
3485 or parse_duration(search_meta('duration'))) or None
3487 live_broadcast_details
, is_live
, streaming_data
, formats
, automatic_captions
= \
3488 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
)
3491 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3492 self
.report_drm(video_id
)
3494 playability_statuses
,
3495 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3496 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3497 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3499 if subreason
== 'The uploader has not made this video available in your country.':
3500 countries
= get_first(microformats
, 'availableCountries')
3502 regions_allowed
= search_meta('regionsAllowed')
3503 countries
= regions_allowed
.split(',') if regions_allowed
else None
3504 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3505 reason
+= f
'. {subreason}'
3507 self
.raise_no_formats(reason
, expected
=True)
3509 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3510 if not keywords
and webpage
:
3512 unescapeHTML(m
.group('content'))
3513 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3514 for keyword
in keywords
:
3515 if keyword
.startswith('yt:stretch='):
3516 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3518 # NB: float is intentional for forcing float division
3519 w
, h
= (float(v
) for v
in mobj
.groups())
3523 if f
.get('vcodec') != 'none':
3524 f
['stretched_ratio'] = ratio
3526 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3527 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3530 'url': thumbnail_url
,
3532 original_thumbnails
= thumbnails
.copy()
3534 # The best resolution thumbnails sometimes does not appear in the webpage
3535 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3536 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3538 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3539 # in resolution, these are not the custom thumbnail. So de-prioritize them
3540 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3541 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3543 n_thumbnail_names
= len(thumbnail_names
)
3545 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3546 video_id
=video_id
, name
=name
, ext
=ext
,
3547 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3548 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3549 for thumb
in thumbnails
:
3550 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3551 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3552 self
._remove
_duplicate
_formats
(thumbnails
)
3553 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3555 category
= get_first(microformats
, 'category') or search_meta('genre')
3556 channel_id
= str_or_none(
3557 get_first(video_details
, 'channelId')
3558 or get_first(microformats
, 'externalChannelId')
3559 or search_meta('channelId'))
3560 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3562 live_content
= get_first(video_details
, 'isLiveContent')
3563 is_upcoming
= get_first(video_details
, 'isUpcoming')
3565 if is_upcoming
or live_content
is False:
3567 if is_upcoming
is None and (live_content
or is_live
):
3569 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3570 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3571 if not duration
and live_end_time
and live_start_time
:
3572 duration
= live_end_time
- live_start_time
3574 if is_live
and self
.get_param('live_from_start'):
3575 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3577 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3579 # source_preference is lower for throttled/potentially damaged formats
3580 self
._sort
_formats
(formats
, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3584 'title': video_title
,
3586 'thumbnails': thumbnails
,
3587 # The best thumbnail that we are sure exists. Prevents unnecessary
3588 # URL checking if user don't care about getting the best possible thumbnail
3589 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3590 'description': video_description
,
3591 'uploader': get_first(video_details
, 'author'),
3592 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3593 'uploader_url': owner_profile_url
,
3594 'channel_id': channel_id
,
3595 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3596 'duration': duration
,
3597 'view_count': int_or_none(
3598 get_first((video_details
, microformats
), (..., 'viewCount'))
3599 or search_meta('interactionCount')),
3600 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3601 'age_limit': 18 if (
3602 get_first(microformats
, 'isFamilySafe') is False
3603 or search_meta('isFamilyFriendly') == 'false'
3604 or search_meta('og:restrictions:age') == '18+') else 0,
3605 'webpage_url': webpage_url
,
3606 'categories': [category
] if category
else None,
3608 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3610 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3611 else None if is_live
is None or is_upcoming
is None
3613 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3614 'release_timestamp': live_start_time
,
3617 if get_first(video_details
, 'isPostLiveDvr'):
3618 self
.write_debug('Video is in Post-Live Manifestless mode')
3619 info
['live_status'] = 'post_live'
3620 if (duration
or 0) > 4 * 3600:
3621 self
.report_warning(
3622 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3623 'This is a known issue and patches are welcome')
3626 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3628 def get_lang_code(track
):
3629 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3630 or track
.get('languageCode'))
3632 # Converted into dicts to remove duplicates
3634 get_lang_code(sub
): sub
3635 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3636 translation_languages
= {
3637 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3638 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3640 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3641 lang_subs
= container
.setdefault(lang_code
, [])
3642 for fmt
in self
._SUBTITLE
_FORMATS
:
3648 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3652 # NB: Constructing the full subtitle dictionary is slow
3653 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3654 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3655 for lang_code
, caption_track
in captions
.items():
3656 base_url
= caption_track
.get('baseUrl')
3657 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3660 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3661 if caption_track
.get('kind') != 'asr':
3665 subtitles
, base_url
, lang_code
, lang_name
, {})
3666 if not caption_track
.get('isTranslatable'):
3668 for trans_code
, trans_name
in translation_languages
.items():
3671 orig_trans_code
= trans_code
3672 if caption_track
.get('kind') != 'asr':
3673 if not get_translated_subs
:
3675 trans_code
+= f
'-{lang_code}'
3676 trans_name
+= format_field(lang_name
, None, ' from %s')
3677 # Add an "-orig" label to the original language so that it can be distinguished.
3678 # The subs are returned without "-orig" as well for compatibility
3679 if lang_code
== f
'a-{orig_trans_code}':
3681 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3682 # Setting tlang=lang returns damaged subtitles.
3683 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3684 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3686 info
['automatic_captions'] = automatic_captions
3687 info
['subtitles'] = subtitles
3689 parsed_url
= urllib
.parse
.urlparse(url
)
3690 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3691 query
= urllib
.parse
.parse_qs(component
)
3692 for k
, v
in query
.items():
3693 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3695 if d_k
not in info
and k
in s_ks
:
3696 info
[d_k
] = parse_duration(query
[k
][0])
3698 # Youtube Music Auto-generated description
3699 if video_description
:
3702 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3704 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3705 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3706 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3707 .+\nAuto-generated\ by\ YouTube\.\s*$
3708 ''', video_description
)
3710 release_year
= mobj
.group('release_year')
3711 release_date
= mobj
.group('release_date')
3713 release_date
= release_date
.replace('-', '')
3714 if not release_year
:
3715 release_year
= release_date
[:4]
3717 'album': mobj
.group('album'.strip()),
3718 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3719 'track': mobj
.group('track').strip(),
3720 'release_date': release_date
,
3721 'release_year': int_or_none(release_year
),
3726 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3727 if not initial_data
:
3728 query
= {'videoId': video_id}
3729 query
.update(self
._get
_checkok
_params
())
3730 initial_data
= self
._extract
_response
(
3731 item_id
=video_id
, ep
='next', fatal
=False,
3732 ytcfg
=master_ytcfg
, query
=query
,
3733 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3734 note
='Downloading initial data API JSON')
3736 info
['comment_count'] = traverse_obj(initial_data
, (
3737 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3738 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3740 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3741 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3742 ), expected_type
=int_or_none
, get_all
=False)
3744 try: # This will error if there is no livechat
3745 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3746 except (KeyError, IndexError, TypeError):
3749 info
.setdefault('subtitles', {})['live_chat'] = [{
3750 # url is needed to set cookies
3751 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3752 'video_id': video_id
,
3754 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3758 info
['chapters'] = (
3759 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3760 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3761 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3764 contents
= traverse_obj(
3765 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3766 expected_type
=list, default
=[])
3768 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3770 stl
= vpir
.get('superTitleLink')
3772 stl
= self
._get
_text
(stl
)
3775 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3776 info
['location'] = stl
3778 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3781 'series': mobj
.group(1),
3782 'season_number': int(mobj
.group(2)),
3783 'episode_number': int(mobj
.group(3)),
3785 for tlb
in (try_get(
3787 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3789 tbr
= tlb
.get('toggleButtonRenderer') or {}
3790 for getter
, regex
in [(
3791 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3792 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3793 lambda x
: x
['accessibility'],
3794 lambda x
: x
['accessibilityData']['accessibilityData'],
3795 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3796 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3798 mobj
= re
.match(regex
, label
)
3800 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3802 sbr_tooltip
= try_get(
3803 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3805 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3807 'like_count': str_to_int(like_count
),
3808 'dislike_count': str_to_int(dislike_count
),
3810 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3812 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3814 'channel': self
._get
_text
(vor
, 'title'),
3815 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3819 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3821 multiple_songs
= False
3823 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3824 multiple_songs
= True
3827 mrr
= row
.get('metadataRowRenderer') or {}
3828 mrr_title
= mrr
.get('title')
3831 mrr_title
= self
._get
_text
(mrr
, 'title')
3832 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3833 if mrr_title
== 'License':
3834 info
['license'] = mrr_contents_text
3835 elif not multiple_songs
:
3836 if mrr_title
== 'Album':
3837 info
['album'] = mrr_contents_text
3838 elif mrr_title
== 'Artist':
3839 info
['artist'] = mrr_contents_text
3840 elif mrr_title
== 'Song':
3841 info
['track'] = mrr_contents_text
3844 'channel': 'uploader',
3845 'channel_id': 'uploader_id',
3846 'channel_url': 'uploader_url',
3849 # The upload date for scheduled, live and past live streams / premieres in microformats
3850 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3851 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3853 unified_strdate(get_first(microformats
, 'uploadDate'))
3854 or unified_strdate(search_meta('uploadDate')))
3855 if not upload_date
or (not info
.get('is_live') and not info
.get('was_live') and info
.get('live_status') != 'is_upcoming'):
3856 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3857 info
['upload_date'] = upload_date
3859 for to
, frm
in fallbacks
.items():
3860 if not info
.get(to
):
3861 info
[to
] = info
.get(frm
)
3863 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3868 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3869 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3870 is_membersonly
= None
3872 if initial_data
and is_private
is not None:
3873 is_membersonly
= False
3875 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3876 badge_labels
= set()
3877 for content
in contents
:
3878 if not isinstance(content
, dict):
3880 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3881 for badge_label
in badge_labels
:
3882 if badge_label
.lower() == 'members only':
3883 is_membersonly
= True
3884 elif badge_label
.lower() == 'premium':
3886 elif badge_label
.lower() == 'unlisted':
3889 info
['availability'] = self
._availability
(
3890 is_private
=is_private
,
3891 needs_premium
=is_premium
,
3892 needs_subscription
=is_membersonly
,
3893 needs_auth
=info
['age_limit'] >= 18,
3894 is_unlisted
=None if is_private
is None else is_unlisted
)
3896 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
3898 self
.mark_watched(video_id
, player_responses
)
3903 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
3906 def passthrough_smuggled_data(func
):
3907 def _smuggle(entries
, smuggled_data
):
3908 for entry
in entries
:
3909 # TODO: Convert URL to music.youtube instead.
3910 # Do we need to passthrough any other smuggled_data?
3911 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
3914 @functools.wraps(func
)
3915 def wrapper(self
, url
):
3916 url
, smuggled_data
= unsmuggle_url(url
, {})
3917 if self
.is_music_url(url
):
3918 smuggled_data
['is_music_url'] = True
3919 info_dict
= func(self
, url
, smuggled_data
)
3920 if smuggled_data
and info_dict
.get('entries'):
3921 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
3925 def _extract_channel_id(self
, webpage
):
3926 channel_id
= self
._html
_search
_meta
(
3927 'channelId', webpage
, 'channel id', default
=None)
3930 channel_url
= self
._html
_search
_meta
(
3931 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3932 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3933 'twitter:app:url:googleplay'), webpage
, 'channel url')
3934 return self
._search
_regex
(
3935 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3936 channel_url
, 'channel id')
3939 def _extract_basic_item_renderer(item
):
3940 # Modified from _extract_grid_item_renderer
3941 known_basic_renderers
= (
3942 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3944 for key
, renderer
in item
.items():
3945 if not isinstance(renderer
, dict):
3947 elif key
in known_basic_renderers
:
3949 elif key
.startswith('grid') and key
.endswith('Renderer'):
3952 def _grid_entries(self
, grid_renderer
):
3953 for item
in grid_renderer
['items']:
3954 if not isinstance(item
, dict):
3956 renderer
= self
._extract
_basic
_item
_renderer
(item
)
3957 if not isinstance(renderer
, dict):
3959 title
= self
._get
_text
(renderer
, 'title')
3962 playlist_id
= renderer
.get('playlistId')
3964 yield self
.url_result(
3965 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
3966 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
3970 video_id
= renderer
.get('videoId')
3972 yield self
._extract
_video
(renderer
)
3975 channel_id
= renderer
.get('channelId')
3977 yield self
.url_result(
3978 'https://www.youtube.com/channel/%s' % channel_id
,
3979 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
3981 # generic endpoint URL support
3982 ep_url
= urljoin('https://www.youtube.com/', try_get(
3983 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3986 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
3987 if ie
.suitable(ep_url
):
3988 yield self
.url_result(
3989 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
3992 def _music_reponsive_list_entry(self
, renderer
):
3993 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
3995 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
3996 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
3997 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3999 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4001 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4002 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4003 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4004 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4005 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4007 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4008 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4010 def _shelf_entries_from_content(self
, shelf_renderer
):
4011 content
= shelf_renderer
.get('content')
4012 if not isinstance(content
, dict):
4014 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4016 # TODO: add support for nested playlists so each shelf is processed
4017 # as separate playlist
4018 # TODO: this includes only first N items
4019 yield from self
._grid
_entries
(renderer
)
4020 renderer
= content
.get('horizontalListRenderer')
4025 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4027 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4029 shelf_url
= urljoin('https://www.youtube.com', ep
)
4031 # Skipping links to another channels, note that checking for
4032 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4034 if skip_channels
and '/channels?' in shelf_url
:
4036 title
= self
._get
_text
(shelf_renderer
, 'title')
4037 yield self
.url_result(shelf_url
, video_title
=title
)
4038 # Shelf may not contain shelf URL, fallback to extraction from content
4039 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4041 def _playlist_entries(self
, video_list_renderer
):
4042 for content
in video_list_renderer
['contents']:
4043 if not isinstance(content
, dict):
4045 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4046 if not isinstance(renderer
, dict):
4048 video_id
= renderer
.get('videoId')
4051 yield self
._extract
_video
(renderer
)
4053 def _rich_entries(self
, rich_grid_renderer
):
4055 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4056 video_id
= renderer
.get('videoId')
4059 yield self
._extract
_video
(renderer
)
4061 def _video_entry(self
, video_renderer
):
4062 video_id
= video_renderer
.get('videoId')
4064 return self
._extract
_video
(video_renderer
)
4066 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4067 url
= urljoin('https://youtube.com', traverse_obj(
4068 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4070 return self
.url_result(
4071 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4073 def _post_thread_entries(self
, post_thread_renderer
):
4074 post_renderer
= try_get(
4075 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4076 if not post_renderer
:
4079 video_renderer
= try_get(
4080 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4081 video_id
= video_renderer
.get('videoId')
4083 entry
= self
._extract
_video
(video_renderer
)
4086 # playlist attachment
4087 playlist_id
= try_get(
4088 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4090 yield self
.url_result(
4091 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4092 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4093 # inline video links
4094 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4096 if not isinstance(run
, dict):
4099 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4102 if not YoutubeIE
.suitable(ep_url
):
4104 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4105 if video_id
== ep_video_id
:
4107 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4109 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4110 contents
= post_thread_continuation
.get('contents')
4111 if not isinstance(contents
, list):
4113 for content
in contents
:
4114 renderer
= content
.get('backstagePostThreadRenderer')
4115 if isinstance(renderer
, dict):
4116 yield from self
._post
_thread
_entries
(renderer
)
4118 renderer
= content
.get('videoRenderer')
4119 if isinstance(renderer
, dict):
4120 yield self
._video
_entry
(renderer
)
4123 def _rich_grid_entries(self, contents):
4124 for content in contents:
4125 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4127 entry = self._video_entry(video_renderer)
4132 def _extract_entries(self
, parent_renderer
, continuation_list
):
4133 # continuation_list is modified in-place with continuation_list = [continuation_token]
4134 continuation_list
[:] = [None]
4135 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4136 for content
in contents
:
4137 if not isinstance(content
, dict):
4139 is_renderer
= traverse_obj(
4140 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4143 renderer
= content
.get('richItemRenderer')
4145 for entry
in self
._rich
_entries
(renderer
):
4147 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4149 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4150 for isr_content
in isr_contents
:
4151 if not isinstance(isr_content
, dict):
4155 'playlistVideoListRenderer': self
._playlist
_entries
,
4156 'gridRenderer': self
._grid
_entries
,
4157 'reelShelfRenderer': self
._grid
_entries
,
4158 'shelfRenderer': self
._shelf
_entries
,
4159 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4160 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4161 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4162 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4163 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4164 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4166 for key
, renderer
in isr_content
.items():
4167 if key
not in known_renderers
:
4169 for entry
in known_renderers
[key
](renderer
):
4172 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4175 if not continuation_list
[0]:
4176 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4178 if not continuation_list
[0]:
4179 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4181 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4182 continuation_list
= [None]
4183 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4184 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4188 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4189 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4190 yield from extract_entries(parent_renderer
)
4191 continuation
= continuation_list
[0]
4193 for page_num
in itertools
.count(1):
4194 if not continuation
:
4196 headers
= self
.generate_api_headers(
4197 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4198 response
= self
._extract
_response
(
4199 item_id
=f
'{item_id} page {page_num}',
4200 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4201 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4205 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4206 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4207 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4209 known_continuation_renderers
= {
4210 'playlistVideoListContinuation': self
._playlist
_entries
,
4211 'gridContinuation': self
._grid
_entries
,
4212 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4213 'sectionListContinuation': extract_entries
, # for feeds
4215 continuation_contents
= try_get(
4216 response
, lambda x
: x
['continuationContents'], dict) or {}
4217 continuation_renderer
= None
4218 for key
, value
in continuation_contents
.items():
4219 if key
not in known_continuation_renderers
:
4221 continuation_renderer
= value
4222 continuation_list
= [None]
4223 yield from known_continuation_renderers
[key
](continuation_renderer
)
4224 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4226 if continuation_renderer
:
4230 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4231 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4232 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4233 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4234 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4235 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4236 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4237 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4239 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4240 continuation_items
= try_get(
4241 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4242 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4243 video_items_renderer
= None
4244 for key
, value
in continuation_item
.items():
4245 if key
not in known_renderers
:
4247 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4248 continuation_list
= [None]
4249 yield from known_renderers
[key
][0](video_items_renderer
)
4250 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4252 if video_items_renderer
:
4257 def _extract_selected_tab(tabs
, fatal
=True):
4259 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4260 if renderer
.get('selected') is True:
4264 raise ExtractorError('Unable to find selected tab')
4266 def _extract_uploader(self
, data
):
4268 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4270 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4272 owner_text
= owner
.get('text')
4273 uploader
['uploader'] = self
._search
_regex
(
4274 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4275 uploader
['uploader_id'] = try_get(
4276 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], str)
4277 uploader
['uploader_url'] = urljoin(
4278 'https://www.youtube.com/',
4279 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4280 return {k: v for k, v in uploader.items() if v is not None}
4282 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4283 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4286 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4287 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4289 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4291 channel_name
= renderer
.get('title')
4292 channel_url
= renderer
.get('channelUrl')
4293 channel_id
= renderer
.get('externalId')
4296 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4299 title
= renderer
.get('title')
4300 description
= renderer
.get('description', '')
4301 playlist_id
= channel_id
4302 tags
= renderer
.get('keywords', '').split()
4304 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4305 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4306 def _get_uncropped(url
):
4307 return url_or_none((url
or '').split('=')[0] + '=s0')
4309 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4310 if avatar_thumbnails
:
4311 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4312 if uncropped_avatar
:
4313 avatar_thumbnails
.append({
4314 'url': uncropped_avatar
,
4315 'id': 'avatar_uncropped',
4319 channel_banners
= self
._extract
_thumbnails
(
4320 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4321 for banner
in channel_banners
:
4322 banner
['preference'] = -10
4325 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4326 if uncropped_banner
:
4327 channel_banners
.append({
4328 'url': uncropped_banner
,
4329 'id': 'banner_uncropped',
4333 primary_thumbnails
= self
._extract
_thumbnails
(
4334 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4336 if playlist_id
is None:
4337 playlist_id
= item_id
4339 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4340 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4342 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4343 title
+= format_field(selected_tab
, 'title', ' - %s')
4344 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4347 'playlist_id': playlist_id
,
4348 'playlist_title': title
,
4349 'playlist_description': description
,
4350 'uploader': channel_name
,
4351 'uploader_id': channel_id
,
4352 'uploader_url': channel_url
,
4353 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4355 'view_count': self
._get
_count
(playlist_stats
, 1),
4356 'availability': self
._extract
_availability
(data
),
4357 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4358 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4359 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4362 metadata
.update(self
._extract
_uploader
(data
))
4364 'channel': metadata
['uploader'],
4365 'channel_id': metadata
['uploader_id'],
4366 'channel_url': metadata
['uploader_url']})
4367 return self
.playlist_result(
4369 selected_tab
, playlist_id
, ytcfg
,
4370 self
._extract
_account
_syncid
(ytcfg
, data
),
4371 self
._extract
_visitor
_data
(data
, ytcfg
)),
4374 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4375 first_id
= last_id
= response
= None
4376 for page_num
in itertools
.count(1):
4377 videos
= list(self
._playlist
_entries
(playlist
))
4380 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4381 if start
>= len(videos
):
4383 yield from videos
[start
:]
4384 first_id
= first_id
or videos
[0]['id']
4385 last_id
= videos
[-1]['id']
4386 watch_endpoint
= try_get(
4387 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4388 headers
= self
.generate_api_headers(
4389 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4390 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4392 'playlistId': playlist_id
,
4393 'videoId': watch_endpoint
.get('videoId') or last_id
,
4394 'index': watch_endpoint
.get('index') or len(videos
),
4395 'params': watch_endpoint
.get('params') or 'OAE%3D'
4397 response
= self
._extract
_response
(
4398 item_id
='%s page %d' % (playlist_id
, page_num
),
4399 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4400 check_get_keys
='contents'
4403 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4405 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4406 title
= playlist
.get('title') or try_get(
4407 data
, lambda x
: x
['titleText']['simpleText'], str)
4408 playlist_id
= playlist
.get('playlistId') or item_id
4410 # Delegating everything except mix playlists to regular tab-based playlist URL
4411 playlist_url
= urljoin(url
, try_get(
4412 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4415 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4416 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4417 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4419 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4420 return self
.url_result(
4421 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4424 return self
.playlist_result(
4425 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4426 playlist_id
=playlist_id
, playlist_title
=title
)
4428 def _extract_availability(self
, data
):
4430 Gets the availability of a given playlist/tab.
4431 Note: Unless YouTube tells us explicitly, we do not assume it is public
4432 @param data: response
4434 is_private
= is_unlisted
= None
4435 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4436 badge_labels
= self
._extract
_badges
(renderer
)
4438 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4439 privacy_dropdown_entries
= try_get(
4440 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4441 for renderer_dict
in privacy_dropdown_entries
:
4442 is_selected
= try_get(
4443 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4446 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4448 badge_labels
.add(label
.lower())
4451 for badge_label
in badge_labels
:
4452 if badge_label
== 'unlisted':
4454 elif badge_label
== 'private':
4456 elif badge_label
== 'public':
4457 is_unlisted
= is_private
= False
4458 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4461 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4462 sidebar_renderer
= try_get(
4463 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4464 for item
in sidebar_renderer
:
4465 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4469 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4471 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4473 browse_id
= params
= None
4474 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4477 menu_renderer
= try_get(
4478 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4479 for menu_item
in menu_renderer
:
4480 if not isinstance(menu_item
, dict):
4482 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4484 nav_item_renderer
, lambda x
: x
['text']['simpleText'], str)
4485 if not text
or text
.lower() != 'show unavailable videos':
4487 browse_endpoint
= try_get(
4488 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4489 browse_id
= browse_endpoint
.get('browseId')
4490 params
= browse_endpoint
.get('params')
4493 headers
= self
.generate_api_headers(
4494 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4495 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4497 'params': params
or 'wgYCCAA=',
4498 'browseId': browse_id
or 'VL%s' % item_id
4500 return self
._extract
_response
(
4501 item_id
=item_id
, headers
=headers
, query
=query
,
4502 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4503 note
='Downloading API JSON with unavailable videos')
4505 @functools.cached_property
4506 def skip_webpage(self
):
4507 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4509 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4510 webpage
, data
= None, None
4511 for retry
in self
.RetryManager(fatal
=fatal
):
4513 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
4514 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4515 except ExtractorError
as e
:
4516 if isinstance(e
.cause
, network_exceptions
):
4517 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4520 self
._error
_or
_warning
(e
, fatal
=fatal
)
4524 self
._extract
_and
_report
_alerts
(data
)
4525 except ExtractorError
as e
:
4526 self
._error
_or
_warning
(e
, fatal
=fatal
)
4529 # Sometimes youtube returns a webpage with incomplete ytInitialData
4530 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4531 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4532 retry
.error
= ExtractorError('Incomplete yt initial data received')
4535 return webpage
, data
4537 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4538 """Use if failed to extract ytcfg (and data) from initial webpage"""
4539 if not ytcfg
and self
.is_authenticated
:
4540 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4541 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4542 raise ExtractorError(
4543 f
'{msg}. If you are not downloading private content, or '
4544 'your cookies are only for the first account and channel,'
4545 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4547 self
.report_warning(msg
, only_once
=True)
4549 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4551 if not self
.skip_webpage
:
4552 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4553 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4554 # Reject webpage data if redirected to home page without explicitly requesting
4555 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4556 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4557 if (url
!= 'https://www.youtube.com/feed/recommended'
4558 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4559 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4560 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4562 raise ExtractorError(msg
, expected
=True)
4563 self
.report_warning(msg
, only_once
=True)
4565 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4566 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4569 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4570 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4571 resolve_response
= self
._extract
_response
(
4572 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4573 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4574 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4575 for ep_key
, ep
in endpoints
.items():
4576 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4578 return self
._extract
_response
(
4579 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4580 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4581 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4582 err_note
= 'Failed to resolve url (does the playlist exist?)'
4584 raise ExtractorError(err_note
, expected
=True)
4585 self
.report_warning(err_note
, item_id
)
4587 _SEARCH_PARAMS
= None
4589 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4590 data
= {'query': query}
4591 if params
is NO_DEFAULT
:
4592 params
= self
._SEARCH
_PARAMS
4594 data
['params'] = params
4597 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4598 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4600 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4601 ('continuationContents', ),
4603 display_id
= f
'query "{query}"'
4604 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4605 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4606 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4608 continuation_list
= [None]
4610 for page_num
in itertools
.count(1):
4611 data
.update(continuation_list
[0] or {})
4612 headers
= self
.generate_api_headers(
4613 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4614 search
= self
._extract
_response
(
4615 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4616 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4617 slr_contents
= traverse_obj(search
, *content_keys
)
4618 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4619 if not continuation_list
[0]:
4623 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4624 IE_DESC
= 'YouTube Tabs'
4625 _VALID_URL
= r
'''(?x:
4629 youtube(?:kids)?\.com|
4633 (?P<channel_type>channel|c|user|browse)/|
4636 (?:playlist|watch)\?.*?\blist=
4638 (?!(?:%(reserved_names)s)\b) # Direct URLs
4642 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4643 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4645 IE_NAME
= 'youtube:tab'
4648 'note': 'playlists, multipage',
4649 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4650 'playlist_mincount': 94,
4652 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4653 'title': 'Igor Kleiner - Playlists',
4654 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4655 'uploader': 'Igor Kleiner',
4656 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4657 'channel': 'Igor Kleiner',
4658 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4659 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4660 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4661 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4662 'channel_follower_count': int
4665 'note': 'playlists, multipage, different order',
4666 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4667 'playlist_mincount': 94,
4669 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4670 'title': 'Igor Kleiner - Playlists',
4671 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4672 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4673 'uploader': 'Igor Kleiner',
4674 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4675 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4676 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4677 'channel': 'Igor Kleiner',
4678 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4679 'channel_follower_count': int
4682 'note': 'playlists, series',
4683 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4684 'playlist_mincount': 5,
4686 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4687 'title': '3Blue1Brown - Playlists',
4688 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4689 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4690 'uploader': '3Blue1Brown',
4691 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4692 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4693 'channel': '3Blue1Brown',
4694 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4695 'tags': ['Mathematics'],
4696 'channel_follower_count': int
4699 'note': 'playlists, singlepage',
4700 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4701 'playlist_mincount': 4,
4703 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4704 'title': 'ThirstForScience - Playlists',
4705 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4706 'uploader': 'ThirstForScience',
4707 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4708 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4709 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4710 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4712 'channel': 'ThirstForScience',
4713 'channel_follower_count': int
4716 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4717 'only_matching': True,
4719 'note': 'basic, single video playlist',
4720 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4722 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4723 'uploader': 'Sergey M.',
4724 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4725 'title': 'youtube-dl public playlist',
4729 'modified_date': '20201130',
4730 'channel': 'Sergey M.',
4731 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4732 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4733 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4735 'playlist_count': 1,
4737 'note': 'empty playlist',
4738 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4740 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4741 'uploader': 'Sergey M.',
4742 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4743 'title': 'youtube-dl empty playlist',
4745 'channel': 'Sergey M.',
4747 'modified_date': '20160902',
4748 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4749 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4750 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4752 'playlist_count': 0,
4755 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4757 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4758 'title': 'lex will - Home',
4759 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4760 'uploader': 'lex will',
4761 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4762 'channel': 'lex will',
4763 'tags': ['bible', 'history', 'prophesy'],
4764 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4765 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4767 'channel_follower_count': int
4769 'playlist_mincount': 2,
4771 'note': 'Videos tab',
4772 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4774 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4775 'title': 'lex will - Videos',
4776 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4777 'uploader': 'lex will',
4778 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4779 'tags': ['bible', 'history', 'prophesy'],
4780 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4781 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4782 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4783 'channel': 'lex will',
4784 'channel_follower_count': int
4786 'playlist_mincount': 975,
4788 'note': 'Videos tab, sorted by popular',
4789 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4791 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4792 'title': 'lex will - Videos',
4793 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4794 'uploader': 'lex will',
4795 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4796 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4797 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel': 'lex will',
4799 'tags': ['bible', 'history', 'prophesy'],
4800 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4801 'channel_follower_count': int
4803 'playlist_mincount': 199,
4805 'note': 'Playlists tab',
4806 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4808 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4809 'title': 'lex will - Playlists',
4810 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4811 'uploader': 'lex will',
4812 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4813 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'channel': 'lex will',
4815 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4816 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'tags': ['bible', 'history', 'prophesy'],
4818 'channel_follower_count': int
4820 'playlist_mincount': 17,
4822 'note': 'Community tab',
4823 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4825 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4826 'title': 'lex will - Community',
4827 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4828 'uploader': 'lex will',
4829 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'channel': 'lex will',
4832 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4833 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'tags': ['bible', 'history', 'prophesy'],
4835 'channel_follower_count': int
4837 'playlist_mincount': 18,
4839 'note': 'Channels tab',
4840 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4842 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4843 'title': 'lex will - Channels',
4844 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4845 'uploader': 'lex will',
4846 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4848 'channel': 'lex will',
4849 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4850 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4851 'tags': ['bible', 'history', 'prophesy'],
4852 'channel_follower_count': int
4854 'playlist_mincount': 12,
4856 'note': 'Search tab',
4857 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4858 'playlist_mincount': 40,
4860 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4861 'title': '3Blue1Brown - Search - linear algebra',
4862 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4863 'uploader': '3Blue1Brown',
4864 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4865 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4866 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4867 'tags': ['Mathematics'],
4868 'channel': '3Blue1Brown',
4869 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4870 'channel_follower_count': int
4873 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4874 'only_matching': True,
4876 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4877 'only_matching': True,
4879 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4880 'only_matching': True,
4882 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4883 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4885 'title': '29C3: Not my department',
4886 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4887 'uploader': 'Christiaan008',
4888 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4889 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4891 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4893 'modified_date': '20150605',
4894 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4895 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4896 'channel': 'Christiaan008',
4898 'playlist_count': 96,
4900 'note': 'Large playlist',
4901 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4903 'title': 'Uploads from Cauchemar',
4904 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4905 'uploader': 'Cauchemar',
4906 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4907 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4909 'modified_date': r
're:\d{8}',
4910 'channel': 'Cauchemar',
4911 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4914 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4916 'playlist_mincount': 1123,
4917 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4919 'note': 'even larger playlist, 8832 videos',
4920 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4921 'only_matching': True,
4923 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4924 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4926 'title': 'Uploads from Interstellar Movie',
4927 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4928 'uploader': 'Interstellar Movie',
4929 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4930 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4933 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4934 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4935 'channel': 'Interstellar Movie',
4937 'modified_date': r
're:\d{8}',
4939 'playlist_mincount': 21,
4941 'note': 'Playlist with "show unavailable videos" button',
4942 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4944 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4945 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4946 'uploader': 'Phim Siêu Nhân Nhật Bản',
4947 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4949 'channel': 'Phim Siêu Nhân Nhật Bản',
4951 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4953 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4954 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4955 'modified_date': r
're:\d{8}',
4957 'playlist_mincount': 200,
4958 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4960 'note': 'Playlist with unavailable videos in page 7',
4961 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4963 'title': 'Uploads from BlankTV',
4964 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4965 'uploader': 'BlankTV',
4966 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4967 'channel': 'BlankTV',
4968 'channel_url': 'https://www.youtube.com/c/blanktv',
4969 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4972 'uploader_url': 'https://www.youtube.com/c/blanktv',
4973 'modified_date': r
're:\d{8}',
4976 'playlist_mincount': 1000,
4977 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4979 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4980 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4982 'title': 'Data Analysis with Dr Mike Pound',
4983 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4984 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4985 'uploader': 'Computerphile',
4986 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4987 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4990 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4991 'channel_url': 'https://www.youtube.com/user/Computerphile',
4992 'channel': 'Computerphile',
4994 'playlist_mincount': 11,
4996 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4997 'only_matching': True,
4999 'note': 'Playlist URL that does not actually serve a playlist',
5000 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5002 'id': 'FqZTN594JQw',
5004 'title': "Smiley's People 01 detective, Adventure Series, Action",
5005 'uploader': 'STREEM',
5006 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5007 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5008 'upload_date': '20150526',
5009 'license': 'Standard YouTube License',
5010 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5011 'categories': ['People & Blogs'],
5017 'skip_download': True,
5019 'skip': 'This video is not available.',
5020 'add_ie': [YoutubeIE
.ie_key()],
5022 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5023 'only_matching': True,
5025 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5026 'only_matching': True,
5028 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5030 'id': 'Wq15eF5vCbI', # This will keep changing
5033 'uploader': 'Sky News',
5034 'uploader_id': 'skynews',
5035 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5036 'upload_date': r
're:\d{8}',
5038 'categories': ['News & Politics'],
5041 'release_timestamp': 1642502819,
5042 'channel': 'Sky News',
5043 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5046 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5047 'playable_in_embed': True,
5048 'release_date': '20220118',
5049 'availability': 'public',
5050 'live_status': 'is_live',
5051 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5052 'channel_follower_count': int
5055 'skip_download': True,
5057 'expected_warnings': ['Ignoring subtitle tracks found in '],
5059 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5061 'id': 'a48o2S1cPoo',
5063 'title': 'The Young Turks - Live Main Show',
5064 'uploader': 'The Young Turks',
5065 'uploader_id': 'TheYoungTurks',
5066 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5067 'upload_date': '20150715',
5068 'license': 'Standard YouTube License',
5069 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5070 'categories': ['News & Politics'],
5071 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5075 'skip_download': True,
5077 'only_matching': True,
5079 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5080 'only_matching': True,
5082 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5083 'only_matching': True,
5085 'note': 'A channel that is not live. Should raise error',
5086 'url': 'https://www.youtube.com/user/numberphile/live',
5087 'only_matching': True,
5089 'url': 'https://www.youtube.com/feed/trending',
5090 'only_matching': True,
5092 'url': 'https://www.youtube.com/feed/library',
5093 'only_matching': True,
5095 'url': 'https://www.youtube.com/feed/history',
5096 'only_matching': True,
5098 'url': 'https://www.youtube.com/feed/subscriptions',
5099 'only_matching': True,
5101 'url': 'https://www.youtube.com/feed/watch_later',
5102 'only_matching': True,
5104 'note': 'Recommended - redirects to home page.',
5105 'url': 'https://www.youtube.com/feed/recommended',
5106 'only_matching': True,
5108 'note': 'inline playlist with not always working continuations',
5109 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5110 'only_matching': True,
5112 'url': 'https://www.youtube.com/course',
5113 'only_matching': True,
5115 'url': 'https://www.youtube.com/zsecurity',
5116 'only_matching': True,
5118 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5119 'only_matching': True,
5121 'url': 'https://www.youtube.com/TheYoungTurks/live',
5122 'only_matching': True,
5124 'url': 'https://www.youtube.com/hashtag/cctv9',
5130 'playlist_mincount': 350,
5132 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5133 'only_matching': True,
5135 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5136 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5137 'only_matching': True
5139 'note': '/browse/ should redirect to /channel/',
5140 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5141 'only_matching': True
5143 'note': 'VLPL, should redirect to playlist?list=PL...',
5144 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5146 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5147 'uploader': 'NoCopyrightSounds',
5148 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5149 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5150 'title': 'NCS : All Releases 💿',
5151 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5152 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5153 'modified_date': r
're:\d{8}',
5155 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5157 'channel': 'NoCopyrightSounds',
5159 'playlist_mincount': 166,
5160 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5162 'note': 'Topic, should redirect to playlist?list=UU...',
5163 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5165 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5166 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5167 'title': 'Uploads from Royalty Free Music - Topic',
5168 'uploader': 'Royalty Free Music - Topic',
5170 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5171 'channel': 'Royalty Free Music - Topic',
5173 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5174 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5175 'modified_date': r
're:\d{8}',
5176 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5179 'expected_warnings': [
5180 'The URL does not have a videos tab',
5181 r
'[Uu]navailable videos (are|will be) hidden',
5183 'playlist_mincount': 101,
5185 'note': 'Topic without a UU playlist',
5186 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5188 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5189 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5192 'expected_warnings': [
5193 'the playlist redirect gave error',
5195 'playlist_mincount': 9,
5197 'note': 'Youtube music Album',
5198 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5200 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5201 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5205 'availability': 'unlisted',
5206 'modified_date': r
're:\d{8}',
5208 'playlist_count': 50,
5210 'note': 'unlisted single video playlist',
5211 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5213 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5214 'uploader': 'colethedj',
5215 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5216 'title': 'yt-dlp unlisted playlist test',
5217 'availability': 'unlisted',
5219 'modified_date': '20220418',
5220 'channel': 'colethedj',
5223 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5224 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5225 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5227 'playlist_count': 1,
5229 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5230 'url': 'https://www.youtube.com/feed/recommended',
5232 'id': 'recommended',
5233 'title': 'recommended',
5236 'playlist_mincount': 50,
5238 'skip_download': True,
5239 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5242 'note': 'API Fallback: /videos tab, sorted by oldest first',
5243 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5245 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5246 'title': 'Cody\'sLab - Videos',
5247 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5248 'uploader': 'Cody\'sLab',
5249 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5250 'channel': 'Cody\'sLab',
5251 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5253 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5254 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5255 'channel_follower_count': int
5257 'playlist_mincount': 650,
5259 'skip_download': True,
5260 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5263 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5264 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5266 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5267 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5268 'title': 'Uploads from Royalty Free Music - Topic',
5269 'uploader': 'Royalty Free Music - Topic',
5270 'modified_date': r
're:\d{8}',
5271 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5273 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5275 'channel': 'Royalty Free Music - Topic',
5277 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5279 'expected_warnings': [
5280 'does not have a videos tab',
5281 r
'[Uu]navailable videos (are|will be) hidden',
5283 'playlist_mincount': 101,
5285 'skip_download': True,
5286 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5289 'note': 'non-standard redirect to regional channel',
5290 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5291 'only_matching': True
5293 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5294 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5296 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5297 'modified_date': '20220407',
5298 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5300 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5301 'uploader': 'pukkandan',
5302 'availability': 'unlisted',
5303 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5304 'channel': 'pukkandan',
5305 'description': 'Test for collaborative playlist',
5306 'title': 'yt-dlp test - collaborative playlist',
5308 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5310 'playlist_mincount': 2
5314 def suitable(cls
, url
):
5315 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5317 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5319 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5320 def _real_extract(self
, url
, smuggled_data
):
5321 item_id
= self
._match
_id
(url
)
5322 url
= urllib
.parse
.urlunparse(
5323 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5324 compat_opts
= self
.get_param('compat_opts', [])
5327 mobj
= self
._URL
_RE
.match(url
).groupdict()
5328 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5331 mobj
, redirect_warning
= get_mobj(url
), None
5332 # Youtube returns incomplete data if tabname is not lower case
5333 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5335 if smuggled_data
.get('is_music_url'):
5336 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5337 item_id
= item_id
[2:]
5338 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5339 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5340 mdata
= self
._extract
_tab
_endpoint
(
5341 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5342 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5343 get_all
=False, expected_type
=str)
5345 raise ExtractorError('Failed to resolve album to playlist')
5346 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5347 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5348 pre
= f
'https://www.youtube.com/channel/{item_id}'
5350 original_tab_name
= tab
5351 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5352 # Home URLs should redirect to /videos/
5353 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5354 'To download only the videos in the home page, add a "/featured" to the URL')
5357 url
= ''.join((pre
, tab
, post
))
5358 mobj
= get_mobj(url
)
5360 # Handle both video/playlist URLs
5362 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5364 if not video_id
and mobj
['not_channel'].startswith('watch'):
5366 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5367 raise ExtractorError('Unable to recognize tab page')
5368 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5369 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5370 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5371 mobj
= get_mobj(url
)
5373 if video_id
and playlist_id
:
5374 if self
.get_param('noplaylist'):
5375 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5376 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5377 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5378 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5380 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5382 # YouTube may provide a non-standard redirect to the regional channel
5383 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5384 redirect_url
= traverse_obj(
5385 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5386 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5387 redirect_url
= ''.join((
5388 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5389 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5390 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5392 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5394 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5395 selected_tab_name
= selected_tab
.get('title', '').lower()
5396 if selected_tab_name
== 'home':
5397 selected_tab_name
= 'featured'
5398 requested_tab_name
= mobj
['tab'][1:]
5399 if 'no-youtube-channel-redirect' not in compat_opts
:
5400 if requested_tab_name
== 'live': # Live tab should have redirected to the video
5401 raise UserNotLive(video_id
=mobj
['id'])
5402 if requested_tab_name
not in ('', selected_tab_name
):
5403 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5404 if not original_tab_name
:
5405 if item_id
[:2] == 'UC':
5406 # Topic channels don't have /videos. Use the equivalent playlist instead
5407 pl_id
= f
'UU{item_id[2:]}'
5408 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5410 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5411 except ExtractorError
:
5412 redirect_warning
+= ' and the playlist redirect gave error'
5414 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5415 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5416 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5417 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5419 raise ExtractorError(redirect_warning
, expected
=True)
5421 if redirect_warning
:
5422 self
.to_screen(redirect_warning
)
5423 self
.write_debug(f
'Final URL: {url}')
5425 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5426 if 'no-youtube-unavailable-videos' not in compat_opts
:
5427 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5428 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5429 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5431 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5433 playlist
= traverse_obj(
5434 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5436 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5438 video_id
= traverse_obj(
5439 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5441 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5442 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5443 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5444 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5446 raise ExtractorError('Unable to recognize tab page')
5449 class YoutubePlaylistIE(InfoExtractor
):
5450 IE_DESC
= 'YouTube playlists'
5451 _VALID_URL
= r
'''(?x)(?:
5456 youtube(?:kids)?\.com|
5461 (?P<id>%(playlist_id)s)
5463 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5464 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5466 IE_NAME
= 'youtube:playlist'
5468 'note': 'issue #673',
5469 'url': 'PLBB231211A4F62143',
5471 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5472 'id': 'PLBB231211A4F62143',
5473 'uploader': 'Wickman',
5474 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5475 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5477 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5478 'modified_date': r
're:\d{8}',
5479 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5480 'channel': 'Wickman',
5482 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5484 'playlist_mincount': 29,
5486 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5488 'title': 'YDL_safe_search',
5489 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5491 'playlist_count': 2,
5492 'skip': 'This playlist is private',
5495 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5496 'playlist_count': 4,
5499 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5500 'uploader': 'milan',
5501 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5503 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5505 'modified_date': '20140919',
5508 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5509 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5511 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5513 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5514 'playlist_mincount': 455,
5516 'title': '2018 Chinese New Singles (11/6 updated)',
5517 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5519 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5520 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5523 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5525 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5526 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5527 'modified_date': r
're:\d{8}',
5529 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5531 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5532 'only_matching': True,
5534 # music album playlist
5535 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5536 'only_matching': True,
5540 def suitable(cls
, url
):
5541 if YoutubeTabIE
.suitable(url
):
5543 from ..utils
import parse_qs
5545 if qs
.get('v', [None])[0]:
5547 return super().suitable(url
)
5549 def _real_extract(self
, url
):
5550 playlist_id
= self
._match
_id
(url
)
5551 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5552 url
= update_url_query(
5553 'https://www.youtube.com/playlist',
5554 parse_qs(url
) or {'list': playlist_id}
)
5556 url
= smuggle_url(url
, {'is_music_url': True}
)
5557 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5560 class YoutubeYtBeIE(InfoExtractor
):
5561 IE_DESC
= 'youtu.be'
5562 _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}
5564 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5566 'id': 'yeWKywCrFtk',
5568 'title': 'Small Scale Baler and Braiding Rugs',
5569 'uploader': 'Backus-Page House Museum',
5570 'uploader_id': 'backuspagemuseum',
5571 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5572 'upload_date': '20161008',
5573 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5574 'categories': ['Nonprofits & Activism'],
5578 'playable_in_embed': True,
5579 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5580 'channel': 'Backus-Page House Museum',
5581 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5582 'live_status': 'not_live',
5584 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5585 'availability': 'public',
5587 'comment_count': int,
5588 'channel_follower_count': int
5592 'skip_download': True,
5595 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5596 'only_matching': True,
5599 def _real_extract(self
, url
):
5600 mobj
= self
._match
_valid
_url
(url
)
5601 video_id
= mobj
.group('id')
5602 playlist_id
= mobj
.group('playlist_id')
5603 return self
.url_result(
5604 update_url_query('https://www.youtube.com/watch', {
5606 'list': playlist_id
,
5607 'feature': 'youtu.be',
5608 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5611 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5612 IE_DESC
= 'YouTube livestream embeds'
5613 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5615 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5616 'only_matching': True,
5619 def _real_extract(self
, url
):
5620 channel_id
= self
._match
_id
(url
)
5621 return self
.url_result(
5622 f
'https://www.youtube.com/channel/{channel_id}/live',
5623 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5626 class YoutubeYtUserIE(InfoExtractor
):
5627 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5628 IE_NAME
= 'youtube:user'
5629 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5631 'url': 'ytuser:phihag',
5632 'only_matching': True,
5635 def _real_extract(self
, url
):
5636 user_id
= self
._match
_id
(url
)
5637 return self
.url_result(
5638 'https://www.youtube.com/user/%s/videos' % user_id
,
5639 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5642 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5643 IE_NAME
= 'youtube:favorites'
5644 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5645 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5646 _LOGIN_REQUIRED
= True
5649 'only_matching': True,
5651 'url': ':ytfavorites',
5652 'only_matching': True,
5655 def _real_extract(self
, url
):
5656 return self
.url_result(
5657 'https://www.youtube.com/playlist?list=LL',
5658 ie
=YoutubeTabIE
.ie_key())
5661 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5662 IE_NAME
= 'youtube:notif'
5663 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5664 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5665 _LOGIN_REQUIRED
= True
5668 'only_matching': True,
5670 'url': ':ytnotifications',
5671 'only_matching': True,
5674 def _extract_notification_menu(self
, response
, continuation_list
):
5675 notification_list
= traverse_obj(
5677 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5678 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5679 expected_type
=list) or []
5680 continuation_list
[0] = None
5681 for item
in notification_list
:
5682 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5685 continuation
= item
.get('continuationItemRenderer')
5687 continuation_list
[0] = continuation
5689 def _extract_notification_renderer(self
, notification
):
5690 video_id
= traverse_obj(
5691 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5692 url
= f
'https://www.youtube.com/watch?v={video_id}'
5695 browse_ep
= traverse_obj(
5696 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5697 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5698 post_id
= self
._search
_regex
(
5699 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5700 'post id', default
=None)
5701 if not channel_id
or not post_id
:
5703 # The direct /post url redirects to this in the browser
5704 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5706 channel
= traverse_obj(
5707 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5709 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5710 if notification_title
:
5711 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5712 # TODO: handle recommended videos
5713 title
= self
._search
_regex
(
5714 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5715 'video title', default
=None)
5716 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5717 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5722 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5723 'video_id': video_id
,
5725 'channel_id': channel_id
,
5727 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5728 'upload_date': upload_date
,
5731 def _notification_menu_entries(self
, ytcfg
):
5732 continuation_list
= [None]
5734 for page
in itertools
.count(1):
5735 ctoken
= traverse_obj(
5736 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5737 response
= self
._extract
_response
(
5738 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5739 ep
='notification/get_notification_menu', check_get_keys
='actions',
5740 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5741 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5742 if not continuation_list
[0]:
5745 def _real_extract(self
, url
):
5746 display_id
= 'notifications'
5747 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5748 self
._report
_playlist
_authcheck
(ytcfg
)
5749 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5752 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5753 IE_DESC
= 'YouTube search'
5754 IE_NAME
= 'youtube:search'
5755 _SEARCH_KEY
= 'ytsearch'
5756 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5758 'url': 'ytsearch5:youtube-dl test video',
5759 'playlist_count': 5,
5761 'id': 'youtube-dl test video',
5762 'title': 'youtube-dl test video',
5767 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5768 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5769 _SEARCH_KEY
= 'ytsearchdate'
5770 IE_DESC
= 'YouTube search, newest videos first'
5771 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5773 'url': 'ytsearchdate5:youtube-dl test video',
5774 'playlist_count': 5,
5776 'id': 'youtube-dl test video',
5777 'title': 'youtube-dl test video',
5782 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5783 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5784 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5785 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5787 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5788 'playlist_mincount': 5,
5790 'id': 'youtube-dl test video',
5791 'title': 'youtube-dl test video',
5794 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5795 'playlist_mincount': 5,
5801 'url': 'https://www.youtube.com/results?search_query=%23cats',
5802 'playlist_mincount': 1,
5806 # The test suite does not have support for nested playlists
5808 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5813 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5814 'only_matching': True,
5817 def _real_extract(self
, url
):
5819 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5820 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5823 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5824 IE_DESC
= 'YouTube music search URLs with selectable sections (Eg: #songs)'
5825 IE_NAME
= 'youtube:music:search_url'
5826 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5828 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5829 'playlist_count': 16,
5831 'id': 'royalty free music',
5832 'title': 'royalty free music',
5835 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5836 'playlist_mincount': 30,
5838 'id': 'royalty free music - songs',
5839 'title': 'royalty free music - songs',
5841 'params': {'extract_flat': 'in_playlist'}
5843 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5844 'playlist_mincount': 30,
5846 'id': 'royalty free music - community playlists',
5847 'title': 'royalty free music - community playlists',
5849 'params': {'extract_flat': 'in_playlist'}
5853 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5854 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5855 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5856 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5857 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5858 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5861 def _real_extract(self
, url
):
5863 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5864 params
= qs
.get('sp', (None,))[0]
5866 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5868 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
5869 params
= self
._SECTIONS
.get(section
)
5872 title
= join_nonempty(query
, section
, delim
=' - ')
5873 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5876 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5878 Base class for feed extractors
5879 Subclasses must re-define the _FEED_NAME property.
5881 _LOGIN_REQUIRED
= True
5882 _FEED_NAME
= 'feeds'
5884 def _real_initialize(self
):
5885 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
5889 return f
'youtube:{self._FEED_NAME}'
5891 def _real_extract(self
, url
):
5892 return self
.url_result(
5893 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
5896 class YoutubeWatchLaterIE(InfoExtractor
):
5897 IE_NAME
= 'youtube:watchlater'
5898 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5899 _VALID_URL
= r
':ytwatchlater'
5901 'url': ':ytwatchlater',
5902 'only_matching': True,
5905 def _real_extract(self
, url
):
5906 return self
.url_result(
5907 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
5910 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
5911 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
5912 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5913 _FEED_NAME
= 'recommended'
5914 _LOGIN_REQUIRED
= False
5917 'only_matching': True,
5919 'url': ':ytrecommended',
5920 'only_matching': True,
5922 'url': 'https://youtube.com',
5923 'only_matching': True,
5927 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
5928 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5929 _VALID_URL
= r
':ytsub(?:scription)?s?'
5930 _FEED_NAME
= 'subscriptions'
5933 'only_matching': True,
5935 'url': ':ytsubscriptions',
5936 'only_matching': True,
5940 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
5941 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
5942 _VALID_URL
= r
':ythis(?:tory)?'
5943 _FEED_NAME
= 'history'
5945 'url': ':ythistory',
5946 'only_matching': True,
5950 class YoutubeStoriesIE(InfoExtractor
):
5951 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
5952 IE_NAME
= 'youtube:stories'
5953 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5955 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5956 'only_matching': True,
5959 def _real_extract(self
, url
):
5960 playlist_id
= f
'RLTD{self._match_id(url)}'
5961 return self
.url_result(
5962 f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5963 ie
=YoutubeTabIE
, video_id
=playlist_id
)
5966 class YoutubeTruncatedURLIE(InfoExtractor
):
5967 IE_NAME
= 'youtube:truncated_url'
5968 IE_DESC
= False # Do not list
5969 _VALID_URL
= r
'''(?x)
5971 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5974 annotation_id=annotation_[^&]+|
5980 attribution_link\?a=[^&]+
5986 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5987 'only_matching': True,
5989 'url': 'https://www.youtube.com/watch?',
5990 'only_matching': True,
5992 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5993 'only_matching': True,
5995 'url': 'https://www.youtube.com/watch?feature=foo',
5996 'only_matching': True,
5998 'url': 'https://www.youtube.com/watch?hl=en-GB',
5999 'only_matching': True,
6001 'url': 'https://www.youtube.com/watch?t=2372',
6002 'only_matching': True,
6005 def _real_extract(self
, url
):
6006 raise ExtractorError(
6007 'Did you forget to quote the URL? Remember that & is a meta '
6008 'character in most shells, so you want to put the URL in quotes, '
6010 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6011 ' or simply youtube-dl BaW_jenozKc .',
6015 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6016 IE_NAME
= 'youtube:clip'
6017 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6019 # FIXME: Other metadata should be extracted from the clip, not from the base video
6020 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6022 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6024 'section_start': 29.0,
6025 'section_end': 39.7,
6028 'availability': 'public',
6029 'categories': ['Gaming'],
6030 'channel': 'Scott The Woz',
6031 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6032 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6033 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6035 'playable_in_embed': True,
6037 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6038 'title': 'Mobile Games on Console - Scott The Woz',
6039 'upload_date': '20210920',
6040 'uploader': 'Scott The Woz',
6041 'uploader_id': 'scottthewoz',
6042 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6044 'live_status': 'not_live',
6045 'channel_follower_count': int
6049 def _real_extract(self
, url
):
6050 clip_id
= self
._match
_id
(url
)
6051 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6053 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6055 raise ExtractorError('Unable to find video ID')
6057 clip_data
= traverse_obj(data
, (
6058 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6059 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6060 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6061 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6064 '_type': 'url_transparent',
6065 'url': f
'https://www.youtube.com/watch?v={video_id}',
6066 'ie_key': YoutubeIE
.ie_key(),
6068 'section_start': int(clip_data
['startTimeMs']) / 1000,
6069 'section_end': int(clip_data
['endTimeMs']) / 1000,
6073 class YoutubeTruncatedIDIE(InfoExtractor
):
6074 IE_NAME
= 'youtube:truncated_id'
6075 IE_DESC
= False # Do not list
6076 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6079 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6080 'only_matching': True,
6083 def _real_extract(self
, url
):
6084 video_id
= self
._match
_id
(url
)
6085 raise ExtractorError(
6086 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',