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
75 def get_first(obj
, keys
, **kwargs
):
76 return traverse_obj(obj
, (..., *variadic(keys
)), **kwargs
, get_all
=False)
79 # any clients starting with _ cannot be explicity requested by the user
82 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
83 'INNERTUBE_CONTEXT': {
86 'clientVersion': '2.20211221.00.00',
89 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
92 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
93 'INNERTUBE_CONTEXT': {
95 'clientName': 'WEB_EMBEDDED_PLAYER',
96 'clientVersion': '1.20211215.00.01',
99 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
102 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
103 'INNERTUBE_HOST': 'music.youtube.com',
104 'INNERTUBE_CONTEXT': {
106 'clientName': 'WEB_REMIX',
107 'clientVersion': '1.20211213.00.00',
110 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
113 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
114 'INNERTUBE_CONTEXT': {
116 'clientName': 'WEB_CREATOR',
117 'clientVersion': '1.20211220.02.00',
120 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
123 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
124 'INNERTUBE_CONTEXT': {
126 'clientName': 'ANDROID',
127 'clientVersion': '16.49',
130 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
131 'REQUIRE_JS_PLAYER': False
133 'android_embedded': {
134 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
135 'INNERTUBE_CONTEXT': {
137 'clientName': 'ANDROID_EMBEDDED_PLAYER',
138 'clientVersion': '16.49',
141 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
142 'REQUIRE_JS_PLAYER': False
145 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
146 'INNERTUBE_CONTEXT': {
148 'clientName': 'ANDROID_MUSIC',
149 'clientVersion': '4.57',
152 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
153 'REQUIRE_JS_PLAYER': False
156 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
157 'INNERTUBE_CONTEXT': {
159 'clientName': 'ANDROID_CREATOR',
160 'clientVersion': '21.47',
163 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
164 'REQUIRE_JS_PLAYER': False
166 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
167 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
169 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
170 'INNERTUBE_CONTEXT': {
173 'clientVersion': '16.46',
174 'deviceModel': 'iPhone14,3',
177 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
178 'REQUIRE_JS_PLAYER': False
181 'INNERTUBE_CONTEXT': {
183 'clientName': 'IOS_MESSAGES_EXTENSION',
184 'clientVersion': '16.46',
185 'deviceModel': 'iPhone14,3',
188 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
189 'REQUIRE_JS_PLAYER': False
192 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
193 'INNERTUBE_CONTEXT': {
195 'clientName': 'IOS_MUSIC',
196 'clientVersion': '4.57',
199 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
200 'REQUIRE_JS_PLAYER': False
203 'INNERTUBE_CONTEXT': {
205 'clientName': 'IOS_CREATOR',
206 'clientVersion': '21.47',
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
216 'INNERTUBE_CONTEXT': {
218 'clientName': 'MWEB',
219 'clientVersion': '2.20211221.01.00',
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
227 def build_innertube_clients():
229 'embedUrl': 'https://google.com', # Can be any valid URL
231 BASE_CLIENTS
= ('android', 'web', 'ios', 'mweb')
232 priority
= qualities(BASE_CLIENTS
[::-1])
234 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
235 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
236 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
237 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
238 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
240 base_client
, *variant
= client
.split('_')
241 ytcfg
['priority'] = 10 * priority(base_client
)
244 INNERTUBE_CLIENTS
[f
'{client}_agegate'] = agegate_ytcfg
= copy
.deepcopy(ytcfg
)
245 agegate_ytcfg
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
246 agegate_ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
247 agegate_ytcfg
['priority'] -= 1
248 elif variant
== ['embedded']:
249 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
250 ytcfg
['priority'] -= 2
252 ytcfg
['priority'] -= 3
255 build_innertube_clients()
258 class YoutubeBaseInfoExtractor(InfoExtractor
):
259 """Provide base functions for Youtube extractors"""
262 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
263 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
264 r
'browse|oembed|get_video_info|iframe_api|s/player|'
265 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
267 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
269 _NETRC_MACHINE
= 'youtube'
271 # If True it will raise an error if no login info is provided
272 _LOGIN_REQUIRED
= False
275 # invidious-redirect websites
276 r
'(?:www\.)?redirect\.invidious\.io',
277 r
'(?:(?:www|dev)\.)?invidio\.us',
278 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
279 r
'(?:www\.)?invidious\.pussthecat\.org',
280 r
'(?:www\.)?invidious\.zee\.li',
281 r
'(?:www\.)?invidious\.ethibox\.fr',
282 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
283 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
284 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
285 # youtube-dl invidious instances list
286 r
'(?:(?:www|no)\.)?invidiou\.sh',
287 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
288 r
'(?:www\.)?invidious\.kabi\.tk',
289 r
'(?:www\.)?invidious\.mastodon\.host',
290 r
'(?:www\.)?invidious\.zapashcanon\.fr',
291 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
292 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
293 r
'(?:www\.)?invidious\.himiko\.cloud',
294 r
'(?:www\.)?invidious\.reallyancient\.tech',
295 r
'(?:www\.)?invidious\.tube',
296 r
'(?:www\.)?invidiou\.site',
297 r
'(?:www\.)?invidious\.site',
298 r
'(?:www\.)?invidious\.xyz',
299 r
'(?:www\.)?invidious\.nixnet\.xyz',
300 r
'(?:www\.)?invidious\.048596\.xyz',
301 r
'(?:www\.)?invidious\.drycat\.fr',
302 r
'(?:www\.)?inv\.skyn3t\.in',
303 r
'(?:www\.)?tube\.poal\.co',
304 r
'(?:www\.)?tube\.connect\.cafe',
305 r
'(?:www\.)?vid\.wxzm\.sx',
306 r
'(?:www\.)?vid\.mint\.lgbt',
307 r
'(?:www\.)?vid\.puffyan\.us',
308 r
'(?:www\.)?yewtu\.be',
309 r
'(?:www\.)?yt\.elukerio\.org',
310 r
'(?:www\.)?yt\.lelux\.fi',
311 r
'(?:www\.)?invidious\.ggc-project\.de',
312 r
'(?:www\.)?yt\.maisputain\.ovh',
313 r
'(?:www\.)?ytprivate\.com',
314 r
'(?:www\.)?invidious\.13ad\.de',
315 r
'(?:www\.)?invidious\.toot\.koeln',
316 r
'(?:www\.)?invidious\.fdn\.fr',
317 r
'(?:www\.)?watch\.nettohikari\.com',
318 r
'(?:www\.)?invidious\.namazso\.eu',
319 r
'(?:www\.)?invidious\.silkky\.cloud',
320 r
'(?:www\.)?invidious\.exonip\.de',
321 r
'(?:www\.)?invidious\.riverside\.rocks',
322 r
'(?:www\.)?invidious\.blamefran\.net',
323 r
'(?:www\.)?invidious\.moomoo\.de',
324 r
'(?:www\.)?ytb\.trom\.tf',
325 r
'(?:www\.)?yt\.cyberhost\.uk',
326 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
327 r
'(?:www\.)?qklhadlycap4cnod\.onion',
328 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
329 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
330 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
331 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
332 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
333 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
334 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
335 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
336 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
337 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
342 Attempt to log in to YouTube.
343 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
346 if (self
._LOGIN
_REQUIRED
347 and self
.get_param('cookiefile') is None
348 and self
.get_param('cookiesfrombrowser') is None):
349 self
.raise_login_required(
350 'Login details are needed to download this content', method
='cookies')
351 username
, password
= self
._get
_login
_info
()
353 self
.report_warning(f
'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
355 def _initialize_consent(self
):
356 cookies
= self
._get
_cookies
('https://www.youtube.com/')
357 if cookies
.get('__Secure-3PSID'):
360 consent
= cookies
.get('CONSENT')
362 if 'YES' in consent
.value
:
364 consent_id
= self
._search
_regex
(
365 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
367 consent_id
= random
.randint(100, 999)
368 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
370 def _initialize_pref(self
):
371 cookies
= self
._get
_cookies
('https://www.youtube.com/')
372 pref_cookie
= cookies
.get('PREF')
376 pref
= dict(compat_urlparse
.parse_qsl(pref_cookie
.value
))
378 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
379 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
380 self
._set
_cookie
('.youtube.com', name
='PREF', value
=compat_urllib_parse_urlencode(pref
))
382 def _real_initialize(self
):
383 self
._initialize
_pref
()
384 self
._initialize
_consent
()
387 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
388 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
389 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
391 def _get_default_ytcfg(self, client='web'):
392 return copy.deepcopy(INNERTUBE_CLIENTS[client])
394 def _get_innertube_host(self, client='web'):
395 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
397 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
398 # try_get but with fallback to default ytcfg client values when present
399 _func = lambda y: try_get(y, getter, expected_type)
400 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
402 def _extract_client_name(self, ytcfg, default_client='web'):
403 return self._ytcfg_get_safe(
404 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
405 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
407 def _extract_client_version(self, ytcfg, default_client='web'):
408 return self._ytcfg_get_safe(
409 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
410 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
412 def _extract_api_key(self, ytcfg=None, default_client='web'):
413 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
415 def _extract_context(self, ytcfg=None, default_client='web'):
417 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
418 # Enforce language and tz for extraction
419 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
420 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
425 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
426 time_now = round(time.time())
427 if self._SAPISID is None:
428 yt_cookies = self._get_cookies('https://www.youtube.com')
429 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
430 # See: https://github.com/yt-dlp/yt-dlp/issues/393
431 sapisid_cookie = dict_get(
432 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
433 if sapisid_cookie and sapisid_cookie.value:
434 self._SAPISID = sapisid_cookie.value
435 self.write_debug('Extracted SAPISID cookie')
436 # SAPISID cookie is required if not already present
437 if not yt_cookies.get('SAPISID'):
438 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
440 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
442 self._SAPISID = False
443 if not self._SAPISID:
445 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
446 sapisidhash = hashlib.sha1(
447 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
448 return f'SAPISIDHASH {time_now}_{sapisidhash}'
450 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
451 note='Downloading API JSON', errnote='Unable to download API page',
452 context=None, api_key=None, api_hostname=None, default_client='web'):
454 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
456 real_headers = self.generate_api_headers(default_client=default_client)
457 real_headers.update({'content-type': 'application/json'})
459 real_headers.update(headers)
460 return self._download_json(
461 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
462 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
463 data=json.dumps(data).encode('utf8'), headers=real_headers,
464 query={'key': api_key or self._extract_api_key()})
466 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
467 data = self._search_regex(
468 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
469 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
471 return self._parse_json(data, item_id, fatal=fatal)
474 def _extract_session_index(*data):
476 Index of current account in account list.
477 See: https://github.com/yt-dlp/yt-dlp/pull/519
480 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
481 if session_index is not None:
485 def _extract_identity_token(self, ytcfg=None, webpage=None):
487 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
491 return self._search_regex(
492 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
493 'identity token
', default=None, fatal=False)
496 def _extract_account_syncid(*args):
498 Extract syncId required to download private playlists of secondary channels
499 @params response and/or ytcfg
502 # ytcfg includes channel_syncid if on secondary channel
503 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
507 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
508 lambda x: x['DATASYNC_ID
']), compat_str) or '').split('||
')
509 if len(sync_ids) >= 2 and sync_ids[1]:
510 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
511 # and just "user_syncid||" for primary channel. We only want the channel_syncid
515 def _extract_visitor_data(*args):
517 Extracts visitorData from an API response or ytcfg
518 Appears to be used to track session state
521 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
525 def is_authenticated(self):
526 return bool(self._generate_sapisidhash_header())
528 def extract_ytcfg(self, video_id, webpage):
531 return self._parse_json(
533 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
534 default='{}'), video_id, fatal=False) or {}
536 def generate_api_headers(
537 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
538 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
540 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(default_client
))
542 'X-YouTube-Client-Name': compat_str(
543 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
544 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
546 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
547 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
548 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
550 if session_index
is None:
551 session_index
= self
._extract
_session
_index
(ytcfg
)
552 if account_syncid
or session_index
is not None:
553 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
555 auth
= self
._generate
_sapisidhash
_header
(origin
)
557 headers
['Authorization'] = auth
558 headers
['X-Origin'] = origin
559 return {h: v for h, v in headers.items() if v is not None}
562 def _build_api_continuation_query(continuation
, ctp
=None):
564 'continuation': continuation
566 # TODO: Inconsistency with clickTrackingParams.
567 # Currently we have a fixed ctp contained within context (from ytcfg)
568 # and a ctp in root query for continuation.
570 query
['clickTracking'] = {'clickTrackingParams': ctp}
574 def _extract_next_continuation_data(cls
, renderer
):
575 next_continuation
= try_get(
576 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
577 lambda x
: x
['continuation']['reloadContinuationData']), dict)
578 if not next_continuation
:
580 continuation
= next_continuation
.get('continuation')
583 ctp
= next_continuation
.get('clickTrackingParams')
584 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
587 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
588 if isinstance(continuation_ep
, dict):
589 continuation
= try_get(
590 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
593 ctp
= continuation_ep
.get('clickTrackingParams')
594 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
597 def _extract_continuation(cls
, renderer
):
598 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
599 if next_continuation
:
600 return next_continuation
603 for key
in ('contents', 'items'):
604 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
606 for content
in contents
:
607 if not isinstance(content
, dict):
609 continuation_ep
= try_get(
610 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
611 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
613 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
618 def _extract_alerts(cls
, data
):
619 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
620 if not isinstance(alert_dict
, dict):
622 for alert
in alert_dict
.values():
623 alert_type
= alert
.get('type')
626 message
= cls
._get
_text
(alert
, 'text')
628 yield alert_type
, message
630 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
633 for alert_type
, alert_message
in alerts
:
634 if alert_type
.lower() == 'error' and fatal
:
635 errors
.append([alert_type
, alert_message
])
637 warnings
.append([alert_type
, alert_message
])
639 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
640 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
), only_once
=only_once
)
642 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
644 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
645 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
647 def _extract_badges(self
, renderer
: dict):
649 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
650 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
652 badges
.add(label
.lower())
656 def _get_text(data
, *path_list
, max_runs
=None):
657 for path
in path_list
or [None]:
661 obj
= traverse_obj(data
, path
, default
=[])
662 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
665 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
668 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
669 if not runs
and isinstance(item
, list):
672 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
673 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
677 def _get_count(self
, data
, *path_list
):
678 count_text
= self
._get
_text
(data
, *path_list
) or ''
679 count
= parse_count(count_text
)
682 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
686 def _extract_thumbnails(data
, *path_list
):
688 Extract thumbnails from thumbnails dict
689 @param path_list: path list to level that contains 'thumbnails' key
692 for path
in path_list
or [()]:
693 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
694 thumbnail_url
= url_or_none(thumbnail
.get('url'))
695 if not thumbnail_url
:
697 # Sometimes youtube gives a wrong thumbnail URL. See:
698 # https://github.com/yt-dlp/yt-dlp/issues/233
699 # https://github.com/ytdl-org/youtube-dl/issues/28023
700 if 'maxresdefault' in thumbnail_url
:
701 thumbnail_url
= thumbnail_url
.split('?')[0]
703 'url': thumbnail_url
,
704 'height': int_or_none(thumbnail
.get('height')),
705 'width': int_or_none(thumbnail
.get('width')),
710 def extract_relative_time(relative_time_text
):
712 Extracts a relative time from string and converts to dt object
713 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
715 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
)
717 start
= mobj
.group('start')
719 return datetime_from_str(start
)
721 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
725 def _extract_time_text(self
, renderer
, *path_list
):
726 text
= self
._get
_text
(renderer
, *path_list
) or ''
727 dt
= self
.extract_relative_time(text
)
729 if isinstance(dt
, datetime
.datetime
):
730 timestamp
= calendar
.timegm(dt
.timetuple())
732 if timestamp
is None:
734 unified_timestamp(text
) or unified_timestamp(
736 (r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r
'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
737 text
.lower(), 'time text', default
=None)))
739 if text
and timestamp
is None:
740 self
.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once
=True)
741 return timestamp
, text
743 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
744 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
745 default_client
='web'):
749 retries
= self
.get_param('extractor_retries', 3)
750 if check_get_keys
is None:
752 while count
< retries
:
755 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
757 response
= self
._call
_api
(
758 ep
=ep
, fatal
=True, headers
=headers
,
759 video_id
=item_id
, query
=query
,
760 context
=self
._extract
_context
(ytcfg
, default_client
),
761 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
762 api_hostname
=api_hostname
, default_client
=default_client
,
763 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
764 except ExtractorError
as e
:
765 if isinstance(e
.cause
, network_exceptions
):
766 if isinstance(e
.cause
, compat_HTTPError
):
767 first_bytes
= e
.cause
.read(512)
768 if not is_html(first_bytes
):
771 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
772 lambda x
: x
['error']['message'], compat_str
)
774 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
775 # Downloading page may result in intermittent 5xx HTTP error
776 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
777 # We also want to catch all other network exceptions since errors in later pages can be troublesome
778 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
779 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
780 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
786 self
.report_warning(error_to_compat_str(e
))
791 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
792 except ExtractorError
as e
:
793 # YouTube servers may return errors we want to retry on in a 200 OK response
794 # See: https://github.com/yt-dlp/yt-dlp/issues/839
795 if 'unknown error' in e
.msg
.lower():
800 self
.report_warning(error_to_compat_str(e
))
802 if not check_get_keys
or dict_get(response
, check_get_keys
):
804 # Youtube sometimes sends incomplete data
805 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
806 last_error
= 'Incomplete data received'
809 raise ExtractorError(last_error
)
811 self
.report_warning(last_error
)
816 def is_music_url(url
):
817 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
819 def _extract_video(self
, renderer
):
820 video_id
= renderer
.get('videoId')
821 title
= self
._get
_text
(renderer
, 'title')
822 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
823 duration
= parse_duration(self
._get
_text
(
824 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
825 view_count
= self
._get
_count
(renderer
, 'viewCountText')
827 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
828 channel_id
= traverse_obj(
829 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type
=str, get_all
=False)
830 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
831 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
832 overlay_style
= traverse_obj(
833 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all
=False, expected_type
=str)
834 badges
= self
._extract
_badges
(renderer
)
835 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
839 'ie_key': YoutubeIE
.ie_key(),
841 'url': f
'https://www.youtube.com/watch?v={video_id}',
843 'description': description
,
844 'duration': duration
,
845 'view_count': view_count
,
846 'uploader': uploader
,
847 'channel_id': channel_id
,
848 'thumbnails': thumbnails
,
849 'upload_date': strftime_or_none(timestamp
, '%Y%m%d') if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab') else None,
850 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
851 else 'was_live' if 'streamed' in time_text
.lower()
852 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
854 'release_timestamp': scheduled_timestamp
,
855 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
859 class YoutubeIE(YoutubeBaseInfoExtractor
):
861 _VALID_URL
= r
"""(?x)^
863 (?:https?://|//) # http(s):// or protocol-independent URL
864 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
865 (?:www\.)?deturl\.com/www\.youtube\.com|
866 (?:www\.)?pwnyoutube\.com|
867 (?:www\.)?hooktube\.com|
868 (?:www\.)?yourepeat\.com|
871 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
872 (?:.*?\#/)? # handle anchor (#/) redirect urls
873 (?: # the various things that can precede the ID:
874 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
875 |(?: # or the v= param in all its forms
876 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
877 (?:\?|\#!?) # the params delimiter ? or # or #!
878 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
883 youtu\.be| # just youtu.be/xxxx
884 vid\.plus| # or vid.plus/xxxx
885 zwearz\.com/watch| # or zwearz.com/watch/xxxx
888 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
890 )? # all until now is optional -> you can pass the naked ID
891 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
892 (?(1).+)? # if we found the ID, everything can follow
894 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
897 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
898 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$',
899 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
902 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
903 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
904 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
905 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
906 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
907 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
908 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
909 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
910 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
911 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
912 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
913 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
914 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
915 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
916 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
917 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
918 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
919 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
923 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
924 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
925 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
926 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
927 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
928 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
929 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
931 # Apple HTTP Live Streaming
932 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
933 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
934 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
935 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
936 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
937 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
938 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
939 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
942 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
943 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
944 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
945 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
946 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
947 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
948 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
949 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
950 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
951 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
952 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
953 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
956 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
957 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
958 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
959 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
960 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
961 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
962 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
965 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
966 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
967 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
968 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
969 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
970 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
971 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
972 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
973 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
974 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
975 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
976 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
977 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
978 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
979 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
980 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
981 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
982 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
983 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
984 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
985 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
986 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
989 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
990 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
992 # Dash webm audio with opus inside
993 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
994 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
995 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
998 '_rtmp': {'protocol': 'rtmp'}
,
1000 # av01 video only formats sometimes served with "unknown" codecs
1001 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1002 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1003 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}
,
1004 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}
,
1005 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}
,
1006 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}
,
1007 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1008 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1010 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1017 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1019 'id': 'BaW_jenozKc',
1021 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1022 'uploader': 'Philipp Hagemeister',
1023 'uploader_id': 'phihag',
1024 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1025 'channel': 'Philipp Hagemeister',
1026 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1027 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1028 'upload_date': '20121002',
1029 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1030 'categories': ['Science & Technology'],
1031 'tags': ['youtube-dl'],
1035 'availability': 'public',
1036 'playable_in_embed': True,
1037 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1038 'live_status': 'not_live',
1042 'channel_follower_count': int
1046 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1047 'note': 'Embed-only video (#1746)',
1049 'id': 'yZIXLfi8CZQ',
1051 'upload_date': '20120608',
1052 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1053 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1054 'uploader': 'SET India',
1055 'uploader_id': 'setindia',
1056 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1059 'skip': 'Private video',
1062 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1063 'note': 'Use the first video ID in the URL',
1065 'id': 'BaW_jenozKc',
1067 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1068 'uploader': 'Philipp Hagemeister',
1069 'uploader_id': 'phihag',
1070 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1071 'channel': 'Philipp Hagemeister',
1072 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1073 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1074 'upload_date': '20121002',
1075 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1076 'categories': ['Science & Technology'],
1077 'tags': ['youtube-dl'],
1081 'availability': 'public',
1082 'playable_in_embed': True,
1083 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1084 'live_status': 'not_live',
1086 'channel_follower_count': int
1089 'skip_download': True,
1093 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1094 'note': '256k DASH audio (format 141) via DASH manifest',
1096 'id': 'a9LDPn-MO4I',
1098 'upload_date': '20121002',
1099 'uploader_id': '8KVIDEO',
1100 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1102 'uploader': '8KVIDEO',
1103 'title': 'UHDTV TEST 8K VIDEO.mp4'
1106 'youtube_include_dash_manifest': True,
1109 'skip': 'format 141 not served anymore',
1111 # DASH manifest with encrypted signature
1113 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1115 'id': 'IB3lcPjvWLA',
1117 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1118 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1120 'uploader': 'AfrojackVEVO',
1121 'uploader_id': 'AfrojackVEVO',
1122 'upload_date': '20131011',
1125 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1126 'playable_in_embed': True,
1127 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1129 'track': 'The Spark',
1130 'live_status': 'not_live',
1131 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1132 'channel': 'Afrojack',
1133 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1135 'availability': 'public',
1136 'categories': ['Music'],
1138 'alt_title': 'The Spark',
1139 'channel_follower_count': int
1142 'youtube_include_dash_manifest': True,
1143 'format': '141/bestaudio[ext=m4a]',
1146 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1148 'note': 'Embed allowed age-gate video',
1149 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1151 'id': 'HtVdAasjOgU',
1153 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1154 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1156 'uploader': 'The Witcher',
1157 'uploader_id': 'WitcherGame',
1158 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1159 'upload_date': '20140605',
1161 'categories': ['Gaming'],
1162 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1163 'availability': 'needs_auth',
1164 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1166 'channel': 'The Witcher',
1167 'live_status': 'not_live',
1169 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1170 'playable_in_embed': True,
1172 'channel_follower_count': int
1176 'note': 'Age-gate video with embed allowed in public site',
1177 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1179 'id': 'HsUATh_Nc2U',
1181 'title': 'Godzilla 2 (Official Video)',
1182 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1183 'upload_date': '20200408',
1184 'uploader_id': 'FlyingKitty900',
1185 'uploader': 'FlyingKitty',
1187 'availability': 'needs_auth',
1188 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1189 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1190 'channel': 'FlyingKitty',
1191 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1193 'categories': ['Entertainment'],
1194 'live_status': 'not_live',
1195 'tags': ['Flyingkitty', 'godzilla 2'],
1196 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1199 'playable_in_embed': True,
1200 'channel_follower_count': int
1204 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1205 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1207 'id': 'Tq92D6wQ1mg',
1208 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1210 'upload_date': '20191227',
1211 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1212 'uploader': 'Projekt Melody',
1213 'description': 'md5:17eccca93a786d51bc67646756894066',
1216 'availability': 'needs_auth',
1217 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1218 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1220 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1221 'channel': 'Projekt Melody',
1222 'live_status': 'not_live',
1223 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1224 'playable_in_embed': True,
1225 'categories': ['Entertainment'],
1227 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1228 'channel_follower_count': int
1232 'note': 'Non-Agegated non-embeddable video',
1233 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1235 'id': 'MeJVWBSsPAY',
1237 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1238 'uploader': 'Herr Lurik',
1239 'uploader_id': 'st3in234',
1240 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1241 'upload_date': '20130730',
1242 'track': 'Such mich find mich',
1244 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1246 'playable_in_embed': False,
1247 'creator': 'OOMPH!',
1248 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1250 'alt_title': 'Such mich find mich',
1252 'channel': 'Herr Lurik',
1253 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1254 'categories': ['Music'],
1255 'availability': 'public',
1256 'uploader_url': 'http://www.youtube.com/user/st3in234',
1257 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1258 'live_status': 'not_live',
1260 'channel_follower_count': int
1264 'note': 'Non-bypassable age-gated video',
1265 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1266 'only_matching': True,
1268 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1269 # YouTube Red ad is not captured for creator
1271 'url': '__2ABJjxzNo',
1273 'id': '__2ABJjxzNo',
1276 'upload_date': '20100430',
1277 'uploader_id': 'deadmau5',
1278 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1279 'creator': 'deadmau5',
1280 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1281 'uploader': 'deadmau5',
1282 'title': 'Deadmau5 - Some Chords (HD)',
1283 'alt_title': 'Some Chords',
1284 'availability': 'public',
1286 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1288 'live_status': 'not_live',
1289 'channel': 'deadmau5',
1290 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1292 'track': 'Some Chords',
1293 'artist': 'deadmau5',
1294 'playable_in_embed': True,
1296 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1297 'categories': ['Music'],
1298 'album': 'Some Chords',
1299 'channel_follower_count': int
1301 'expected_warnings': [
1302 'DASH manifest missing',
1305 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1307 'url': 'lqQg6PlCWgI',
1309 'id': 'lqQg6PlCWgI',
1312 'upload_date': '20150827',
1313 'uploader_id': 'olympic',
1314 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1315 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1316 'uploader': 'Olympics',
1317 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1319 'release_timestamp': 1343767800,
1320 'playable_in_embed': True,
1321 'categories': ['Sports'],
1322 'release_date': '20120731',
1323 'channel': 'Olympics',
1324 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1325 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1326 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1328 'availability': 'public',
1329 'live_status': 'was_live',
1331 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1332 'channel_follower_count': int
1335 'skip_download': 'requires avconv',
1340 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1342 'id': '_b-2C3KPAM0',
1344 'stretched_ratio': 16 / 9.,
1346 'upload_date': '20110310',
1347 'uploader_id': 'AllenMeow',
1348 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1349 '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',
1351 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1352 'playable_in_embed': True,
1356 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1357 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1358 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1360 'categories': ['People & Blogs'],
1362 'live_status': 'not_live',
1363 'availability': 'unlisted',
1364 'channel_follower_count': int
1367 # url_encoded_fmt_stream_map is empty string
1369 'url': 'qEJwOuvDf7I',
1371 'id': 'qEJwOuvDf7I',
1373 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1375 'upload_date': '20150404',
1376 'uploader_id': 'spbelect',
1377 'uploader': 'Наблюдатели Петербурга',
1380 'skip_download': 'requires avconv',
1382 'skip': 'This live event has ended.',
1384 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1386 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1388 'id': 'FIl7x6_3R5Y',
1390 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1391 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1393 'upload_date': '20150625',
1394 'uploader_id': 'dorappi2000',
1395 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1396 'uploader': 'dorappi2000',
1397 'formats': 'mincount:31',
1399 'skip': 'not actual anymore',
1401 # DASH manifest with segment_list
1403 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1404 'md5': '8ce563a1d667b599d21064e982ab9e31',
1406 'id': 'CsmdDsKjzN8',
1408 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1409 'uploader': 'Airtek',
1410 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1411 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1412 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1415 'youtube_include_dash_manifest': True,
1416 'format': '135', # bestvideo
1418 'skip': 'This live event has ended.',
1421 # Multifeed videos (multiple cameras), URL is for Main Camera
1422 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1424 'id': 'jvGDaLqkpTg',
1425 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1426 'description': 'md5:e03b909557865076822aa169218d6a5d',
1430 'id': 'jvGDaLqkpTg',
1432 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1433 'description': 'md5:e03b909557865076822aa169218d6a5d',
1435 'upload_date': '20161111',
1436 'uploader': 'Team PGP',
1437 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1438 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1442 'id': '3AKt1R1aDnw',
1444 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1445 'description': 'md5:e03b909557865076822aa169218d6a5d',
1447 'upload_date': '20161111',
1448 'uploader': 'Team PGP',
1449 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1450 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1454 'id': 'RtAMM00gpVc',
1456 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1457 'description': 'md5:e03b909557865076822aa169218d6a5d',
1459 'upload_date': '20161111',
1460 'uploader': 'Team PGP',
1461 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1462 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1466 'id': '6N2fdlP3C5U',
1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
1471 'upload_date': '20161111',
1472 'uploader': 'Team PGP',
1473 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1474 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1478 'skip_download': True,
1480 'skip': 'Not multifeed anymore',
1483 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1484 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1486 'id': 'gVfLd0zydlo',
1487 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1489 'playlist_count': 2,
1490 'skip': 'Not multifeed anymore',
1493 'url': 'https://vid.plus/FlRa-iH7PGw',
1494 'only_matching': True,
1497 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1498 'only_matching': True,
1501 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1502 # Also tests cut-off URL expansion in video description (see
1503 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1504 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1505 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1507 'id': 'lsguqyKfVQg',
1509 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1510 'alt_title': 'Dark Walk',
1511 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1513 'upload_date': '20151119',
1514 'uploader_id': 'IronSoulElf',
1515 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1516 'uploader': 'IronSoulElf',
1517 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1518 'track': 'Dark Walk',
1519 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1520 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1521 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1522 'categories': ['Film & Animation'],
1524 'live_status': 'not_live',
1525 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1526 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1528 'availability': 'public',
1529 'channel': 'IronSoulElf',
1530 'playable_in_embed': True,
1533 'channel_follower_count': int
1536 'skip_download': True,
1540 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1541 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1542 'only_matching': True,
1545 # Video with yt:stretch=17:0
1546 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1548 'id': 'Q39EVAstoRM',
1550 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1551 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1552 'upload_date': '20151107',
1553 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1554 'uploader': 'CH GAMER DROID',
1557 'skip_download': True,
1559 'skip': 'This video does not exist.',
1562 # Video with incomplete 'yt:stretch=16:'
1563 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1564 'only_matching': True,
1567 # Video licensed under Creative Commons
1568 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1570 'id': 'M4gD1WSo5mA',
1572 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1573 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1575 'upload_date': '20150127',
1576 'uploader_id': 'BerkmanCenter',
1577 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1578 'uploader': 'The Berkman Klein Center for Internet & Society',
1579 'license': 'Creative Commons Attribution license (reuse allowed)',
1580 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1581 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1584 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1585 'channel': 'The Berkman Klein Center for Internet & Society',
1586 'availability': 'public',
1588 'categories': ['Education'],
1589 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1590 'live_status': 'not_live',
1591 'playable_in_embed': True,
1592 'channel_follower_count': int
1595 'skip_download': True,
1599 # Channel-like uploader_url
1600 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1602 'id': 'eQcmzGIKrzg',
1604 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1605 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1607 'upload_date': '20151119',
1608 'uploader': 'Bernie Sanders',
1609 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1610 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1611 'license': 'Creative Commons Attribution license (reuse allowed)',
1612 'playable_in_embed': True,
1615 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1617 'availability': 'public',
1618 'categories': ['News & Politics'],
1619 'channel': 'Bernie Sanders',
1620 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1622 'live_status': 'not_live',
1623 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1624 'channel_follower_count': int
1627 'skip_download': True,
1631 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1632 'only_matching': True,
1635 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1636 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1637 'only_matching': True,
1640 # Rental video preview
1641 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1643 'id': 'uGpuVWrhIzE',
1645 'title': 'Piku - Trailer',
1646 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1647 'upload_date': '20150811',
1648 'uploader': 'FlixMatrix',
1649 'uploader_id': 'FlixMatrixKaravan',
1650 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1651 'license': 'Standard YouTube License',
1654 'skip_download': True,
1656 'skip': 'This video is not available.',
1659 # YouTube Red video with episode data
1660 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1662 'id': 'iqKdEhx-dD4',
1664 'title': 'Isolation - Mind Field (Ep 1)',
1665 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1667 'upload_date': '20170118',
1668 'uploader': 'Vsauce',
1669 'uploader_id': 'Vsauce',
1670 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1671 'series': 'Mind Field',
1673 'episode_number': 1,
1674 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1677 'availability': 'public',
1679 'channel': 'Vsauce',
1680 'episode': 'Episode 1',
1681 'categories': ['Entertainment'],
1682 'season': 'Season 1',
1683 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1684 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1686 'playable_in_embed': True,
1687 'live_status': 'not_live',
1688 'channel_follower_count': int
1691 'skip_download': True,
1693 'expected_warnings': [
1694 'Skipping DASH manifest',
1698 # The following content has been identified by the YouTube community
1699 # as inappropriate or offensive to some audiences.
1700 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1702 'id': '6SJNVb0GnPI',
1704 'title': 'Race Differences in Intelligence',
1705 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1707 'upload_date': '20140124',
1708 'uploader': 'New Century Foundation',
1709 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1710 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1713 'skip_download': True,
1715 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1719 'url': '1t24XAntNCY',
1720 'only_matching': True,
1723 # geo restricted to JP
1724 'url': 'sJL6WA-aGkQ',
1725 'only_matching': True,
1728 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1729 'only_matching': True,
1732 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1733 'only_matching': True,
1736 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1737 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1738 'only_matching': True,
1742 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1743 'only_matching': True,
1746 # Video with unsupported adaptive stream type formats
1747 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1749 'id': 'Z4Vy8R84T1U',
1751 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1752 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1754 'upload_date': '20130923',
1755 'uploader': 'Amelia Putri Harwita',
1756 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1757 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1758 'formats': 'maxcount:10',
1761 'skip_download': True,
1762 'youtube_include_dash_manifest': False,
1764 'skip': 'not actual anymore',
1767 # Youtube Music Auto-generated description
1768 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1770 'id': 'MgNrAu2pzNs',
1772 'title': 'Voyeur Girl',
1773 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1774 'upload_date': '20190312',
1775 'uploader': 'Stephen - Topic',
1776 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1777 'artist': 'Stephen',
1778 'track': 'Voyeur Girl',
1779 'album': 'it\'s too much love to know my dear',
1780 'release_date': '20190313',
1781 'release_year': 2019,
1782 'alt_title': 'Voyeur Girl',
1784 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1785 'playable_in_embed': True,
1787 'categories': ['Music'],
1788 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1789 'channel': 'Stephen',
1790 'availability': 'public',
1791 'creator': 'Stephen',
1793 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1795 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1797 'live_status': 'not_live',
1798 'channel_follower_count': int
1801 'skip_download': True,
1805 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1806 'only_matching': True,
1809 # invalid -> valid video id redirection
1810 'url': 'DJztXj2GPfl',
1812 'id': 'DJztXj2GPfk',
1814 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1815 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1816 'upload_date': '20090125',
1817 'uploader': 'Prochorowka',
1818 'uploader_id': 'Prochorowka',
1819 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1820 'artist': 'Panjabi MC',
1821 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1822 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1825 'skip_download': True,
1827 'skip': 'Video unavailable',
1830 # empty description results in an empty string
1831 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1833 'id': 'x41yOUIvK2k',
1835 'title': 'IMG 3456',
1837 'upload_date': '20170613',
1838 'uploader_id': 'ElevageOrVert',
1839 'uploader': 'ElevageOrVert',
1841 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1842 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1844 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1846 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1847 'availability': 'public',
1849 'categories': ['Pets & Animals'],
1851 'playable_in_embed': True,
1852 'live_status': 'not_live',
1853 'channel': 'ElevageOrVert',
1854 'channel_follower_count': int
1857 'skip_download': True,
1861 # with '};' inside yt initial data (see [1])
1862 # see [2] for an example with '};' inside ytInitialPlayerResponse
1863 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1864 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1865 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1867 'id': 'CHqg6qOn4no',
1869 'title': 'Part 77 Sort a list of simple types in c#',
1870 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1871 'upload_date': '20130831',
1872 'uploader_id': 'kudvenkat',
1873 'uploader': 'kudvenkat',
1874 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1876 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1877 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1878 'live_status': 'not_live',
1879 'categories': ['Education'],
1880 'availability': 'public',
1881 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1883 'playable_in_embed': True,
1887 'channel': 'kudvenkat',
1888 'channel_follower_count': int
1891 'skip_download': True,
1895 # another example of '};' in ytInitialData
1896 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1897 'only_matching': True,
1900 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1901 'only_matching': True,
1904 # https://github.com/ytdl-org/youtube-dl/pull/28094
1905 'url': 'OtqTfy26tG0',
1907 'id': 'OtqTfy26tG0',
1909 'title': 'Burn Out',
1910 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1911 'upload_date': '20141120',
1912 'uploader': 'The Cinematic Orchestra - Topic',
1913 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1914 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1915 'artist': 'The Cinematic Orchestra',
1916 'track': 'Burn Out',
1917 'album': 'Every Day',
1919 'live_status': 'not_live',
1920 'alt_title': 'Burn Out',
1924 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1925 'creator': 'The Cinematic Orchestra',
1926 'channel': 'The Cinematic Orchestra',
1927 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1928 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1929 'availability': 'public',
1930 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1931 'categories': ['Music'],
1932 'playable_in_embed': True,
1933 'channel_follower_count': int
1936 'skip_download': True,
1940 # controversial video, only works with bpctr when authenticated with cookies
1941 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1942 'only_matching': True,
1945 # controversial video, requires bpctr/contentCheckOk
1946 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1948 'id': 'SZJvDhaSDnc',
1950 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1951 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1952 'uploader': 'CBS Mornings',
1953 'uploader_id': 'CBSThisMorning',
1954 'upload_date': '20140716',
1955 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1957 'categories': ['News & Politics'],
1958 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1960 'channel': 'CBS Mornings',
1961 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1962 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1964 'availability': 'needs_auth',
1965 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1967 'live_status': 'not_live',
1968 'playable_in_embed': True,
1969 'channel_follower_count': int
1973 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1974 'url': 'cBvYw8_A0vQ',
1976 'id': 'cBvYw8_A0vQ',
1978 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1979 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1980 'upload_date': '20201120',
1981 'uploader': 'Walk around Japan',
1982 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1983 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1985 'categories': ['Travel & Events'],
1986 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1988 'channel': 'Walk around Japan',
1989 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1990 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1992 'availability': 'public',
1993 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1994 'live_status': 'not_live',
1995 'playable_in_embed': True,
1996 'channel_follower_count': int
1999 'skip_download': True,
2002 # Has multiple audio streams
2003 'url': 'WaOKSUlf4TM',
2004 'only_matching': True
2006 # Requires Premium: has format 141 when requested using YTM url
2007 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2008 'only_matching': True
2010 # multiple subtitles with same lang_code
2011 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2012 'only_matching': True,
2014 # Force use android client fallback
2015 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2017 'id': 'YOelRv7fMxY',
2018 'title': 'DIGGING A SECRET TUNNEL Part 1',
2020 'upload_date': '20210624',
2021 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2022 'uploader': 'colinfurze',
2023 'uploader_id': 'colinfurze',
2024 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2025 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2027 'categories': ['Entertainment'],
2028 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2030 'channel': 'colinfurze',
2031 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2032 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2034 'availability': 'public',
2036 'live_status': 'not_live',
2037 'playable_in_embed': True,
2038 'channel_follower_count': int
2041 'format': '17', # 3gp format available on android
2042 'extractor_args': {'youtube': {'player_client': ['android']}
},
2046 # Skip download of additional client configs (remix client config in this case)
2047 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2048 'only_matching': True,
2050 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
2054 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2055 'only_matching': True,
2057 'note': 'Storyboards',
2058 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2060 'id': '5KLPxDtMqe8',
2063 'title': 'Your Brain is Plastic',
2064 'uploader_id': 'scishow',
2065 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2066 'upload_date': '20140324',
2067 'uploader': 'SciShow',
2069 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2070 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2072 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2073 'playable_in_embed': True,
2075 'uploader_url': 'http://www.youtube.com/user/scishow',
2076 'availability': 'public',
2077 'channel': 'SciShow',
2078 'live_status': 'not_live',
2080 'categories': ['Education'],
2082 'channel_follower_count': int
2083 }, 'params': {'format': 'mhtml', 'skip_download': True}
2088 def suitable(cls
, url
):
2089 from ..utils
import parse_qs
2092 if qs
.get('list', [None])[0]:
2094 return super(YoutubeIE
, cls
).suitable(url
)
2096 def __init__(self
, *args
, **kwargs
):
2097 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
2098 self
._code
_cache
= {}
2099 self
._player
_cache
= {}
2101 def _prepare_live_from_start_formats(self
, formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
):
2102 lock
= threading
.Lock()
2105 start_time
= time
.time()
2106 formats
= [f
for f
in formats
if f
.get('is_from_start')]
2108 def refetch_manifest(format_id
, delay
):
2109 nonlocal formats
, start_time
, is_live
2110 if time
.time() <= start_time
+ delay
:
2113 _
, _
, prs
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
2114 video_details
= traverse_obj(
2115 prs
, (..., 'videoDetails'), expected_type
=dict, default
=[])
2116 microformats
= traverse_obj(
2117 prs
, (..., 'microformat', 'playerMicroformatRenderer'),
2118 expected_type
=dict, default
=[])
2119 _
, is_live
, _
, formats
= self
._list
_formats
(video_id
, microformats
, video_details
, prs
, player_url
)
2120 start_time
= time
.time()
2122 def mpd_feed(format_id
, delay
):
2124 @returns (manifest_url, manifest_stream_number, is_live) or None
2127 refetch_manifest(format_id
, delay
)
2129 f
= next((f
for f
in formats
if f
['format_id'] == format_id
), None)
2132 self
.to_screen(f
'{video_id}: Video is no longer live')
2134 self
.report_warning(
2135 f
'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2137 return f
['manifest_url'], f
['manifest_stream_number'], is_live
2141 f
['protocol'] = 'http_dash_segments_generator'
2142 f
['fragments'] = functools
.partial(
2143 self
._live
_dash
_fragments
, f
['format_id'], live_start_time
, mpd_feed
)
2145 def _live_dash_fragments(self
, format_id
, live_start_time
, mpd_feed
, ctx
):
2146 FETCH_SPAN
, MAX_DURATION
= 5, 432000
2148 mpd_url
, stream_number
, is_live
= None, None, True
2151 download_start_time
= ctx
.get('start') or time
.time()
2153 lack_early_segments
= download_start_time
- (live_start_time
or download_start_time
) > MAX_DURATION
2154 if lack_early_segments
:
2155 self
.report_warning(bug_reports_message(
2156 'Starting download from the last 120 hours of the live stream since '
2157 'YouTube does not have data before that. If you think this is wrong,'), only_once
=True)
2158 lack_early_segments
= True
2160 known_idx
, no_fragment_score
, last_segment_url
= begin_index
, 0, None
2161 fragments
, fragment_base_url
= None, None
2163 def _extract_sequence_from_mpd(refresh_sequence
, immediate
):
2164 nonlocal mpd_url
, stream_number
, is_live
, no_fragment_score
, fragments
, fragment_base_url
2165 # Obtain from MPD's maximum seq value
2166 old_mpd_url
= mpd_url
2167 last_error
= ctx
.pop('last_error', None)
2168 expire_fast
= immediate
or last_error
and isinstance(last_error
, compat_HTTPError
) and last_error
.code
== 403
2169 mpd_url
, stream_number
, is_live
= (mpd_feed(format_id
, 5 if expire_fast
else 18000)
2170 or (mpd_url
, stream_number
, False))
2171 if not refresh_sequence
:
2172 if expire_fast
and not is_live
:
2173 return False, last_seq
2174 elif old_mpd_url
== mpd_url
:
2175 return True, last_seq
2177 fmts
, _
= self
._extract
_mpd
_formats
_and
_subtitles
(
2178 mpd_url
, None, note
=False, errnote
=False, fatal
=False)
2179 except ExtractorError
:
2182 no_fragment_score
+= 2
2183 return False, last_seq
2184 fmt_info
= next(x
for x
in fmts
if x
['manifest_stream_number'] == stream_number
)
2185 fragments
= fmt_info
['fragments']
2186 fragment_base_url
= fmt_info
['fragment_base_url']
2187 assert fragment_base_url
2189 _last_seq
= int(re
.search(r
'(?:/|^)sq/(\d+)', fragments
[-1]['path']).group(1))
2190 return True, _last_seq
2193 fetch_time
= time
.time()
2194 if no_fragment_score
> 30:
2196 if last_segment_url
:
2197 # Obtain from "X-Head-Seqnum" header value from each segment
2199 urlh
= self
._request
_webpage
(
2200 last_segment_url
, None, note
=False, errnote
=False, fatal
=False)
2201 except ExtractorError
:
2203 last_seq
= try_get(urlh
, lambda x
: int_or_none(x
.headers
['X-Head-Seqnum']))
2204 if last_seq
is None:
2205 no_fragment_score
+= 2
2206 last_segment_url
= None
2209 should_continue
, last_seq
= _extract_sequence_from_mpd(True, no_fragment_score
> 15)
2210 no_fragment_score
+= 2
2211 if not should_continue
:
2214 if known_idx
> last_seq
:
2215 last_segment_url
= None
2220 if begin_index
< 0 and known_idx
< 0:
2221 # skip from the start when it's negative value
2222 known_idx
= last_seq
+ begin_index
2223 if lack_early_segments
:
2224 known_idx
= max(known_idx
, last_seq
- int(MAX_DURATION
// fragments
[-1]['duration']))
2226 for idx
in range(known_idx
, last_seq
):
2227 # do not update sequence here or you'll get skipped some part of it
2228 should_continue
, _
= _extract_sequence_from_mpd(False, False)
2229 if not should_continue
:
2231 raise ExtractorError('breaking out of outer loop')
2232 last_segment_url
= urljoin(fragment_base_url
, 'sq/%d' % idx
)
2234 'url': last_segment_url
,
2236 if known_idx
== last_seq
:
2237 no_fragment_score
+= 5
2239 no_fragment_score
= 0
2240 known_idx
= last_seq
2241 except ExtractorError
:
2244 time
.sleep(max(0, FETCH_SPAN
+ fetch_time
- time
.time()))
2246 def _extract_player_url(self
, *ytcfgs
, webpage
=None):
2247 player_url
= traverse_obj(
2248 ytcfgs
, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2249 get_all
=False, expected_type
=compat_str
)
2252 return urljoin('https://www.youtube.com', player_url
)
2254 def _download_player_url(self
, video_id
, fatal
=False):
2255 res
= self
._download
_webpage
(
2256 'https://www.youtube.com/iframe_api',
2257 note
='Downloading iframe API JS', video_id
=video_id
, fatal
=fatal
)
2259 player_version
= self
._search
_regex
(
2260 r
'player\\?/([0-9a-fA-F]{8})\\?/', res
, 'player version', fatal
=fatal
)
2262 return f
'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2264 def _signature_cache_id(self
, example_sig
):
2265 """ Return a string representation of a signature """
2266 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
2269 def _extract_player_info(cls
, player_url
):
2270 for player_re
in cls
._PLAYER
_INFO
_RE
:
2271 id_m
= re
.search(player_re
, player_url
)
2275 raise ExtractorError('Cannot identify player %r' % player_url
)
2276 return id_m
.group('id')
2278 def _load_player(self
, video_id
, player_url
, fatal
=True):
2279 player_id
= self
._extract
_player
_info
(player_url
)
2280 if player_id
not in self
._code
_cache
:
2281 code
= self
._download
_webpage
(
2282 player_url
, video_id
, fatal
=fatal
,
2283 note
='Downloading player ' + player_id
,
2284 errnote
='Download of %s failed' % player_url
)
2286 self
._code
_cache
[player_id
] = code
2287 return self
._code
_cache
.get(player_id
)
2289 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
2290 player_id
= self
._extract
_player
_info
(player_url
)
2292 # Read from filesystem cache
2293 func_id
= 'js_%s_%s' % (
2294 player_id
, self
._signature
_cache
_id
(example_sig
))
2295 assert os
.path
.basename(func_id
) == func_id
2297 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
2298 if cache_spec
is not None:
2299 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
2301 code
= self
._load
_player
(video_id
, player_url
)
2303 res
= self
._parse
_sig
_js
(code
)
2305 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2306 cache_res
= res(test_string
)
2307 cache_spec
= [ord(c
) for c
in cache_res
]
2309 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
2312 def _print_sig_code(self
, func
, example_sig
):
2313 if not self
.get_param('youtube_print_sig_code'):
2316 def gen_sig_code(idxs
):
2317 def _genslice(start
, end
, step
):
2318 starts
= '' if start
== 0 else str(start
)
2319 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
2320 steps
= '' if step
== 1 else (':%d' % step
)
2321 return 's[%s%s%s]' % (starts
, ends
, steps
)
2324 # Quelch pyflakes warnings - start will be set when step is set
2325 start
= '(Never used)'
2326 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
2327 if step
is not None:
2328 if i
- prev
== step
:
2330 yield _genslice(start
, prev
, step
)
2333 if i
- prev
in [-1, 1]:
2338 yield 's[%d]' % prev
2342 yield _genslice(start
, i
, step
)
2344 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2345 cache_res
= func(test_string
)
2346 cache_spec
= [ord(c
) for c
in cache_res
]
2347 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
2348 signature_id_tuple
= '(%s)' % (
2349 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
2350 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2351 ' return %s\n') % (signature_id_tuple
, expr_code
)
2352 self
.to_screen('Extracted signature function:\n' + code
)
2354 def _parse_sig_js(self
, jscode
):
2355 funcname
= self
._search
_regex
(
2356 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2357 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2358 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2359 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2360 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}\(a,\d+\)',
2361 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\(\s*""\s*\)',
2362 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2364 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2365 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2366 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2367 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2368 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2369 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2370 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2371 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
2372 jscode, 'Initial JS player signature function name
', group='sig
')
2374 jsi = JSInterpreter(jscode)
2375 initial_function = jsi.extract_function(funcname)
2376 return lambda s: initial_function([s])
2378 def _decrypt_signature(self, s, video_id, player_url):
2379 """Turn the encrypted s field into a working signature"""
2381 if player_url is None:
2382 raise ExtractorError('Cannot decrypt signature without player_url
')
2385 player_id = (player_url, self._signature_cache_id(s))
2386 if player_id not in self._player_cache:
2387 func = self._extract_signature_function(
2388 video_id, player_url, s
2390 self._player_cache[player_id] = func
2391 func = self._player_cache[player_id]
2392 self._print_sig_code(func, s)
2394 except Exception as e:
2395 raise ExtractorError('Signature extraction failed
: ' + traceback.format_exc(), cause=e)
2397 def _decrypt_nsig(self, s, video_id, player_url):
2398 """Turn the encrypted n field into a working signature"""
2399 if player_url is None:
2400 raise ExtractorError('Cannot decrypt nsig without player_url
')
2401 player_url = urljoin('https
://www
.youtube
.com
', player_url)
2403 sig_id = ('nsig_value
', s)
2404 if sig_id in self._player_cache:
2405 return self._player_cache[sig_id]
2408 player_id = ('nsig
', player_url)
2409 if player_id not in self._player_cache:
2410 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2411 func = self._player_cache[player_id]
2412 self._player_cache[sig_id] = func(s)
2413 self.write_debug(f'Decrypted nsig {s}
=> {self._player_cache[sig_id]}
')
2414 return self._player_cache[sig_id]
2415 except Exception as e:
2416 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2418 def _extract_n_function_name(self, jscode):
2419 nfunc, idx = self._search_regex(
2420 r'\
.get\
("n"\
)\
)&&\
(b
=(?P
<nfunc
>[a
-zA
-Z0
-9$
]+)(?
:\
[(?P
<idx
>\d
+)\
])?\
([a
-zA
-Z0
-9]\
)',
2421 jscode, 'Initial JS player n function name
', group=('nfunc
', 'idx
'))
2424 return json.loads(js_to_json(self._search_regex(
2425 rf'var {re.escape(nfunc)}\s
*=\s
*(\
[.+?\
]);', jscode,
2426 f'Initial JS player n function
list ({nfunc}
.{idx}
)')))[int(idx)]
2428 def _extract_n_function(self, video_id, player_url):
2429 player_id = self._extract_player_info(player_url)
2430 func_code = self._downloader.cache.load('youtube
-nsig
', player_id)
2433 jsi = JSInterpreter(func_code)
2435 jscode = self._load_player(video_id, player_url)
2436 funcname = self._extract_n_function_name(jscode)
2437 jsi = JSInterpreter(jscode)
2438 func_code = jsi.extract_function_code(funcname)
2439 self._downloader.cache.store('youtube
-nsig
', player_id, func_code)
2441 if self.get_param('youtube_print_sig_code
'):
2442 self.to_screen(f'Extracted nsig function
from {player_id}
:\n{func_code[1]}
\n')
2444 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2446 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2448 Extract signatureTimestamp (sts)
2449 Required to tell API what sig/player version is in use.
2452 if isinstance(ytcfg, dict):
2453 sts = int_or_none(ytcfg.get('STS
'))
2456 # Attempt to extract from player
2457 if player_url is None:
2458 error_msg = 'Cannot extract signature timestamp without player_url
.'
2460 raise ExtractorError(error_msg)
2461 self.report_warning(error_msg)
2463 code = self._load_player(video_id, player_url, fatal=fatal)
2465 sts = int_or_none(self._search_regex(
2466 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
2467 'JS player signature timestamp
', group='sts
', fatal=fatal))
2470 def _mark_watched(self, video_id, player_responses):
2471 playback_url = get_first(
2472 player_responses, ('playbackTracking
', 'videostatsPlaybackUrl
', 'baseUrl
'),
2473 expected_type=url_or_none)
2474 if not playback_url:
2475 self.report_warning('Unable to mark watched
')
2477 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2478 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2480 # cpn generation algorithm is reverse engineered from base.js.
2481 # In fact it works even with dummy cpn.
2482 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
2483 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2489 playback_url = compat_urlparse.urlunparse(
2490 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2492 self._download_webpage(
2493 playback_url, video_id, 'Marking watched
',
2494 'Unable to mark watched
', fatal=False)
2497 def _extract_urls(webpage):
2498 # Embedded YouTube player
2500 unescapeHTML(mobj.group('url
'))
2501 for mobj in re.finditer(r'''(?x)
2511 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2512 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2515 # lazyYT YouTube embed
2516 entries.extend(list(map(
2518 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
2520 # Wordpress "YouTube Video Importer
" plugin
2521 matches = re.findall(r'''(?x)<div[^>]+
2522 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
2523 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
2524 entries.extend(m[-1] for m in matches)
2529 def _extract_url(webpage):
2530 urls = YoutubeIE._extract_urls(webpage)
2531 return urls[0] if urls else None
2534 def extract_id(cls, url):
2535 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2537 raise ExtractorError('Invalid URL: %s' % url)
2538 return mobj.group('id')
2540 def _extract_chapters_from_json(self, data, duration):
2541 chapter_list = traverse_obj(
2543 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2544 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2545 ), expected_type=list)
2547 return self._extract_chapters(
2549 chapter_time=lambda chapter: float_or_none(
2550 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2551 chapter_title=lambda chapter: traverse_obj(
2552 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2555 def _extract_chapters_from_engagement_panel(self, data, duration):
2556 content_list = traverse_obj(
2558 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2559 expected_type=list, default=[])
2560 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2561 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2565 self._extract_chapters(
2566 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2567 chapter_time, chapter_title, duration)
2568 for contents in content_list
2571 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2573 last_chapter = {'start_time': 0}
2574 for idx, chapter in enumerate(chapter_list or []):
2575 title = chapter_title(chapter)
2576 start_time = chapter_time(chapter)
2577 if start_time is None:
2579 last_chapter['end_time'] = start_time
2580 if start_time < last_chapter['start_time']:
2583 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2585 self.report_warning(f'Invalid start time for chapter "{title}"')
2587 last_chapter = {'start_time': start_time, 'title': title}
2588 chapters.append(last_chapter)
2589 last_chapter['end_time'] = duration
2592 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2593 return self._parse_json(self._search_regex(
2594 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2595 regex), webpage, name, default='{}'), video_id, fatal=False)
2597 def _extract_comment(self, comment_renderer, parent=None):
2598 comment_id = comment_renderer.get('commentId')
2602 text = self._get_text(comment_renderer, 'contentText')
2604 # note: timestamp is an estimate calculated from the current time and time_text
2605 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2606 author = self._get_text(comment_renderer, 'authorText')
2607 author_id = try_get(comment_renderer,
2608 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2610 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2611 lambda x: x['likeCount']), compat_str)) or 0
2612 author_thumbnail = try_get(comment_renderer,
2613 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2615 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2616 is_favorited = 'creatorHeart' in (try_get(
2617 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2621 'timestamp': timestamp,
2622 'time_text': time_text,
2623 'like_count': votes,
2624 'is_favorited': is_favorited,
2626 'author_id': author_id,
2627 'author_thumbnail': author_thumbnail,
2628 'author_is_uploader': author_is_uploader,
2629 'parent': parent or 'root'
2632 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2634 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2636 def extract_header(contents):
2637 _continuation = None
2638 for content in contents:
2639 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2640 expected_comment_count = self._get_count(
2641 comments_header_renderer, 'countText', 'commentsCount')
2643 if expected_comment_count:
2644 tracker['est_total'] = expected_comment_count
2645 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2646 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2648 sort_menu_item = try_get(
2649 comments_header_renderer,
2650 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2651 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2653 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2654 if not _continuation:
2657 sort_text = str_or_none(sort_menu_item.get('title'))
2659 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2660 self.to_screen('Sorting comments by %s' % sort_text.lower())
2662 return _continuation
2664 def extract_thread(contents):
2666 tracker['current_page_thread'] = 0
2667 for content in contents:
2668 if not parent and tracker['total_parent_comments'] >= max_parents:
2670 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2671 comment_renderer = get_first(
2672 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2673 expected_type=dict, default={})
2675 comment = self._extract_comment(comment_renderer, parent)
2679 tracker['running_total'] += 1
2680 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2683 # Attempt to get the replies
2684 comment_replies_renderer = try_get(
2685 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2687 if comment_replies_renderer:
2688 tracker['current_page_thread'] += 1
2689 comment_entries_iter = self._comment_entries(
2690 comment_replies_renderer, ytcfg, video_id,
2691 parent=comment.get('id'), tracker=tracker)
2692 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2695 # Keeps track of counts across recursive calls
2700 current_page_thread=0,
2701 total_parent_comments=0,
2702 total_reply_comments=0)
2705 # YouTube comments have a max depth of 2
2706 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2708 self._downloader.deprecation_warning(
2709 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2710 if max_depth == 1 and parent:
2713 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2714 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2716 continuation = self._extract_continuation(root_continuation_data)
2717 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2718 if message and not parent:
2719 self.report_warning(message, video_id=video_id)
2722 is_first_continuation = parent is None
2724 for page_num in itertools.count(0):
2725 if not continuation:
2727 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2728 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2730 if is_first_continuation:
2731 note_prefix = 'Downloading comment section API JSON'
2733 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2734 tracker['current_page_thread'], comment_prog_str)
2736 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2737 ' ' if parent else '', ' replies' if parent else '',
2738 page_num, comment_prog_str)
2740 response = self._extract_response(
2741 item_id=None, query=continuation,
2742 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2743 check_get_keys='onResponseReceivedEndpoints')
2745 continuation_contents = traverse_obj(
2746 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2749 for continuation_section in continuation_contents:
2750 continuation_items = traverse_obj(
2751 continuation_section,
2752 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2753 get_all=False, expected_type=list) or []
2754 if is_first_continuation:
2755 continuation = extract_header(continuation_items)
2756 is_first_continuation = False
2761 for entry in extract_thread(continuation_items):
2765 continuation = self._extract_continuation({'contents': continuation_items})
2769 def _get_comments(self, ytcfg, video_id, contents, webpage):
2770 """Entry for comment extraction"""
2771 def _real_comment_extract(contents):
2773 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2774 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2775 yield from self._comment_entries(renderer, ytcfg, video_id)
2777 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2778 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2781 def _get_checkok_params():
2782 return {'contentCheckOk': True, 'racyCheckOk': True}
2785 def _generate_player_context(cls, sts=None):
2787 'html5Preference': 'HTML5_PREF_WANTS',
2790 context['signatureTimestamp'] = sts
2792 'playbackContext': {
2793 'contentPlaybackContext': context
2795 **cls._get_checkok_params()
2799 def _is_agegated(player_response):
2800 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2803 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2804 AGE_GATE_REASONS = (
2805 'confirm your age', 'age-restricted', 'inappropriate', # reason
2806 'age_verification_required', 'age_check_required', # status
2808 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2811 def _is_unplayable(player_response):
2812 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2814 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2816 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2817 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2818 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2819 headers = self.generate_api_headers(
2820 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2822 yt_query = {'videoId': video_id}
2823 yt_query.update(self._generate_player_context(sts))
2824 return self._extract_response(
2825 item_id=video_id, ep='player', query=yt_query,
2826 ytcfg=player_ytcfg, headers=headers, fatal=True,
2827 default_client=client,
2828 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2831 def _get_requested_clients(self, url, smuggled_data):
2832 requested_clients = []
2833 default = ['android', 'web']
2834 allowed_clients = sorted(
2835 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2836 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2837 for client in self._configuration_arg('player_client'):
2838 if client in allowed_clients:
2839 requested_clients.append(client)
2840 elif client == 'default':
2841 requested_clients.extend(default)
2842 elif client == 'all':
2843 requested_clients.extend(allowed_clients)
2845 self.report_warning(f'Skipping unsupported client {client}')
2846 if not requested_clients:
2847 requested_clients = default
2849 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2850 requested_clients.extend(
2851 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2853 return orderedSet(requested_clients)
2855 def _extract_player_ytcfg(self, client, video_id):
2857 'web_music': 'https://music.youtube.com',
2858 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2862 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2863 return self.extract_ytcfg(video_id, webpage) or {}
2865 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2868 initial_pr = self._extract_yt_initial_variable(
2869 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2870 video_id, 'initial player response')
2872 original_clients = clients
2873 clients = clients[::-1]
2876 def append_client(client_name):
2877 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2878 clients.append(client_name)
2880 # Android player_response does not have microFormats which are needed for
2881 # extraction of some data. So we return the initial_pr with formats
2882 # stripped out even if not requested by the user
2883 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2885 pr = dict(initial_pr)
2886 pr['streamingData'] = None
2890 tried_iframe_fallback = False
2893 client = clients.pop()
2894 player_ytcfg = master_ytcfg if client == 'web' else {}
2895 if 'configs' not in self._configuration_arg('player_skip'):
2896 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2898 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2899 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2900 if 'js' in self._configuration_arg('player_skip'):
2901 require_js_player = False
2904 if not player_url and not tried_iframe_fallback and require_js_player:
2905 player_url = self._download_player_url(video_id)
2906 tried_iframe_fallback = True
2909 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2910 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
2911 except ExtractorError as e:
2913 self.report_warning(last_error)
2920 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2921 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
2922 append_client(client.replace('_agegate', '_creator'))
2923 elif self._is_agegated(pr):
2924 append_client(f'{client}_agegate')
2929 self.report_warning(last_error)
2930 return prs, player_url
2932 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2933 itags, stream_ids = {}, []
2934 itag_qualities, res_qualities = {}, {}
2936 # Normally tiny is the smallest video-only formats. But
2937 # audio-only formats with unknown quality may get tagged as tiny
2939 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2940 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2942 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2943 approx_duration = max(traverse_obj(streaming_formats, (..., 'approxDurationMs'), expected_type=float_or_none) or [0]) or None
2945 for fmt in streaming_formats:
2946 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2949 itag = str_or_none(fmt.get('itag'))
2950 audio_track = fmt.get('audioTrack') or {}
2951 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2952 if stream_id in stream_ids:
2955 quality = fmt.get('quality')
2956 height = int_or_none(fmt.get('height'))
2957 if quality == 'tiny' or not quality:
2958 quality = fmt.get('audioQuality', '').lower() or quality
2959 # The 3gp format (17) in android client has a quality of "small",
2960 # but is actually worse than other formats
2965 itag_qualities[itag] = quality
2967 res_qualities[height] = quality
2968 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2969 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2970 # number of fragment that would subsequently requested with (`&sq=N`)
2971 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2974 fmt_url = fmt.get('url')
2976 sc = compat_parse_qs(fmt.get('signatureCipher'))
2977 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2978 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2979 if not (sc and fmt_url and encrypted_sig):
2983 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2984 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2985 fmt_url += '&' + sp + '=' + signature
2987 query = parse_qs(fmt_url)
2991 fmt_url = update_url_query(fmt_url, {
2992 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2993 except ExtractorError as e:
2994 self.report_warning(
2995 f'nsig extraction failed: You may experience throttling for some formats\n'
2996 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
3000 itags[itag] = 'https'
3001 stream_ids.append(stream_id)
3003 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3004 language_preference = (
3005 10 if audio_track.get('audioIsDefault') and 10
3006 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3008 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3009 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3010 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) < approx_duration - 10000)
3012 'asr': int_or_none(fmt.get('audioSampleRate')),
3013 'filesize': int_or_none(fmt.get('contentLength')),
3015 'format_note': join_nonempty(
3016 '%s%s' % (audio_track.get('displayName') or '',
3017 ' (default)' if language_preference > 0 else ''),
3018 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3019 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3020 'source_preference': -10 if throttled else -1,
3021 'fps': int_or_none(fmt.get('fps')) or None,
3023 'quality': q(quality),
3026 'width': int_or_none(fmt.get('width')),
3027 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3028 'desc' if language_preference < -1 else ''),
3029 'language_preference': language_preference,
3030 'preference': -10 if is_damaged else None,
3032 mime_mobj = re.match(
3033 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3035 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3036 dct.update(parse_codecs(mime_mobj.group(2)))
3037 no_audio = dct.get('acodec') == 'none'
3038 no_video = dct.get('vcodec') == 'none'
3043 if no_audio or no_video:
3044 dct['downloader_options'] = {
3045 # Youtube throttles chunks >~10M
3046 'http_chunk_size': 10485760,
3049 dct['container'] = dct['ext'] + '_dash'
3052 live_from_start = is_live and self.get_param('live_from_start')
3053 skip_manifests = self._configuration_arg('skip')
3054 if not self.get_param('youtube_include_hls_manifest', True):
3055 skip_manifests.append('hls')
3056 get_dash = 'dash' not in skip_manifests and (
3057 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3058 get_hls = not live_from_start and 'hls' not in skip_manifests
3060 def process_manifest_format(f, proto, itag):
3062 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3064 itag = f'{itag}-{proto}'
3066 f['format_id'] = itag
3069 f['quality'] = next((
3071 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3072 if val in qdict), -1)
3075 for sd in streaming_data:
3076 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3077 if hls_manifest_url:
3078 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3079 if process_manifest_format(f, 'hls', self._search_regex(
3080 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3083 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3084 if dash_manifest_url:
3085 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3086 if process_manifest_format(f, 'dash', f['format_id']):
3087 f['filesize'] = int_or_none(self._search_regex(
3088 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3090 f['is_from_start'] = True
3094 def _extract_storyboard(self, player_responses, duration):
3096 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3097 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3101 for i, args in enumerate(spec):
3102 args = args.split('#')
3103 counts = list(map(int_or_none, args[:5]))
3104 if len(args) != 8 or not all(counts):
3105 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3107 width, height, frame_count, cols, rows = counts
3110 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3111 fragment_count = frame_count / (cols * rows)
3112 fragment_duration = duration / fragment_count
3114 'format_id': f'sb{i}',
3115 'format_note': 'storyboard',
3117 'protocol': 'mhtml',
3124 'path': url.replace('$M', str(j)),
3125 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3126 } for j in range(math.ceil(fragment_count))],
3129 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3131 if 'webpage' not in self._configuration_arg('player_skip'):
3132 webpage = self._download_webpage(
3133 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3135 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3137 player_responses, player_url = self._extract_player_responses(
3138 self._get_requested_clients(url, smuggled_data),
3139 video_id, webpage, master_ytcfg)
3141 return webpage, master_ytcfg, player_responses, player_url
3143 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3144 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3145 is_live = get_first(video_details, 'isLive')
3147 is_live = get_first(live_broadcast_details, 'isLiveNow')
3149 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3150 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3152 return live_broadcast_details, is_live, streaming_data, formats
3154 def _real_extract(self, url):
3155 url, smuggled_data = unsmuggle_url(url, {})
3156 video_id = self._match_id(url)
3158 base_url = self.http_scheme() + '//www.youtube.com/'
3159 webpage_url = base_url + 'watch?v=' + video_id
3161 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3163 playability_statuses = traverse_obj(
3164 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3166 trailer_video_id = get_first(
3167 playability_statuses,
3168 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3170 if trailer_video_id:
3171 return self.url_result(
3172 trailer_video_id, self.ie_key(), trailer_video_id)
3174 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3175 if webpage else (lambda x: None))
3177 video_details = traverse_obj(
3178 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3179 microformats = traverse_obj(
3180 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3181 expected_type=dict, default=[])
3183 get_first(video_details, 'title')
3184 or self._get_text(microformats, (..., 'title'))
3185 or search_meta(['og:title', 'twitter:title', 'title']))
3186 video_description = get_first(video_details, 'shortDescription')
3188 multifeed_metadata_list = get_first(
3190 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3192 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3193 if self.get_param('noplaylist'):
3194 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3198 for feed in multifeed_metadata_list.split(','):
3199 # Unquote should take place before split on comma (,) since textual
3200 # fields may contain comma as well (see
3201 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3202 feed_data = compat_parse_qs(
3203 compat_urllib_parse_unquote_plus(feed))
3205 def feed_entry(name):
3207 feed_data, lambda x: x[name][0], compat_str)
3209 feed_id = feed_entry('id')
3212 feed_title = feed_entry('title')
3215 title += ' (%s)' % feed_title
3217 '_type': 'url_transparent',
3218 'ie_key': 'Youtube',
3220 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3221 {'force_singlefeed': True}),
3224 feed_ids.append(feed_id)
3226 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3227 % (', '.join(feed_ids), video_id))
3228 return self.playlist_result(
3229 entries, video_id, video_title, video_description)
3231 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
3234 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3235 self.report_drm(video_id)
3237 playability_statuses,
3238 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3239 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3240 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3242 if subreason == 'The uploader has not made this video available in your country.':
3243 countries = get_first(microformats, 'availableCountries')
3245 regions_allowed = search_meta('regionsAllowed')
3246 countries = regions_allowed.split(',') if regions_allowed else None
3247 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3248 reason += f'. {subreason}'
3250 self.raise_no_formats(reason, expected=True)
3252 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3253 if not keywords and webpage:
3255 unescapeHTML(m.group('content'))
3256 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3257 for keyword in keywords:
3258 if keyword.startswith('yt:stretch='):
3259 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3261 # NB: float is intentional for forcing float division
3262 w, h = (float(v) for v in mobj.groups())
3266 if f.get('vcodec') != 'none':
3267 f['stretched_ratio'] = ratio
3269 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3270 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3273 'url': thumbnail_url,
3275 original_thumbnails = thumbnails.copy()
3277 # The best resolution thumbnails sometimes does not appear in the webpage
3278 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3279 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3281 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3282 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3283 'mqdefault', 'mq1', 'mq2', 'mq3',
3284 'default', '1', '2', '3'
3286 n_thumbnail_names = len(thumbnail_names)
3288 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3289 video_id=video_id, name=name, ext=ext,
3290 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3291 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3292 for thumb in thumbnails:
3293 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3294 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3295 self._remove_duplicate_formats(thumbnails)
3296 self._downloader._sort_thumbnails(original_thumbnails)
3298 category = get_first(microformats, 'category') or search_meta('genre')
3299 channel_id = str_or_none(
3300 get_first(video_details, 'channelId')
3301 or get_first(microformats, 'externalChannelId')
3302 or search_meta('channelId'))
3303 duration = int_or_none(
3304 get_first(video_details, 'lengthSeconds')
3305 or get_first(microformats, 'lengthSeconds')
3306 or parse_duration(search_meta('duration'))) or None
3307 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3309 live_content = get_first(video_details, 'isLiveContent')
3310 is_upcoming = get_first(video_details, 'isUpcoming')
3312 if is_upcoming or live_content is False:
3314 if is_upcoming is None and (live_content or is_live):
3316 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3317 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3318 if not duration and live_end_time and live_start_time:
3319 duration = live_end_time - live_start_time
3321 if is_live and self.get_param('live_from_start'):
3322 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3324 formats.extend(self._extract_storyboard(player_responses, duration))
3326 # Source is given priority since formats that throttle are given lower source_preference
3327 # When throttling issue is fully fixed, remove this
3328 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3332 'title': video_title,
3334 'thumbnails': thumbnails,
3335 # The best thumbnail that we are sure exists. Prevents unnecessary
3336 # URL checking if user don't care about getting the best possible thumbnail
3337 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3338 'description': video_description,
3339 'upload_date': unified_strdate(
3340 get_first(microformats, 'uploadDate')
3341 or search_meta('uploadDate')),
3342 'uploader': get_first(video_details, 'author'),
3343 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3344 'uploader_url': owner_profile_url,
3345 'channel_id': channel_id,
3346 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3347 'duration': duration,
3348 'view_count': int_or_none(
3349 get_first((video_details, microformats), (..., 'viewCount'))
3350 or search_meta('interactionCount')),
3351 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3352 'age_limit': 18 if (
3353 get_first(microformats, 'isFamilySafe') is False
3354 or search_meta('isFamilyFriendly') == 'false'
3355 or search_meta('og:restrictions:age') == '18+') else 0,
3356 'webpage_url': webpage_url,
3357 'categories': [category] if category else None,
3359 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3361 'was_live': (False if is_live or is_upcoming or live_content is False
3362 else None if is_live is None or is_upcoming is None
3364 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3365 'release_timestamp': live_start_time,
3368 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3370 def get_lang_code(track):
3371 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3372 or track.get('languageCode'))
3374 # Converted into dicts to remove duplicates
3376 get_lang_code(sub): sub
3377 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3378 translation_languages = {
3379 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3380 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3382 def process_language(container, base_url, lang_code, sub_name, query):
3383 lang_subs = container.setdefault(lang_code, [])
3384 for fmt in self._SUBTITLE_FORMATS:
3390 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3394 subtitles, automatic_captions = {}, {}
3395 for lang_code, caption_track in captions.items():
3396 base_url = caption_track.get('baseUrl')
3399 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3400 if caption_track.get('kind') != 'asr':
3404 subtitles, base_url, lang_code, lang_name, {})
3405 if not caption_track.get('isTranslatable'):
3407 for trans_code, trans_name in translation_languages.items():
3410 if caption_track.get('kind') != 'asr':
3411 trans_code += f'-{lang_code}'
3412 trans_name += format_field(lang_name, template=' from %s')
3414 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3415 if lang_code == f'a-{trans_code}':
3417 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {'tlang': trans_code})
3418 info['automatic_captions'] = automatic_captions
3419 info['subtitles'] = subtitles
3421 parsed_url = compat_urllib_parse_urlparse(url)
3422 for component in [parsed_url.fragment, parsed_url.query]:
3423 query = compat_parse_qs(component)
3424 for k, v in query.items():
3425 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3427 if d_k not in info and k in s_ks:
3428 info[d_k] = parse_duration(query[k][0])
3430 # Youtube Music Auto-generated description
3431 if video_description:
3432 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)
3434 release_year = mobj.group('release_year')
3435 release_date = mobj.group('release_date')
3437 release_date = release_date.replace('-', '')
3438 if not release_year:
3439 release_year = release_date[:4]
3441 'album': mobj.group('album'.strip()),
3442 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3443 'track': mobj.group('track').strip(),
3444 'release_date': release_date,
3445 'release_year': int_or_none(release_year),
3450 initial_data = self._extract_yt_initial_variable(
3451 webpage, self._YT_INITIAL_DATA_RE, video_id,
3453 if not initial_data:
3454 query = {'videoId': video_id}
3455 query.update(self._get_checkok_params())
3456 initial_data = self._extract_response(
3457 item_id=video_id, ep='next', fatal=False,
3458 ytcfg=master_ytcfg, query=query,
3459 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3460 note='Downloading initial data API JSON')
3463 # This will error if there is no livechat
3464 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3465 info.setdefault('subtitles', {})['live_chat'] = [{
3466 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3467 'video_id': video_id,
3469 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3471 except (KeyError, IndexError, TypeError):
3475 info['chapters'] = (
3476 self._extract_chapters_from_json(initial_data, duration)
3477 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3482 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3484 for content in contents:
3485 vpir = content.get('videoPrimaryInfoRenderer')
3487 stl = vpir.get('superTitleLink')
3489 stl = self._get_text(stl)
3492 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3493 info['location'] = stl
3495 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3498 'series': mobj.group(1),
3499 'season_number': int(mobj.group(2)),
3500 'episode_number': int(mobj.group(3)),
3502 for tlb in (try_get(
3504 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3506 tbr = tlb.get('toggleButtonRenderer') or {}
3507 for getter, regex in [(
3508 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3509 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3510 lambda x: x['accessibility'],
3511 lambda x: x['accessibilityData']['accessibilityData'],
3512 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3513 label = (try_get(tbr, getter, dict) or {}).get('label')
3515 mobj = re.match(regex, label)
3517 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3519 sbr_tooltip = try_get(
3520 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3522 like_count, dislike_count = sbr_tooltip.split(' / ')
3524 'like_count': str_to_int(like_count),
3525 'dislike_count': str_to_int(dislike_count),
3527 vsir = content.get('videoSecondaryInfoRenderer')
3529 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3531 'channel': self._get_text(vor, 'title'),
3532 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3536 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3538 multiple_songs = False
3540 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3541 multiple_songs = True
3544 mrr = row.get('metadataRowRenderer') or {}
3545 mrr_title = mrr.get('title')
3548 mrr_title = self._get_text(mrr, 'title')
3549 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3550 if mrr_title == 'License':
3551 info['license'] = mrr_contents_text
3552 elif not multiple_songs:
3553 if mrr_title == 'Album':
3554 info['album'] = mrr_contents_text
3555 elif mrr_title == 'Artist':
3556 info['artist'] = mrr_contents_text
3557 elif mrr_title == 'Song':
3558 info['track'] = mrr_contents_text
3561 'channel': 'uploader',
3562 'channel_id': 'uploader_id',
3563 'channel_url': 'uploader_url',
3565 for to, frm in fallbacks.items():
3566 if not info.get(to):
3567 info[to] = info.get(frm)
3569 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3574 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3575 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3576 is_membersonly = None
3578 if initial_data and is_private is not None:
3579 is_membersonly = False
3581 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3582 badge_labels = set()
3583 for content in contents:
3584 if not isinstance(content, dict):
3586 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3587 for badge_label in badge_labels:
3588 if badge_label.lower() == 'members only':
3589 is_membersonly = True
3590 elif badge_label.lower() == 'premium':
3592 elif badge_label.lower() == 'unlisted':
3595 info['availability'] = self._availability(
3596 is_private=is_private,
3597 needs_premium=is_premium,
3598 needs_subscription=is_membersonly,
3599 needs_auth=info['age_limit'] >= 18,
3600 is_unlisted=None if is_private is None else is_unlisted)
3602 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3604 self.mark_watched(video_id, player_responses)
3609 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3612 def passthrough_smuggled_data(func):
3613 def _smuggle(entries, smuggled_data):
3614 for entry in entries:
3615 # TODO: Convert URL to music.youtube instead.
3616 # Do we need to passthrough any other smuggled_data?
3617 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3620 @functools.wraps(func)
3621 def wrapper(self, url):
3622 url, smuggled_data = unsmuggle_url(url, {})
3623 if self.is_music_url(url):
3624 smuggled_data['is_music_url'] = True
3625 info_dict = func(self, url, smuggled_data)
3626 if smuggled_data and info_dict.get('entries'):
3627 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3631 def _extract_channel_id(self, webpage):
3632 channel_id = self._html_search_meta(
3633 'channelId', webpage, 'channel id', default=None)
3636 channel_url = self._html_search_meta(
3637 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3638 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3639 'twitter:app:url:googleplay'), webpage, 'channel url')
3640 return self._search_regex(
3641 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3642 channel_url, 'channel id')
3645 def _extract_basic_item_renderer(item):
3646 # Modified from _extract_grid_item_renderer
3647 known_basic_renderers = (
3648 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3650 for key, renderer in item.items():
3651 if not isinstance(renderer, dict):
3653 elif key in known_basic_renderers:
3655 elif key.startswith('grid') and key.endswith('Renderer'):
3658 def _grid_entries(self, grid_renderer):
3659 for item in grid_renderer['items']:
3660 if not isinstance(item, dict):
3662 renderer = self._extract_basic_item_renderer(item)
3663 if not isinstance(renderer, dict):
3665 title = self._get_text(renderer, 'title')
3668 playlist_id = renderer.get('playlistId')
3670 yield self.url_result(
3671 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3672 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3676 video_id = renderer.get('videoId')
3678 yield self._extract_video(renderer)
3681 channel_id = renderer.get('channelId')
3683 yield self.url_result(
3684 'https://www.youtube.com/channel/%s' % channel_id,
3685 ie=YoutubeTabIE.ie_key(), video_title=title)
3687 # generic endpoint URL support
3688 ep_url = urljoin('https://www.youtube.com/', try_get(
3689 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3692 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3693 if ie.suitable(ep_url):
3694 yield self.url_result(
3695 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3698 def _music_reponsive_list_entry(self, renderer):
3699 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3701 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3702 ie=YoutubeIE.ie_key(), video_id=video_id)
3703 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3705 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3707 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3708 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3709 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3710 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3711 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3713 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3714 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3716 def _shelf_entries_from_content(self, shelf_renderer):
3717 content = shelf_renderer.get('content')
3718 if not isinstance(content, dict):
3720 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3722 # TODO: add support for nested playlists so each shelf is processed
3723 # as separate playlist
3724 # TODO: this includes only first N items
3725 for entry in self._grid_entries(renderer):
3727 renderer = content.get('horizontalListRenderer')
3732 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3734 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3736 shelf_url = urljoin('https://www.youtube.com', ep)
3738 # Skipping links to another channels, note that checking for
3739 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3741 if skip_channels and '/channels?' in shelf_url:
3743 title = self._get_text(shelf_renderer, 'title')
3744 yield self.url_result(shelf_url, video_title=title)
3745 # Shelf may not contain shelf URL, fallback to extraction from content
3746 for entry in self._shelf_entries_from_content(shelf_renderer):
3749 def _playlist_entries(self, video_list_renderer):
3750 for content in video_list_renderer['contents']:
3751 if not isinstance(content, dict):
3753 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3754 if not isinstance(renderer, dict):
3756 video_id = renderer.get('videoId')
3759 yield self._extract_video(renderer)
3761 def _rich_entries(self, rich_grid_renderer):
3763 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3764 video_id = renderer.get('videoId')
3767 yield self._extract_video(renderer)
3769 def _video_entry(self, video_renderer):
3770 video_id = video_renderer.get('videoId')
3772 return self._extract_video(video_renderer)
3774 def _post_thread_entries(self, post_thread_renderer):
3775 post_renderer = try_get(
3776 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3777 if not post_renderer:
3780 video_renderer = try_get(
3781 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3782 video_id = video_renderer.get('videoId')
3784 entry = self._extract_video(video_renderer)
3787 # playlist attachment
3788 playlist_id = try_get(
3789 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3791 yield self.url_result(
3792 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3793 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3794 # inline video links
3795 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3797 if not isinstance(run, dict):
3800 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3803 if not YoutubeIE.suitable(ep_url):
3805 ep_video_id = YoutubeIE._match_id(ep_url)
3806 if video_id == ep_video_id:
3808 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3810 def _post_thread_continuation_entries(self, post_thread_continuation):
3811 contents = post_thread_continuation.get('contents')
3812 if not isinstance(contents, list):
3814 for content in contents:
3815 renderer = content.get('backstagePostThreadRenderer')
3816 if not isinstance(renderer, dict):
3818 for entry in self._post_thread_entries(renderer):
3822 def _rich_grid_entries(self
, contents
):
3823 for content
in contents
:
3824 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3826 entry
= self
._video
_entry
(video_renderer
)
3830 def _extract_entries(self, parent_renderer, continuation_list):
3831 # continuation_list is modified in-place with continuation_list = [continuation_token]
3832 continuation_list[:] = [None]
3833 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3834 for content in contents:
3835 if not isinstance(content, dict):
3837 is_renderer = traverse_obj(
3838 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3841 renderer = content.get('richItemRenderer')
3843 for entry in self._rich_entries(renderer):
3845 continuation_list[0] = self._extract_continuation(parent_renderer)
3847 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3848 for isr_content in isr_contents:
3849 if not isinstance(isr_content, dict):
3853 'playlistVideoListRenderer': self._playlist_entries,
3854 'gridRenderer': self._grid_entries,
3855 'shelfRenderer': lambda x: self._shelf_entries(x),
3856 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
3857 'backstagePostThreadRenderer': self._post_thread_entries,
3858 'videoRenderer': lambda x: [self._video_entry(x)],
3859 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3860 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
3862 for key, renderer in isr_content.items():
3863 if key not in known_renderers:
3865 for entry in known_renderers[key](renderer):
3868 continuation_list[0] = self._extract_continuation(renderer)
3871 if not continuation_list[0]:
3872 continuation_list[0] = self._extract_continuation(is_renderer)
3874 if not continuation_list[0]:
3875 continuation_list[0] = self._extract_continuation(parent_renderer)
3877 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3878 continuation_list = [None]
3879 extract_entries = lambda x: self._extract_entries(x, continuation_list)
3880 tab_content = try_get(tab, lambda x: x['content'], dict)
3884 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3885 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3886 for entry in extract_entries(parent_renderer):
3888 continuation = continuation_list[0]
3890 for page_num in itertools.count(1):
3891 if not continuation:
3893 headers = self.generate_api_headers(
3894 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
3895 response = self._extract_response(
3896 item_id='%s page %s' % (item_id, page_num),
3897 query=continuation, headers=headers, ytcfg=ytcfg,
3898 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3902 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3903 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3904 visitor_data = self._extract_visitor_data(response) or visitor_data
3906 known_continuation_renderers = {
3907 'playlistVideoListContinuation': self._playlist_entries,
3908 'gridContinuation': self._grid_entries,
3909 'itemSectionContinuation': self._post_thread_continuation_entries,
3910 'sectionListContinuation': extract_entries, # for feeds
3912 continuation_contents = try_get(
3913 response, lambda x: x['continuationContents'], dict) or {}
3914 continuation_renderer = None
3915 for key, value in continuation_contents.items():
3916 if key not in known_continuation_renderers:
3918 continuation_renderer = value
3919 continuation_list = [None]
3920 for entry in known_continuation_renderers[key](continuation_renderer):
3922 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3924 if continuation_renderer:
3928 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3929 'gridVideoRenderer': (self._grid_entries, 'items'),
3930 'gridChannelRenderer': (self._grid_entries, 'items'),
3931 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3932 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3933 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3934 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3936 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3937 continuation_items = try_get(
3938 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3939 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3940 video_items_renderer = None
3941 for key, value in continuation_item.items():
3942 if key not in known_renderers:
3944 video_items_renderer = {known_renderers[key][1]: continuation_items}
3945 continuation_list = [None]
3946 for entry in known_renderers[key][0](video_items_renderer):
3948 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3950 if video_items_renderer:
3955 def _extract_selected_tab(tabs, fatal=True):
3957 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3958 if renderer.get('selected') is True:
3962 raise ExtractorError('Unable to find selected tab')
3965 def _extract_uploader(cls, data):
3967 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3969 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3971 uploader['uploader'] = owner.get('text')
3972 uploader['uploader_id'] = try_get(
3973 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3974 uploader['uploader_url'] = urljoin(
3975 'https://www.youtube.com/',
3976 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3977 return {k: v for k, v in uploader.items() if v is not None}
3979 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
3980 playlist_id = title = description = channel_url = channel_name = channel_id = None
3983 selected_tab = self._extract_selected_tab(tabs)
3984 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3986 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3988 channel_name = renderer.get('title')
3989 channel_url = renderer.get('channelUrl')
3990 channel_id = renderer.get('externalId')
3993 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3996 title = renderer.get('title')
3997 description = renderer.get('description', '')
3998 playlist_id = channel_id
3999 tags = renderer.get('keywords', '').split()
4001 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4002 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4003 def _get_uncropped(url):
4004 return url_or_none((url or '').split('=')[0] + '=s0')
4006 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4007 if avatar_thumbnails:
4008 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4009 if uncropped_avatar:
4010 avatar_thumbnails.append({
4011 'url': uncropped_avatar,
4012 'id': 'avatar_uncropped',
4016 channel_banners = self._extract_thumbnails(
4017 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4018 for banner in channel_banners:
4019 banner['preference'] = -10
4022 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4023 if uncropped_banner:
4024 channel_banners.append({
4025 'url': uncropped_banner,
4026 'id': 'banner_uncropped',
4030 primary_thumbnails = self._extract_thumbnails(
4031 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
4033 if playlist_id is None:
4034 playlist_id = item_id
4036 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4037 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4039 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4040 title += format_field(selected_tab, 'title', ' - %s')
4041 title += format_field(selected_tab, 'expandedText', ' - %s')
4044 'playlist_id': playlist_id,
4045 'playlist_title': title,
4046 'playlist_description': description,
4047 'uploader': channel_name,
4048 'uploader_id': channel_id,
4049 'uploader_url': channel_url,
4050 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4052 'view_count': self._get_count(playlist_stats, 1),
4053 'availability': self._extract_availability(data),
4054 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4055 'playlist_count': self._get_count(playlist_stats, 0),
4056 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4059 metadata.update(self._extract_uploader(data))
4061 'channel': metadata['uploader'],
4062 'channel_id': metadata['uploader_id'],
4063 'channel_url': metadata['uploader_url']})
4064 return self.playlist_result(
4066 selected_tab, playlist_id, ytcfg,
4067 self._extract_account_syncid(ytcfg, data),
4068 self._extract_visitor_data(data, ytcfg)),
4071 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4072 first_id = last_id = response = None
4073 for page_num in itertools.count(1):
4074 videos = list(self._playlist_entries(playlist))
4077 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4078 if start >= len(videos):
4080 for video in videos[start:]:
4081 if video['id'] == first_id:
4082 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4085 first_id = first_id or videos[0]['id']
4086 last_id = videos[-1]['id']
4087 watch_endpoint = try_get(
4088 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4089 headers = self.generate_api_headers(
4090 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4091 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4093 'playlistId': playlist_id,
4094 'videoId': watch_endpoint.get('videoId') or last_id,
4095 'index': watch_endpoint.get('index') or len(videos),
4096 'params': watch_endpoint.get('params') or 'OAE%3D'
4098 response = self._extract_response(
4099 item_id='%s page %d' % (playlist_id, page_num),
4100 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4101 check_get_keys='contents'
4104 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4106 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4107 title = playlist.get('title') or try_get(
4108 data, lambda x: x['titleText']['simpleText'], compat_str)
4109 playlist_id = playlist.get('playlistId') or item_id
4111 # Delegating everything except mix playlists to regular tab-based playlist URL
4112 playlist_url = urljoin(url, try_get(
4113 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4115 if playlist_url and playlist_url != url:
4116 return self.url_result(
4117 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4120 return self.playlist_result(
4121 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4122 playlist_id=playlist_id, playlist_title=title)
4124 def _extract_availability(self, data):
4126 Gets the availability of a given playlist/tab.
4127 Note: Unless YouTube tells us explicitly, we do not assume it is public
4128 @param data: response
4130 is_private = is_unlisted = None
4131 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4132 badge_labels = self._extract_badges(renderer)
4134 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4135 privacy_dropdown_entries = try_get(
4136 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4137 for renderer_dict in privacy_dropdown_entries:
4138 is_selected = try_get(
4139 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4142 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4144 badge_labels.add(label.lower())
4147 for badge_label in badge_labels:
4148 if badge_label == 'unlisted':
4150 elif badge_label == 'private':
4152 elif badge_label == 'public':
4153 is_unlisted = is_private = False
4154 return self._availability(is_private, False, False, False, is_unlisted)
4157 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4158 sidebar_renderer = try_get(
4159 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4160 for item in sidebar_renderer:
4161 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4165 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4167 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4169 browse_id = params = None
4170 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4173 menu_renderer = try_get(
4174 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4175 for menu_item in menu_renderer:
4176 if not isinstance(menu_item, dict):
4178 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4180 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4181 if not text or text.lower() != 'show unavailable videos':
4183 browse_endpoint = try_get(
4184 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4185 browse_id = browse_endpoint.get('browseId')
4186 params = browse_endpoint.get('params')
4189 headers = self.generate_api_headers(
4190 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4191 visitor_data=self._extract_visitor_data(data, ytcfg))
4193 'params': params or 'wgYCCAA=',
4194 'browseId': browse_id or 'VL%s' % item_id
4196 return self._extract_response(
4197 item_id=item_id, headers=headers, query=query,
4198 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4199 note='Downloading API JSON with unavailable videos')
4201 def _extract_webpage(self, url, item_id, fatal=True):
4202 retries = self.get_param('extractor_retries', 3)
4204 webpage = data = last_error = None
4205 while count < retries:
4207 # Sometimes youtube returns a webpage with incomplete ytInitialData
4208 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4210 self.report_warning('%s. Retrying ...' % last_error)
4212 webpage = self._download_webpage(
4214 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4215 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4216 except ExtractorError as e:
4217 if isinstance(e.cause, network_exceptions):
4218 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4219 last_error = error_to_compat_str(e.cause or e.msg)
4224 self.report_warning(error_to_compat_str(e))
4228 self._extract_and_report_alerts(data)
4229 except ExtractorError as e:
4232 self.report_warning(error_to_compat_str(e))
4235 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4238 last_error = 'Incomplete yt initial data received'
4239 if count >= retries:
4241 raise ExtractorError(last_error)
4242 self.report_warning(last_error)
4245 return webpage, data
4247 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4249 if 'webpage' not in self._configuration_arg('skip'):
4250 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4251 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4252 # Reject webpage data if redirected to home page without explicitly requesting
4253 selected_tab = self._extract_selected_tab(traverse_obj(
4254 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4255 if (url != 'https://www.youtube.com/feed/recommended'
4256 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4257 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4258 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4260 raise ExtractorError(msg, expected=True)
4261 self.report_warning(msg, only_once=True)
4263 if not ytcfg and self.is_authenticated:
4264 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4265 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4266 raise ExtractorError(
4267 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4268 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4270 self.report_warning(msg, only_once=True)
4271 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4274 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4275 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4276 resolve_response = self._extract_response(
4277 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4278 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4279 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4280 for ep_key, ep in endpoints.items():
4281 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4283 return self._extract_response(
4284 item_id=item_id, query=params, ep=ep, headers=headers,
4285 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4286 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4287 err_note = 'Failed to resolve url (does the playlist exist?)'
4289 raise ExtractorError(err_note, expected=True)
4290 self.report_warning(err_note, item_id)
4292 _SEARCH_PARAMS = None
4294 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4295 data = {'query': query}
4296 if params is NO_DEFAULT:
4297 params = self._SEARCH_PARAMS
4299 data['params'] = params
4302 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4303 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4305 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4306 ('continuationContents', ),
4308 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4310 continuation_list = [None]
4311 for page_num in itertools.count(1):
4312 data.update(continuation_list[0] or {})
4313 search = self._extract_response(
4314 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4315 default_client=default_client, check_get_keys=check_get_keys)
4316 slr_contents = traverse_obj(search, *content_keys)
4317 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4318 if not continuation_list[0]:
4322 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4323 IE_DESC = 'YouTube Tabs'
4324 _VALID_URL = r'''(?x
:
4328 youtube(?
:kids
)?\
.com|
4332 (?P
<channel_type
>channel|c|user|browse
)/|
4335 (?
:playlist|watch
)\?.*?
\blist
=
4337 (?
!(?
:%(reserved_names)s)\b) # Direct URLs
4341 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4342 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4344 IE_NAME = 'youtube:tab'
4347 'note': 'playlists, multipage',
4348 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4349 'playlist_mincount': 94,
4351 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4352 'title': 'Igor Kleiner - Playlists',
4353 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4354 'uploader': 'Igor Kleiner',
4355 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4356 'channel': 'Igor Kleiner',
4357 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4358 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4359 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4360 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4361 'channel_follower_count': int
4364 'note': 'playlists, multipage, different order',
4365 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4366 'playlist_mincount': 94,
4368 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4369 'title': 'Igor Kleiner - Playlists',
4370 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4371 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4372 'uploader': 'Igor Kleiner',
4373 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4374 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4375 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4376 'channel': 'Igor Kleiner',
4377 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4378 'channel_follower_count': int
4381 'note': 'playlists, series',
4382 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4383 'playlist_mincount': 5,
4385 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4386 'title': '3Blue1Brown - Playlists',
4387 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4388 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4389 'uploader': '3Blue1Brown',
4390 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4391 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4392 'channel': '3Blue1Brown',
4393 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4394 'tags': ['Mathematics'],
4395 'channel_follower_count': int
4398 'note': 'playlists, singlepage',
4399 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4400 'playlist_mincount': 4,
4402 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4403 'title': 'ThirstForScience - Playlists',
4404 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4405 'uploader': 'ThirstForScience',
4406 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4407 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4408 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4409 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4411 'channel': 'ThirstForScience',
4412 'channel_follower_count': int
4415 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4416 'only_matching': True,
4418 'note': 'basic, single video playlist',
4419 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4421 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4422 'uploader': 'Sergey M.',
4423 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4424 'title': 'youtube-dl public playlist',
4428 'modified_date': '20201130',
4429 'channel': 'Sergey M.',
4430 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4431 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4432 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4434 'playlist_count': 1,
4436 'note': 'empty playlist',
4437 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4439 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4440 'uploader': 'Sergey M.',
4441 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4442 'title': 'youtube-dl empty playlist',
4444 'channel': 'Sergey M.',
4446 'modified_date': '20160902',
4447 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4448 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4449 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4451 'playlist_count': 0,
4454 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4456 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4457 'title': 'lex will - Home',
4458 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4459 'uploader': 'lex will',
4460 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4461 'channel': 'lex will',
4462 'tags': ['bible', 'history', 'prophesy'],
4463 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4464 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4465 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4466 'channel_follower_count': int
4468 'playlist_mincount': 2,
4470 'note': 'Videos tab',
4471 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4473 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4474 'title': 'lex will - Videos',
4475 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4476 'uploader': 'lex will',
4477 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4478 'tags': ['bible', 'history', 'prophesy'],
4479 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4480 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4481 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4482 'channel': 'lex will',
4483 'channel_follower_count': int
4485 'playlist_mincount': 975,
4487 'note': 'Videos tab, sorted by popular',
4488 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4490 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4491 'title': 'lex will - Videos',
4492 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4493 'uploader': 'lex will',
4494 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4495 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4496 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4497 'channel': 'lex will',
4498 'tags': ['bible', 'history', 'prophesy'],
4499 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4500 'channel_follower_count': int
4502 'playlist_mincount': 199,
4504 'note': 'Playlists tab',
4505 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4507 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4508 'title': 'lex will - Playlists',
4509 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4510 'uploader': 'lex will',
4511 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4512 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4513 'channel': 'lex will',
4514 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4515 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4516 'tags': ['bible', 'history', 'prophesy'],
4517 'channel_follower_count': int
4519 'playlist_mincount': 17,
4521 'note': 'Community tab',
4522 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4524 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4525 'title': 'lex will - Community',
4526 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4527 'uploader': 'lex will',
4528 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4529 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4530 'channel': 'lex will',
4531 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4532 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4533 'tags': ['bible', 'history', 'prophesy'],
4534 'channel_follower_count': int
4536 'playlist_mincount': 18,
4538 'note': 'Channels tab',
4539 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4541 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4542 'title': 'lex will - Channels',
4543 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4544 'uploader': 'lex will',
4545 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4546 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4547 'channel': 'lex will',
4548 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4549 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4550 'tags': ['bible', 'history', 'prophesy'],
4551 'channel_follower_count': int
4553 'playlist_mincount': 12,
4555 'note': 'Search tab',
4556 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4557 'playlist_mincount': 40,
4559 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4560 'title': '3Blue1Brown - Search - linear algebra',
4561 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4562 'uploader': '3Blue1Brown',
4563 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4564 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4565 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4566 'tags': ['Mathematics'],
4567 'channel': '3Blue1Brown',
4568 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4569 'channel_follower_count': int
4572 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4573 'only_matching': True,
4575 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4576 'only_matching': True,
4578 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4579 'only_matching': True,
4581 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4582 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4584 'title': '29C3: Not my department',
4585 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4586 'uploader': 'Christiaan008',
4587 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4588 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4590 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4592 'modified_date': '20150605',
4593 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4594 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4595 'channel': 'Christiaan008',
4597 'playlist_count': 96,
4599 'note': 'Large playlist',
4600 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4602 'title': 'Uploads from Cauchemar',
4603 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4604 'uploader': 'Cauchemar',
4605 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4606 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4608 'modified_date': r're:\d{8}',
4609 'channel': 'Cauchemar',
4610 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4613 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4615 'playlist_mincount': 1123,
4616 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4618 'note': 'even larger playlist, 8832 videos',
4619 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4620 'only_matching': True,
4622 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4623 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4625 'title': 'Uploads from Interstellar Movie',
4626 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4627 'uploader': 'Interstellar Movie',
4628 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4629 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4632 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4633 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4634 'channel': 'Interstellar Movie',
4636 'modified_date': r're:\d{8}',
4638 'playlist_mincount': 21,
4640 'note': 'Playlist with "show unavailable videos" button',
4641 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4643 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4644 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4645 'uploader': 'Phim Siêu Nhân Nhật Bản',
4646 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4648 'channel': 'Phim Siêu Nhân Nhật Bản',
4650 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4652 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4653 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4654 'modified_date': r're:\d{8}',
4656 'playlist_mincount': 200,
4657 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4659 'note': 'Playlist with unavailable videos in page 7',
4660 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4662 'title': 'Uploads from BlankTV',
4663 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4664 'uploader': 'BlankTV',
4665 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4666 'channel': 'BlankTV',
4667 'channel_url': 'https://www.youtube.com/c/blanktv',
4668 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4671 'uploader_url': 'https://www.youtube.com/c/blanktv',
4672 'modified_date': r're:\d{8}',
4675 'playlist_mincount': 1000,
4676 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4678 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4679 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4681 'title': 'Data Analysis with Dr Mike Pound',
4682 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4683 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4684 'uploader': 'Computerphile',
4685 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4686 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4689 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4690 'channel_url': 'https://www.youtube.com/user/Computerphile',
4691 'channel': 'Computerphile',
4693 'playlist_mincount': 11,
4695 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4696 'only_matching': True,
4698 'note': 'Playlist URL that does not actually serve a playlist',
4699 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4701 'id': 'FqZTN594JQw',
4703 'title': "Smiley's People 01 detective, Adventure Series, Action",
4704 'uploader': 'STREEM',
4705 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4706 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4707 'upload_date': '20150526',
4708 'license': 'Standard YouTube License',
4709 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4710 'categories': ['People & Blogs'],
4716 'skip_download': True,
4718 'skip': 'This video is not available.',
4719 'add_ie': [YoutubeIE.ie_key()],
4721 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4722 'only_matching': True,
4724 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4725 'only_matching': True,
4727 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4729 'id': 'GgL890LIznQ', # This will keep changing
4732 'uploader': 'Sky News',
4733 'uploader_id': 'skynews',
4734 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4735 'upload_date': r're:\d{8}',
4737 'categories': ['News & Politics'],
4740 'release_timestamp': 1642502819,
4741 'channel': 'Sky News',
4742 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4745 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4746 'playable_in_embed': True,
4747 'release_date': '20220118',
4748 'availability': 'public',
4749 'live_status': 'is_live',
4750 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4751 'channel_follower_count': int
4754 'skip_download': True,
4756 'expected_warnings': ['Ignoring subtitle tracks found in '],
4758 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4760 'id': 'a48o2S1cPoo',
4762 'title': 'The Young Turks - Live Main Show',
4763 'uploader': 'The Young Turks',
4764 'uploader_id': 'TheYoungTurks',
4765 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4766 'upload_date': '20150715',
4767 'license': 'Standard YouTube License',
4768 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4769 'categories': ['News & Politics'],
4770 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4774 'skip_download': True,
4776 'only_matching': True,
4778 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4779 'only_matching': True,
4781 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4782 'only_matching': True,
4784 'note': 'A channel that is not live. Should raise error',
4785 'url': 'https://www.youtube.com/user/numberphile/live',
4786 'only_matching': True,
4788 'url': 'https://www.youtube.com/feed/trending',
4789 'only_matching': True,
4791 'url': 'https://www.youtube.com/feed/library',
4792 'only_matching': True,
4794 'url': 'https://www.youtube.com/feed/history',
4795 'only_matching': True,
4797 'url': 'https://www.youtube.com/feed/subscriptions',
4798 'only_matching': True,
4800 'url': 'https://www.youtube.com/feed/watch_later',
4801 'only_matching': True,
4803 'note': 'Recommended - redirects to home page.',
4804 'url': 'https://www.youtube.com/feed/recommended',
4805 'only_matching': True,
4807 'note': 'inline playlist with not always working continuations',
4808 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4809 'only_matching': True,
4811 'url': 'https://www.youtube.com/course',
4812 'only_matching': True,
4814 'url': 'https://www.youtube.com/zsecurity',
4815 'only_matching': True,
4817 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4818 'only_matching': True,
4820 'url': 'https://www.youtube.com/TheYoungTurks/live',
4821 'only_matching': True,
4823 'url': 'https://www.youtube.com/hashtag/cctv9',
4829 'playlist_mincount': 350,
4831 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4832 'only_matching': True,
4834 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4835 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4836 'only_matching': True
4838 'note': '/browse/ should redirect to /channel/',
4839 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4840 'only_matching': True
4842 'note': 'VLPL, should redirect to playlist?list=PL...',
4843 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4845 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4846 'uploader': 'NoCopyrightSounds',
4847 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4848 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4849 'title': 'NCS Releases',
4850 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4851 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4852 'modified_date': r're:\d{8}',
4854 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4856 'channel': 'NoCopyrightSounds',
4858 'playlist_mincount': 166,
4859 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4861 'note': 'Topic, should redirect to playlist?list=UU...',
4862 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4864 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4865 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4866 'title': 'Uploads from Royalty Free Music - Topic',
4867 'uploader': 'Royalty Free Music - Topic',
4869 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4870 'channel': 'Royalty Free Music - Topic',
4872 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4873 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4874 'modified_date': r're:\d{8}',
4875 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4878 'expected_warnings': [
4879 'The URL does not have a videos tab',
4880 r'[Uu]navailable videos (are|will be) hidden',
4882 'playlist_mincount': 101,
4884 'note': 'Topic without a UU playlist',
4885 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4887 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4888 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
4891 'expected_warnings': [
4892 'the playlist redirect gave error',
4894 'playlist_mincount': 9,
4896 'note': 'Youtube music Album',
4897 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4899 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4900 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
4904 'availability': 'unlisted',
4905 'modified_date': r're:\d{8}',
4907 'playlist_count': 50,
4909 'note': 'unlisted single video playlist',
4910 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4912 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4913 'uploader': 'colethedj',
4914 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4915 'title': 'yt-dlp unlisted playlist test',
4916 'availability': 'unlisted',
4918 'modified_date': '20211208',
4919 'channel': 'colethedj',
4922 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4923 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4924 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4926 'playlist_count': 1,
4928 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4929 'url': 'https://www.youtube.com/feed/recommended',
4931 'id': 'recommended',
4932 'title': 'recommended',
4935 'playlist_mincount': 50,
4937 'skip_download': True,
4938 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4941 'note': 'API Fallback: /videos tab, sorted by oldest first',
4942 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4944 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4945 'title': 'Cody\'sLab - Videos',
4946 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4947 'uploader': 'Cody\'sLab',
4948 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4949 'channel': 'Cody\'sLab',
4950 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4952 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4953 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4954 'channel_follower_count': int
4956 'playlist_mincount': 650,
4958 'skip_download': True,
4959 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4962 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4963 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4965 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4966 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4967 'title': 'Uploads from Royalty Free Music - Topic',
4968 'uploader': 'Royalty Free Music - Topic',
4969 'modified_date': r're:\d{8}',
4970 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4972 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4974 'channel': 'Royalty Free Music - Topic',
4976 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4978 'expected_warnings': [
4979 'does not have a videos tab',
4980 r'[Uu]navailable videos (are|will be) hidden',
4982 'playlist_mincount': 101,
4984 'skip_download': True,
4985 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4988 'note': 'non-standard redirect to regional channel',
4989 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
4990 'only_matching': True
4994 def suitable(cls, url):
4995 return False if YoutubeIE.suitable(url) else super(
4996 YoutubeTabIE, cls).suitable(url)
4998 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5000 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5001 def _real_extract(self, url, smuggled_data):
5002 item_id = self._match_id(url)
5003 url = compat_urlparse.urlunparse(
5004 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
5005 compat_opts = self.get_param('compat_opts', [])
5008 mobj = self._URL_RE.match(url).groupdict()
5009 mobj.update((k, '') for k, v in mobj.items() if v is None)
5012 mobj, redirect_warning = get_mobj(url), None
5013 # Youtube returns incomplete data if tabname is not lower case
5014 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5016 if smuggled_data.get('is_music_url'):
5017 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5018 item_id = item_id[2:]
5019 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5020 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5021 mdata = self._extract_tab_endpoint(
5022 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5023 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5024 get_all=False, expected_type=compat_str)
5026 raise ExtractorError('Failed to resolve album to playlist')
5027 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5028 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5029 pre = f'https://www.youtube.com/channel/{item_id}'
5031 original_tab_name = tab
5032 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5033 # Home URLs should redirect to /videos/
5034 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5035 'To download only the videos in the home page, add a "/featured" to the URL')
5038 url = ''.join((pre, tab, post))
5039 mobj = get_mobj(url)
5041 # Handle both video/playlist URLs
5043 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
5045 if not video_id and mobj['not_channel'].startswith('watch'):
5047 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5048 raise ExtractorError('Unable to recognize tab page')
5049 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5050 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5051 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5052 mobj = get_mobj(url)
5054 if video_id and playlist_id:
5055 if self.get_param('noplaylist'):
5056 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5057 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5058 ie=YoutubeIE.ie_key(), video_id=video_id)
5059 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5061 data, ytcfg = self._extract_data(url, item_id)
5063 # YouTube may provide a non-standard redirect to the regional channel
5064 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5065 redirect_url = traverse_obj(
5066 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5067 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5068 redirect_url = ''.join((
5069 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5070 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5071 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5073 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5075 selected_tab = self._extract_selected_tab(tabs)
5076 selected_tab_name = selected_tab.get('title', '').lower()
5077 if selected_tab_name == 'home':
5078 selected_tab_name = 'featured'
5079 requested_tab_name = mobj['tab'][1:]
5080 if 'no-youtube-channel-redirect' not in compat_opts:
5081 if requested_tab_name == 'live':
5082 # Live tab should have redirected to the video
5083 raise ExtractorError('The channel is not currently live', expected=True)
5084 if requested_tab_name not in ('', selected_tab_name):
5085 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5086 if not original_tab_name:
5087 if item_id[:2] == 'UC':
5088 # Topic channels don't have /videos. Use the equivalent playlist instead
5089 pl_id = f'UU{item_id[2:]}'
5090 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5092 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5093 except ExtractorError:
5094 redirect_warning += ' and the playlist redirect gave error'
5096 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5097 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5098 if selected_tab_name and selected_tab_name != requested_tab_name:
5099 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5101 raise ExtractorError(redirect_warning, expected=True)
5103 if redirect_warning:
5104 self.to_screen(redirect_warning)
5105 self.write_debug(f'Final URL: {url}')
5107 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5108 if 'no-youtube-unavailable-videos' not in compat_opts:
5109 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5110 self._extract_and_report_alerts(data, only_once=True)
5111 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5113 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5115 playlist = traverse_obj(
5116 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5118 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5120 video_id = traverse_obj(
5121 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5123 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5124 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5125 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5126 ie=YoutubeIE.ie_key(), video_id=video_id)
5128 raise ExtractorError('Unable to recognize tab page')
5131 class YoutubePlaylistIE(InfoExtractor):
5132 IE_DESC = 'YouTube playlists'
5133 _VALID_URL = r'''(?x
)(?
:
5138 youtube(?
:kids
)?\
.com|
5143 (?P
<id>%(playlist_id)s)
5145 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5146 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5148 IE_NAME = 'youtube:playlist'
5150 'note': 'issue #673',
5151 'url': 'PLBB231211A4F62143',
5153 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5154 'id': 'PLBB231211A4F62143',
5155 'uploader': 'Wickman',
5156 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5157 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5159 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5160 'modified_date': r're:\d{8}',
5161 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5162 'channel': 'Wickman',
5164 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5166 'playlist_mincount': 29,
5168 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5170 'title': 'YDL_safe_search',
5171 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5173 'playlist_count': 2,
5174 'skip': 'This playlist is private',
5177 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5178 'playlist_count': 4,
5181 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5182 'uploader': 'milan',
5183 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5185 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5187 'modified_date': '20140919',
5190 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5191 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5193 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5195 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5196 'playlist_mincount': 654,
5198 'title': '2018 Chinese New Singles (11/6 updated)',
5199 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5201 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5202 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5205 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5207 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5208 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5209 'modified_date': r're:\d{8}',
5211 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5213 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5214 'only_matching': True,
5216 # music album playlist
5217 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5218 'only_matching': True,
5222 def suitable(cls, url):
5223 if YoutubeTabIE.suitable(url):
5225 from ..utils import parse_qs
5227 if qs.get('v', [None])[0]:
5229 return super(YoutubePlaylistIE, cls).suitable(url)
5231 def _real_extract(self, url):
5232 playlist_id = self._match_id(url)
5233 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5234 url = update_url_query(
5235 'https://www.youtube.com/playlist',
5236 parse_qs(url) or {'list': playlist_id})
5238 url = smuggle_url(url, {'is_music_url': True})
5239 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5242 class YoutubeYtBeIE(InfoExtractor):
5243 IE_DESC = 'youtu.be'
5244 _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}
5246 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5248 'id': 'yeWKywCrFtk',
5250 'title': 'Small Scale Baler and Braiding Rugs',
5251 'uploader': 'Backus-Page House Museum',
5252 'uploader_id': 'backuspagemuseum',
5253 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5254 'upload_date': '20161008',
5255 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5256 'categories': ['Nonprofits & Activism'],
5260 'playable_in_embed': True,
5261 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5262 'channel': 'Backus-Page House Museum',
5263 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5264 'live_status': 'not_live',
5266 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5267 'availability': 'public',
5272 'skip_download': True,
5275 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5276 'only_matching': True,
5279 def _real_extract(self, url):
5280 mobj = self._match_valid_url(url)
5281 video_id = mobj.group('id')
5282 playlist_id = mobj.group('playlist_id')
5283 return self.url_result(
5284 update_url_query('https://www.youtube.com/watch', {
5286 'list': playlist_id,
5287 'feature': 'youtu.be',
5288 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5291 class YoutubeLivestreamEmbedIE(InfoExtractor):
5292 IE_DESC = 'YouTube livestream embeds'
5293 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5295 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5296 'only_matching': True,
5299 def _real_extract(self, url):
5300 channel_id = self._match_id(url)
5301 return self.url_result(
5302 f'https://www.youtube.com/channel/{channel_id}/live',
5303 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5306 class YoutubeYtUserIE(InfoExtractor):
5307 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5308 IE_NAME = 'youtube:user'
5309 _VALID_URL = r'ytuser:(?P<id>.+)'
5311 'url': 'ytuser:phihag',
5312 'only_matching': True,
5315 def _real_extract(self, url):
5316 user_id = self._match_id(url)
5317 return self.url_result(
5318 'https://www.youtube.com/user/%s/videos' % user_id,
5319 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5322 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5323 IE_NAME = 'youtube:favorites'
5324 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5325 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5326 _LOGIN_REQUIRED = True
5329 'only_matching': True,
5331 'url': ':ytfavorites',
5332 'only_matching': True,
5335 def _real_extract(self, url):
5336 return self.url_result(
5337 'https://www.youtube.com/playlist?list=LL',
5338 ie=YoutubeTabIE.ie_key())
5341 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5342 IE_DESC = 'YouTube search'
5343 IE_NAME = 'youtube:search'
5344 _SEARCH_KEY = 'ytsearch'
5345 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5347 'url': 'ytsearch5:youtube-dl test video',
5348 'playlist_count': 5,
5350 'id': 'youtube-dl test video',
5351 'title': 'youtube-dl test video',
5356 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5357 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5358 _SEARCH_KEY = 'ytsearchdate'
5359 IE_DESC = 'YouTube search, newest videos first'
5360 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5362 'url': 'ytsearchdate5:youtube-dl test video',
5363 'playlist_count': 5,
5365 'id': 'youtube-dl test video',
5366 'title': 'youtube-dl test video',
5371 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5372 IE_DESC = 'YouTube search URLs with sorting and filter support'
5373 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5374 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5376 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5377 'playlist_mincount': 5,
5379 'id': 'youtube-dl test video',
5380 'title': 'youtube-dl test video',
5383 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5384 'playlist_mincount': 5,
5391 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5392 'only_matching': True,
5395 def _real_extract(self, url):
5397 query = (qs.get('search_query') or qs.get('q'))[0]
5398 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5401 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5402 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5403 IE_NAME = 'youtube:music:search_url'
5404 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5406 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5407 'playlist_count': 16,
5409 'id': 'royalty free music',
5410 'title': 'royalty free music',
5413 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5414 'playlist_mincount': 30,
5416 'id': 'royalty free music - songs',
5417 'title': 'royalty free music - songs',
5419 'params': {'extract_flat': 'in_playlist'}
5421 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5422 'playlist_mincount': 30,
5424 'id': 'royalty free music - community playlists',
5425 'title': 'royalty free music - community playlists',
5427 'params': {'extract_flat': 'in_playlist'}
5431 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5432 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5433 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5434 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5435 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5436 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5439 def _real_extract(self, url):
5441 query = (qs.get('search_query') or qs.get('q'))[0]
5442 params = qs.get('sp', (None,))[0]
5444 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5446 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5447 params = self._SECTIONS.get(section)
5450 title = join_nonempty(query, section, delim=' - ')
5451 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5454 class YoutubeFeedsInfoExtractor(InfoExtractor):
5456 Base class for feed extractors
5457 Subclasses must define the _FEED_NAME property.
5459 _LOGIN_REQUIRED = True
5464 return 'youtube:%s' % self._FEED_NAME
5466 def _real_extract(self, url):
5467 return self.url_result(
5468 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5471 class YoutubeWatchLaterIE(InfoExtractor):
5472 IE_NAME = 'youtube:watchlater'
5473 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5474 _VALID_URL = r':ytwatchlater'
5476 'url': ':ytwatchlater',
5477 'only_matching': True,
5480 def _real_extract(self, url):
5481 return self.url_result(
5482 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5485 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5486 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5487 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5488 _FEED_NAME = 'recommended'
5489 _LOGIN_REQUIRED = False
5492 'only_matching': True,
5494 'url': ':ytrecommended',
5495 'only_matching': True,
5497 'url': 'https://youtube.com',
5498 'only_matching': True,
5502 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5503 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5504 _VALID_URL = r':ytsub(?:scription)?s?'
5505 _FEED_NAME = 'subscriptions'
5508 'only_matching': True,
5510 'url': ':ytsubscriptions',
5511 'only_matching': True,
5515 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5516 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5517 _VALID_URL = r':ythis(?:tory)?'
5518 _FEED_NAME = 'history'
5520 'url': ':ythistory',
5521 'only_matching': True,
5525 class YoutubeTruncatedURLIE(InfoExtractor):
5526 IE_NAME = 'youtube:truncated_url'
5527 IE_DESC = False # Do not list
5528 _VALID_URL = r'''(?x
)
5530 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
5533 annotation_id
=annotation_
[^
&]+|
5539 attribution_link
\?a
=[^
&]+
5545 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5546 'only_matching': True,
5548 'url': 'https://www.youtube.com/watch?',
5549 'only_matching': True,
5551 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5552 'only_matching': True,
5554 'url': 'https://www.youtube.com/watch?feature=foo',
5555 'only_matching': True,
5557 'url': 'https://www.youtube.com/watch?hl=en-GB',
5558 'only_matching': True,
5560 'url': 'https://www.youtube.com/watch?t=2372',
5561 'only_matching': True,
5564 def _real_extract(self, url):
5565 raise ExtractorError(
5566 'Did you forget to quote the URL? Remember that & is a meta '
5567 'character in most shells, so you want to put the URL in quotes, '
5569 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5570 ' or simply youtube-dl BaW_jenozKc .',
5574 class YoutubeClipIE(InfoExtractor):
5575 IE_NAME = 'youtube:clip'
5576 IE_DESC = False # Do not list
5577 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5579 def _real_extract(self, url):
5580 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5581 return self.url_result(url, 'Generic')
5584 class YoutubeTruncatedIDIE(InfoExtractor):
5585 IE_NAME = 'youtube:truncated_id'
5586 IE_DESC = False # Do not list
5587 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5590 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5591 'only_matching': True,
5594 def _real_extract(self, url):
5595 video_id = self._match_id(url)
5596 raise ExtractorError(
5597 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),