3 from __future__
import unicode_literals
21 from .common
import InfoExtractor
, SearchInfoExtractor
22 from ..compat
import (
27 compat_urllib_parse_unquote_plus
,
28 compat_urllib_parse_urlencode
,
29 compat_urllib_parse_urlparse
,
32 from ..jsinterp
import JSInterpreter
74 def get_first(obj
, keys
, **kwargs
):
75 return traverse_obj(obj
, (..., *variadic(keys
)), **kwargs
, get_all
=False)
78 # any clients starting with _ cannot be explicity requested by the user
81 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
82 'INNERTUBE_CONTEXT': {
85 'clientVersion': '2.20211221.00.00',
88 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
91 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
92 'INNERTUBE_CONTEXT': {
94 'clientName': 'WEB_EMBEDDED_PLAYER',
95 'clientVersion': '1.20211215.00.01',
98 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
101 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
102 'INNERTUBE_HOST': 'music.youtube.com',
103 'INNERTUBE_CONTEXT': {
105 'clientName': 'WEB_REMIX',
106 'clientVersion': '1.20211213.00.00',
109 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
112 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
113 'INNERTUBE_CONTEXT': {
115 'clientName': 'WEB_CREATOR',
116 'clientVersion': '1.20211220.02.00',
119 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
122 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
123 'INNERTUBE_CONTEXT': {
125 'clientName': 'ANDROID',
126 'clientVersion': '16.49',
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
130 'REQUIRE_JS_PLAYER': False
132 'android_embedded': {
133 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
134 'INNERTUBE_CONTEXT': {
136 'clientName': 'ANDROID_EMBEDDED_PLAYER',
137 'clientVersion': '16.49',
140 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
141 'REQUIRE_JS_PLAYER': False
144 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
145 'INNERTUBE_CONTEXT': {
147 'clientName': 'ANDROID_MUSIC',
148 'clientVersion': '4.57',
151 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
152 'REQUIRE_JS_PLAYER': False
155 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
156 'INNERTUBE_CONTEXT': {
158 'clientName': 'ANDROID_CREATOR',
159 'clientVersion': '21.47',
162 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
163 'REQUIRE_JS_PLAYER': False
165 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
166 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
168 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
169 'INNERTUBE_CONTEXT': {
172 'clientVersion': '16.46',
173 'deviceModel': 'iPhone14,3',
176 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
177 'REQUIRE_JS_PLAYER': False
180 'INNERTUBE_CONTEXT': {
182 'clientName': 'IOS_MESSAGES_EXTENSION',
183 'clientVersion': '16.46',
184 'deviceModel': 'iPhone14,3',
187 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
188 'REQUIRE_JS_PLAYER': False
191 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
192 'INNERTUBE_CONTEXT': {
194 'clientName': 'IOS_MUSIC',
195 'clientVersion': '4.57',
198 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
199 'REQUIRE_JS_PLAYER': False
202 'INNERTUBE_CONTEXT': {
204 'clientName': 'IOS_CREATOR',
205 'clientVersion': '21.47',
208 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
209 'REQUIRE_JS_PLAYER': False
211 # mweb has 'ultralow' formats
212 # See: https://github.com/yt-dlp/yt-dlp/pull/557
214 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
215 'INNERTUBE_CONTEXT': {
217 'clientName': 'MWEB',
218 'clientVersion': '2.20211221.01.00',
221 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
226 def build_innertube_clients():
228 'embedUrl': 'https://google.com', # Can be any valid URL
230 base_clients
= ('android', 'web', 'ios', 'mweb')
231 priority
= qualities(base_clients
[::-1])
233 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
234 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
235 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
236 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
237 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
238 ytcfg
['priority'] = 10 * priority(client
.split('_', 1)[0])
240 if client
in base_clients
:
241 INNERTUBE_CLIENTS
[f
'{client}_agegate'] = agegate_ytcfg
= copy
.deepcopy(ytcfg
)
242 agegate_ytcfg
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
243 agegate_ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
244 agegate_ytcfg
['priority'] -= 1
245 elif client
.endswith('_embedded'):
246 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
247 ytcfg
['priority'] -= 2
249 ytcfg
['priority'] -= 3
252 build_innertube_clients()
255 class YoutubeBaseInfoExtractor(InfoExtractor
):
256 """Provide base functions for Youtube extractors"""
259 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
260 r
'shorts|movies|results|shared|hashtag|trending|explore|feed|feeds|'
261 r
'browse|oembed|get_video_info|iframe_api|s/player|'
262 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
264 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
266 _NETRC_MACHINE
= 'youtube'
268 # If True it will raise an error if no login info is provided
269 _LOGIN_REQUIRED
= False
272 # invidious-redirect websites
273 r
'(?:www\.)?redirect\.invidious\.io',
274 r
'(?:(?:www|dev)\.)?invidio\.us',
275 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
276 r
'(?:www\.)?invidious\.pussthecat\.org',
277 r
'(?:www\.)?invidious\.zee\.li',
278 r
'(?:www\.)?invidious\.ethibox\.fr',
279 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
280 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
281 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
282 # youtube-dl invidious instances list
283 r
'(?:(?:www|no)\.)?invidiou\.sh',
284 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
285 r
'(?:www\.)?invidious\.kabi\.tk',
286 r
'(?:www\.)?invidious\.mastodon\.host',
287 r
'(?:www\.)?invidious\.zapashcanon\.fr',
288 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
289 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
290 r
'(?:www\.)?invidious\.himiko\.cloud',
291 r
'(?:www\.)?invidious\.reallyancient\.tech',
292 r
'(?:www\.)?invidious\.tube',
293 r
'(?:www\.)?invidiou\.site',
294 r
'(?:www\.)?invidious\.site',
295 r
'(?:www\.)?invidious\.xyz',
296 r
'(?:www\.)?invidious\.nixnet\.xyz',
297 r
'(?:www\.)?invidious\.048596\.xyz',
298 r
'(?:www\.)?invidious\.drycat\.fr',
299 r
'(?:www\.)?inv\.skyn3t\.in',
300 r
'(?:www\.)?tube\.poal\.co',
301 r
'(?:www\.)?tube\.connect\.cafe',
302 r
'(?:www\.)?vid\.wxzm\.sx',
303 r
'(?:www\.)?vid\.mint\.lgbt',
304 r
'(?:www\.)?vid\.puffyan\.us',
305 r
'(?:www\.)?yewtu\.be',
306 r
'(?:www\.)?yt\.elukerio\.org',
307 r
'(?:www\.)?yt\.lelux\.fi',
308 r
'(?:www\.)?invidious\.ggc-project\.de',
309 r
'(?:www\.)?yt\.maisputain\.ovh',
310 r
'(?:www\.)?ytprivate\.com',
311 r
'(?:www\.)?invidious\.13ad\.de',
312 r
'(?:www\.)?invidious\.toot\.koeln',
313 r
'(?:www\.)?invidious\.fdn\.fr',
314 r
'(?:www\.)?watch\.nettohikari\.com',
315 r
'(?:www\.)?invidious\.namazso\.eu',
316 r
'(?:www\.)?invidious\.silkky\.cloud',
317 r
'(?:www\.)?invidious\.exonip\.de',
318 r
'(?:www\.)?invidious\.riverside\.rocks',
319 r
'(?:www\.)?invidious\.blamefran\.net',
320 r
'(?:www\.)?invidious\.moomoo\.de',
321 r
'(?:www\.)?ytb\.trom\.tf',
322 r
'(?:www\.)?yt\.cyberhost\.uk',
323 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
324 r
'(?:www\.)?qklhadlycap4cnod\.onion',
325 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
326 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
327 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
328 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
329 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
330 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
331 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
332 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
333 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
334 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
339 Attempt to log in to YouTube.
340 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
343 if (self
._LOGIN
_REQUIRED
344 and self
.get_param('cookiefile') is None
345 and self
.get_param('cookiesfrombrowser') is None):
346 self
.raise_login_required(
347 'Login details are needed to download this content', method
='cookies')
348 username
, password
= self
._get
_login
_info
()
350 self
.report_warning(f
'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
352 def _initialize_consent(self
):
353 cookies
= self
._get
_cookies
('https://www.youtube.com/')
354 if cookies
.get('__Secure-3PSID'):
357 consent
= cookies
.get('CONSENT')
359 if 'YES' in consent
.value
:
361 consent_id
= self
._search
_regex
(
362 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
364 consent_id
= random
.randint(100, 999)
365 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
367 def _initialize_pref(self
):
368 cookies
= self
._get
_cookies
('https://www.youtube.com/')
369 pref_cookie
= cookies
.get('PREF')
373 pref
= dict(compat_urlparse
.parse_qsl(pref_cookie
.value
))
375 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
376 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
377 self
._set
_cookie
('.youtube.com', name
='PREF', value
=compat_urllib_parse_urlencode(pref
))
379 def _real_initialize(self
):
380 self
._initialize
_pref
()
381 self
._initialize
_consent
()
384 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
385 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
388 def _get_default_ytcfg(self, client='web'):
389 return copy.deepcopy(INNERTUBE_CLIENTS[client])
391 def _get_innertube_host(self, client='web'):
392 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
394 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
395 # try_get but with fallback to default ytcfg client values when present
396 _func = lambda y: try_get(y, getter, expected_type)
397 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
399 def _extract_client_name(self, ytcfg, default_client='web'):
400 return self._ytcfg_get_safe(
401 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
402 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
404 def _extract_client_version(self, ytcfg, default_client='web'):
405 return self._ytcfg_get_safe(
406 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
407 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
409 def _extract_api_key(self, ytcfg=None, default_client='web'):
410 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
412 def _extract_context(self, ytcfg=None, default_client='web'):
414 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
415 # Enforce language and tz for extraction
416 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
417 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
422 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
423 time_now = round(time.time())
424 if self._SAPISID is None:
425 yt_cookies = self._get_cookies('https://www.youtube.com')
426 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
427 # See: https://github.com/yt-dlp/yt-dlp/issues/393
428 sapisid_cookie = dict_get(
429 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
430 if sapisid_cookie and sapisid_cookie.value:
431 self._SAPISID = sapisid_cookie.value
432 self.write_debug('Extracted SAPISID cookie')
433 # SAPISID cookie is required if not already present
434 if not yt_cookies.get('SAPISID'):
435 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
437 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
439 self._SAPISID = False
440 if not self._SAPISID:
442 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
443 sapisidhash = hashlib.sha1(
444 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
445 return f'SAPISIDHASH {time_now}_{sapisidhash}'
447 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
448 note='Downloading API JSON', errnote='Unable to download API page',
449 context=None, api_key=None, api_hostname=None, default_client='web'):
451 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
453 real_headers = self.generate_api_headers(default_client=default_client)
454 real_headers.update({'content-type': 'application/json'})
456 real_headers.update(headers)
457 return self._download_json(
458 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
459 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
460 data=json.dumps(data).encode('utf8'), headers=real_headers,
461 query={'key': api_key or self._extract_api_key()})
463 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
464 data = self._search_regex(
465 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
466 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
468 return self._parse_json(data, item_id, fatal=fatal)
471 def _extract_session_index(*data):
473 Index of current account in account list.
474 See: https://github.com/yt-dlp/yt-dlp/pull/519
477 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
478 if session_index is not None:
482 def _extract_identity_token(self, ytcfg=None, webpage=None):
484 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
488 return self._search_regex(
489 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
490 'identity token
', default=None, fatal=False)
493 def _extract_account_syncid(*args):
495 Extract syncId required to download private playlists of secondary channels
496 @params response and/or ytcfg
499 # ytcfg includes channel_syncid if on secondary channel
500 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
504 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
505 lambda x: x['DATASYNC_ID
']), compat_str) or '').split('||
')
506 if len(sync_ids) >= 2 and sync_ids[1]:
507 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
508 # and just "user_syncid||" for primary channel. We only want the channel_syncid
512 def _extract_visitor_data(*args):
514 Extracts visitorData from an API response or ytcfg
515 Appears to be used to track session state
518 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
522 def is_authenticated(self):
523 return bool(self._generate_sapisidhash_header())
525 def extract_ytcfg(self, video_id, webpage):
528 return self._parse_json(
530 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
531 default='{}'), video_id, fatal=False) or {}
533 def generate_api_headers(
534 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
535 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
537 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(default_client
))
539 'X-YouTube-Client-Name': compat_str(
540 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
541 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
543 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
544 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
545 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
547 if session_index
is None:
548 session_index
= self
._extract
_session
_index
(ytcfg
)
549 if account_syncid
or session_index
is not None:
550 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
552 auth
= self
._generate
_sapisidhash
_header
(origin
)
554 headers
['Authorization'] = auth
555 headers
['X-Origin'] = origin
556 return {h: v for h, v in headers.items() if v is not None}
559 def _build_api_continuation_query(continuation
, ctp
=None):
561 'continuation': continuation
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
567 query
['clickTracking'] = {'clickTrackingParams': ctp}
571 def _extract_next_continuation_data(cls
, renderer
):
572 next_continuation
= try_get(
573 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
574 lambda x
: x
['continuation']['reloadContinuationData']), dict)
575 if not next_continuation
:
577 continuation
= next_continuation
.get('continuation')
580 ctp
= next_continuation
.get('clickTrackingParams')
581 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
584 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
585 if isinstance(continuation_ep
, dict):
586 continuation
= try_get(
587 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
590 ctp
= continuation_ep
.get('clickTrackingParams')
591 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
594 def _extract_continuation(cls
, renderer
):
595 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
596 if next_continuation
:
597 return next_continuation
600 for key
in ('contents', 'items'):
601 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
603 for content
in contents
:
604 if not isinstance(content
, dict):
606 continuation_ep
= try_get(
607 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
608 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
610 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
615 def _extract_alerts(cls
, data
):
616 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
617 if not isinstance(alert_dict
, dict):
619 for alert
in alert_dict
.values():
620 alert_type
= alert
.get('type')
623 message
= cls
._get
_text
(alert
, 'text')
625 yield alert_type
, message
627 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
630 for alert_type
, alert_message
in alerts
:
631 if alert_type
.lower() == 'error' and fatal
:
632 errors
.append([alert_type
, alert_message
])
634 warnings
.append([alert_type
, alert_message
])
636 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
637 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
), only_once
=only_once
)
639 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
641 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
642 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
644 def _extract_badges(self
, renderer
: dict):
646 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
647 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
649 badges
.add(label
.lower())
653 def _get_text(data
, *path_list
, max_runs
=None):
654 for path
in path_list
or [None]:
658 obj
= traverse_obj(data
, path
, default
=[])
659 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
662 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
665 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
666 if not runs
and isinstance(item
, list):
669 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
670 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
674 def _get_count(self
, data
, *path_list
):
675 count_text
= self
._get
_text
(data
, *path_list
) or ''
676 count
= parse_count(count_text
)
679 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
683 def _extract_thumbnails(data
, *path_list
):
685 Extract thumbnails from thumbnails dict
686 @param path_list: path list to level that contains 'thumbnails' key
689 for path
in path_list
or [()]:
690 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
691 thumbnail_url
= url_or_none(thumbnail
.get('url'))
692 if not thumbnail_url
:
694 # Sometimes youtube gives a wrong thumbnail URL. See:
695 # https://github.com/yt-dlp/yt-dlp/issues/233
696 # https://github.com/ytdl-org/youtube-dl/issues/28023
697 if 'maxresdefault' in thumbnail_url
:
698 thumbnail_url
= thumbnail_url
.split('?')[0]
700 'url': thumbnail_url
,
701 'height': int_or_none(thumbnail
.get('height')),
702 'width': int_or_none(thumbnail
.get('width')),
707 def extract_relative_time(relative_time_text
):
709 Extracts a relative time from string and converts to dt object
710 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
712 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
)
714 start
= mobj
.group('start')
716 return datetime_from_str(start
)
718 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
722 def _extract_time_text(self
, renderer
, *path_list
):
723 text
= self
._get
_text
(renderer
, *path_list
) or ''
724 dt
= self
.extract_relative_time(text
)
726 if isinstance(dt
, datetime
.datetime
):
727 timestamp
= calendar
.timegm(dt
.timetuple())
729 if timestamp
is None:
731 unified_timestamp(text
) or unified_timestamp(
733 (r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r
'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
734 text
.lower(), 'time text', default
=None)))
736 if text
and timestamp
is None:
737 self
.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once
=True)
738 return timestamp
, text
740 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
741 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
742 default_client
='web'):
746 retries
= self
.get_param('extractor_retries', 3)
747 if check_get_keys
is None:
749 while count
< retries
:
752 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
754 response
= self
._call
_api
(
755 ep
=ep
, fatal
=True, headers
=headers
,
756 video_id
=item_id
, query
=query
,
757 context
=self
._extract
_context
(ytcfg
, default_client
),
758 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
759 api_hostname
=api_hostname
, default_client
=default_client
,
760 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
761 except ExtractorError
as e
:
762 if isinstance(e
.cause
, network_exceptions
):
763 if isinstance(e
.cause
, compat_HTTPError
) and not is_html(e
.cause
.read(512)):
766 self
._parse
_json
(e
.cause
.read().decode(), item_id
, fatal
=False),
767 lambda x
: x
['error']['message'], compat_str
)
769 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
770 # Downloading page may result in intermittent 5xx HTTP error
771 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
772 # We also want to catch all other network exceptions since errors in later pages can be troublesome
773 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
774 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
775 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
781 self
.report_warning(error_to_compat_str(e
))
786 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
787 except ExtractorError
as e
:
788 # YouTube servers may return errors we want to retry on in a 200 OK response
789 # See: https://github.com/yt-dlp/yt-dlp/issues/839
790 if 'unknown error' in e
.msg
.lower():
795 self
.report_warning(error_to_compat_str(e
))
797 if not check_get_keys
or dict_get(response
, check_get_keys
):
799 # Youtube sometimes sends incomplete data
800 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
801 last_error
= 'Incomplete data received'
804 raise ExtractorError(last_error
)
806 self
.report_warning(last_error
)
811 def is_music_url(url
):
812 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
814 def _extract_video(self
, renderer
):
815 video_id
= renderer
.get('videoId')
816 title
= self
._get
_text
(renderer
, 'title')
817 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
818 duration
= parse_duration(self
._get
_text
(
819 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
820 view_count
= self
._get
_count
(renderer
, 'viewCountText')
822 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
823 channel_id
= traverse_obj(
824 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type
=str, get_all
=False)
825 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
826 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
827 overlay_style
= traverse_obj(
828 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all
=False, expected_type
=str)
829 badges
= self
._extract
_badges
(renderer
)
830 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
834 'ie_key': YoutubeIE
.ie_key(),
836 'url': f
'https://www.youtube.com/watch?v={video_id}',
838 'description': description
,
839 'duration': duration
,
840 'view_count': view_count
,
841 'uploader': uploader
,
842 'channel_id': channel_id
,
843 'thumbnails': thumbnails
,
844 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
845 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
846 else 'was_live' if 'streamed' in time_text
.lower()
847 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
849 'release_timestamp': scheduled_timestamp
,
850 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
854 class YoutubeIE(YoutubeBaseInfoExtractor
):
856 _VALID_URL
= r
"""(?x)^
858 (?:https?://|//) # http(s):// or protocol-independent URL
859 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
860 (?:www\.)?deturl\.com/www\.youtube\.com|
861 (?:www\.)?pwnyoutube\.com|
862 (?:www\.)?hooktube\.com|
863 (?:www\.)?yourepeat\.com|
866 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
867 (?:.*?\#/)? # handle anchor (#/) redirect urls
868 (?: # the various things that can precede the ID:
869 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
870 |(?: # or the v= param in all its forms
871 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
872 (?:\?|\#!?) # the params delimiter ? or # or #!
873 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
878 youtu\.be| # just youtu.be/xxxx
879 vid\.plus| # or vid.plus/xxxx
880 zwearz\.com/watch| # or zwearz.com/watch/xxxx
883 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
885 )? # all until now is optional -> you can pass the naked ID
886 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
887 (?(1).+)? # if we found the ID, everything can follow
889 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
892 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
893 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$',
894 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
897 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
898 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
899 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
900 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
901 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
902 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
903 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
904 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
905 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
906 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
907 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
908 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
909 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
910 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
911 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
912 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
913 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
914 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
918 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
919 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
920 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
921 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
922 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
923 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
924 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
926 # Apple HTTP Live Streaming
927 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
928 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
929 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
930 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
931 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
932 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
933 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
934 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
937 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
938 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
939 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
940 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
941 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
942 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
943 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
944 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
945 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
946 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
947 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
948 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
951 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
952 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
953 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
954 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
955 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
956 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
957 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
960 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
961 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
962 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
963 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
964 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
965 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
966 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
967 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
968 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
969 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
970 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
971 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
972 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
973 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
974 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
975 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
976 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
977 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
978 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
979 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
980 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
981 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
984 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
985 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
987 # Dash webm audio with opus inside
988 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
989 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
990 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
993 '_rtmp': {'protocol': 'rtmp'}
,
995 # av01 video only formats sometimes served with "unknown" codecs
996 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
997 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
998 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}
,
999 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}
,
1000 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}
,
1001 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}
,
1002 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1003 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1005 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1012 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1014 'id': 'BaW_jenozKc',
1016 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1017 'uploader': 'Philipp Hagemeister',
1018 'uploader_id': 'phihag',
1019 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1020 'channel': 'Philipp Hagemeister',
1021 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1022 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1023 'upload_date': '20121002',
1024 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1025 'categories': ['Science & Technology'],
1026 'tags': ['youtube-dl'],
1030 'availability': 'public',
1031 'playable_in_embed': True,
1032 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1033 'live_status': 'not_live',
1037 'channel_follower_count': int
1041 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1042 'note': 'Embed-only video (#1746)',
1044 'id': 'yZIXLfi8CZQ',
1046 'upload_date': '20120608',
1047 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1048 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1049 'uploader': 'SET India',
1050 'uploader_id': 'setindia',
1051 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1054 'skip': 'Private video',
1057 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1058 'note': 'Use the first video ID in the URL',
1060 'id': 'BaW_jenozKc',
1062 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1063 'uploader': 'Philipp Hagemeister',
1064 'uploader_id': 'phihag',
1065 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1066 'channel': 'Philipp Hagemeister',
1067 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1068 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1069 'upload_date': '20121002',
1070 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1071 'categories': ['Science & Technology'],
1072 'tags': ['youtube-dl'],
1076 'availability': 'public',
1077 'playable_in_embed': True,
1078 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1079 'live_status': 'not_live',
1081 'channel_follower_count': int
1084 'skip_download': True,
1088 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1089 'note': '256k DASH audio (format 141) via DASH manifest',
1091 'id': 'a9LDPn-MO4I',
1093 'upload_date': '20121002',
1094 'uploader_id': '8KVIDEO',
1095 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1097 'uploader': '8KVIDEO',
1098 'title': 'UHDTV TEST 8K VIDEO.mp4'
1101 'youtube_include_dash_manifest': True,
1104 'skip': 'format 141 not served anymore',
1106 # DASH manifest with encrypted signature
1108 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1110 'id': 'IB3lcPjvWLA',
1112 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1113 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1115 'uploader': 'AfrojackVEVO',
1116 'uploader_id': 'AfrojackVEVO',
1117 'upload_date': '20131011',
1120 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1121 'playable_in_embed': True,
1122 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1124 'track': 'The Spark',
1125 'live_status': 'not_live',
1126 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1127 'channel': 'Afrojack',
1128 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1130 'availability': 'public',
1131 'categories': ['Music'],
1133 'alt_title': 'The Spark',
1134 'channel_follower_count': int
1137 'youtube_include_dash_manifest': True,
1138 'format': '141/bestaudio[ext=m4a]',
1141 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1143 'note': 'Embed allowed age-gate video',
1144 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1146 'id': 'HtVdAasjOgU',
1148 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1149 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1151 'uploader': 'The Witcher',
1152 'uploader_id': 'WitcherGame',
1153 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1154 'upload_date': '20140605',
1156 'categories': ['Gaming'],
1157 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1158 'availability': 'needs_auth',
1159 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1161 'channel': 'The Witcher',
1162 'live_status': 'not_live',
1164 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1165 'playable_in_embed': True,
1167 'channel_follower_count': int
1171 'note': 'Age-gate video with embed allowed in public site',
1172 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1174 'id': 'HsUATh_Nc2U',
1176 'title': 'Godzilla 2 (Official Video)',
1177 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1178 'upload_date': '20200408',
1179 'uploader_id': 'FlyingKitty900',
1180 'uploader': 'FlyingKitty',
1182 'availability': 'needs_auth',
1183 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1184 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1185 'channel': 'FlyingKitty',
1186 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1188 'categories': ['Entertainment'],
1189 'live_status': 'not_live',
1190 'tags': ['Flyingkitty', 'godzilla 2'],
1191 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1194 'playable_in_embed': True,
1195 'channel_follower_count': int
1199 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1200 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1202 'id': 'Tq92D6wQ1mg',
1203 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1205 'upload_date': '20191227',
1206 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1207 'uploader': 'Projekt Melody',
1208 'description': 'md5:17eccca93a786d51bc67646756894066',
1211 'availability': 'needs_auth',
1212 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1213 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1215 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1216 'channel': 'Projekt Melody',
1217 'live_status': 'not_live',
1218 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1219 'playable_in_embed': True,
1220 'categories': ['Entertainment'],
1222 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1223 'channel_follower_count': int
1227 'note': 'Non-Agegated non-embeddable video',
1228 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1230 'id': 'MeJVWBSsPAY',
1232 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1233 'uploader': 'Herr Lurik',
1234 'uploader_id': 'st3in234',
1235 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1236 'upload_date': '20130730',
1237 'track': 'Such mich find mich',
1239 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1241 'playable_in_embed': False,
1242 'creator': 'OOMPH!',
1243 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1245 'alt_title': 'Such mich find mich',
1247 'channel': 'Herr Lurik',
1248 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1249 'categories': ['Music'],
1250 'availability': 'public',
1251 'uploader_url': 'http://www.youtube.com/user/st3in234',
1252 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1253 'live_status': 'not_live',
1255 'channel_follower_count': int
1259 'note': 'Non-bypassable age-gated video',
1260 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1261 'only_matching': True,
1263 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1264 # YouTube Red ad is not captured for creator
1266 'url': '__2ABJjxzNo',
1268 'id': '__2ABJjxzNo',
1271 'upload_date': '20100430',
1272 'uploader_id': 'deadmau5',
1273 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1274 'creator': 'deadmau5',
1275 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1276 'uploader': 'deadmau5',
1277 'title': 'Deadmau5 - Some Chords (HD)',
1278 'alt_title': 'Some Chords',
1279 'availability': 'public',
1281 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1283 'live_status': 'not_live',
1284 'channel': 'deadmau5',
1285 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1287 'track': 'Some Chords',
1288 'artist': 'deadmau5',
1289 'playable_in_embed': True,
1291 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1292 'categories': ['Music'],
1293 'album': 'Some Chords',
1294 'channel_follower_count': int
1296 'expected_warnings': [
1297 'DASH manifest missing',
1300 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1302 'url': 'lqQg6PlCWgI',
1304 'id': 'lqQg6PlCWgI',
1307 'upload_date': '20150827',
1308 'uploader_id': 'olympic',
1309 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1310 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1311 'uploader': 'Olympics',
1312 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1314 'release_timestamp': 1343767800,
1315 'playable_in_embed': True,
1316 'categories': ['Sports'],
1317 'release_date': '20120731',
1318 'channel': 'Olympics',
1319 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1320 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1321 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1323 'availability': 'public',
1324 'live_status': 'was_live',
1326 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1327 'channel_follower_count': int
1330 'skip_download': 'requires avconv',
1335 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1337 'id': '_b-2C3KPAM0',
1339 'stretched_ratio': 16 / 9.,
1341 'upload_date': '20110310',
1342 'uploader_id': 'AllenMeow',
1343 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1344 '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',
1346 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1347 'playable_in_embed': True,
1351 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1352 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1353 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1355 'categories': ['People & Blogs'],
1357 'live_status': 'not_live',
1358 'availability': 'unlisted',
1359 'channel_follower_count': int
1362 # url_encoded_fmt_stream_map is empty string
1364 'url': 'qEJwOuvDf7I',
1366 'id': 'qEJwOuvDf7I',
1368 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1370 'upload_date': '20150404',
1371 'uploader_id': 'spbelect',
1372 'uploader': 'Наблюдатели Петербурга',
1375 'skip_download': 'requires avconv',
1377 'skip': 'This live event has ended.',
1379 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1381 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1383 'id': 'FIl7x6_3R5Y',
1385 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1386 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1388 'upload_date': '20150625',
1389 'uploader_id': 'dorappi2000',
1390 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1391 'uploader': 'dorappi2000',
1392 'formats': 'mincount:31',
1394 'skip': 'not actual anymore',
1396 # DASH manifest with segment_list
1398 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1399 'md5': '8ce563a1d667b599d21064e982ab9e31',
1401 'id': 'CsmdDsKjzN8',
1403 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1404 'uploader': 'Airtek',
1405 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1406 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1407 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1410 'youtube_include_dash_manifest': True,
1411 'format': '135', # bestvideo
1413 'skip': 'This live event has ended.',
1416 # Multifeed videos (multiple cameras), URL is for Main Camera
1417 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1419 'id': 'jvGDaLqkpTg',
1420 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1421 'description': 'md5:e03b909557865076822aa169218d6a5d',
1425 'id': 'jvGDaLqkpTg',
1427 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1428 'description': 'md5:e03b909557865076822aa169218d6a5d',
1430 'upload_date': '20161111',
1431 'uploader': 'Team PGP',
1432 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1433 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1437 'id': '3AKt1R1aDnw',
1439 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1440 'description': 'md5:e03b909557865076822aa169218d6a5d',
1442 'upload_date': '20161111',
1443 'uploader': 'Team PGP',
1444 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1445 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1449 'id': 'RtAMM00gpVc',
1451 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1452 'description': 'md5:e03b909557865076822aa169218d6a5d',
1454 'upload_date': '20161111',
1455 'uploader': 'Team PGP',
1456 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1457 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1461 'id': '6N2fdlP3C5U',
1463 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
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 'skip_download': True,
1475 'skip': 'Not multifeed anymore',
1478 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1479 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1481 'id': 'gVfLd0zydlo',
1482 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1484 'playlist_count': 2,
1485 'skip': 'Not multifeed anymore',
1488 'url': 'https://vid.plus/FlRa-iH7PGw',
1489 'only_matching': True,
1492 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1493 'only_matching': True,
1496 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1497 # Also tests cut-off URL expansion in video description (see
1498 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1499 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1500 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1502 'id': 'lsguqyKfVQg',
1504 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1505 'alt_title': 'Dark Walk',
1506 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1508 'upload_date': '20151119',
1509 'uploader_id': 'IronSoulElf',
1510 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1511 'uploader': 'IronSoulElf',
1512 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1513 'track': 'Dark Walk',
1514 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1515 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1516 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1517 'categories': ['Film & Animation'],
1519 'live_status': 'not_live',
1520 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1521 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1523 'availability': 'public',
1524 'channel': 'IronSoulElf',
1525 'playable_in_embed': True,
1528 'channel_follower_count': int
1531 'skip_download': True,
1535 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1536 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1537 'only_matching': True,
1540 # Video with yt:stretch=17:0
1541 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1543 'id': 'Q39EVAstoRM',
1545 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1546 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1547 'upload_date': '20151107',
1548 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1549 'uploader': 'CH GAMER DROID',
1552 'skip_download': True,
1554 'skip': 'This video does not exist.',
1557 # Video with incomplete 'yt:stretch=16:'
1558 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1559 'only_matching': True,
1562 # Video licensed under Creative Commons
1563 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1565 'id': 'M4gD1WSo5mA',
1567 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1568 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1570 'upload_date': '20150127',
1571 'uploader_id': 'BerkmanCenter',
1572 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1573 'uploader': 'The Berkman Klein Center for Internet & Society',
1574 'license': 'Creative Commons Attribution license (reuse allowed)',
1575 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1576 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1579 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1580 'channel': 'The Berkman Klein Center for Internet & Society',
1581 'availability': 'public',
1583 'categories': ['Education'],
1584 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1585 'live_status': 'not_live',
1586 'playable_in_embed': True,
1587 'channel_follower_count': int
1590 'skip_download': True,
1594 # Channel-like uploader_url
1595 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1597 'id': 'eQcmzGIKrzg',
1599 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1600 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1602 'upload_date': '20151119',
1603 'uploader': 'Bernie Sanders',
1604 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1605 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1606 'license': 'Creative Commons Attribution license (reuse allowed)',
1607 'playable_in_embed': True,
1610 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1612 'availability': 'public',
1613 'categories': ['News & Politics'],
1614 'channel': 'Bernie Sanders',
1615 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1617 'live_status': 'not_live',
1618 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1619 'channel_follower_count': int
1622 'skip_download': True,
1626 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1627 'only_matching': True,
1630 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1631 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1632 'only_matching': True,
1635 # Rental video preview
1636 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1638 'id': 'uGpuVWrhIzE',
1640 'title': 'Piku - Trailer',
1641 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1642 'upload_date': '20150811',
1643 'uploader': 'FlixMatrix',
1644 'uploader_id': 'FlixMatrixKaravan',
1645 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1646 'license': 'Standard YouTube License',
1649 'skip_download': True,
1651 'skip': 'This video is not available.',
1654 # YouTube Red video with episode data
1655 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1657 'id': 'iqKdEhx-dD4',
1659 'title': 'Isolation - Mind Field (Ep 1)',
1660 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1662 'upload_date': '20170118',
1663 'uploader': 'Vsauce',
1664 'uploader_id': 'Vsauce',
1665 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1666 'series': 'Mind Field',
1668 'episode_number': 1,
1669 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1672 'availability': 'public',
1674 'channel': 'Vsauce',
1675 'episode': 'Episode 1',
1676 'categories': ['Entertainment'],
1677 'season': 'Season 1',
1678 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1679 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1681 'playable_in_embed': True,
1682 'live_status': 'not_live',
1683 'channel_follower_count': int
1686 'skip_download': True,
1688 'expected_warnings': [
1689 'Skipping DASH manifest',
1693 # The following content has been identified by the YouTube community
1694 # as inappropriate or offensive to some audiences.
1695 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1697 'id': '6SJNVb0GnPI',
1699 'title': 'Race Differences in Intelligence',
1700 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1702 'upload_date': '20140124',
1703 'uploader': 'New Century Foundation',
1704 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1705 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1708 'skip_download': True,
1710 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1714 'url': '1t24XAntNCY',
1715 'only_matching': True,
1718 # geo restricted to JP
1719 'url': 'sJL6WA-aGkQ',
1720 'only_matching': True,
1723 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1724 'only_matching': True,
1727 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1728 'only_matching': True,
1731 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1732 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1733 'only_matching': True,
1737 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1738 'only_matching': True,
1741 # Video with unsupported adaptive stream type formats
1742 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1744 'id': 'Z4Vy8R84T1U',
1746 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1747 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1749 'upload_date': '20130923',
1750 'uploader': 'Amelia Putri Harwita',
1751 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1752 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1753 'formats': 'maxcount:10',
1756 'skip_download': True,
1757 'youtube_include_dash_manifest': False,
1759 'skip': 'not actual anymore',
1762 # Youtube Music Auto-generated description
1763 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1765 'id': 'MgNrAu2pzNs',
1767 'title': 'Voyeur Girl',
1768 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1769 'upload_date': '20190312',
1770 'uploader': 'Stephen - Topic',
1771 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1772 'artist': 'Stephen',
1773 'track': 'Voyeur Girl',
1774 'album': 'it\'s too much love to know my dear',
1775 'release_date': '20190313',
1776 'release_year': 2019,
1777 'alt_title': 'Voyeur Girl',
1779 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1780 'playable_in_embed': True,
1782 'categories': ['Music'],
1783 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1784 'channel': 'Stephen',
1785 'availability': 'public',
1786 'creator': 'Stephen',
1788 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1790 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1792 'live_status': 'not_live',
1793 'channel_follower_count': int
1796 'skip_download': True,
1800 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1801 'only_matching': True,
1804 # invalid -> valid video id redirection
1805 'url': 'DJztXj2GPfl',
1807 'id': 'DJztXj2GPfk',
1809 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1810 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1811 'upload_date': '20090125',
1812 'uploader': 'Prochorowka',
1813 'uploader_id': 'Prochorowka',
1814 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1815 'artist': 'Panjabi MC',
1816 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1817 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1820 'skip_download': True,
1822 'skip': 'Video unavailable',
1825 # empty description results in an empty string
1826 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1828 'id': 'x41yOUIvK2k',
1830 'title': 'IMG 3456',
1832 'upload_date': '20170613',
1833 'uploader_id': 'ElevageOrVert',
1834 'uploader': 'ElevageOrVert',
1836 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1837 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1839 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1841 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1842 'availability': 'public',
1844 'categories': ['Pets & Animals'],
1846 'playable_in_embed': True,
1847 'live_status': 'not_live',
1848 'channel': 'ElevageOrVert',
1849 'channel_follower_count': int
1852 'skip_download': True,
1856 # with '};' inside yt initial data (see [1])
1857 # see [2] for an example with '};' inside ytInitialPlayerResponse
1858 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1859 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1860 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1862 'id': 'CHqg6qOn4no',
1864 'title': 'Part 77 Sort a list of simple types in c#',
1865 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1866 'upload_date': '20130831',
1867 'uploader_id': 'kudvenkat',
1868 'uploader': 'kudvenkat',
1869 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1871 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1872 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1873 'live_status': 'not_live',
1874 'categories': ['Education'],
1875 'availability': 'public',
1876 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1878 'playable_in_embed': True,
1882 'channel': 'kudvenkat',
1883 'channel_follower_count': int
1886 'skip_download': True,
1890 # another example of '};' in ytInitialData
1891 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1892 'only_matching': True,
1895 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1896 'only_matching': True,
1899 # https://github.com/ytdl-org/youtube-dl/pull/28094
1900 'url': 'OtqTfy26tG0',
1902 'id': 'OtqTfy26tG0',
1904 'title': 'Burn Out',
1905 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1906 'upload_date': '20141120',
1907 'uploader': 'The Cinematic Orchestra - Topic',
1908 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1909 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1910 'artist': 'The Cinematic Orchestra',
1911 'track': 'Burn Out',
1912 'album': 'Every Day',
1914 'live_status': 'not_live',
1915 'alt_title': 'Burn Out',
1919 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1920 'creator': 'The Cinematic Orchestra',
1921 'channel': 'The Cinematic Orchestra',
1922 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1923 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1924 'availability': 'public',
1925 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1926 'categories': ['Music'],
1927 'playable_in_embed': True,
1928 'channel_follower_count': int
1931 'skip_download': True,
1935 # controversial video, only works with bpctr when authenticated with cookies
1936 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1937 'only_matching': True,
1940 # controversial video, requires bpctr/contentCheckOk
1941 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1943 'id': 'SZJvDhaSDnc',
1945 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1946 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1947 'uploader': 'CBS Mornings',
1948 'uploader_id': 'CBSThisMorning',
1949 'upload_date': '20140716',
1950 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1952 'categories': ['News & Politics'],
1953 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1955 'channel': 'CBS Mornings',
1956 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1957 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1959 'availability': 'needs_auth',
1960 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1962 'live_status': 'not_live',
1963 'playable_in_embed': True,
1964 'channel_follower_count': int
1968 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1969 'url': 'cBvYw8_A0vQ',
1971 'id': 'cBvYw8_A0vQ',
1973 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1974 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1975 'upload_date': '20201120',
1976 'uploader': 'Walk around Japan',
1977 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1978 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1980 'categories': ['Travel & Events'],
1981 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1983 'channel': 'Walk around Japan',
1984 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1985 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1987 'availability': 'public',
1988 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1989 'live_status': 'not_live',
1990 'playable_in_embed': True,
1991 'channel_follower_count': int
1994 'skip_download': True,
1997 # Has multiple audio streams
1998 'url': 'WaOKSUlf4TM',
1999 'only_matching': True
2001 # Requires Premium: has format 141 when requested using YTM url
2002 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2003 'only_matching': True
2005 # multiple subtitles with same lang_code
2006 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2007 'only_matching': True,
2009 # Force use android client fallback
2010 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2012 'id': 'YOelRv7fMxY',
2013 'title': 'DIGGING A SECRET TUNNEL Part 1',
2015 'upload_date': '20210624',
2016 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2017 'uploader': 'colinfurze',
2018 'uploader_id': 'colinfurze',
2019 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2020 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2022 'categories': ['Entertainment'],
2023 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2025 'channel': 'colinfurze',
2026 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2027 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2029 'availability': 'public',
2031 'live_status': 'not_live',
2032 'playable_in_embed': True,
2033 'channel_follower_count': int
2036 'format': '17', # 3gp format available on android
2037 'extractor_args': {'youtube': {'player_client': ['android']}
},
2041 # Skip download of additional client configs (remix client config in this case)
2042 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2043 'only_matching': True,
2045 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
2049 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2050 'only_matching': True,
2052 'note': 'Storyboards',
2053 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2055 'id': '5KLPxDtMqe8',
2058 'title': 'Your Brain is Plastic',
2059 'uploader_id': 'scishow',
2060 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2061 'upload_date': '20140324',
2062 'uploader': 'SciShow',
2064 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2065 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2067 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2068 'playable_in_embed': True,
2070 'uploader_url': 'http://www.youtube.com/user/scishow',
2071 'availability': 'public',
2072 'channel': 'SciShow',
2073 'live_status': 'not_live',
2075 'categories': ['Education'],
2077 'channel_follower_count': int
2078 }, 'params': {'format': 'mhtml', 'skip_download': True}
2083 def suitable(cls
, url
):
2084 from ..utils
import parse_qs
2087 if qs
.get('list', [None])[0]:
2089 return super(YoutubeIE
, cls
).suitable(url
)
2091 def __init__(self
, *args
, **kwargs
):
2092 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
2093 self
._code
_cache
= {}
2094 self
._player
_cache
= {}
2096 def _prepare_live_from_start_formats(self
, formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
):
2097 lock
= threading
.Lock()
2100 start_time
= time
.time()
2101 formats
= [f
for f
in formats
if f
.get('is_from_start')]
2103 def refetch_manifest(format_id
, delay
):
2104 nonlocal formats
, start_time
, is_live
2105 if time
.time() <= start_time
+ delay
:
2108 _
, _
, prs
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
2109 video_details
= traverse_obj(
2110 prs
, (..., 'videoDetails'), expected_type
=dict, default
=[])
2111 microformats
= traverse_obj(
2112 prs
, (..., 'microformat', 'playerMicroformatRenderer'),
2113 expected_type
=dict, default
=[])
2114 _
, is_live
, _
, formats
= self
._list
_formats
(video_id
, microformats
, video_details
, prs
, player_url
)
2115 start_time
= time
.time()
2117 def mpd_feed(format_id
, delay
):
2119 @returns (manifest_url, manifest_stream_number, is_live) or None
2122 refetch_manifest(format_id
, delay
)
2124 f
= next((f
for f
in formats
if f
['format_id'] == format_id
), None)
2127 self
.to_screen(f
'{video_id}: Video is no longer live')
2129 self
.report_warning(
2130 f
'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2132 return f
['manifest_url'], f
['manifest_stream_number'], is_live
2135 f
['protocol'] = 'http_dash_segments_generator'
2136 f
['fragments'] = functools
.partial(
2137 self
._live
_dash
_fragments
, f
['format_id'], live_start_time
, mpd_feed
)
2139 def _live_dash_fragments(self
, format_id
, live_start_time
, mpd_feed
, ctx
):
2140 FETCH_SPAN
, MAX_DURATION
= 5, 432000
2142 mpd_url
, stream_number
, is_live
= None, None, True
2145 download_start_time
= ctx
.get('start') or time
.time()
2147 lack_early_segments
= download_start_time
- (live_start_time
or download_start_time
) > MAX_DURATION
2148 if lack_early_segments
:
2149 self
.report_warning(bug_reports_message(
2150 'Starting download from the last 120 hours of the live stream since '
2151 'YouTube does not have data before that. If you think this is wrong,'), only_once
=True)
2152 lack_early_segments
= True
2154 known_idx
, no_fragment_score
, last_segment_url
= begin_index
, 0, None
2155 fragments
, fragment_base_url
= None, None
2157 def _extract_sequence_from_mpd(refresh_sequence
):
2158 nonlocal mpd_url
, stream_number
, is_live
, no_fragment_score
, fragments
, fragment_base_url
2159 # Obtain from MPD's maximum seq value
2160 old_mpd_url
= mpd_url
2161 last_error
= ctx
.pop('last_error', None)
2162 expire_fast
= last_error
and isinstance(last_error
, compat_HTTPError
) and last_error
.code
== 403
2163 mpd_url
, stream_number
, is_live
= (mpd_feed(format_id
, 5 if expire_fast
else 18000)
2164 or (mpd_url
, stream_number
, False))
2165 if not refresh_sequence
:
2166 if expire_fast
and not is_live
:
2167 return False, last_seq
2168 elif old_mpd_url
== mpd_url
:
2169 return True, last_seq
2171 fmts
, _
= self
._extract
_mpd
_formats
_and
_subtitles
(
2172 mpd_url
, None, note
=False, errnote
=False, fatal
=False)
2173 except ExtractorError
:
2176 no_fragment_score
+= 1
2177 return False, last_seq
2178 fmt_info
= next(x
for x
in fmts
if x
['manifest_stream_number'] == stream_number
)
2179 fragments
= fmt_info
['fragments']
2180 fragment_base_url
= fmt_info
['fragment_base_url']
2181 assert fragment_base_url
2183 _last_seq
= int(re
.search(r
'(?:/|^)sq/(\d+)', fragments
[-1]['path']).group(1))
2184 return True, _last_seq
2187 fetch_time
= time
.time()
2188 if no_fragment_score
> 30:
2190 if last_segment_url
:
2191 # Obtain from "X-Head-Seqnum" header value from each segment
2193 urlh
= self
._request
_webpage
(
2194 last_segment_url
, None, note
=False, errnote
=False, fatal
=False)
2195 except ExtractorError
:
2197 last_seq
= try_get(urlh
, lambda x
: int_or_none(x
.headers
['X-Head-Seqnum']))
2198 if last_seq
is None:
2199 no_fragment_score
+= 1
2200 last_segment_url
= None
2203 should_continue
, last_seq
= _extract_sequence_from_mpd(True)
2204 if not should_continue
:
2207 if known_idx
> last_seq
:
2208 last_segment_url
= None
2213 if begin_index
< 0 and known_idx
< 0:
2214 # skip from the start when it's negative value
2215 known_idx
= last_seq
+ begin_index
2216 if lack_early_segments
:
2217 known_idx
= max(known_idx
, last_seq
- int(MAX_DURATION
// fragments
[-1]['duration']))
2219 for idx
in range(known_idx
, last_seq
):
2220 # do not update sequence here or you'll get skipped some part of it
2221 should_continue
, _
= _extract_sequence_from_mpd(False)
2222 if not should_continue
:
2224 raise ExtractorError('breaking out of outer loop')
2225 last_segment_url
= urljoin(fragment_base_url
, 'sq/%d' % idx
)
2227 'url': last_segment_url
,
2229 if known_idx
== last_seq
:
2230 no_fragment_score
+= 5
2232 no_fragment_score
= 0
2233 known_idx
= last_seq
2234 except ExtractorError
:
2237 time
.sleep(max(0, FETCH_SPAN
+ fetch_time
- time
.time()))
2239 def _extract_player_url(self
, *ytcfgs
, webpage
=None):
2240 player_url
= traverse_obj(
2241 ytcfgs
, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2242 get_all
=False, expected_type
=compat_str
)
2245 if player_url
.startswith('//'):
2246 player_url
= 'https:' + player_url
2247 elif not re
.match(r
'https?://', player_url
):
2248 player_url
= compat_urlparse
.urljoin(
2249 'https://www.youtube.com', player_url
)
2252 def _download_player_url(self
, video_id
, fatal
=False):
2253 res
= self
._download
_webpage
(
2254 'https://www.youtube.com/iframe_api',
2255 note
='Downloading iframe API JS', video_id
=video_id
, fatal
=fatal
)
2257 player_version
= self
._search
_regex
(
2258 r
'player\\?/([0-9a-fA-F]{8})\\?/', res
, 'player version', fatal
=fatal
)
2260 return f
'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2262 def _signature_cache_id(self
, example_sig
):
2263 """ Return a string representation of a signature """
2264 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
2267 def _extract_player_info(cls
, player_url
):
2268 for player_re
in cls
._PLAYER
_INFO
_RE
:
2269 id_m
= re
.search(player_re
, player_url
)
2273 raise ExtractorError('Cannot identify player %r' % player_url
)
2274 return id_m
.group('id')
2276 def _load_player(self
, video_id
, player_url
, fatal
=True):
2277 player_id
= self
._extract
_player
_info
(player_url
)
2278 if player_id
not in self
._code
_cache
:
2279 code
= self
._download
_webpage
(
2280 player_url
, video_id
, fatal
=fatal
,
2281 note
='Downloading player ' + player_id
,
2282 errnote
='Download of %s failed' % player_url
)
2284 self
._code
_cache
[player_id
] = code
2285 return self
._code
_cache
.get(player_id
)
2287 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
2288 player_id
= self
._extract
_player
_info
(player_url
)
2290 # Read from filesystem cache
2291 func_id
= 'js_%s_%s' % (
2292 player_id
, self
._signature
_cache
_id
(example_sig
))
2293 assert os
.path
.basename(func_id
) == func_id
2295 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
2296 if cache_spec
is not None:
2297 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
2299 code
= self
._load
_player
(video_id
, player_url
)
2301 res
= self
._parse
_sig
_js
(code
)
2303 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2304 cache_res
= res(test_string
)
2305 cache_spec
= [ord(c
) for c
in cache_res
]
2307 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
2310 def _print_sig_code(self
, func
, example_sig
):
2311 if not self
.get_param('youtube_print_sig_code'):
2314 def gen_sig_code(idxs
):
2315 def _genslice(start
, end
, step
):
2316 starts
= '' if start
== 0 else str(start
)
2317 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
2318 steps
= '' if step
== 1 else (':%d' % step
)
2319 return 's[%s%s%s]' % (starts
, ends
, steps
)
2322 # Quelch pyflakes warnings - start will be set when step is set
2323 start
= '(Never used)'
2324 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
2325 if step
is not None:
2326 if i
- prev
== step
:
2328 yield _genslice(start
, prev
, step
)
2331 if i
- prev
in [-1, 1]:
2336 yield 's[%d]' % prev
2340 yield _genslice(start
, i
, step
)
2342 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2343 cache_res
= func(test_string
)
2344 cache_spec
= [ord(c
) for c
in cache_res
]
2345 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
2346 signature_id_tuple
= '(%s)' % (
2347 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
2348 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2349 ' return %s\n') % (signature_id_tuple
, expr_code
)
2350 self
.to_screen('Extracted signature function:\n' + code
)
2352 def _parse_sig_js(self
, jscode
):
2353 funcname
= self
._search
_regex
(
2354 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2355 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2356 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2357 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2358 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}\(a,\d+\)',
2359 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\(\s*""\s*\)',
2360 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2362 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2363 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2364 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2365 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2366 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2367 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2368 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2369 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
2370 jscode, 'Initial JS player signature function name
', group='sig
')
2372 jsi = JSInterpreter(jscode)
2373 initial_function = jsi.extract_function(funcname)
2374 return lambda s: initial_function([s])
2376 def _decrypt_signature(self, s, video_id, player_url):
2377 """Turn the encrypted s field into a working signature"""
2379 if player_url is None:
2380 raise ExtractorError('Cannot decrypt signature without player_url
')
2383 player_id = (player_url, self._signature_cache_id(s))
2384 if player_id not in self._player_cache:
2385 func = self._extract_signature_function(
2386 video_id, player_url, s
2388 self._player_cache[player_id] = func
2389 func = self._player_cache[player_id]
2390 self._print_sig_code(func, s)
2392 except Exception as e:
2393 raise ExtractorError('Signature extraction failed
: ' + traceback.format_exc(), cause=e)
2395 def _decrypt_nsig(self, s, video_id, player_url):
2396 """Turn the encrypted n field into a working signature"""
2397 if player_url is None:
2398 raise ExtractorError('Cannot decrypt nsig without player_url
')
2399 if player_url.startswith('//'):
2400 player_url = 'https
:' + player_url
2401 elif not re.match(r'https?
://', player_url):
2402 player_url = compat_urlparse.urljoin(
2403 'https
://www
.youtube
.com
', player_url)
2405 sig_id = ('nsig_value
', s)
2406 if sig_id in self._player_cache:
2407 return self._player_cache[sig_id]
2410 player_id = ('nsig
', player_url)
2411 if player_id not in self._player_cache:
2412 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2413 func = self._player_cache[player_id]
2414 self._player_cache[sig_id] = func(s)
2415 self.write_debug(f'Decrypted nsig {s}
=> {self._player_cache[sig_id]}
')
2416 return self._player_cache[sig_id]
2417 except Exception as e:
2418 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2420 def _extract_n_function_name(self, jscode):
2421 return self._search_regex(
2422 (r'\
.get\
("n"\
)\
)&&\
(b
=(?P
<nfunc
>[a
-zA
-Z0
-9$
]{3}
)\
([a
-zA
-Z0
-9]\
)',),
2423 jscode, 'Initial JS player n function name
', group='nfunc
')
2425 def _extract_n_function(self, video_id, player_url):
2426 player_id = self._extract_player_info(player_url)
2427 func_code = self._downloader.cache.load('youtube
-nsig
', player_id)
2430 jsi = JSInterpreter(func_code)
2432 jscode = self._load_player(video_id, player_url)
2433 funcname = self._extract_n_function_name(jscode)
2434 jsi = JSInterpreter(jscode)
2435 func_code = jsi.extract_function_code(funcname)
2436 self._downloader.cache.store('youtube
-nsig
', player_id, func_code)
2438 if self.get_param('youtube_print_sig_code
'):
2439 self.to_screen(f'Extracted nsig function
from {player_id}
:\n{func_code[1]}
\n')
2441 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2443 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2445 Extract signatureTimestamp (sts)
2446 Required to tell API what sig/player version is in use.
2449 if isinstance(ytcfg, dict):
2450 sts = int_or_none(ytcfg.get('STS
'))
2453 # Attempt to extract from player
2454 if player_url is None:
2455 error_msg = 'Cannot extract signature timestamp without player_url
.'
2457 raise ExtractorError(error_msg)
2458 self.report_warning(error_msg)
2460 code = self._load_player(video_id, player_url, fatal=fatal)
2462 sts = int_or_none(self._search_regex(
2463 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
2464 'JS player signature timestamp
', group='sts
', fatal=fatal))
2467 def _mark_watched(self, video_id, player_responses):
2468 playback_url = get_first(
2469 player_responses, ('playbackTracking
', 'videostatsPlaybackUrl
', 'baseUrl
'),
2470 expected_type=url_or_none)
2471 if not playback_url:
2472 self.report_warning('Unable to mark watched
')
2474 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2475 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2477 # cpn generation algorithm is reverse engineered from base.js.
2478 # In fact it works even with dummy cpn.
2479 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
2480 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2486 playback_url = compat_urlparse.urlunparse(
2487 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2489 self._download_webpage(
2490 playback_url, video_id, 'Marking watched
',
2491 'Unable to mark watched
', fatal=False)
2494 def _extract_urls(webpage):
2495 # Embedded YouTube player
2497 unescapeHTML(mobj.group('url
'))
2498 for mobj in re.finditer(r'''(?x)
2508 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2509 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2512 # lazyYT YouTube embed
2513 entries.extend(list(map(
2515 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
2517 # Wordpress "YouTube Video Importer
" plugin
2518 matches = re.findall(r'''(?x)<div[^>]+
2519 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
2520 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
2521 entries.extend(m[-1] for m in matches)
2526 def _extract_url(webpage):
2527 urls = YoutubeIE._extract_urls(webpage)
2528 return urls[0] if urls else None
2531 def extract_id(cls, url):
2532 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2534 raise ExtractorError('Invalid URL: %s' % url)
2535 return mobj.group('id')
2537 def _extract_chapters_from_json(self, data, duration):
2538 chapter_list = traverse_obj(
2540 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2541 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2542 ), expected_type=list)
2544 return self._extract_chapters(
2546 chapter_time=lambda chapter: float_or_none(
2547 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2548 chapter_title=lambda chapter: traverse_obj(
2549 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2552 def _extract_chapters_from_engagement_panel(self, data, duration):
2553 content_list = traverse_obj(
2555 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2556 expected_type=list, default=[])
2557 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2558 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2562 self._extract_chapters(
2563 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2564 chapter_time, chapter_title, duration)
2565 for contents in content_list
2568 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2570 last_chapter = {'start_time': 0}
2571 for idx, chapter in enumerate(chapter_list or []):
2572 title = chapter_title(chapter)
2573 start_time = chapter_time(chapter)
2574 if start_time is None:
2576 last_chapter['end_time'] = start_time
2577 if start_time < last_chapter['start_time']:
2580 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2582 self.report_warning(f'Invalid start time for chapter "{title}"')
2584 last_chapter = {'start_time': start_time, 'title': title}
2585 chapters.append(last_chapter)
2586 last_chapter['end_time'] = duration
2589 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2590 return self._parse_json(self._search_regex(
2591 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2592 regex), webpage, name, default='{}'), video_id, fatal=False)
2594 def _extract_comment(self, comment_renderer, parent=None):
2595 comment_id = comment_renderer.get('commentId')
2599 text = self._get_text(comment_renderer, 'contentText')
2601 # note: timestamp is an estimate calculated from the current time and time_text
2602 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2603 author = self._get_text(comment_renderer, 'authorText')
2604 author_id = try_get(comment_renderer,
2605 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2607 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2608 lambda x: x['likeCount']), compat_str)) or 0
2609 author_thumbnail = try_get(comment_renderer,
2610 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2612 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2613 is_favorited = 'creatorHeart' in (try_get(
2614 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2618 'timestamp': timestamp,
2619 'time_text': time_text,
2620 'like_count': votes,
2621 'is_favorited': is_favorited,
2623 'author_id': author_id,
2624 'author_thumbnail': author_thumbnail,
2625 'author_is_uploader': author_is_uploader,
2626 'parent': parent or 'root'
2629 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2631 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2633 def extract_header(contents):
2634 _continuation = None
2635 for content in contents:
2636 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2637 expected_comment_count = self._get_count(
2638 comments_header_renderer, 'countText', 'commentsCount')
2640 if expected_comment_count:
2641 tracker['est_total'] = expected_comment_count
2642 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2643 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2645 sort_menu_item = try_get(
2646 comments_header_renderer,
2647 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2648 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2650 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2651 if not _continuation:
2654 sort_text = str_or_none(sort_menu_item.get('title'))
2656 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2657 self.to_screen('Sorting comments by %s' % sort_text.lower())
2659 return _continuation
2661 def extract_thread(contents):
2663 tracker['current_page_thread'] = 0
2664 for content in contents:
2665 if not parent and tracker['total_parent_comments'] >= max_parents:
2667 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2668 comment_renderer = get_first(
2669 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2670 expected_type=dict, default={})
2672 comment = self._extract_comment(comment_renderer, parent)
2676 tracker['running_total'] += 1
2677 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2680 # Attempt to get the replies
2681 comment_replies_renderer = try_get(
2682 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2684 if comment_replies_renderer:
2685 tracker['current_page_thread'] += 1
2686 comment_entries_iter = self._comment_entries(
2687 comment_replies_renderer, ytcfg, video_id,
2688 parent=comment.get('id'), tracker=tracker)
2689 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2692 # Keeps track of counts across recursive calls
2697 current_page_thread=0,
2698 total_parent_comments=0,
2699 total_reply_comments=0)
2702 # YouTube comments have a max depth of 2
2703 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2705 self._downloader.deprecation_warning(
2706 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2707 if max_depth == 1 and parent:
2710 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2711 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2713 continuation = self._extract_continuation(root_continuation_data)
2714 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2715 if message and not parent:
2716 self.report_warning(message, video_id=video_id)
2719 is_first_continuation = parent is None
2721 for page_num in itertools.count(0):
2722 if not continuation:
2724 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2725 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2727 if is_first_continuation:
2728 note_prefix = 'Downloading comment section API JSON'
2730 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2731 tracker['current_page_thread'], comment_prog_str)
2733 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2734 ' ' if parent else '', ' replies' if parent else '',
2735 page_num, comment_prog_str)
2737 response = self._extract_response(
2738 item_id=None, query=continuation,
2739 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2740 check_get_keys='onResponseReceivedEndpoints')
2742 continuation_contents = traverse_obj(
2743 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2746 for continuation_section in continuation_contents:
2747 continuation_items = traverse_obj(
2748 continuation_section,
2749 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2750 get_all=False, expected_type=list) or []
2751 if is_first_continuation:
2752 continuation = extract_header(continuation_items)
2753 is_first_continuation = False
2758 for entry in extract_thread(continuation_items):
2762 continuation = self._extract_continuation({'contents': continuation_items})
2766 def _get_comments(self, ytcfg, video_id, contents, webpage):
2767 """Entry for comment extraction"""
2768 def _real_comment_extract(contents):
2770 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2771 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2772 yield from self._comment_entries(renderer, ytcfg, video_id)
2774 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2775 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2778 def _get_checkok_params():
2779 return {'contentCheckOk': True, 'racyCheckOk': True}
2782 def _generate_player_context(cls, sts=None):
2784 'html5Preference': 'HTML5_PREF_WANTS',
2787 context['signatureTimestamp'] = sts
2789 'playbackContext': {
2790 'contentPlaybackContext': context
2792 **cls._get_checkok_params()
2796 def _is_agegated(player_response):
2797 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2800 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2801 AGE_GATE_REASONS = (
2802 'confirm your age', 'age-restricted', 'inappropriate', # reason
2803 'age_verification_required', 'age_check_required', # status
2805 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2808 def _is_unplayable(player_response):
2809 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2811 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2813 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2814 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2815 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2816 headers = self.generate_api_headers(
2817 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2819 yt_query = {'videoId': video_id}
2820 yt_query.update(self._generate_player_context(sts))
2821 return self._extract_response(
2822 item_id=video_id, ep='player', query=yt_query,
2823 ytcfg=player_ytcfg, headers=headers, fatal=True,
2824 default_client=client,
2825 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2828 def _get_requested_clients(self, url, smuggled_data):
2829 requested_clients = []
2830 default = ['android', 'web']
2831 allowed_clients = sorted(
2832 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2833 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2834 for client in self._configuration_arg('player_client'):
2835 if client in allowed_clients:
2836 requested_clients.append(client)
2837 elif client == 'default':
2838 requested_clients.extend(default)
2839 elif client == 'all':
2840 requested_clients.extend(allowed_clients)
2842 self.report_warning(f'Skipping unsupported client {client}')
2843 if not requested_clients:
2844 requested_clients = default
2846 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2847 requested_clients.extend(
2848 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2850 return orderedSet(requested_clients)
2852 def _extract_player_ytcfg(self, client, video_id):
2854 'web_music': 'https://music.youtube.com',
2855 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2859 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2860 return self.extract_ytcfg(video_id, webpage) or {}
2862 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2865 initial_pr = self._extract_yt_initial_variable(
2866 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2867 video_id, 'initial player response')
2869 original_clients = clients
2870 clients = clients[::-1]
2873 def append_client(client_name):
2874 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2875 clients.append(client_name)
2877 # Android player_response does not have microFormats which are needed for
2878 # extraction of some data. So we return the initial_pr with formats
2879 # stripped out even if not requested by the user
2880 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2882 pr = dict(initial_pr)
2883 pr['streamingData'] = None
2887 tried_iframe_fallback = False
2890 client = clients.pop()
2891 player_ytcfg = master_ytcfg if client == 'web' else {}
2892 if 'configs' not in self._configuration_arg('player_skip'):
2893 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2895 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2896 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2897 if 'js' in self._configuration_arg('player_skip'):
2898 require_js_player = False
2901 if not player_url and not tried_iframe_fallback and require_js_player:
2902 player_url = self._download_player_url(video_id)
2903 tried_iframe_fallback = True
2906 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2907 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
2908 except ExtractorError as e:
2910 self.report_warning(last_error)
2917 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2918 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
2919 append_client(client.replace('_agegate', '_creator'))
2920 elif self._is_agegated(pr):
2921 append_client(f'{client}_agegate')
2926 self.report_warning(last_error)
2927 return prs, player_url
2929 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2930 itags, stream_ids = {}, []
2931 itag_qualities, res_qualities = {}, {}
2933 # Normally tiny is the smallest video-only formats. But
2934 # audio-only formats with unknown quality may get tagged as tiny
2936 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2937 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2939 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2941 for fmt in streaming_formats:
2942 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2945 itag = str_or_none(fmt.get('itag'))
2946 audio_track = fmt.get('audioTrack') or {}
2947 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2948 if stream_id in stream_ids:
2951 quality = fmt.get('quality')
2952 height = int_or_none(fmt.get('height'))
2953 if quality == 'tiny' or not quality:
2954 quality = fmt.get('audioQuality', '').lower() or quality
2955 # The 3gp format (17) in android client has a quality of "small",
2956 # but is actually worse than other formats
2961 itag_qualities[itag] = quality
2963 res_qualities[height] = quality
2964 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2965 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2966 # number of fragment that would subsequently requested with (`&sq=N`)
2967 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2970 fmt_url = fmt.get('url')
2972 sc = compat_parse_qs(fmt.get('signatureCipher'))
2973 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2974 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2975 if not (sc and fmt_url and encrypted_sig):
2979 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2980 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2981 fmt_url += '&' + sp + '=' + signature
2983 query = parse_qs(fmt_url)
2987 fmt_url = update_url_query(fmt_url, {
2988 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2989 except ExtractorError as e:
2990 self.report_warning(
2991 f'nsig extraction failed: You may experience throttling for some formats\n'
2992 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
2996 itags[itag] = 'https'
2997 stream_ids.append(stream_id)
2999 tbr = float_or_none(
3000 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3002 'asr': int_or_none(fmt.get('audioSampleRate')),
3003 'filesize': int_or_none(fmt.get('contentLength')),
3005 'format_note': join_nonempty(
3006 '%s%s' % (audio_track.get('displayName') or '',
3007 ' (default)' if audio_track.get('audioIsDefault') else ''),
3008 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3009 throttled and 'THROTTLED', delim=', '),
3010 'source_preference': -10 if throttled else -1,
3011 'fps': int_or_none(fmt.get('fps')) or None,
3013 'quality': q(quality),
3016 'width': int_or_none(fmt.get('width')),
3017 'language': audio_track.get('id', '').split('.')[0],
3018 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
3020 mime_mobj = re.match(
3021 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3023 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3024 dct.update(parse_codecs(mime_mobj.group(2)))
3025 no_audio = dct.get('acodec') == 'none'
3026 no_video = dct.get('vcodec') == 'none'
3031 if no_audio or no_video:
3032 dct['downloader_options'] = {
3033 # Youtube throttles chunks >~10M
3034 'http_chunk_size': 10485760,
3037 dct['container'] = dct['ext'] + '_dash'
3040 live_from_start = is_live and self.get_param('live_from_start')
3041 skip_manifests = self._configuration_arg('skip')
3042 if not self.get_param('youtube_include_hls_manifest', True):
3043 skip_manifests.append('hls')
3044 get_dash = 'dash' not in skip_manifests and (
3045 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3046 get_hls = not live_from_start and 'hls' not in skip_manifests
3048 def process_manifest_format(f, proto, itag):
3050 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3052 itag = f'{itag}-{proto}'
3054 f['format_id'] = itag
3057 f['quality'] = next((
3059 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3060 if val in qdict), -1)
3063 for sd in streaming_data:
3064 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3065 if hls_manifest_url:
3066 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3067 if process_manifest_format(f, 'hls', self._search_regex(
3068 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3071 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3072 if dash_manifest_url:
3073 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3074 if process_manifest_format(f, 'dash', f['format_id']):
3075 f['filesize'] = int_or_none(self._search_regex(
3076 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3078 f['is_from_start'] = True
3082 def _extract_storyboard(self, player_responses, duration):
3084 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3085 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3089 for i, args in enumerate(spec):
3090 args = args.split('#')
3091 counts = list(map(int_or_none, args[:5]))
3092 if len(args) != 8 or not all(counts):
3093 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3095 width, height, frame_count, cols, rows = counts
3098 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3099 fragment_count = frame_count / (cols * rows)
3100 fragment_duration = duration / fragment_count
3102 'format_id': f'sb{i}',
3103 'format_note': 'storyboard',
3105 'protocol': 'mhtml',
3112 'path': url.replace('$M', str(j)),
3113 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3114 } for j in range(math.ceil(fragment_count))],
3117 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3119 if 'webpage' not in self._configuration_arg('player_skip'):
3120 webpage = self._download_webpage(
3121 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3123 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3125 player_responses, player_url = self._extract_player_responses(
3126 self._get_requested_clients(url, smuggled_data),
3127 video_id, webpage, master_ytcfg)
3129 return webpage, master_ytcfg, player_responses, player_url
3131 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3132 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3133 is_live = get_first(video_details, 'isLive')
3135 is_live = get_first(live_broadcast_details, 'isLiveNow')
3137 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3138 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3140 return live_broadcast_details, is_live, streaming_data, formats
3142 def _real_extract(self, url):
3143 url, smuggled_data = unsmuggle_url(url, {})
3144 video_id = self._match_id(url)
3146 base_url = self.http_scheme() + '//www.youtube.com/'
3147 webpage_url = base_url + 'watch?v=' + video_id
3149 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3151 playability_statuses = traverse_obj(
3152 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3154 trailer_video_id = get_first(
3155 playability_statuses,
3156 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3158 if trailer_video_id:
3159 return self.url_result(
3160 trailer_video_id, self.ie_key(), trailer_video_id)
3162 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3163 if webpage else (lambda x: None))
3165 video_details = traverse_obj(
3166 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3167 microformats = traverse_obj(
3168 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3169 expected_type=dict, default=[])
3171 get_first(video_details, 'title')
3172 or self._get_text(microformats, (..., 'title'))
3173 or search_meta(['og:title', 'twitter:title', 'title']))
3174 video_description = get_first(video_details, 'shortDescription')
3176 multifeed_metadata_list = get_first(
3178 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3180 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3181 if self.get_param('noplaylist'):
3182 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3186 for feed in multifeed_metadata_list.split(','):
3187 # Unquote should take place before split on comma (,) since textual
3188 # fields may contain comma as well (see
3189 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3190 feed_data = compat_parse_qs(
3191 compat_urllib_parse_unquote_plus(feed))
3193 def feed_entry(name):
3195 feed_data, lambda x: x[name][0], compat_str)
3197 feed_id = feed_entry('id')
3200 feed_title = feed_entry('title')
3203 title += ' (%s)' % feed_title
3205 '_type': 'url_transparent',
3206 'ie_key': 'Youtube',
3208 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3209 {'force_singlefeed': True}),
3212 feed_ids.append(feed_id)
3214 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3215 % (', '.join(feed_ids), video_id))
3216 return self.playlist_result(
3217 entries, video_id, video_title, video_description)
3219 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
3222 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3223 self.report_drm(video_id)
3225 playability_statuses,
3226 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3227 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3228 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3230 if subreason == 'The uploader has not made this video available in your country.':
3231 countries = get_first(microformats, 'availableCountries')
3233 regions_allowed = search_meta('regionsAllowed')
3234 countries = regions_allowed.split(',') if regions_allowed else None
3235 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3236 reason += f'. {subreason}'
3238 self.raise_no_formats(reason, expected=True)
3240 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3241 if not keywords and webpage:
3243 unescapeHTML(m.group('content'))
3244 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3245 for keyword in keywords:
3246 if keyword.startswith('yt:stretch='):
3247 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3249 # NB: float is intentional for forcing float division
3250 w, h = (float(v) for v in mobj.groups())
3254 if f.get('vcodec') != 'none':
3255 f['stretched_ratio'] = ratio
3257 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3258 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3261 'url': thumbnail_url,
3263 original_thumbnails = thumbnails.copy()
3265 # The best resolution thumbnails sometimes does not appear in the webpage
3266 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3267 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3269 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3270 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3271 'mqdefault', 'mq1', 'mq2', 'mq3',
3272 'default', '1', '2', '3'
3274 n_thumbnail_names = len(thumbnail_names)
3276 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3277 video_id=video_id, name=name, ext=ext,
3278 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3279 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3280 for thumb in thumbnails:
3281 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3282 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3283 self._remove_duplicate_formats(thumbnails)
3284 self._downloader._sort_thumbnails(original_thumbnails)
3286 category = get_first(microformats, 'category') or search_meta('genre')
3287 channel_id = str_or_none(
3288 get_first(video_details, 'channelId')
3289 or get_first(microformats, 'externalChannelId')
3290 or search_meta('channelId'))
3291 duration = int_or_none(
3292 get_first(video_details, 'lengthSeconds')
3293 or get_first(microformats, 'lengthSeconds')
3294 or parse_duration(search_meta('duration'))) or None
3295 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3297 live_content = get_first(video_details, 'isLiveContent')
3298 is_upcoming = get_first(video_details, 'isUpcoming')
3300 if is_upcoming or live_content is False:
3302 if is_upcoming is None and (live_content or is_live):
3304 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3305 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3306 if not duration and live_end_time and live_start_time:
3307 duration = live_end_time - live_start_time
3309 if is_live and self.get_param('live_from_start'):
3310 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3312 formats.extend(self._extract_storyboard(player_responses, duration))
3314 # Source is given priority since formats that throttle are given lower source_preference
3315 # When throttling issue is fully fixed, remove this
3316 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3320 'title': video_title,
3322 'thumbnails': thumbnails,
3323 # The best thumbnail that we are sure exists. Prevents unnecessary
3324 # URL checking if user don't care about getting the best possible thumbnail
3325 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3326 'description': video_description,
3327 'upload_date': unified_strdate(
3328 get_first(microformats, 'uploadDate')
3329 or search_meta('uploadDate')),
3330 'uploader': get_first(video_details, 'author'),
3331 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3332 'uploader_url': owner_profile_url,
3333 'channel_id': channel_id,
3334 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3335 'duration': duration,
3336 'view_count': int_or_none(
3337 get_first((video_details, microformats), (..., 'viewCount'))
3338 or search_meta('interactionCount')),
3339 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3340 'age_limit': 18 if (
3341 get_first(microformats, 'isFamilySafe') is False
3342 or search_meta('isFamilyFriendly') == 'false'
3343 or search_meta('og:restrictions:age') == '18+') else 0,
3344 'webpage_url': webpage_url,
3345 'categories': [category] if category else None,
3347 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3349 'was_live': (False if is_live or is_upcoming or live_content is False
3350 else None if is_live is None or is_upcoming is None
3352 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3353 'release_timestamp': live_start_time,
3356 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3358 def get_lang_code(track):
3359 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3360 or track.get('languageCode'))
3362 # Converted into dicts to remove duplicates
3364 get_lang_code(sub): sub
3365 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3366 translation_languages = {
3367 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3368 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3370 def process_language(container, base_url, lang_code, sub_name, query):
3371 lang_subs = container.setdefault(lang_code, [])
3372 for fmt in self._SUBTITLE_FORMATS:
3378 'url': update_url_query(base_url, query),
3382 subtitles, automatic_captions = {}, {}
3383 for lang_code, caption_track in captions.items():
3384 base_url = caption_track.get('baseUrl')
3387 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3388 if caption_track.get('kind') != 'asr':
3392 subtitles, base_url, lang_code, lang_name, {})
3393 if not caption_track.get('isTranslatable'):
3395 for trans_code, trans_name in translation_languages.items():
3398 if caption_track.get('kind') != 'asr':
3399 trans_code += f'-{lang_code}'
3400 trans_name += format_field(lang_name, template=' from %s')
3402 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3403 info['automatic_captions'] = automatic_captions
3404 info['subtitles'] = subtitles
3406 parsed_url = compat_urllib_parse_urlparse(url)
3407 for component in [parsed_url.fragment, parsed_url.query]:
3408 query = compat_parse_qs(component)
3409 for k, v in query.items():
3410 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3412 if d_k not in info and k in s_ks:
3413 info[d_k] = parse_duration(query[k][0])
3415 # Youtube Music Auto-generated description
3416 if video_description:
3417 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
3419 release_year = mobj.group('release_year')
3420 release_date = mobj.group('release_date')
3422 release_date = release_date.replace('-', '')
3423 if not release_year:
3424 release_year = release_date[:4]
3426 'album': mobj.group('album'.strip()),
3427 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3428 'track': mobj.group('track').strip(),
3429 'release_date': release_date,
3430 'release_year': int_or_none(release_year),
3435 initial_data = self._extract_yt_initial_variable(
3436 webpage, self._YT_INITIAL_DATA_RE, video_id,
3438 if not initial_data:
3439 query = {'videoId': video_id}
3440 query.update(self._get_checkok_params())
3441 initial_data = self._extract_response(
3442 item_id=video_id, ep='next', fatal=False,
3443 ytcfg=master_ytcfg, query=query,
3444 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3445 note='Downloading initial data API JSON')
3448 # This will error if there is no livechat
3449 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3450 info.setdefault('subtitles', {})['live_chat'] = [{
3451 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3452 'video_id': video_id,
3454 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3456 except (KeyError, IndexError, TypeError):
3460 info['chapters'] = (
3461 self._extract_chapters_from_json(initial_data, duration)
3462 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3467 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3469 for content in contents:
3470 vpir = content.get('videoPrimaryInfoRenderer')
3472 stl = vpir.get('superTitleLink')
3474 stl = self._get_text(stl)
3477 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3478 info['location'] = stl
3480 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3483 'series': mobj.group(1),
3484 'season_number': int(mobj.group(2)),
3485 'episode_number': int(mobj.group(3)),
3487 for tlb in (try_get(
3489 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3491 tbr = tlb.get('toggleButtonRenderer') or {}
3492 for getter, regex in [(
3493 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3494 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3495 lambda x: x['accessibility'],
3496 lambda x: x['accessibilityData']['accessibilityData'],
3497 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3498 label = (try_get(tbr, getter, dict) or {}).get('label')
3500 mobj = re.match(regex, label)
3502 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3504 sbr_tooltip = try_get(
3505 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3507 like_count, dislike_count = sbr_tooltip.split(' / ')
3509 'like_count': str_to_int(like_count),
3510 'dislike_count': str_to_int(dislike_count),
3512 vsir = content.get('videoSecondaryInfoRenderer')
3514 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3516 'channel': self._get_text(vor, 'title'),
3517 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3521 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3523 multiple_songs = False
3525 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3526 multiple_songs = True
3529 mrr = row.get('metadataRowRenderer') or {}
3530 mrr_title = mrr.get('title')
3533 mrr_title = self._get_text(mrr, 'title')
3534 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3535 if mrr_title == 'License':
3536 info['license'] = mrr_contents_text
3537 elif not multiple_songs:
3538 if mrr_title == 'Album':
3539 info['album'] = mrr_contents_text
3540 elif mrr_title == 'Artist':
3541 info['artist'] = mrr_contents_text
3542 elif mrr_title == 'Song':
3543 info['track'] = mrr_contents_text
3546 'channel': 'uploader',
3547 'channel_id': 'uploader_id',
3548 'channel_url': 'uploader_url',
3550 for to, frm in fallbacks.items():
3551 if not info.get(to):
3552 info[to] = info.get(frm)
3554 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3559 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3560 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3561 is_membersonly = None
3563 if initial_data and is_private is not None:
3564 is_membersonly = False
3566 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3567 badge_labels = set()
3568 for content in contents:
3569 if not isinstance(content, dict):
3571 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3572 for badge_label in badge_labels:
3573 if badge_label.lower() == 'members only':
3574 is_membersonly = True
3575 elif badge_label.lower() == 'premium':
3577 elif badge_label.lower() == 'unlisted':
3580 info['availability'] = self._availability(
3581 is_private=is_private,
3582 needs_premium=is_premium,
3583 needs_subscription=is_membersonly,
3584 needs_auth=info['age_limit'] >= 18,
3585 is_unlisted=None if is_private is None else is_unlisted)
3587 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3589 self.mark_watched(video_id, player_responses)
3594 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3596 def _extract_channel_id(self, webpage):
3597 channel_id = self._html_search_meta(
3598 'channelId', webpage, 'channel id', default=None)
3601 channel_url = self._html_search_meta(
3602 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3603 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3604 'twitter:app:url:googleplay'), webpage, 'channel url')
3605 return self._search_regex(
3606 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3607 channel_url, 'channel id')
3610 def _extract_basic_item_renderer(item):
3611 # Modified from _extract_grid_item_renderer
3612 known_basic_renderers = (
3613 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3615 for key, renderer in item.items():
3616 if not isinstance(renderer, dict):
3618 elif key in known_basic_renderers:
3620 elif key.startswith('grid') and key.endswith('Renderer'):
3623 def _grid_entries(self, grid_renderer):
3624 for item in grid_renderer['items']:
3625 if not isinstance(item, dict):
3627 renderer = self._extract_basic_item_renderer(item)
3628 if not isinstance(renderer, dict):
3630 title = self._get_text(renderer, 'title')
3633 playlist_id = renderer.get('playlistId')
3635 yield self.url_result(
3636 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3637 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3641 video_id = renderer.get('videoId')
3643 yield self._extract_video(renderer)
3646 channel_id = renderer.get('channelId')
3648 yield self.url_result(
3649 'https://www.youtube.com/channel/%s' % channel_id,
3650 ie=YoutubeTabIE.ie_key(), video_title=title)
3652 # generic endpoint URL support
3653 ep_url = urljoin('https://www.youtube.com/', try_get(
3654 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3657 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3658 if ie.suitable(ep_url):
3659 yield self.url_result(
3660 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3663 def _shelf_entries_from_content(self, shelf_renderer):
3664 content = shelf_renderer.get('content')
3665 if not isinstance(content, dict):
3667 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3669 # TODO: add support for nested playlists so each shelf is processed
3670 # as separate playlist
3671 # TODO: this includes only first N items
3672 for entry in self._grid_entries(renderer):
3674 renderer = content.get('horizontalListRenderer')
3679 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3681 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3683 shelf_url = urljoin('https://www.youtube.com', ep)
3685 # Skipping links to another channels, note that checking for
3686 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3688 if skip_channels and '/channels?' in shelf_url:
3690 title = self._get_text(shelf_renderer, 'title')
3691 yield self.url_result(shelf_url, video_title=title)
3692 # Shelf may not contain shelf URL, fallback to extraction from content
3693 for entry in self._shelf_entries_from_content(shelf_renderer):
3696 def _playlist_entries(self, video_list_renderer):
3697 for content in video_list_renderer['contents']:
3698 if not isinstance(content, dict):
3700 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3701 if not isinstance(renderer, dict):
3703 video_id = renderer.get('videoId')
3706 yield self._extract_video(renderer)
3708 def _rich_entries(self, rich_grid_renderer):
3710 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3711 video_id = renderer.get('videoId')
3714 yield self._extract_video(renderer)
3716 def _video_entry(self, video_renderer):
3717 video_id = video_renderer.get('videoId')
3719 return self._extract_video(video_renderer)
3721 def _post_thread_entries(self, post_thread_renderer):
3722 post_renderer = try_get(
3723 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3724 if not post_renderer:
3727 video_renderer = try_get(
3728 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3729 video_id = video_renderer.get('videoId')
3731 entry = self._extract_video(video_renderer)
3734 # playlist attachment
3735 playlist_id = try_get(
3736 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3738 yield self.url_result(
3739 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3740 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3741 # inline video links
3742 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3744 if not isinstance(run, dict):
3747 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3750 if not YoutubeIE.suitable(ep_url):
3752 ep_video_id = YoutubeIE._match_id(ep_url)
3753 if video_id == ep_video_id:
3755 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3757 def _post_thread_continuation_entries(self, post_thread_continuation):
3758 contents = post_thread_continuation.get('contents')
3759 if not isinstance(contents, list):
3761 for content in contents:
3762 renderer = content.get('backstagePostThreadRenderer')
3763 if not isinstance(renderer, dict):
3765 for entry in self._post_thread_entries(renderer):
3769 def _rich_grid_entries(self
, contents
):
3770 for content
in contents
:
3771 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3773 entry
= self
._video
_entry
(video_renderer
)
3777 def _extract_entries(self, parent_renderer, continuation_list):
3778 # continuation_list is modified in-place with continuation_list = [continuation_token]
3779 continuation_list[:] = [None]
3780 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3781 for content in contents:
3782 if not isinstance(content, dict):
3784 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3786 renderer = content.get('richItemRenderer')
3788 for entry in self._rich_entries(renderer):
3790 continuation_list[0] = self._extract_continuation(parent_renderer)
3792 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3793 for isr_content in isr_contents:
3794 if not isinstance(isr_content, dict):
3798 'playlistVideoListRenderer': self._playlist_entries,
3799 'gridRenderer': self._grid_entries,
3800 'shelfRenderer': lambda x: self._shelf_entries(x),
3801 'backstagePostThreadRenderer': self._post_thread_entries,
3802 'videoRenderer': lambda x: [self._video_entry(x)],
3803 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3804 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
3806 for key, renderer in isr_content.items():
3807 if key not in known_renderers:
3809 for entry in known_renderers[key](renderer):
3812 continuation_list[0] = self._extract_continuation(renderer)
3815 if not continuation_list[0]:
3816 continuation_list[0] = self._extract_continuation(is_renderer)
3818 if not continuation_list[0]:
3819 continuation_list[0] = self._extract_continuation(parent_renderer)
3821 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3822 continuation_list = [None]
3823 extract_entries = lambda x: self._extract_entries(x, continuation_list)
3824 tab_content = try_get(tab, lambda x: x['content'], dict)
3828 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3829 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3830 for entry in extract_entries(parent_renderer):
3832 continuation = continuation_list[0]
3834 for page_num in itertools.count(1):
3835 if not continuation:
3837 headers = self.generate_api_headers(
3838 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
3839 response = self._extract_response(
3840 item_id='%s page %s' % (item_id, page_num),
3841 query=continuation, headers=headers, ytcfg=ytcfg,
3842 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3846 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3847 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3848 visitor_data = self._extract_visitor_data(response) or visitor_data
3850 known_continuation_renderers = {
3851 'playlistVideoListContinuation': self._playlist_entries,
3852 'gridContinuation': self._grid_entries,
3853 'itemSectionContinuation': self._post_thread_continuation_entries,
3854 'sectionListContinuation': extract_entries, # for feeds
3856 continuation_contents = try_get(
3857 response, lambda x: x['continuationContents'], dict) or {}
3858 continuation_renderer = None
3859 for key, value in continuation_contents.items():
3860 if key not in known_continuation_renderers:
3862 continuation_renderer = value
3863 continuation_list = [None]
3864 for entry in known_continuation_renderers[key](continuation_renderer):
3866 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3868 if continuation_renderer:
3872 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3873 'gridVideoRenderer': (self._grid_entries, 'items'),
3874 'gridChannelRenderer': (self._grid_entries, 'items'),
3875 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3876 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3877 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3878 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3880 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3881 continuation_items = try_get(
3882 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3883 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3884 video_items_renderer = None
3885 for key, value in continuation_item.items():
3886 if key not in known_renderers:
3888 video_items_renderer = {known_renderers[key][1]: continuation_items}
3889 continuation_list = [None]
3890 for entry in known_renderers[key][0](video_items_renderer):
3892 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3894 if video_items_renderer:
3899 def _extract_selected_tab(tabs):
3901 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3902 if renderer.get('selected') is True:
3905 raise ExtractorError('Unable to find selected tab')
3908 def _extract_uploader(cls, data):
3910 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3912 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3914 uploader['uploader'] = owner.get('text')
3915 uploader['uploader_id'] = try_get(
3916 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3917 uploader['uploader_url'] = urljoin(
3918 'https://www.youtube.com/',
3919 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3920 return {k: v for k, v in uploader.items() if v is not None}
3922 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
3923 playlist_id = title = description = channel_url = channel_name = channel_id = None
3926 selected_tab = self._extract_selected_tab(tabs)
3927 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3929 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3931 channel_name = renderer.get('title')
3932 channel_url = renderer.get('channelUrl')
3933 channel_id = renderer.get('externalId')
3936 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3939 title = renderer.get('title')
3940 description = renderer.get('description', '')
3941 playlist_id = channel_id
3942 tags = renderer.get('keywords', '').split()
3944 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3945 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3946 def _get_uncropped(url):
3947 return url_or_none((url or '').split('=')[0] + '=s0')
3949 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3950 if avatar_thumbnails:
3951 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3952 if uncropped_avatar:
3953 avatar_thumbnails.append({
3954 'url': uncropped_avatar,
3955 'id': 'avatar_uncropped',
3959 channel_banners = self._extract_thumbnails(
3960 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3961 for banner in channel_banners:
3962 banner['preference'] = -10
3965 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3966 if uncropped_banner:
3967 channel_banners.append({
3968 'url': uncropped_banner,
3969 'id': 'banner_uncropped',
3973 primary_thumbnails = self._extract_thumbnails(
3974 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
3976 if playlist_id is None:
3977 playlist_id = item_id
3979 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
3980 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
3982 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
3983 title += format_field(selected_tab, 'title', ' - %s')
3984 title += format_field(selected_tab, 'expandedText', ' - %s')
3987 'playlist_id': playlist_id,
3988 'playlist_title': title,
3989 'playlist_description': description,
3990 'uploader': channel_name,
3991 'uploader_id': channel_id,
3992 'uploader_url': channel_url,
3993 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
3995 'view_count': self._get_count(playlist_stats, 1),
3996 'availability': self._extract_availability(data),
3997 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
3998 'playlist_count': self._get_count(playlist_stats, 0),
3999 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4002 metadata.update(self._extract_uploader(data))
4004 'channel': metadata['uploader'],
4005 'channel_id': metadata['uploader_id'],
4006 'channel_url': metadata['uploader_url']})
4007 return self.playlist_result(
4009 selected_tab, playlist_id, ytcfg,
4010 self._extract_account_syncid(ytcfg, data),
4011 self._extract_visitor_data(data, ytcfg)),
4014 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4015 first_id = last_id = response = None
4016 for page_num in itertools.count(1):
4017 videos = list(self._playlist_entries(playlist))
4020 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4021 if start >= len(videos):
4023 for video in videos[start:]:
4024 if video['id'] == first_id:
4025 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4028 first_id = first_id or videos[0]['id']
4029 last_id = videos[-1]['id']
4030 watch_endpoint = try_get(
4031 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4032 headers = self.generate_api_headers(
4033 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4034 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4036 'playlistId': playlist_id,
4037 'videoId': watch_endpoint.get('videoId') or last_id,
4038 'index': watch_endpoint.get('index') or len(videos),
4039 'params': watch_endpoint.get('params') or 'OAE%3D'
4041 response = self._extract_response(
4042 item_id='%s page %d' % (playlist_id, page_num),
4043 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4044 check_get_keys='contents'
4047 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4049 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4050 title = playlist.get('title') or try_get(
4051 data, lambda x: x['titleText']['simpleText'], compat_str)
4052 playlist_id = playlist.get('playlistId') or item_id
4054 # Delegating everything except mix playlists to regular tab-based playlist URL
4055 playlist_url = urljoin(url, try_get(
4056 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4058 if playlist_url and playlist_url != url:
4059 return self.url_result(
4060 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4063 return self.playlist_result(
4064 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4065 playlist_id=playlist_id, playlist_title=title)
4067 def _extract_availability(self, data):
4069 Gets the availability of a given playlist/tab.
4070 Note: Unless YouTube tells us explicitly, we do not assume it is public
4071 @param data: response
4073 is_private = is_unlisted = None
4074 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4075 badge_labels = self._extract_badges(renderer)
4077 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4078 privacy_dropdown_entries = try_get(
4079 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4080 for renderer_dict in privacy_dropdown_entries:
4081 is_selected = try_get(
4082 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4085 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4087 badge_labels.add(label.lower())
4090 for badge_label in badge_labels:
4091 if badge_label == 'unlisted':
4093 elif badge_label == 'private':
4095 elif badge_label == 'public':
4096 is_unlisted = is_private = False
4097 return self._availability(is_private, False, False, False, is_unlisted)
4100 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4101 sidebar_renderer = try_get(
4102 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4103 for item in sidebar_renderer:
4104 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4108 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4110 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4112 browse_id = params = None
4113 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4116 menu_renderer = try_get(
4117 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4118 for menu_item in menu_renderer:
4119 if not isinstance(menu_item, dict):
4121 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4123 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4124 if not text or text.lower() != 'show unavailable videos':
4126 browse_endpoint = try_get(
4127 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4128 browse_id = browse_endpoint.get('browseId')
4129 params = browse_endpoint.get('params')
4132 headers = self.generate_api_headers(
4133 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4134 visitor_data=self._extract_visitor_data(data, ytcfg))
4136 'params': params or 'wgYCCAA=',
4137 'browseId': browse_id or 'VL%s' % item_id
4139 return self._extract_response(
4140 item_id=item_id, headers=headers, query=query,
4141 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4142 note='Downloading API JSON with unavailable videos')
4144 def _extract_webpage(self, url, item_id, fatal=True):
4145 retries = self.get_param('extractor_retries', 3)
4147 webpage = data = last_error = None
4148 while count < retries:
4150 # Sometimes youtube returns a webpage with incomplete ytInitialData
4151 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4153 self.report_warning('%s. Retrying ...' % last_error)
4155 webpage = self._download_webpage(
4157 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4158 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4159 except ExtractorError as e:
4160 if isinstance(e.cause, network_exceptions):
4161 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4162 last_error = error_to_compat_str(e.cause or e.msg)
4167 self.report_warning(error_to_compat_str(e))
4171 self._extract_and_report_alerts(data)
4172 except ExtractorError as e:
4175 self.report_warning(error_to_compat_str(e))
4178 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4181 last_error = 'Incomplete yt initial data received'
4182 if count >= retries:
4184 raise ExtractorError(last_error)
4185 self.report_warning(last_error)
4188 return webpage, data
4190 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4192 if 'webpage' not in self._configuration_arg('skip'):
4193 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4194 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4196 if not ytcfg and self.is_authenticated:
4197 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4198 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4199 raise ExtractorError(
4200 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4201 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4203 self.report_warning(msg, only_once=True)
4204 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4207 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4208 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4209 resolve_response = self._extract_response(
4210 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4211 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4212 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4213 for ep_key, ep in endpoints.items():
4214 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4216 return self._extract_response(
4217 item_id=item_id, query=params, ep=ep, headers=headers,
4218 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4219 check_get_keys=('contents', 'currentVideoEndpoint'))
4220 err_note = 'Failed to resolve url (does the playlist exist?)'
4222 raise ExtractorError(err_note, expected=True)
4223 self.report_warning(err_note, item_id)
4226 def _smuggle_data(entries, data):
4227 for entry in entries:
4229 entry['url'] = smuggle_url(entry['url'], data)
4232 _SEARCH_PARAMS = None
4234 def _search_results(self, query, params=NO_DEFAULT):
4235 data = {'query': query}
4236 if params is NO_DEFAULT:
4237 params = self._SEARCH_PARAMS
4239 data['params'] = params
4240 continuation_list = [None]
4241 for page_num in itertools.count(1):
4242 data.update(continuation_list[0] or {})
4243 search = self._extract_response(
4244 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4245 check_get_keys=('contents', 'onResponseReceivedCommands'))
4246 slr_contents = try_get(
4248 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4249 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4251 yield from self._extract_entries({'contents': slr_contents}, continuation_list)
4252 if not continuation_list[0]:
4256 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4257 IE_DESC = 'YouTube Tabs'
4258 _VALID_URL = r'''(?x
:
4262 youtube(?
:kids
)?\
.com|
4266 (?P
<channel_type
>channel|c|user|browse
)/|
4269 (?
:playlist|watch
)\?.*?
\blist
=
4271 (?
!(?
:%(reserved_names)s)\b) # Direct URLs
4275 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4276 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4278 IE_NAME = 'youtube:tab'
4281 'note': 'playlists, multipage',
4282 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4283 'playlist_mincount': 94,
4285 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4286 'title': 'Igor Kleiner - Playlists',
4287 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4288 'uploader': 'Igor Kleiner',
4289 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4290 'channel': 'Igor Kleiner',
4291 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4292 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4293 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4294 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4295 'channel_follower_count': int
4298 'note': 'playlists, multipage, different order',
4299 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4300 'playlist_mincount': 94,
4302 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4303 'title': 'Igor Kleiner - Playlists',
4304 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4305 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4306 'uploader': 'Igor Kleiner',
4307 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4308 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4309 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4310 'channel': 'Igor Kleiner',
4311 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4312 'channel_follower_count': int
4315 'note': 'playlists, series',
4316 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4317 'playlist_mincount': 5,
4319 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4320 'title': '3Blue1Brown - Playlists',
4321 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4322 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4323 'uploader': '3Blue1Brown',
4324 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4325 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4326 'channel': '3Blue1Brown',
4327 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4328 'tags': ['Mathematics'],
4329 'channel_follower_count': int
4332 'note': 'playlists, singlepage',
4333 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4334 'playlist_mincount': 4,
4336 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4337 'title': 'ThirstForScience - Playlists',
4338 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4339 'uploader': 'ThirstForScience',
4340 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4341 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4342 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4343 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4345 'channel': 'ThirstForScience',
4346 'channel_follower_count': int
4349 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4350 'only_matching': True,
4352 'note': 'basic, single video playlist',
4353 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4355 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4356 'uploader': 'Sergey M.',
4357 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4358 'title': 'youtube-dl public playlist',
4362 'modified_date': '20201130',
4363 'channel': 'Sergey M.',
4364 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4365 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4366 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4368 'playlist_count': 1,
4370 'note': 'empty playlist',
4371 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4373 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4374 'uploader': 'Sergey M.',
4375 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4376 'title': 'youtube-dl empty playlist',
4378 'channel': 'Sergey M.',
4380 'modified_date': '20160902',
4381 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4382 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4383 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4385 'playlist_count': 0,
4388 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4390 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4391 'title': 'lex will - Home',
4392 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4393 'uploader': 'lex will',
4394 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4395 'channel': 'lex will',
4396 'tags': ['bible', 'history', 'prophesy'],
4397 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4398 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4399 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4400 'channel_follower_count': int
4402 'playlist_mincount': 2,
4404 'note': 'Videos tab',
4405 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4407 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4408 'title': 'lex will - Videos',
4409 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4410 'uploader': 'lex will',
4411 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4412 'tags': ['bible', 'history', 'prophesy'],
4413 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4414 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4415 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4416 'channel': 'lex will',
4417 'channel_follower_count': int
4419 'playlist_mincount': 975,
4421 'note': 'Videos tab, sorted by popular',
4422 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4424 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4425 'title': 'lex will - Videos',
4426 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4427 'uploader': 'lex will',
4428 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4429 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4430 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4431 'channel': 'lex will',
4432 'tags': ['bible', 'history', 'prophesy'],
4433 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4434 'channel_follower_count': int
4436 'playlist_mincount': 199,
4438 'note': 'Playlists tab',
4439 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4441 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4442 'title': 'lex will - Playlists',
4443 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4444 'uploader': 'lex will',
4445 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4446 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4447 'channel': 'lex will',
4448 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4449 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4450 'tags': ['bible', 'history', 'prophesy'],
4451 'channel_follower_count': int
4453 'playlist_mincount': 17,
4455 'note': 'Community tab',
4456 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4458 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4459 'title': 'lex will - Community',
4460 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4461 'uploader': 'lex will',
4462 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4463 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4464 'channel': 'lex will',
4465 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4466 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4467 'tags': ['bible', 'history', 'prophesy'],
4468 'channel_follower_count': int
4470 'playlist_mincount': 18,
4472 'note': 'Channels tab',
4473 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4475 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4476 'title': 'lex will - Channels',
4477 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4478 'uploader': 'lex will',
4479 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4480 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4481 'channel': 'lex will',
4482 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4483 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4484 'tags': ['bible', 'history', 'prophesy'],
4485 'channel_follower_count': int
4487 'playlist_mincount': 12,
4489 'note': 'Search tab',
4490 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4491 'playlist_mincount': 40,
4493 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4494 'title': '3Blue1Brown - Search - linear algebra',
4495 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4496 'uploader': '3Blue1Brown',
4497 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4498 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4499 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4500 'tags': ['Mathematics'],
4501 'channel': '3Blue1Brown',
4502 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4503 'channel_follower_count': int
4506 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4507 'only_matching': True,
4509 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4510 'only_matching': True,
4512 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4513 'only_matching': True,
4515 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4516 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4518 'title': '29C3: Not my department',
4519 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4520 'uploader': 'Christiaan008',
4521 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4522 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4524 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4526 'modified_date': '20150605',
4527 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4528 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4529 'channel': 'Christiaan008',
4531 'playlist_count': 96,
4533 'note': 'Large playlist',
4534 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4536 'title': 'Uploads from Cauchemar',
4537 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4538 'uploader': 'Cauchemar',
4539 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4540 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4542 'modified_date': r're:\d{8}',
4543 'channel': 'Cauchemar',
4544 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4547 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4549 'playlist_mincount': 1123,
4550 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4552 'note': 'even larger playlist, 8832 videos',
4553 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4554 'only_matching': True,
4556 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4557 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4559 'title': 'Uploads from Interstellar Movie',
4560 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4561 'uploader': 'Interstellar Movie',
4562 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4563 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4566 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4567 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4568 'channel': 'Interstellar Movie',
4570 'modified_date': r're:\d{8}',
4572 'playlist_mincount': 21,
4574 'note': 'Playlist with "show unavailable videos" button',
4575 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4577 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4578 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4579 'uploader': 'Phim Siêu Nhân Nhật Bản',
4580 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4582 'channel': 'Phim Siêu Nhân Nhật Bản',
4584 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4586 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4587 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4588 'modified_date': r're:\d{8}',
4590 'playlist_mincount': 200,
4591 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4593 'note': 'Playlist with unavailable videos in page 7',
4594 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4596 'title': 'Uploads from BlankTV',
4597 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4598 'uploader': 'BlankTV',
4599 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4600 'channel': 'BlankTV',
4601 'channel_url': 'https://www.youtube.com/c/blanktv',
4602 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4605 'uploader_url': 'https://www.youtube.com/c/blanktv',
4606 'modified_date': r're:\d{8}',
4609 'playlist_mincount': 1000,
4610 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4612 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4613 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4615 'title': 'Data Analysis with Dr Mike Pound',
4616 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4617 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4618 'uploader': 'Computerphile',
4619 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4620 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4623 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4624 'channel_url': 'https://www.youtube.com/user/Computerphile',
4625 'channel': 'Computerphile',
4627 'playlist_mincount': 11,
4629 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4630 'only_matching': True,
4632 'note': 'Playlist URL that does not actually serve a playlist',
4633 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4635 'id': 'FqZTN594JQw',
4637 'title': "Smiley's People 01 detective, Adventure Series, Action",
4638 'uploader': 'STREEM',
4639 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4640 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4641 'upload_date': '20150526',
4642 'license': 'Standard YouTube License',
4643 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4644 'categories': ['People & Blogs'],
4650 'skip_download': True,
4652 'skip': 'This video is not available.',
4653 'add_ie': [YoutubeIE.ie_key()],
4655 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4656 'only_matching': True,
4658 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4659 'only_matching': True,
4661 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4663 'id': 'GgL890LIznQ', # This will keep changing
4666 'uploader': 'Sky News',
4667 'uploader_id': 'skynews',
4668 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4669 'upload_date': r're:\d{8}',
4671 'categories': ['News & Politics'],
4674 'release_timestamp': 1642502819,
4675 'channel': 'Sky News',
4676 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4679 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4680 'playable_in_embed': True,
4681 'release_date': '20220118',
4682 'availability': 'public',
4683 'live_status': 'is_live',
4684 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4685 'channel_follower_count': int
4688 'skip_download': True,
4690 'expected_warnings': ['Ignoring subtitle tracks found in '],
4692 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4694 'id': 'a48o2S1cPoo',
4696 'title': 'The Young Turks - Live Main Show',
4697 'uploader': 'The Young Turks',
4698 'uploader_id': 'TheYoungTurks',
4699 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4700 'upload_date': '20150715',
4701 'license': 'Standard YouTube License',
4702 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4703 'categories': ['News & Politics'],
4704 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4708 'skip_download': True,
4710 'only_matching': True,
4712 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4713 'only_matching': True,
4715 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4716 'only_matching': True,
4718 'note': 'A channel that is not live. Should raise error',
4719 'url': 'https://www.youtube.com/user/numberphile/live',
4720 'only_matching': True,
4722 'url': 'https://www.youtube.com/feed/trending',
4723 'only_matching': True,
4725 'url': 'https://www.youtube.com/feed/library',
4726 'only_matching': True,
4728 'url': 'https://www.youtube.com/feed/history',
4729 'only_matching': True,
4731 'url': 'https://www.youtube.com/feed/subscriptions',
4732 'only_matching': True,
4734 'url': 'https://www.youtube.com/feed/watch_later',
4735 'only_matching': True,
4737 'note': 'Recommended - redirects to home page.',
4738 'url': 'https://www.youtube.com/feed/recommended',
4739 'only_matching': True,
4741 'note': 'inline playlist with not always working continuations',
4742 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4743 'only_matching': True,
4745 'url': 'https://www.youtube.com/course',
4746 'only_matching': True,
4748 'url': 'https://www.youtube.com/zsecurity',
4749 'only_matching': True,
4751 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4752 'only_matching': True,
4754 'url': 'https://www.youtube.com/TheYoungTurks/live',
4755 'only_matching': True,
4757 'url': 'https://www.youtube.com/hashtag/cctv9',
4763 'playlist_mincount': 350,
4765 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4766 'only_matching': True,
4768 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4769 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4770 'only_matching': True
4772 'note': '/browse/ should redirect to /channel/',
4773 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4774 'only_matching': True
4776 'note': 'VLPL, should redirect to playlist?list=PL...',
4777 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4779 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4780 'uploader': 'NoCopyrightSounds',
4781 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4782 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4783 'title': 'NCS Releases',
4784 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4785 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4786 'modified_date': r're:\d{8}',
4788 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4790 'channel': 'NoCopyrightSounds',
4792 'playlist_mincount': 166,
4793 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4795 'note': 'Topic, should redirect to playlist?list=UU...',
4796 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4798 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4799 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4800 'title': 'Uploads from Royalty Free Music - Topic',
4801 'uploader': 'Royalty Free Music - Topic',
4803 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4804 'channel': 'Royalty Free Music - Topic',
4806 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4807 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4808 'modified_date': r're:\d{8}',
4809 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4812 'expected_warnings': [
4813 'The URL does not have a videos tab',
4814 r'[Uu]navailable videos (are|will be) hidden',
4816 'playlist_mincount': 101,
4818 'note': 'Topic without a UU playlist',
4819 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4821 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4822 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
4825 'expected_warnings': [
4826 'the playlist redirect gave error',
4828 'playlist_mincount': 9,
4830 'note': 'Youtube music Album',
4831 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4833 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4834 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
4838 'availability': 'unlisted',
4839 'modified_date': r're:\d{8}',
4841 'playlist_count': 50,
4843 'note': 'unlisted single video playlist',
4844 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4846 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4847 'uploader': 'colethedj',
4848 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4849 'title': 'yt-dlp unlisted playlist test',
4850 'availability': 'unlisted',
4852 'modified_date': '20211208',
4853 'channel': 'colethedj',
4856 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4857 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4858 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4860 'playlist_count': 1,
4862 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4863 'url': 'https://www.youtube.com/feed/recommended',
4865 'id': 'recommended',
4866 'title': 'recommended',
4869 'playlist_mincount': 50,
4871 'skip_download': True,
4872 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4875 'note': 'API Fallback: /videos tab, sorted by oldest first',
4876 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4878 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4879 'title': 'Cody\'sLab - Videos',
4880 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4881 'uploader': 'Cody\'sLab',
4882 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4883 'channel': 'Cody\'sLab',
4884 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4886 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4887 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4888 'channel_follower_count': int
4890 'playlist_mincount': 650,
4892 'skip_download': True,
4893 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4896 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4897 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4899 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4900 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4901 'title': 'Uploads from Royalty Free Music - Topic',
4902 'uploader': 'Royalty Free Music - Topic',
4903 'modified_date': r're:\d{8}',
4904 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4906 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4908 'channel': 'Royalty Free Music - Topic',
4910 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4912 'expected_warnings': [
4913 'does not have a videos tab',
4914 r'[Uu]navailable videos (are|will be) hidden',
4916 'playlist_mincount': 101,
4918 'skip_download': True,
4919 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4924 def suitable(cls, url):
4925 return False if YoutubeIE.suitable(url) else super(
4926 YoutubeTabIE, cls).suitable(url)
4928 def _real_extract(self, url):
4929 url, smuggled_data = unsmuggle_url(url, {})
4930 if self.is_music_url(url):
4931 smuggled_data['is_music_url'] = True
4932 info_dict = self.__real_extract(url, smuggled_data)
4933 if info_dict.get('entries'):
4934 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4937 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
4939 def __real_extract(self, url, smuggled_data):
4940 item_id = self._match_id(url)
4941 url = compat_urlparse.urlunparse(
4942 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4943 compat_opts = self.get_param('compat_opts', [])
4946 mobj = self._URL_RE.match(url).groupdict()
4947 mobj.update((k, '') for k, v in mobj.items() if v is None)
4950 mobj, redirect_warning = get_mobj(url), None
4951 # Youtube returns incomplete data if tabname is not lower case
4952 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4954 if smuggled_data.get('is_music_url'):
4955 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
4956 item_id = item_id[2:]
4957 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4958 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
4959 mdata = self._extract_tab_endpoint(
4960 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4961 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4962 get_all=False, expected_type=compat_str)
4964 raise ExtractorError('Failed to resolve album to playlist')
4965 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
4966 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
4967 pre = f'https://www.youtube.com/channel/{item_id}'
4969 original_tab_name = tab
4970 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4971 # Home URLs should redirect to /videos/
4972 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
4973 'To download only the videos in the home page, add a "/featured" to the URL')
4976 url = ''.join((pre, tab, post))
4977 mobj = get_mobj(url)
4979 # Handle both video/playlist URLs
4981 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
4983 if not video_id and mobj['not_channel'].startswith('watch'):
4985 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4986 raise ExtractorError('Unable to recognize tab page')
4987 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4988 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
4989 url = f'https://www.youtube.com/playlist?list={playlist_id}'
4990 mobj = get_mobj(url)
4992 if video_id and playlist_id:
4993 if self.get_param('noplaylist'):
4994 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
4995 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
4996 ie=YoutubeIE.ie_key(), video_id=video_id)
4997 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
4999 data, ytcfg = self._extract_data(url, item_id)
5001 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5003 selected_tab = self._extract_selected_tab(tabs)
5004 selected_tab_name = selected_tab.get('title', '').lower()
5005 if selected_tab_name == 'home':
5006 selected_tab_name = 'featured'
5007 requested_tab_name = mobj['tab'][1:]
5008 if 'no-youtube-channel-redirect' not in compat_opts:
5009 if requested_tab_name == 'live':
5010 # Live tab should have redirected to the video
5011 raise ExtractorError('The channel is not currently live', expected=True)
5012 if requested_tab_name not in ('', selected_tab_name):
5013 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5014 if not original_tab_name:
5015 if item_id[:2] == 'UC':
5016 # Topic channels don't have /videos. Use the equivalent playlist instead
5017 pl_id = f'UU{item_id[2:]}'
5018 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5020 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5021 except ExtractorError:
5022 redirect_warning += ' and the playlist redirect gave error'
5024 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5025 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5026 if selected_tab_name and selected_tab_name != requested_tab_name:
5027 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5029 raise ExtractorError(redirect_warning, expected=True)
5031 if redirect_warning:
5032 self.to_screen(redirect_warning)
5033 self.write_debug(f'Final URL: {url}')
5035 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5036 if 'no-youtube-unavailable-videos' not in compat_opts:
5037 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5038 self._extract_and_report_alerts(data, only_once=True)
5039 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5041 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5043 playlist = traverse_obj(
5044 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5046 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5048 video_id = traverse_obj(
5049 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5051 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5052 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5053 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5054 ie=YoutubeIE.ie_key(), video_id=video_id)
5056 raise ExtractorError('Unable to recognize tab page')
5059 class YoutubePlaylistIE(InfoExtractor):
5060 IE_DESC = 'YouTube playlists'
5061 _VALID_URL = r'''(?x
)(?
:
5066 youtube(?
:kids
)?\
.com|
5071 (?P
<id>%(playlist_id)s)
5073 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5074 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5076 IE_NAME = 'youtube:playlist'
5078 'note': 'issue #673',
5079 'url': 'PLBB231211A4F62143',
5081 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5082 'id': 'PLBB231211A4F62143',
5083 'uploader': 'Wickman',
5084 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5085 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5087 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5088 'modified_date': r're:\d{8}',
5089 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5090 'channel': 'Wickman',
5092 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5094 'playlist_mincount': 29,
5096 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5098 'title': 'YDL_safe_search',
5099 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5101 'playlist_count': 2,
5102 'skip': 'This playlist is private',
5105 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5106 'playlist_count': 4,
5109 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5110 'uploader': 'milan',
5111 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5113 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5115 'modified_date': '20140919',
5118 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5119 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5121 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5123 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5124 'playlist_mincount': 654,
5126 'title': '2018 Chinese New Singles (11/6 updated)',
5127 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5129 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5130 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5133 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5135 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5136 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5137 'modified_date': r're:\d{8}',
5139 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5141 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5142 'only_matching': True,
5144 # music album playlist
5145 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5146 'only_matching': True,
5150 def suitable(cls, url):
5151 if YoutubeTabIE.suitable(url):
5153 from ..utils import parse_qs
5155 if qs.get('v', [None])[0]:
5157 return super(YoutubePlaylistIE, cls).suitable(url)
5159 def _real_extract(self, url):
5160 playlist_id = self._match_id(url)
5161 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5162 url = update_url_query(
5163 'https://www.youtube.com/playlist',
5164 parse_qs(url) or {'list': playlist_id})
5166 url = smuggle_url(url, {'is_music_url': True})
5167 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5170 class YoutubeYtBeIE(InfoExtractor):
5171 IE_DESC = 'youtu.be'
5172 _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}
5174 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5176 'id': 'yeWKywCrFtk',
5178 'title': 'Small Scale Baler and Braiding Rugs',
5179 'uploader': 'Backus-Page House Museum',
5180 'uploader_id': 'backuspagemuseum',
5181 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5182 'upload_date': '20161008',
5183 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5184 'categories': ['Nonprofits & Activism'],
5188 'playable_in_embed': True,
5189 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5190 'channel': 'Backus-Page House Museum',
5191 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5192 'live_status': 'not_live',
5194 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5195 'availability': 'public',
5200 'skip_download': True,
5203 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5204 'only_matching': True,
5207 def _real_extract(self, url):
5208 mobj = self._match_valid_url(url)
5209 video_id = mobj.group('id')
5210 playlist_id = mobj.group('playlist_id')
5211 return self.url_result(
5212 update_url_query('https://www.youtube.com/watch', {
5214 'list': playlist_id,
5215 'feature': 'youtu.be',
5216 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5219 class YoutubeLivestreamEmbedIE(InfoExtractor):
5220 IE_DESC = 'YouTube livestream embeds'
5221 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5223 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5224 'only_matching': True,
5227 def _real_extract(self, url):
5228 channel_id = self._match_id(url)
5229 return self.url_result(
5230 f'https://www.youtube.com/channel/{channel_id}/live',
5231 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5234 class YoutubeYtUserIE(InfoExtractor):
5235 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5236 IE_NAME = 'youtube:user'
5237 _VALID_URL = r'ytuser:(?P<id>.+)'
5239 'url': 'ytuser:phihag',
5240 'only_matching': True,
5243 def _real_extract(self, url):
5244 user_id = self._match_id(url)
5245 return self.url_result(
5246 'https://www.youtube.com/user/%s/videos' % user_id,
5247 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5250 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5251 IE_NAME = 'youtube:favorites'
5252 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5253 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5254 _LOGIN_REQUIRED = True
5257 'only_matching': True,
5259 'url': ':ytfavorites',
5260 'only_matching': True,
5263 def _real_extract(self, url):
5264 return self.url_result(
5265 'https://www.youtube.com/playlist?list=LL',
5266 ie=YoutubeTabIE.ie_key())
5269 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5270 IE_DESC = 'YouTube search'
5271 IE_NAME = 'youtube:search'
5272 _SEARCH_KEY = 'ytsearch'
5273 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5277 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5278 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5279 _SEARCH_KEY = 'ytsearchdate'
5280 IE_DESC = 'YouTube search, newest videos first'
5281 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5284 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5285 IE_DESC = 'YouTube search URLs with sorting and filter support'
5286 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5287 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
5289 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5290 'playlist_mincount': 5,
5292 'id': 'youtube-dl test video',
5293 'title': 'youtube-dl test video',
5296 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5297 'playlist_mincount': 5,
5304 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5305 'only_matching': True,
5308 def _real_extract(self, url):
5310 query = (qs.get('search_query') or qs.get('q'))[0]
5311 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5314 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
5316 Base class for feed extractors
5317 Subclasses must define the _FEED_NAME property.
5319 _LOGIN_REQUIRED = True
5324 return 'youtube:%s' % self._FEED_NAME
5326 def _real_extract(self, url):
5327 return self.url_result(
5328 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5329 ie=YoutubeTabIE.ie_key())
5332 class YoutubeWatchLaterIE(InfoExtractor):
5333 IE_NAME = 'youtube:watchlater'
5334 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5335 _VALID_URL = r':ytwatchlater'
5337 'url': ':ytwatchlater',
5338 'only_matching': True,
5341 def _real_extract(self, url):
5342 return self.url_result(
5343 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5346 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5347 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5348 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5349 _FEED_NAME = 'recommended'
5350 _LOGIN_REQUIRED = False
5353 'only_matching': True,
5355 'url': ':ytrecommended',
5356 'only_matching': True,
5358 'url': 'https://youtube.com',
5359 'only_matching': True,
5363 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5364 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5365 _VALID_URL = r':ytsub(?:scription)?s?'
5366 _FEED_NAME = 'subscriptions'
5369 'only_matching': True,
5371 'url': ':ytsubscriptions',
5372 'only_matching': True,
5376 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5377 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5378 _VALID_URL = r':ythis(?:tory)?'
5379 _FEED_NAME = 'history'
5381 'url': ':ythistory',
5382 'only_matching': True,
5386 class YoutubeTruncatedURLIE(InfoExtractor):
5387 IE_NAME = 'youtube:truncated_url'
5388 IE_DESC = False # Do not list
5389 _VALID_URL = r'''(?x
)
5391 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
5394 annotation_id
=annotation_
[^
&]+|
5400 attribution_link
\?a
=[^
&]+
5406 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5407 'only_matching': True,
5409 'url': 'https://www.youtube.com/watch?',
5410 'only_matching': True,
5412 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5413 'only_matching': True,
5415 'url': 'https://www.youtube.com/watch?feature=foo',
5416 'only_matching': True,
5418 'url': 'https://www.youtube.com/watch?hl=en-GB',
5419 'only_matching': True,
5421 'url': 'https://www.youtube.com/watch?t=2372',
5422 'only_matching': True,
5425 def _real_extract(self, url):
5426 raise ExtractorError(
5427 'Did you forget to quote the URL? Remember that & is a meta '
5428 'character in most shells, so you want to put the URL in quotes, '
5430 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5431 ' or simply youtube-dl BaW_jenozKc .',
5435 class YoutubeClipIE(InfoExtractor):
5436 IE_NAME = 'youtube:clip'
5437 IE_DESC = False # Do not list
5438 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5440 def _real_extract(self, url):
5441 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5442 return self.url_result(url, 'Generic')
5445 class YoutubeTruncatedIDIE(InfoExtractor):
5446 IE_NAME = 'youtube:truncated_id'
5447 IE_DESC = False # Do not list
5448 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5451 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5452 'only_matching': True,
5455 def _real_extract(self, url):
5456 video_id = self._match_id(url)
5457 raise ExtractorError(
5458 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),