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')
239 ytcfg
['priority'] = 10 * priority(client
.split('_', 1)[0])
241 if client
in base_clients
:
242 INNERTUBE_CLIENTS
[f
'{client}_agegate'] = agegate_ytcfg
= copy
.deepcopy(ytcfg
)
243 agegate_ytcfg
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
244 agegate_ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
245 agegate_ytcfg
['priority'] -= 1
246 elif client
.endswith('_embedded'):
247 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
248 ytcfg
['priority'] -= 2
250 ytcfg
['priority'] -= 3
253 build_innertube_clients()
256 class YoutubeBaseInfoExtractor(InfoExtractor
):
257 """Provide base functions for Youtube extractors"""
260 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
261 r
'shorts|movies|results|shared|hashtag|trending|explore|feed|feeds|'
262 r
'browse|oembed|get_video_info|iframe_api|s/player|'
263 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
265 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
267 _NETRC_MACHINE
= 'youtube'
269 # If True it will raise an error if no login info is provided
270 _LOGIN_REQUIRED
= False
273 # invidious-redirect websites
274 r
'(?:www\.)?redirect\.invidious\.io',
275 r
'(?:(?:www|dev)\.)?invidio\.us',
276 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
277 r
'(?:www\.)?invidious\.pussthecat\.org',
278 r
'(?:www\.)?invidious\.zee\.li',
279 r
'(?:www\.)?invidious\.ethibox\.fr',
280 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
281 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
282 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
283 # youtube-dl invidious instances list
284 r
'(?:(?:www|no)\.)?invidiou\.sh',
285 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
286 r
'(?:www\.)?invidious\.kabi\.tk',
287 r
'(?:www\.)?invidious\.mastodon\.host',
288 r
'(?:www\.)?invidious\.zapashcanon\.fr',
289 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
290 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
291 r
'(?:www\.)?invidious\.himiko\.cloud',
292 r
'(?:www\.)?invidious\.reallyancient\.tech',
293 r
'(?:www\.)?invidious\.tube',
294 r
'(?:www\.)?invidiou\.site',
295 r
'(?:www\.)?invidious\.site',
296 r
'(?:www\.)?invidious\.xyz',
297 r
'(?:www\.)?invidious\.nixnet\.xyz',
298 r
'(?:www\.)?invidious\.048596\.xyz',
299 r
'(?:www\.)?invidious\.drycat\.fr',
300 r
'(?:www\.)?inv\.skyn3t\.in',
301 r
'(?:www\.)?tube\.poal\.co',
302 r
'(?:www\.)?tube\.connect\.cafe',
303 r
'(?:www\.)?vid\.wxzm\.sx',
304 r
'(?:www\.)?vid\.mint\.lgbt',
305 r
'(?:www\.)?vid\.puffyan\.us',
306 r
'(?:www\.)?yewtu\.be',
307 r
'(?:www\.)?yt\.elukerio\.org',
308 r
'(?:www\.)?yt\.lelux\.fi',
309 r
'(?:www\.)?invidious\.ggc-project\.de',
310 r
'(?:www\.)?yt\.maisputain\.ovh',
311 r
'(?:www\.)?ytprivate\.com',
312 r
'(?:www\.)?invidious\.13ad\.de',
313 r
'(?:www\.)?invidious\.toot\.koeln',
314 r
'(?:www\.)?invidious\.fdn\.fr',
315 r
'(?:www\.)?watch\.nettohikari\.com',
316 r
'(?:www\.)?invidious\.namazso\.eu',
317 r
'(?:www\.)?invidious\.silkky\.cloud',
318 r
'(?:www\.)?invidious\.exonip\.de',
319 r
'(?:www\.)?invidious\.riverside\.rocks',
320 r
'(?:www\.)?invidious\.blamefran\.net',
321 r
'(?:www\.)?invidious\.moomoo\.de',
322 r
'(?:www\.)?ytb\.trom\.tf',
323 r
'(?:www\.)?yt\.cyberhost\.uk',
324 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
325 r
'(?:www\.)?qklhadlycap4cnod\.onion',
326 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
327 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
328 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
329 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
330 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
331 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
332 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
333 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
334 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
335 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
340 Attempt to log in to YouTube.
341 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
344 if (self
._LOGIN
_REQUIRED
345 and self
.get_param('cookiefile') is None
346 and self
.get_param('cookiesfrombrowser') is None):
347 self
.raise_login_required(
348 'Login details are needed to download this content', method
='cookies')
349 username
, password
= self
._get
_login
_info
()
351 self
.report_warning(f
'Cannot login to YouTube using username and password. {self._LOGIN_HINTS["cookies"]}')
353 def _initialize_consent(self
):
354 cookies
= self
._get
_cookies
('https://www.youtube.com/')
355 if cookies
.get('__Secure-3PSID'):
358 consent
= cookies
.get('CONSENT')
360 if 'YES' in consent
.value
:
362 consent_id
= self
._search
_regex
(
363 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
365 consent_id
= random
.randint(100, 999)
366 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
368 def _initialize_pref(self
):
369 cookies
= self
._get
_cookies
('https://www.youtube.com/')
370 pref_cookie
= cookies
.get('PREF')
374 pref
= dict(compat_urlparse
.parse_qsl(pref_cookie
.value
))
376 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
377 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
378 self
._set
_cookie
('.youtube.com', name
='PREF', value
=compat_urllib_parse_urlencode(pref
))
380 def _real_initialize(self
):
381 self
._initialize
_pref
()
382 self
._initialize
_consent
()
385 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
386 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
387 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
389 def _get_default_ytcfg(self, client='web'):
390 return copy.deepcopy(INNERTUBE_CLIENTS[client])
392 def _get_innertube_host(self, client='web'):
393 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
395 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
396 # try_get but with fallback to default ytcfg client values when present
397 _func = lambda y: try_get(y, getter, expected_type)
398 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
400 def _extract_client_name(self, ytcfg, default_client='web'):
401 return self._ytcfg_get_safe(
402 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
403 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
405 def _extract_client_version(self, ytcfg, default_client='web'):
406 return self._ytcfg_get_safe(
407 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
408 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
410 def _extract_api_key(self, ytcfg=None, default_client='web'):
411 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
413 def _extract_context(self, ytcfg=None, default_client='web'):
415 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
416 # Enforce language and tz for extraction
417 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
418 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
423 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
424 time_now = round(time.time())
425 if self._SAPISID is None:
426 yt_cookies = self._get_cookies('https://www.youtube.com')
427 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
428 # See: https://github.com/yt-dlp/yt-dlp/issues/393
429 sapisid_cookie = dict_get(
430 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
431 if sapisid_cookie and sapisid_cookie.value:
432 self._SAPISID = sapisid_cookie.value
433 self.write_debug('Extracted SAPISID cookie')
434 # SAPISID cookie is required if not already present
435 if not yt_cookies.get('SAPISID'):
436 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
438 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
440 self._SAPISID = False
441 if not self._SAPISID:
443 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
444 sapisidhash = hashlib.sha1(
445 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
446 return f'SAPISIDHASH {time_now}_{sapisidhash}'
448 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
449 note='Downloading API JSON', errnote='Unable to download API page',
450 context=None, api_key=None, api_hostname=None, default_client='web'):
452 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
454 real_headers = self.generate_api_headers(default_client=default_client)
455 real_headers.update({'content-type': 'application/json'})
457 real_headers.update(headers)
458 return self._download_json(
459 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
460 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
461 data=json.dumps(data).encode('utf8'), headers=real_headers,
462 query={'key': api_key or self._extract_api_key()})
464 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
465 data = self._search_regex(
466 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
467 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
469 return self._parse_json(data, item_id, fatal=fatal)
472 def _extract_session_index(*data):
474 Index of current account in account list.
475 See: https://github.com/yt-dlp/yt-dlp/pull/519
478 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
479 if session_index is not None:
483 def _extract_identity_token(self, ytcfg=None, webpage=None):
485 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
489 return self._search_regex(
490 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
491 'identity token
', default=None, fatal=False)
494 def _extract_account_syncid(*args):
496 Extract syncId required to download private playlists of secondary channels
497 @params response and/or ytcfg
500 # ytcfg includes channel_syncid if on secondary channel
501 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
505 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
506 lambda x: x['DATASYNC_ID
']), compat_str) or '').split('||
')
507 if len(sync_ids) >= 2 and sync_ids[1]:
508 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
509 # and just "user_syncid||" for primary channel. We only want the channel_syncid
513 def _extract_visitor_data(*args):
515 Extracts visitorData from an API response or ytcfg
516 Appears to be used to track session state
519 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
523 def is_authenticated(self):
524 return bool(self._generate_sapisidhash_header())
526 def extract_ytcfg(self, video_id, webpage):
529 return self._parse_json(
531 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
532 default='{}'), video_id, fatal=False) or {}
534 def generate_api_headers(
535 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
536 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
538 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(default_client
))
540 'X-YouTube-Client-Name': compat_str(
541 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
542 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
544 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
545 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
546 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
548 if session_index
is None:
549 session_index
= self
._extract
_session
_index
(ytcfg
)
550 if account_syncid
or session_index
is not None:
551 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
553 auth
= self
._generate
_sapisidhash
_header
(origin
)
555 headers
['Authorization'] = auth
556 headers
['X-Origin'] = origin
557 return {h: v for h, v in headers.items() if v is not None}
560 def _build_api_continuation_query(continuation
, ctp
=None):
562 'continuation': continuation
564 # TODO: Inconsistency with clickTrackingParams.
565 # Currently we have a fixed ctp contained within context (from ytcfg)
566 # and a ctp in root query for continuation.
568 query
['clickTracking'] = {'clickTrackingParams': ctp}
572 def _extract_next_continuation_data(cls
, renderer
):
573 next_continuation
= try_get(
574 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
575 lambda x
: x
['continuation']['reloadContinuationData']), dict)
576 if not next_continuation
:
578 continuation
= next_continuation
.get('continuation')
581 ctp
= next_continuation
.get('clickTrackingParams')
582 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
585 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
586 if isinstance(continuation_ep
, dict):
587 continuation
= try_get(
588 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
591 ctp
= continuation_ep
.get('clickTrackingParams')
592 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
595 def _extract_continuation(cls
, renderer
):
596 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
597 if next_continuation
:
598 return next_continuation
601 for key
in ('contents', 'items'):
602 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
604 for content
in contents
:
605 if not isinstance(content
, dict):
607 continuation_ep
= try_get(
608 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
609 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
611 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
616 def _extract_alerts(cls
, data
):
617 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
618 if not isinstance(alert_dict
, dict):
620 for alert
in alert_dict
.values():
621 alert_type
= alert
.get('type')
624 message
= cls
._get
_text
(alert
, 'text')
626 yield alert_type
, message
628 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
631 for alert_type
, alert_message
in alerts
:
632 if alert_type
.lower() == 'error' and fatal
:
633 errors
.append([alert_type
, alert_message
])
635 warnings
.append([alert_type
, alert_message
])
637 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
638 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
), only_once
=only_once
)
640 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
642 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
643 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
645 def _extract_badges(self
, renderer
: dict):
647 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
648 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
650 badges
.add(label
.lower())
654 def _get_text(data
, *path_list
, max_runs
=None):
655 for path
in path_list
or [None]:
659 obj
= traverse_obj(data
, path
, default
=[])
660 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
663 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
666 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
667 if not runs
and isinstance(item
, list):
670 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
671 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
675 def _get_count(self
, data
, *path_list
):
676 count_text
= self
._get
_text
(data
, *path_list
) or ''
677 count
= parse_count(count_text
)
680 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
684 def _extract_thumbnails(data
, *path_list
):
686 Extract thumbnails from thumbnails dict
687 @param path_list: path list to level that contains 'thumbnails' key
690 for path
in path_list
or [()]:
691 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
692 thumbnail_url
= url_or_none(thumbnail
.get('url'))
693 if not thumbnail_url
:
695 # Sometimes youtube gives a wrong thumbnail URL. See:
696 # https://github.com/yt-dlp/yt-dlp/issues/233
697 # https://github.com/ytdl-org/youtube-dl/issues/28023
698 if 'maxresdefault' in thumbnail_url
:
699 thumbnail_url
= thumbnail_url
.split('?')[0]
701 'url': thumbnail_url
,
702 'height': int_or_none(thumbnail
.get('height')),
703 'width': int_or_none(thumbnail
.get('width')),
708 def extract_relative_time(relative_time_text
):
710 Extracts a relative time from string and converts to dt object
711 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
713 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
)
715 start
= mobj
.group('start')
717 return datetime_from_str(start
)
719 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
723 def _extract_time_text(self
, renderer
, *path_list
):
724 text
= self
._get
_text
(renderer
, *path_list
) or ''
725 dt
= self
.extract_relative_time(text
)
727 if isinstance(dt
, datetime
.datetime
):
728 timestamp
= calendar
.timegm(dt
.timetuple())
730 if timestamp
is None:
732 unified_timestamp(text
) or unified_timestamp(
734 (r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*on)?\s*(.+\d)', r
'\w+[\s,\.-]*\w+[\s,\.-]+20\d{2}'),
735 text
.lower(), 'time text', default
=None)))
737 if text
and timestamp
is None:
738 self
.report_warning('Cannot parse localized time text' + bug_reports_message(), only_once
=True)
739 return timestamp
, text
741 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
742 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
743 default_client
='web'):
747 retries
= self
.get_param('extractor_retries', 3)
748 if check_get_keys
is None:
750 while count
< retries
:
753 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
755 response
= self
._call
_api
(
756 ep
=ep
, fatal
=True, headers
=headers
,
757 video_id
=item_id
, query
=query
,
758 context
=self
._extract
_context
(ytcfg
, default_client
),
759 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
760 api_hostname
=api_hostname
, default_client
=default_client
,
761 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
762 except ExtractorError
as e
:
763 if isinstance(e
.cause
, network_exceptions
):
764 if isinstance(e
.cause
, compat_HTTPError
):
765 first_bytes
= e
.cause
.read(512)
766 if not is_html(first_bytes
):
769 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
770 lambda x
: x
['error']['message'], compat_str
)
772 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
773 # Downloading page may result in intermittent 5xx HTTP error
774 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
775 # We also want to catch all other network exceptions since errors in later pages can be troublesome
776 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
777 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
778 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
784 self
.report_warning(error_to_compat_str(e
))
789 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
790 except ExtractorError
as e
:
791 # YouTube servers may return errors we want to retry on in a 200 OK response
792 # See: https://github.com/yt-dlp/yt-dlp/issues/839
793 if 'unknown error' in e
.msg
.lower():
798 self
.report_warning(error_to_compat_str(e
))
800 if not check_get_keys
or dict_get(response
, check_get_keys
):
802 # Youtube sometimes sends incomplete data
803 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
804 last_error
= 'Incomplete data received'
807 raise ExtractorError(last_error
)
809 self
.report_warning(last_error
)
814 def is_music_url(url
):
815 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
817 def _extract_video(self
, renderer
):
818 video_id
= renderer
.get('videoId')
819 title
= self
._get
_text
(renderer
, 'title')
820 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
821 duration
= parse_duration(self
._get
_text
(
822 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
823 view_count
= self
._get
_count
(renderer
, 'viewCountText')
825 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
826 channel_id
= traverse_obj(
827 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'), expected_type
=str, get_all
=False)
828 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
829 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
830 overlay_style
= traverse_obj(
831 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'), get_all
=False, expected_type
=str)
832 badges
= self
._extract
_badges
(renderer
)
833 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
837 'ie_key': YoutubeIE
.ie_key(),
839 'url': f
'https://www.youtube.com/watch?v={video_id}',
841 'description': description
,
842 'duration': duration
,
843 'view_count': view_count
,
844 'uploader': uploader
,
845 'channel_id': channel_id
,
846 'thumbnails': thumbnails
,
847 # 'upload_date': strftime_or_none(timestamp, '%Y%m%d'),
848 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
849 else 'was_live' if 'streamed' in time_text
.lower()
850 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
852 'release_timestamp': scheduled_timestamp
,
853 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
857 class YoutubeIE(YoutubeBaseInfoExtractor
):
859 _VALID_URL
= r
"""(?x)^
861 (?:https?://|//) # http(s):// or protocol-independent URL
862 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
863 (?:www\.)?deturl\.com/www\.youtube\.com|
864 (?:www\.)?pwnyoutube\.com|
865 (?:www\.)?hooktube\.com|
866 (?:www\.)?yourepeat\.com|
869 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
870 (?:.*?\#/)? # handle anchor (#/) redirect urls
871 (?: # the various things that can precede the ID:
872 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
873 |(?: # or the v= param in all its forms
874 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
875 (?:\?|\#!?) # the params delimiter ? or # or #!
876 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
881 youtu\.be| # just youtu.be/xxxx
882 vid\.plus| # or vid.plus/xxxx
883 zwearz\.com/watch| # or zwearz.com/watch/xxxx
886 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
888 )? # all until now is optional -> you can pass the naked ID
889 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
890 (?(1).+)? # if we found the ID, everything can follow
892 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
895 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
896 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$',
897 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
900 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
901 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
902 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
903 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
904 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
905 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
906 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
907 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
908 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
909 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
910 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
911 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
912 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
913 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
914 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
915 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
916 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
917 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
921 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
922 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
923 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
924 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
925 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
926 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
927 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
929 # Apple HTTP Live Streaming
930 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
931 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
932 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
933 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
934 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
935 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
936 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
937 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
940 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
941 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
942 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
943 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
944 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
945 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
946 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
947 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
948 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
949 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
950 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
951 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
954 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
955 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
956 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
957 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
958 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
959 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
960 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
963 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
964 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
965 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
966 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
967 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
968 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
969 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
970 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
971 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
972 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
973 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
974 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
975 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
976 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
977 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
978 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
979 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
980 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
981 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
982 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
983 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
984 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
987 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
988 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
990 # Dash webm audio with opus inside
991 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
992 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
993 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
996 '_rtmp': {'protocol': 'rtmp'}
,
998 # av01 video only formats sometimes served with "unknown" codecs
999 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1000 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1001 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}
,
1002 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}
,
1003 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}
,
1004 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}
,
1005 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1006 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1008 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1015 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1017 'id': 'BaW_jenozKc',
1019 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1020 'uploader': 'Philipp Hagemeister',
1021 'uploader_id': 'phihag',
1022 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1023 'channel': 'Philipp Hagemeister',
1024 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1025 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1026 'upload_date': '20121002',
1027 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1028 'categories': ['Science & Technology'],
1029 'tags': ['youtube-dl'],
1033 'availability': 'public',
1034 'playable_in_embed': True,
1035 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1036 'live_status': 'not_live',
1040 'channel_follower_count': int
1044 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1045 'note': 'Embed-only video (#1746)',
1047 'id': 'yZIXLfi8CZQ',
1049 'upload_date': '20120608',
1050 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1051 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1052 'uploader': 'SET India',
1053 'uploader_id': 'setindia',
1054 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1057 'skip': 'Private video',
1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1061 'note': 'Use the first video ID in the URL',
1063 'id': 'BaW_jenozKc',
1065 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1066 'uploader': 'Philipp Hagemeister',
1067 'uploader_id': 'phihag',
1068 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1069 'channel': 'Philipp Hagemeister',
1070 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1071 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1072 'upload_date': '20121002',
1073 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1074 'categories': ['Science & Technology'],
1075 'tags': ['youtube-dl'],
1079 'availability': 'public',
1080 'playable_in_embed': True,
1081 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1082 'live_status': 'not_live',
1084 'channel_follower_count': int
1087 'skip_download': True,
1091 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1092 'note': '256k DASH audio (format 141) via DASH manifest',
1094 'id': 'a9LDPn-MO4I',
1096 'upload_date': '20121002',
1097 'uploader_id': '8KVIDEO',
1098 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1100 'uploader': '8KVIDEO',
1101 'title': 'UHDTV TEST 8K VIDEO.mp4'
1104 'youtube_include_dash_manifest': True,
1107 'skip': 'format 141 not served anymore',
1109 # DASH manifest with encrypted signature
1111 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1113 'id': 'IB3lcPjvWLA',
1115 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1116 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1118 'uploader': 'AfrojackVEVO',
1119 'uploader_id': 'AfrojackVEVO',
1120 'upload_date': '20131011',
1123 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1124 'playable_in_embed': True,
1125 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1127 'track': 'The Spark',
1128 'live_status': 'not_live',
1129 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1130 'channel': 'Afrojack',
1131 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1133 'availability': 'public',
1134 'categories': ['Music'],
1136 'alt_title': 'The Spark',
1137 'channel_follower_count': int
1140 'youtube_include_dash_manifest': True,
1141 'format': '141/bestaudio[ext=m4a]',
1144 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1146 'note': 'Embed allowed age-gate video',
1147 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1149 'id': 'HtVdAasjOgU',
1151 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1152 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1154 'uploader': 'The Witcher',
1155 'uploader_id': 'WitcherGame',
1156 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1157 'upload_date': '20140605',
1159 'categories': ['Gaming'],
1160 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1161 'availability': 'needs_auth',
1162 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1164 'channel': 'The Witcher',
1165 'live_status': 'not_live',
1167 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1168 'playable_in_embed': True,
1170 'channel_follower_count': int
1174 'note': 'Age-gate video with embed allowed in public site',
1175 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1177 'id': 'HsUATh_Nc2U',
1179 'title': 'Godzilla 2 (Official Video)',
1180 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1181 'upload_date': '20200408',
1182 'uploader_id': 'FlyingKitty900',
1183 'uploader': 'FlyingKitty',
1185 'availability': 'needs_auth',
1186 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1187 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1188 'channel': 'FlyingKitty',
1189 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1191 'categories': ['Entertainment'],
1192 'live_status': 'not_live',
1193 'tags': ['Flyingkitty', 'godzilla 2'],
1194 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1197 'playable_in_embed': True,
1198 'channel_follower_count': int
1202 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1203 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1205 'id': 'Tq92D6wQ1mg',
1206 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1208 'upload_date': '20191227',
1209 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1210 'uploader': 'Projekt Melody',
1211 'description': 'md5:17eccca93a786d51bc67646756894066',
1214 'availability': 'needs_auth',
1215 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1216 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1218 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1219 'channel': 'Projekt Melody',
1220 'live_status': 'not_live',
1221 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1222 'playable_in_embed': True,
1223 'categories': ['Entertainment'],
1225 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1226 'channel_follower_count': int
1230 'note': 'Non-Agegated non-embeddable video',
1231 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1233 'id': 'MeJVWBSsPAY',
1235 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1236 'uploader': 'Herr Lurik',
1237 'uploader_id': 'st3in234',
1238 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1239 'upload_date': '20130730',
1240 'track': 'Such mich find mich',
1242 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1244 'playable_in_embed': False,
1245 'creator': 'OOMPH!',
1246 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1248 'alt_title': 'Such mich find mich',
1250 'channel': 'Herr Lurik',
1251 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1252 'categories': ['Music'],
1253 'availability': 'public',
1254 'uploader_url': 'http://www.youtube.com/user/st3in234',
1255 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1256 'live_status': 'not_live',
1258 'channel_follower_count': int
1262 'note': 'Non-bypassable age-gated video',
1263 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1264 'only_matching': True,
1266 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1267 # YouTube Red ad is not captured for creator
1269 'url': '__2ABJjxzNo',
1271 'id': '__2ABJjxzNo',
1274 'upload_date': '20100430',
1275 'uploader_id': 'deadmau5',
1276 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1277 'creator': 'deadmau5',
1278 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1279 'uploader': 'deadmau5',
1280 'title': 'Deadmau5 - Some Chords (HD)',
1281 'alt_title': 'Some Chords',
1282 'availability': 'public',
1284 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1286 'live_status': 'not_live',
1287 'channel': 'deadmau5',
1288 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1290 'track': 'Some Chords',
1291 'artist': 'deadmau5',
1292 'playable_in_embed': True,
1294 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1295 'categories': ['Music'],
1296 'album': 'Some Chords',
1297 'channel_follower_count': int
1299 'expected_warnings': [
1300 'DASH manifest missing',
1303 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1305 'url': 'lqQg6PlCWgI',
1307 'id': 'lqQg6PlCWgI',
1310 'upload_date': '20150827',
1311 'uploader_id': 'olympic',
1312 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1313 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1314 'uploader': 'Olympics',
1315 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1317 'release_timestamp': 1343767800,
1318 'playable_in_embed': True,
1319 'categories': ['Sports'],
1320 'release_date': '20120731',
1321 'channel': 'Olympics',
1322 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1323 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1324 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1326 'availability': 'public',
1327 'live_status': 'was_live',
1329 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1330 'channel_follower_count': int
1333 'skip_download': 'requires avconv',
1338 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1340 'id': '_b-2C3KPAM0',
1342 'stretched_ratio': 16 / 9.,
1344 'upload_date': '20110310',
1345 'uploader_id': 'AllenMeow',
1346 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1347 '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',
1349 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1350 'playable_in_embed': True,
1354 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1355 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1356 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1358 'categories': ['People & Blogs'],
1360 'live_status': 'not_live',
1361 'availability': 'unlisted',
1362 'channel_follower_count': int
1365 # url_encoded_fmt_stream_map is empty string
1367 'url': 'qEJwOuvDf7I',
1369 'id': 'qEJwOuvDf7I',
1371 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1373 'upload_date': '20150404',
1374 'uploader_id': 'spbelect',
1375 'uploader': 'Наблюдатели Петербурга',
1378 'skip_download': 'requires avconv',
1380 'skip': 'This live event has ended.',
1382 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1384 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1386 'id': 'FIl7x6_3R5Y',
1388 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1389 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1391 'upload_date': '20150625',
1392 'uploader_id': 'dorappi2000',
1393 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1394 'uploader': 'dorappi2000',
1395 'formats': 'mincount:31',
1397 'skip': 'not actual anymore',
1399 # DASH manifest with segment_list
1401 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1402 'md5': '8ce563a1d667b599d21064e982ab9e31',
1404 'id': 'CsmdDsKjzN8',
1406 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1407 'uploader': 'Airtek',
1408 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1409 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1410 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1413 'youtube_include_dash_manifest': True,
1414 'format': '135', # bestvideo
1416 'skip': 'This live event has ended.',
1419 # Multifeed videos (multiple cameras), URL is for Main Camera
1420 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1422 'id': 'jvGDaLqkpTg',
1423 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1424 'description': 'md5:e03b909557865076822aa169218d6a5d',
1428 'id': 'jvGDaLqkpTg',
1430 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1431 'description': 'md5:e03b909557865076822aa169218d6a5d',
1433 'upload_date': '20161111',
1434 'uploader': 'Team PGP',
1435 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1436 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1440 'id': '3AKt1R1aDnw',
1442 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1443 'description': 'md5:e03b909557865076822aa169218d6a5d',
1445 'upload_date': '20161111',
1446 'uploader': 'Team PGP',
1447 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1448 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1452 'id': 'RtAMM00gpVc',
1454 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1455 'description': 'md5:e03b909557865076822aa169218d6a5d',
1457 'upload_date': '20161111',
1458 'uploader': 'Team PGP',
1459 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1460 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1464 'id': '6N2fdlP3C5U',
1466 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1467 'description': 'md5:e03b909557865076822aa169218d6a5d',
1469 'upload_date': '20161111',
1470 'uploader': 'Team PGP',
1471 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1472 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1476 'skip_download': True,
1478 'skip': 'Not multifeed anymore',
1481 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1482 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1484 'id': 'gVfLd0zydlo',
1485 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1487 'playlist_count': 2,
1488 'skip': 'Not multifeed anymore',
1491 'url': 'https://vid.plus/FlRa-iH7PGw',
1492 'only_matching': True,
1495 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1496 'only_matching': True,
1499 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1500 # Also tests cut-off URL expansion in video description (see
1501 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1502 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1503 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1505 'id': 'lsguqyKfVQg',
1507 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1508 'alt_title': 'Dark Walk',
1509 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1511 'upload_date': '20151119',
1512 'uploader_id': 'IronSoulElf',
1513 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1514 'uploader': 'IronSoulElf',
1515 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1516 'track': 'Dark Walk',
1517 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1518 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1519 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1520 'categories': ['Film & Animation'],
1522 'live_status': 'not_live',
1523 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1524 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1526 'availability': 'public',
1527 'channel': 'IronSoulElf',
1528 'playable_in_embed': True,
1531 'channel_follower_count': int
1534 'skip_download': True,
1538 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1539 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1540 'only_matching': True,
1543 # Video with yt:stretch=17:0
1544 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1546 'id': 'Q39EVAstoRM',
1548 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1549 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1550 'upload_date': '20151107',
1551 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1552 'uploader': 'CH GAMER DROID',
1555 'skip_download': True,
1557 'skip': 'This video does not exist.',
1560 # Video with incomplete 'yt:stretch=16:'
1561 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1562 'only_matching': True,
1565 # Video licensed under Creative Commons
1566 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1568 'id': 'M4gD1WSo5mA',
1570 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1571 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1573 'upload_date': '20150127',
1574 'uploader_id': 'BerkmanCenter',
1575 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1576 'uploader': 'The Berkman Klein Center for Internet & Society',
1577 'license': 'Creative Commons Attribution license (reuse allowed)',
1578 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1579 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1582 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1583 'channel': 'The Berkman Klein Center for Internet & Society',
1584 'availability': 'public',
1586 'categories': ['Education'],
1587 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1588 'live_status': 'not_live',
1589 'playable_in_embed': True,
1590 'channel_follower_count': int
1593 'skip_download': True,
1597 # Channel-like uploader_url
1598 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1600 'id': 'eQcmzGIKrzg',
1602 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1603 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1605 'upload_date': '20151119',
1606 'uploader': 'Bernie Sanders',
1607 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1608 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1609 'license': 'Creative Commons Attribution license (reuse allowed)',
1610 'playable_in_embed': True,
1613 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1615 'availability': 'public',
1616 'categories': ['News & Politics'],
1617 'channel': 'Bernie Sanders',
1618 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1620 'live_status': 'not_live',
1621 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1622 'channel_follower_count': int
1625 'skip_download': True,
1629 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1630 'only_matching': True,
1633 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1634 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1635 'only_matching': True,
1638 # Rental video preview
1639 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1641 'id': 'uGpuVWrhIzE',
1643 'title': 'Piku - Trailer',
1644 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1645 'upload_date': '20150811',
1646 'uploader': 'FlixMatrix',
1647 'uploader_id': 'FlixMatrixKaravan',
1648 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1649 'license': 'Standard YouTube License',
1652 'skip_download': True,
1654 'skip': 'This video is not available.',
1657 # YouTube Red video with episode data
1658 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1660 'id': 'iqKdEhx-dD4',
1662 'title': 'Isolation - Mind Field (Ep 1)',
1663 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1665 'upload_date': '20170118',
1666 'uploader': 'Vsauce',
1667 'uploader_id': 'Vsauce',
1668 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1669 'series': 'Mind Field',
1671 'episode_number': 1,
1672 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1675 'availability': 'public',
1677 'channel': 'Vsauce',
1678 'episode': 'Episode 1',
1679 'categories': ['Entertainment'],
1680 'season': 'Season 1',
1681 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1682 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1684 'playable_in_embed': True,
1685 'live_status': 'not_live',
1686 'channel_follower_count': int
1689 'skip_download': True,
1691 'expected_warnings': [
1692 'Skipping DASH manifest',
1696 # The following content has been identified by the YouTube community
1697 # as inappropriate or offensive to some audiences.
1698 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1700 'id': '6SJNVb0GnPI',
1702 'title': 'Race Differences in Intelligence',
1703 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1705 'upload_date': '20140124',
1706 'uploader': 'New Century Foundation',
1707 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1708 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1711 'skip_download': True,
1713 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1717 'url': '1t24XAntNCY',
1718 'only_matching': True,
1721 # geo restricted to JP
1722 'url': 'sJL6WA-aGkQ',
1723 'only_matching': True,
1726 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1727 'only_matching': True,
1730 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1731 'only_matching': True,
1734 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1735 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1736 'only_matching': True,
1740 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1741 'only_matching': True,
1744 # Video with unsupported adaptive stream type formats
1745 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1747 'id': 'Z4Vy8R84T1U',
1749 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1750 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1752 'upload_date': '20130923',
1753 'uploader': 'Amelia Putri Harwita',
1754 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1755 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1756 'formats': 'maxcount:10',
1759 'skip_download': True,
1760 'youtube_include_dash_manifest': False,
1762 'skip': 'not actual anymore',
1765 # Youtube Music Auto-generated description
1766 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1768 'id': 'MgNrAu2pzNs',
1770 'title': 'Voyeur Girl',
1771 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1772 'upload_date': '20190312',
1773 'uploader': 'Stephen - Topic',
1774 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1775 'artist': 'Stephen',
1776 'track': 'Voyeur Girl',
1777 'album': 'it\'s too much love to know my dear',
1778 'release_date': '20190313',
1779 'release_year': 2019,
1780 'alt_title': 'Voyeur Girl',
1782 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1783 'playable_in_embed': True,
1785 'categories': ['Music'],
1786 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1787 'channel': 'Stephen',
1788 'availability': 'public',
1789 'creator': 'Stephen',
1791 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1793 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1795 'live_status': 'not_live',
1796 'channel_follower_count': int
1799 'skip_download': True,
1803 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1804 'only_matching': True,
1807 # invalid -> valid video id redirection
1808 'url': 'DJztXj2GPfl',
1810 'id': 'DJztXj2GPfk',
1812 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1813 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1814 'upload_date': '20090125',
1815 'uploader': 'Prochorowka',
1816 'uploader_id': 'Prochorowka',
1817 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1818 'artist': 'Panjabi MC',
1819 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1820 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1823 'skip_download': True,
1825 'skip': 'Video unavailable',
1828 # empty description results in an empty string
1829 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1831 'id': 'x41yOUIvK2k',
1833 'title': 'IMG 3456',
1835 'upload_date': '20170613',
1836 'uploader_id': 'ElevageOrVert',
1837 'uploader': 'ElevageOrVert',
1839 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1840 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1842 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1844 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1845 'availability': 'public',
1847 'categories': ['Pets & Animals'],
1849 'playable_in_embed': True,
1850 'live_status': 'not_live',
1851 'channel': 'ElevageOrVert',
1852 'channel_follower_count': int
1855 'skip_download': True,
1859 # with '};' inside yt initial data (see [1])
1860 # see [2] for an example with '};' inside ytInitialPlayerResponse
1861 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1862 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1863 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1865 'id': 'CHqg6qOn4no',
1867 'title': 'Part 77 Sort a list of simple types in c#',
1868 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1869 'upload_date': '20130831',
1870 'uploader_id': 'kudvenkat',
1871 'uploader': 'kudvenkat',
1872 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1874 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1875 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1876 'live_status': 'not_live',
1877 'categories': ['Education'],
1878 'availability': 'public',
1879 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1881 'playable_in_embed': True,
1885 'channel': 'kudvenkat',
1886 'channel_follower_count': int
1889 'skip_download': True,
1893 # another example of '};' in ytInitialData
1894 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1895 'only_matching': True,
1898 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1899 'only_matching': True,
1902 # https://github.com/ytdl-org/youtube-dl/pull/28094
1903 'url': 'OtqTfy26tG0',
1905 'id': 'OtqTfy26tG0',
1907 'title': 'Burn Out',
1908 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1909 'upload_date': '20141120',
1910 'uploader': 'The Cinematic Orchestra - Topic',
1911 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1912 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1913 'artist': 'The Cinematic Orchestra',
1914 'track': 'Burn Out',
1915 'album': 'Every Day',
1917 'live_status': 'not_live',
1918 'alt_title': 'Burn Out',
1922 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1923 'creator': 'The Cinematic Orchestra',
1924 'channel': 'The Cinematic Orchestra',
1925 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1926 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1927 'availability': 'public',
1928 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1929 'categories': ['Music'],
1930 'playable_in_embed': True,
1931 'channel_follower_count': int
1934 'skip_download': True,
1938 # controversial video, only works with bpctr when authenticated with cookies
1939 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1940 'only_matching': True,
1943 # controversial video, requires bpctr/contentCheckOk
1944 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1946 'id': 'SZJvDhaSDnc',
1948 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1949 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1950 'uploader': 'CBS Mornings',
1951 'uploader_id': 'CBSThisMorning',
1952 'upload_date': '20140716',
1953 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1955 'categories': ['News & Politics'],
1956 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1958 'channel': 'CBS Mornings',
1959 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1960 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
1962 'availability': 'needs_auth',
1963 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
1965 'live_status': 'not_live',
1966 'playable_in_embed': True,
1967 'channel_follower_count': int
1971 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1972 'url': 'cBvYw8_A0vQ',
1974 'id': 'cBvYw8_A0vQ',
1976 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1977 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1978 'upload_date': '20201120',
1979 'uploader': 'Walk around Japan',
1980 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1981 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1983 'categories': ['Travel & Events'],
1984 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1986 'channel': 'Walk around Japan',
1987 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
1988 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
1990 'availability': 'public',
1991 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1992 'live_status': 'not_live',
1993 'playable_in_embed': True,
1994 'channel_follower_count': int
1997 'skip_download': True,
2000 # Has multiple audio streams
2001 'url': 'WaOKSUlf4TM',
2002 'only_matching': True
2004 # Requires Premium: has format 141 when requested using YTM url
2005 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2006 'only_matching': True
2008 # multiple subtitles with same lang_code
2009 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2010 'only_matching': True,
2012 # Force use android client fallback
2013 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2015 'id': 'YOelRv7fMxY',
2016 'title': 'DIGGING A SECRET TUNNEL Part 1',
2018 'upload_date': '20210624',
2019 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2020 'uploader': 'colinfurze',
2021 'uploader_id': 'colinfurze',
2022 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2023 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2025 'categories': ['Entertainment'],
2026 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2028 'channel': 'colinfurze',
2029 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2030 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2032 'availability': 'public',
2034 'live_status': 'not_live',
2035 'playable_in_embed': True,
2036 'channel_follower_count': int
2039 'format': '17', # 3gp format available on android
2040 'extractor_args': {'youtube': {'player_client': ['android']}
},
2044 # Skip download of additional client configs (remix client config in this case)
2045 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2046 'only_matching': True,
2048 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
2052 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2053 'only_matching': True,
2055 'note': 'Storyboards',
2056 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2058 'id': '5KLPxDtMqe8',
2061 'title': 'Your Brain is Plastic',
2062 'uploader_id': 'scishow',
2063 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2064 'upload_date': '20140324',
2065 'uploader': 'SciShow',
2067 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2068 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2070 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2071 'playable_in_embed': True,
2073 'uploader_url': 'http://www.youtube.com/user/scishow',
2074 'availability': 'public',
2075 'channel': 'SciShow',
2076 'live_status': 'not_live',
2078 'categories': ['Education'],
2080 'channel_follower_count': int
2081 }, 'params': {'format': 'mhtml', 'skip_download': True}
2086 def suitable(cls
, url
):
2087 from ..utils
import parse_qs
2090 if qs
.get('list', [None])[0]:
2092 return super(YoutubeIE
, cls
).suitable(url
)
2094 def __init__(self
, *args
, **kwargs
):
2095 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
2096 self
._code
_cache
= {}
2097 self
._player
_cache
= {}
2099 def _prepare_live_from_start_formats(self
, formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
):
2100 lock
= threading
.Lock()
2103 start_time
= time
.time()
2104 formats
= [f
for f
in formats
if f
.get('is_from_start')]
2106 def refetch_manifest(format_id
, delay
):
2107 nonlocal formats
, start_time
, is_live
2108 if time
.time() <= start_time
+ delay
:
2111 _
, _
, prs
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
2112 video_details
= traverse_obj(
2113 prs
, (..., 'videoDetails'), expected_type
=dict, default
=[])
2114 microformats
= traverse_obj(
2115 prs
, (..., 'microformat', 'playerMicroformatRenderer'),
2116 expected_type
=dict, default
=[])
2117 _
, is_live
, _
, formats
= self
._list
_formats
(video_id
, microformats
, video_details
, prs
, player_url
)
2118 start_time
= time
.time()
2120 def mpd_feed(format_id
, delay
):
2122 @returns (manifest_url, manifest_stream_number, is_live) or None
2125 refetch_manifest(format_id
, delay
)
2127 f
= next((f
for f
in formats
if f
['format_id'] == format_id
), None)
2130 self
.to_screen(f
'{video_id}: Video is no longer live')
2132 self
.report_warning(
2133 f
'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2135 return f
['manifest_url'], f
['manifest_stream_number'], is_live
2138 f
['protocol'] = 'http_dash_segments_generator'
2139 f
['fragments'] = functools
.partial(
2140 self
._live
_dash
_fragments
, f
['format_id'], live_start_time
, mpd_feed
)
2142 def _live_dash_fragments(self
, format_id
, live_start_time
, mpd_feed
, ctx
):
2143 FETCH_SPAN
, MAX_DURATION
= 5, 432000
2145 mpd_url
, stream_number
, is_live
= None, None, True
2148 download_start_time
= ctx
.get('start') or time
.time()
2150 lack_early_segments
= download_start_time
- (live_start_time
or download_start_time
) > MAX_DURATION
2151 if lack_early_segments
:
2152 self
.report_warning(bug_reports_message(
2153 'Starting download from the last 120 hours of the live stream since '
2154 'YouTube does not have data before that. If you think this is wrong,'), only_once
=True)
2155 lack_early_segments
= True
2157 known_idx
, no_fragment_score
, last_segment_url
= begin_index
, 0, None
2158 fragments
, fragment_base_url
= None, None
2160 def _extract_sequence_from_mpd(refresh_sequence
):
2161 nonlocal mpd_url
, stream_number
, is_live
, no_fragment_score
, fragments
, fragment_base_url
2162 # Obtain from MPD's maximum seq value
2163 old_mpd_url
= mpd_url
2164 last_error
= ctx
.pop('last_error', None)
2165 expire_fast
= last_error
and isinstance(last_error
, compat_HTTPError
) and last_error
.code
== 403
2166 mpd_url
, stream_number
, is_live
= (mpd_feed(format_id
, 5 if expire_fast
else 18000)
2167 or (mpd_url
, stream_number
, False))
2168 if not refresh_sequence
:
2169 if expire_fast
and not is_live
:
2170 return False, last_seq
2171 elif old_mpd_url
== mpd_url
:
2172 return True, last_seq
2174 fmts
, _
= self
._extract
_mpd
_formats
_and
_subtitles
(
2175 mpd_url
, None, note
=False, errnote
=False, fatal
=False)
2176 except ExtractorError
:
2179 no_fragment_score
+= 1
2180 return False, last_seq
2181 fmt_info
= next(x
for x
in fmts
if x
['manifest_stream_number'] == stream_number
)
2182 fragments
= fmt_info
['fragments']
2183 fragment_base_url
= fmt_info
['fragment_base_url']
2184 assert fragment_base_url
2186 _last_seq
= int(re
.search(r
'(?:/|^)sq/(\d+)', fragments
[-1]['path']).group(1))
2187 return True, _last_seq
2190 fetch_time
= time
.time()
2191 if no_fragment_score
> 30:
2193 if last_segment_url
:
2194 # Obtain from "X-Head-Seqnum" header value from each segment
2196 urlh
= self
._request
_webpage
(
2197 last_segment_url
, None, note
=False, errnote
=False, fatal
=False)
2198 except ExtractorError
:
2200 last_seq
= try_get(urlh
, lambda x
: int_or_none(x
.headers
['X-Head-Seqnum']))
2201 if last_seq
is None:
2202 no_fragment_score
+= 1
2203 last_segment_url
= None
2206 should_continue
, last_seq
= _extract_sequence_from_mpd(True)
2207 if not should_continue
:
2210 if known_idx
> last_seq
:
2211 last_segment_url
= None
2216 if begin_index
< 0 and known_idx
< 0:
2217 # skip from the start when it's negative value
2218 known_idx
= last_seq
+ begin_index
2219 if lack_early_segments
:
2220 known_idx
= max(known_idx
, last_seq
- int(MAX_DURATION
// fragments
[-1]['duration']))
2222 for idx
in range(known_idx
, last_seq
):
2223 # do not update sequence here or you'll get skipped some part of it
2224 should_continue
, _
= _extract_sequence_from_mpd(False)
2225 if not should_continue
:
2227 raise ExtractorError('breaking out of outer loop')
2228 last_segment_url
= urljoin(fragment_base_url
, 'sq/%d' % idx
)
2230 'url': last_segment_url
,
2232 if known_idx
== last_seq
:
2233 no_fragment_score
+= 5
2235 no_fragment_score
= 0
2236 known_idx
= last_seq
2237 except ExtractorError
:
2240 time
.sleep(max(0, FETCH_SPAN
+ fetch_time
- time
.time()))
2242 def _extract_player_url(self
, *ytcfgs
, webpage
=None):
2243 player_url
= traverse_obj(
2244 ytcfgs
, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2245 get_all
=False, expected_type
=compat_str
)
2248 if player_url
.startswith('//'):
2249 player_url
= 'https:' + player_url
2250 elif not re
.match(r
'https?://', player_url
):
2251 player_url
= compat_urlparse
.urljoin(
2252 'https://www.youtube.com', player_url
)
2255 def _download_player_url(self
, video_id
, fatal
=False):
2256 res
= self
._download
_webpage
(
2257 'https://www.youtube.com/iframe_api',
2258 note
='Downloading iframe API JS', video_id
=video_id
, fatal
=fatal
)
2260 player_version
= self
._search
_regex
(
2261 r
'player\\?/([0-9a-fA-F]{8})\\?/', res
, 'player version', fatal
=fatal
)
2263 return f
'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2265 def _signature_cache_id(self
, example_sig
):
2266 """ Return a string representation of a signature """
2267 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
2270 def _extract_player_info(cls
, player_url
):
2271 for player_re
in cls
._PLAYER
_INFO
_RE
:
2272 id_m
= re
.search(player_re
, player_url
)
2276 raise ExtractorError('Cannot identify player %r' % player_url
)
2277 return id_m
.group('id')
2279 def _load_player(self
, video_id
, player_url
, fatal
=True):
2280 player_id
= self
._extract
_player
_info
(player_url
)
2281 if player_id
not in self
._code
_cache
:
2282 code
= self
._download
_webpage
(
2283 player_url
, video_id
, fatal
=fatal
,
2284 note
='Downloading player ' + player_id
,
2285 errnote
='Download of %s failed' % player_url
)
2287 self
._code
_cache
[player_id
] = code
2288 return self
._code
_cache
.get(player_id
)
2290 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
2291 player_id
= self
._extract
_player
_info
(player_url
)
2293 # Read from filesystem cache
2294 func_id
= 'js_%s_%s' % (
2295 player_id
, self
._signature
_cache
_id
(example_sig
))
2296 assert os
.path
.basename(func_id
) == func_id
2298 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
2299 if cache_spec
is not None:
2300 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
2302 code
= self
._load
_player
(video_id
, player_url
)
2304 res
= self
._parse
_sig
_js
(code
)
2306 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2307 cache_res
= res(test_string
)
2308 cache_spec
= [ord(c
) for c
in cache_res
]
2310 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
2313 def _print_sig_code(self
, func
, example_sig
):
2314 if not self
.get_param('youtube_print_sig_code'):
2317 def gen_sig_code(idxs
):
2318 def _genslice(start
, end
, step
):
2319 starts
= '' if start
== 0 else str(start
)
2320 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
2321 steps
= '' if step
== 1 else (':%d' % step
)
2322 return 's[%s%s%s]' % (starts
, ends
, steps
)
2325 # Quelch pyflakes warnings - start will be set when step is set
2326 start
= '(Never used)'
2327 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
2328 if step
is not None:
2329 if i
- prev
== step
:
2331 yield _genslice(start
, prev
, step
)
2334 if i
- prev
in [-1, 1]:
2339 yield 's[%d]' % prev
2343 yield _genslice(start
, i
, step
)
2345 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2346 cache_res
= func(test_string
)
2347 cache_spec
= [ord(c
) for c
in cache_res
]
2348 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
2349 signature_id_tuple
= '(%s)' % (
2350 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
2351 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2352 ' return %s\n') % (signature_id_tuple
, expr_code
)
2353 self
.to_screen('Extracted signature function:\n' + code
)
2355 def _parse_sig_js(self
, jscode
):
2356 funcname
= self
._search
_regex
(
2357 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2358 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2359 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2360 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
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\(\s*""\s*\);[a-zA-Z0-9$]{2}\.[a-zA-Z0-9$]{2}\(a,\d+\)',
2362 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\(\s*""\s*\)',
2363 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2365 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2366 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2367 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2368 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2369 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2370 r'\bc\s
*&&\s
*a\
.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 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
2373 jscode, 'Initial JS player signature function name
', group='sig
')
2375 jsi = JSInterpreter(jscode)
2376 initial_function = jsi.extract_function(funcname)
2377 return lambda s: initial_function([s])
2379 def _decrypt_signature(self, s, video_id, player_url):
2380 """Turn the encrypted s field into a working signature"""
2382 if player_url is None:
2383 raise ExtractorError('Cannot decrypt signature without player_url
')
2386 player_id = (player_url, self._signature_cache_id(s))
2387 if player_id not in self._player_cache:
2388 func = self._extract_signature_function(
2389 video_id, player_url, s
2391 self._player_cache[player_id] = func
2392 func = self._player_cache[player_id]
2393 self._print_sig_code(func, s)
2395 except Exception as e:
2396 raise ExtractorError('Signature extraction failed
: ' + traceback.format_exc(), cause=e)
2398 def _decrypt_nsig(self, s, video_id, player_url):
2399 """Turn the encrypted n field into a working signature"""
2400 if player_url is None:
2401 raise ExtractorError('Cannot decrypt nsig without player_url
')
2402 if player_url.startswith('//'):
2403 player_url = 'https
:' + player_url
2404 elif not re.match(r'https?
://', player_url):
2405 player_url = compat_urlparse.urljoin(
2406 'https
://www
.youtube
.com
', player_url)
2408 sig_id = ('nsig_value
', s)
2409 if sig_id in self._player_cache:
2410 return self._player_cache[sig_id]
2413 player_id = ('nsig
', player_url)
2414 if player_id not in self._player_cache:
2415 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2416 func = self._player_cache[player_id]
2417 self._player_cache[sig_id] = func(s)
2418 self.write_debug(f'Decrypted nsig {s}
=> {self._player_cache[sig_id]}
')
2419 return self._player_cache[sig_id]
2420 except Exception as e:
2421 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2423 def _extract_n_function_name(self, jscode):
2424 nfunc, idx = self._search_regex(
2425 r'\
.get\
("n"\
)\
)&&\
(b
=(?P
<nfunc
>[a
-zA
-Z0
-9$
]{3}
)(\
[(?P
<idx
>\d
+)\
])?\
([a
-zA
-Z0
-9]\
)',
2426 jscode, 'Initial JS player n function name
', group=('nfunc
', 'idx
'))
2429 return json.loads(js_to_json(self._search_regex(
2430 rf'var {nfunc}\s
*=\s
*(\
[.+?\
]);', jscode,
2431 f'Initial JS player n function
list ({nfunc}
.{idx}
)')))[int(idx)]
2433 def _extract_n_function(self, video_id, player_url):
2434 player_id = self._extract_player_info(player_url)
2435 func_code = self._downloader.cache.load('youtube
-nsig
', player_id)
2438 jsi = JSInterpreter(func_code)
2440 jscode = self._load_player(video_id, player_url)
2441 funcname = self._extract_n_function_name(jscode)
2442 jsi = JSInterpreter(jscode)
2443 func_code = jsi.extract_function_code(funcname)
2444 self._downloader.cache.store('youtube
-nsig
', player_id, func_code)
2446 if self.get_param('youtube_print_sig_code
'):
2447 self.to_screen(f'Extracted nsig function
from {player_id}
:\n{func_code[1]}
\n')
2449 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2451 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2453 Extract signatureTimestamp (sts)
2454 Required to tell API what sig/player version is in use.
2457 if isinstance(ytcfg, dict):
2458 sts = int_or_none(ytcfg.get('STS
'))
2461 # Attempt to extract from player
2462 if player_url is None:
2463 error_msg = 'Cannot extract signature timestamp without player_url
.'
2465 raise ExtractorError(error_msg)
2466 self.report_warning(error_msg)
2468 code = self._load_player(video_id, player_url, fatal=fatal)
2470 sts = int_or_none(self._search_regex(
2471 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
2472 'JS player signature timestamp
', group='sts
', fatal=fatal))
2475 def _mark_watched(self, video_id, player_responses):
2476 playback_url = get_first(
2477 player_responses, ('playbackTracking
', 'videostatsPlaybackUrl
', 'baseUrl
'),
2478 expected_type=url_or_none)
2479 if not playback_url:
2480 self.report_warning('Unable to mark watched
')
2482 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2483 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2485 # cpn generation algorithm is reverse engineered from base.js.
2486 # In fact it works even with dummy cpn.
2487 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
2488 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2494 playback_url = compat_urlparse.urlunparse(
2495 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2497 self._download_webpage(
2498 playback_url, video_id, 'Marking watched
',
2499 'Unable to mark watched
', fatal=False)
2502 def _extract_urls(webpage):
2503 # Embedded YouTube player
2505 unescapeHTML(mobj.group('url
'))
2506 for mobj in re.finditer(r'''(?x)
2516 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2517 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2520 # lazyYT YouTube embed
2521 entries.extend(list(map(
2523 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
2525 # Wordpress "YouTube Video Importer
" plugin
2526 matches = re.findall(r'''(?x)<div[^>]+
2527 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
2528 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
2529 entries.extend(m[-1] for m in matches)
2534 def _extract_url(webpage):
2535 urls = YoutubeIE._extract_urls(webpage)
2536 return urls[0] if urls else None
2539 def extract_id(cls, url):
2540 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2542 raise ExtractorError('Invalid URL: %s' % url)
2543 return mobj.group('id')
2545 def _extract_chapters_from_json(self, data, duration):
2546 chapter_list = traverse_obj(
2548 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2549 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2550 ), expected_type=list)
2552 return self._extract_chapters(
2554 chapter_time=lambda chapter: float_or_none(
2555 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2556 chapter_title=lambda chapter: traverse_obj(
2557 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2560 def _extract_chapters_from_engagement_panel(self, data, duration):
2561 content_list = traverse_obj(
2563 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2564 expected_type=list, default=[])
2565 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2566 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2570 self._extract_chapters(
2571 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2572 chapter_time, chapter_title, duration)
2573 for contents in content_list
2576 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2578 last_chapter = {'start_time': 0}
2579 for idx, chapter in enumerate(chapter_list or []):
2580 title = chapter_title(chapter)
2581 start_time = chapter_time(chapter)
2582 if start_time is None:
2584 last_chapter['end_time'] = start_time
2585 if start_time < last_chapter['start_time']:
2588 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2590 self.report_warning(f'Invalid start time for chapter "{title}"')
2592 last_chapter = {'start_time': start_time, 'title': title}
2593 chapters.append(last_chapter)
2594 last_chapter['end_time'] = duration
2597 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2598 return self._parse_json(self._search_regex(
2599 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2600 regex), webpage, name, default='{}'), video_id, fatal=False)
2602 def _extract_comment(self, comment_renderer, parent=None):
2603 comment_id = comment_renderer.get('commentId')
2607 text = self._get_text(comment_renderer, 'contentText')
2609 # note: timestamp is an estimate calculated from the current time and time_text
2610 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2611 author = self._get_text(comment_renderer, 'authorText')
2612 author_id = try_get(comment_renderer,
2613 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2615 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2616 lambda x: x['likeCount']), compat_str)) or 0
2617 author_thumbnail = try_get(comment_renderer,
2618 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2620 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2621 is_favorited = 'creatorHeart' in (try_get(
2622 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2626 'timestamp': timestamp,
2627 'time_text': time_text,
2628 'like_count': votes,
2629 'is_favorited': is_favorited,
2631 'author_id': author_id,
2632 'author_thumbnail': author_thumbnail,
2633 'author_is_uploader': author_is_uploader,
2634 'parent': parent or 'root'
2637 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2639 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2641 def extract_header(contents):
2642 _continuation = None
2643 for content in contents:
2644 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2645 expected_comment_count = self._get_count(
2646 comments_header_renderer, 'countText', 'commentsCount')
2648 if expected_comment_count:
2649 tracker['est_total'] = expected_comment_count
2650 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2651 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2653 sort_menu_item = try_get(
2654 comments_header_renderer,
2655 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2656 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2658 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2659 if not _continuation:
2662 sort_text = str_or_none(sort_menu_item.get('title'))
2664 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2665 self.to_screen('Sorting comments by %s' % sort_text.lower())
2667 return _continuation
2669 def extract_thread(contents):
2671 tracker['current_page_thread'] = 0
2672 for content in contents:
2673 if not parent and tracker['total_parent_comments'] >= max_parents:
2675 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2676 comment_renderer = get_first(
2677 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2678 expected_type=dict, default={})
2680 comment = self._extract_comment(comment_renderer, parent)
2684 tracker['running_total'] += 1
2685 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2688 # Attempt to get the replies
2689 comment_replies_renderer = try_get(
2690 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2692 if comment_replies_renderer:
2693 tracker['current_page_thread'] += 1
2694 comment_entries_iter = self._comment_entries(
2695 comment_replies_renderer, ytcfg, video_id,
2696 parent=comment.get('id'), tracker=tracker)
2697 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2700 # Keeps track of counts across recursive calls
2705 current_page_thread=0,
2706 total_parent_comments=0,
2707 total_reply_comments=0)
2710 # YouTube comments have a max depth of 2
2711 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2713 self._downloader.deprecation_warning(
2714 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2715 if max_depth == 1 and parent:
2718 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2719 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2721 continuation = self._extract_continuation(root_continuation_data)
2722 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2723 if message and not parent:
2724 self.report_warning(message, video_id=video_id)
2727 is_first_continuation = parent is None
2729 for page_num in itertools.count(0):
2730 if not continuation:
2732 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2733 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2735 if is_first_continuation:
2736 note_prefix = 'Downloading comment section API JSON'
2738 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2739 tracker['current_page_thread'], comment_prog_str)
2741 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2742 ' ' if parent else '', ' replies' if parent else '',
2743 page_num, comment_prog_str)
2745 response = self._extract_response(
2746 item_id=None, query=continuation,
2747 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2748 check_get_keys='onResponseReceivedEndpoints')
2750 continuation_contents = traverse_obj(
2751 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2754 for continuation_section in continuation_contents:
2755 continuation_items = traverse_obj(
2756 continuation_section,
2757 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2758 get_all=False, expected_type=list) or []
2759 if is_first_continuation:
2760 continuation = extract_header(continuation_items)
2761 is_first_continuation = False
2766 for entry in extract_thread(continuation_items):
2770 continuation = self._extract_continuation({'contents': continuation_items})
2774 def _get_comments(self, ytcfg, video_id, contents, webpage):
2775 """Entry for comment extraction"""
2776 def _real_comment_extract(contents):
2778 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2779 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2780 yield from self._comment_entries(renderer, ytcfg, video_id)
2782 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2783 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2786 def _get_checkok_params():
2787 return {'contentCheckOk': True, 'racyCheckOk': True}
2790 def _generate_player_context(cls, sts=None):
2792 'html5Preference': 'HTML5_PREF_WANTS',
2795 context['signatureTimestamp'] = sts
2797 'playbackContext': {
2798 'contentPlaybackContext': context
2800 **cls._get_checkok_params()
2804 def _is_agegated(player_response):
2805 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2808 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2809 AGE_GATE_REASONS = (
2810 'confirm your age', 'age-restricted', 'inappropriate', # reason
2811 'age_verification_required', 'age_check_required', # status
2813 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2816 def _is_unplayable(player_response):
2817 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2819 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2821 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2822 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2823 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2824 headers = self.generate_api_headers(
2825 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2827 yt_query = {'videoId': video_id}
2828 yt_query.update(self._generate_player_context(sts))
2829 return self._extract_response(
2830 item_id=video_id, ep='player', query=yt_query,
2831 ytcfg=player_ytcfg, headers=headers, fatal=True,
2832 default_client=client,
2833 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2836 def _get_requested_clients(self, url, smuggled_data):
2837 requested_clients = []
2838 default = ['android', 'web']
2839 allowed_clients = sorted(
2840 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2841 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2842 for client in self._configuration_arg('player_client'):
2843 if client in allowed_clients:
2844 requested_clients.append(client)
2845 elif client == 'default':
2846 requested_clients.extend(default)
2847 elif client == 'all':
2848 requested_clients.extend(allowed_clients)
2850 self.report_warning(f'Skipping unsupported client {client}')
2851 if not requested_clients:
2852 requested_clients = default
2854 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2855 requested_clients.extend(
2856 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2858 return orderedSet(requested_clients)
2860 def _extract_player_ytcfg(self, client, video_id):
2862 'web_music': 'https://music.youtube.com',
2863 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2867 webpage = self._download_webpage(url, video_id, fatal=False, note='Downloading %s config' % client.replace('_', ' ').strip())
2868 return self.extract_ytcfg(video_id, webpage) or {}
2870 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2873 initial_pr = self._extract_yt_initial_variable(
2874 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2875 video_id, 'initial player response')
2877 original_clients = clients
2878 clients = clients[::-1]
2881 def append_client(client_name):
2882 if client_name in INNERTUBE_CLIENTS and client_name not in original_clients:
2883 clients.append(client_name)
2885 # Android player_response does not have microFormats which are needed for
2886 # extraction of some data. So we return the initial_pr with formats
2887 # stripped out even if not requested by the user
2888 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2890 pr = dict(initial_pr)
2891 pr['streamingData'] = None
2895 tried_iframe_fallback = False
2898 client = clients.pop()
2899 player_ytcfg = master_ytcfg if client == 'web' else {}
2900 if 'configs' not in self._configuration_arg('player_skip'):
2901 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2903 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
2904 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
2905 if 'js' in self._configuration_arg('player_skip'):
2906 require_js_player = False
2909 if not player_url and not tried_iframe_fallback and require_js_player:
2910 player_url = self._download_player_url(video_id)
2911 tried_iframe_fallback = True
2914 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
2915 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
2916 except ExtractorError as e:
2918 self.report_warning(last_error)
2925 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
2926 if client.endswith('_agegate') and self._is_unplayable(pr) and self.is_authenticated:
2927 append_client(client.replace('_agegate', '_creator'))
2928 elif self._is_agegated(pr):
2929 append_client(f'{client}_agegate')
2934 self.report_warning(last_error)
2935 return prs, player_url
2937 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2938 itags, stream_ids = {}, []
2939 itag_qualities, res_qualities = {}, {}
2941 # Normally tiny is the smallest video-only formats. But
2942 # audio-only formats with unknown quality may get tagged as tiny
2944 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2945 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2947 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2949 for fmt in streaming_formats:
2950 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2953 itag = str_or_none(fmt.get('itag'))
2954 audio_track = fmt.get('audioTrack') or {}
2955 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2956 if stream_id in stream_ids:
2959 quality = fmt.get('quality')
2960 height = int_or_none(fmt.get('height'))
2961 if quality == 'tiny' or not quality:
2962 quality = fmt.get('audioQuality', '').lower() or quality
2963 # The 3gp format (17) in android client has a quality of "small",
2964 # but is actually worse than other formats
2969 itag_qualities[itag] = quality
2971 res_qualities[height] = quality
2972 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2973 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2974 # number of fragment that would subsequently requested with (`&sq=N`)
2975 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2978 fmt_url = fmt.get('url')
2980 sc = compat_parse_qs(fmt.get('signatureCipher'))
2981 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2982 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2983 if not (sc and fmt_url and encrypted_sig):
2987 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2988 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2989 fmt_url += '&' + sp + '=' + signature
2991 query = parse_qs(fmt_url)
2995 fmt_url = update_url_query(fmt_url, {
2996 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
2997 except ExtractorError as e:
2998 self.report_warning(
2999 f'nsig extraction failed: You may experience throttling for some formats\n'
3000 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
3004 itags[itag] = 'https'
3005 stream_ids.append(stream_id)
3007 tbr = float_or_none(
3008 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3010 'asr': int_or_none(fmt.get('audioSampleRate')),
3011 'filesize': int_or_none(fmt.get('contentLength')),
3013 'format_note': join_nonempty(
3014 '%s%s' % (audio_track.get('displayName') or '',
3015 ' (default)' if audio_track.get('audioIsDefault') else ''),
3016 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3017 throttled and 'THROTTLED', delim=', '),
3018 'source_preference': -10 if throttled else -1,
3019 'fps': int_or_none(fmt.get('fps')) or None,
3021 'quality': q(quality),
3024 'width': int_or_none(fmt.get('width')),
3025 'language': audio_track.get('id', '').split('.')[0],
3026 'language_preference': 1 if audio_track.get('audioIsDefault') else -1,
3028 mime_mobj = re.match(
3029 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3031 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3032 dct.update(parse_codecs(mime_mobj.group(2)))
3033 no_audio = dct.get('acodec') == 'none'
3034 no_video = dct.get('vcodec') == 'none'
3039 if no_audio or no_video:
3040 dct['downloader_options'] = {
3041 # Youtube throttles chunks >~10M
3042 'http_chunk_size': 10485760,
3045 dct['container'] = dct['ext'] + '_dash'
3048 live_from_start = is_live and self.get_param('live_from_start')
3049 skip_manifests = self._configuration_arg('skip')
3050 if not self.get_param('youtube_include_hls_manifest', True):
3051 skip_manifests.append('hls')
3052 get_dash = 'dash' not in skip_manifests and (
3053 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3054 get_hls = not live_from_start and 'hls' not in skip_manifests
3056 def process_manifest_format(f, proto, itag):
3058 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3060 itag = f'{itag}-{proto}'
3062 f['format_id'] = itag
3065 f['quality'] = next((
3067 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3068 if val in qdict), -1)
3071 for sd in streaming_data:
3072 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3073 if hls_manifest_url:
3074 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3075 if process_manifest_format(f, 'hls', self._search_regex(
3076 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3079 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3080 if dash_manifest_url:
3081 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3082 if process_manifest_format(f, 'dash', f['format_id']):
3083 f['filesize'] = int_or_none(self._search_regex(
3084 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3086 f['is_from_start'] = True
3090 def _extract_storyboard(self, player_responses, duration):
3092 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3093 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3097 for i, args in enumerate(spec):
3098 args = args.split('#')
3099 counts = list(map(int_or_none, args[:5]))
3100 if len(args) != 8 or not all(counts):
3101 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3103 width, height, frame_count, cols, rows = counts
3106 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3107 fragment_count = frame_count / (cols * rows)
3108 fragment_duration = duration / fragment_count
3110 'format_id': f'sb{i}',
3111 'format_note': 'storyboard',
3113 'protocol': 'mhtml',
3120 'path': url.replace('$M', str(j)),
3121 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3122 } for j in range(math.ceil(fragment_count))],
3125 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3127 if 'webpage' not in self._configuration_arg('player_skip'):
3128 webpage = self._download_webpage(
3129 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3131 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3133 player_responses, player_url = self._extract_player_responses(
3134 self._get_requested_clients(url, smuggled_data),
3135 video_id, webpage, master_ytcfg)
3137 return webpage, master_ytcfg, player_responses, player_url
3139 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url):
3140 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3141 is_live = get_first(video_details, 'isLive')
3143 is_live = get_first(live_broadcast_details, 'isLiveNow')
3145 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3146 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
3148 return live_broadcast_details, is_live, streaming_data, formats
3150 def _real_extract(self, url):
3151 url, smuggled_data = unsmuggle_url(url, {})
3152 video_id = self._match_id(url)
3154 base_url = self.http_scheme() + '//www.youtube.com/'
3155 webpage_url = base_url + 'watch?v=' + video_id
3157 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3159 playability_statuses = traverse_obj(
3160 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3162 trailer_video_id = get_first(
3163 playability_statuses,
3164 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3166 if trailer_video_id:
3167 return self.url_result(
3168 trailer_video_id, self.ie_key(), trailer_video_id)
3170 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3171 if webpage else (lambda x: None))
3173 video_details = traverse_obj(
3174 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3175 microformats = traverse_obj(
3176 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3177 expected_type=dict, default=[])
3179 get_first(video_details, 'title')
3180 or self._get_text(microformats, (..., 'title'))
3181 or search_meta(['og:title', 'twitter:title', 'title']))
3182 video_description = get_first(video_details, 'shortDescription')
3184 multifeed_metadata_list = get_first(
3186 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3188 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3189 if self.get_param('noplaylist'):
3190 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3194 for feed in multifeed_metadata_list.split(','):
3195 # Unquote should take place before split on comma (,) since textual
3196 # fields may contain comma as well (see
3197 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3198 feed_data = compat_parse_qs(
3199 compat_urllib_parse_unquote_plus(feed))
3201 def feed_entry(name):
3203 feed_data, lambda x: x[name][0], compat_str)
3205 feed_id = feed_entry('id')
3208 feed_title = feed_entry('title')
3211 title += ' (%s)' % feed_title
3213 '_type': 'url_transparent',
3214 'ie_key': 'Youtube',
3216 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3217 {'force_singlefeed': True}),
3220 feed_ids.append(feed_id)
3222 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3223 % (', '.join(feed_ids), video_id))
3224 return self.playlist_result(
3225 entries, video_id, video_title, video_description)
3227 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(video_id, microformats, video_details, player_responses, player_url)
3230 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3231 self.report_drm(video_id)
3233 playability_statuses,
3234 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3235 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3236 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3238 if subreason == 'The uploader has not made this video available in your country.':
3239 countries = get_first(microformats, 'availableCountries')
3241 regions_allowed = search_meta('regionsAllowed')
3242 countries = regions_allowed.split(',') if regions_allowed else None
3243 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3244 reason += f'. {subreason}'
3246 self.raise_no_formats(reason, expected=True)
3248 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3249 if not keywords and webpage:
3251 unescapeHTML(m.group('content'))
3252 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3253 for keyword in keywords:
3254 if keyword.startswith('yt:stretch='):
3255 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3257 # NB: float is intentional for forcing float division
3258 w, h = (float(v) for v in mobj.groups())
3262 if f.get('vcodec') != 'none':
3263 f['stretched_ratio'] = ratio
3265 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3266 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3269 'url': thumbnail_url,
3271 original_thumbnails = thumbnails.copy()
3273 # The best resolution thumbnails sometimes does not appear in the webpage
3274 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3275 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3277 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3278 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3279 'mqdefault', 'mq1', 'mq2', 'mq3',
3280 'default', '1', '2', '3'
3282 n_thumbnail_names = len(thumbnail_names)
3284 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3285 video_id=video_id, name=name, ext=ext,
3286 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3287 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3288 for thumb in thumbnails:
3289 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3290 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3291 self._remove_duplicate_formats(thumbnails)
3292 self._downloader._sort_thumbnails(original_thumbnails)
3294 category = get_first(microformats, 'category') or search_meta('genre')
3295 channel_id = str_or_none(
3296 get_first(video_details, 'channelId')
3297 or get_first(microformats, 'externalChannelId')
3298 or search_meta('channelId'))
3299 duration = int_or_none(
3300 get_first(video_details, 'lengthSeconds')
3301 or get_first(microformats, 'lengthSeconds')
3302 or parse_duration(search_meta('duration'))) or None
3303 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3305 live_content = get_first(video_details, 'isLiveContent')
3306 is_upcoming = get_first(video_details, 'isUpcoming')
3308 if is_upcoming or live_content is False:
3310 if is_upcoming is None and (live_content or is_live):
3312 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3313 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3314 if not duration and live_end_time and live_start_time:
3315 duration = live_end_time - live_start_time
3317 if is_live and self.get_param('live_from_start'):
3318 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3320 formats.extend(self._extract_storyboard(player_responses, duration))
3322 # Source is given priority since formats that throttle are given lower source_preference
3323 # When throttling issue is fully fixed, remove this
3324 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3328 'title': video_title,
3330 'thumbnails': thumbnails,
3331 # The best thumbnail that we are sure exists. Prevents unnecessary
3332 # URL checking if user don't care about getting the best possible thumbnail
3333 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3334 'description': video_description,
3335 'upload_date': unified_strdate(
3336 get_first(microformats, 'uploadDate')
3337 or search_meta('uploadDate')),
3338 'uploader': get_first(video_details, 'author'),
3339 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3340 'uploader_url': owner_profile_url,
3341 'channel_id': channel_id,
3342 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3343 'duration': duration,
3344 'view_count': int_or_none(
3345 get_first((video_details, microformats), (..., 'viewCount'))
3346 or search_meta('interactionCount')),
3347 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3348 'age_limit': 18 if (
3349 get_first(microformats, 'isFamilySafe') is False
3350 or search_meta('isFamilyFriendly') == 'false'
3351 or search_meta('og:restrictions:age') == '18+') else 0,
3352 'webpage_url': webpage_url,
3353 'categories': [category] if category else None,
3355 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3357 'was_live': (False if is_live or is_upcoming or live_content is False
3358 else None if is_live is None or is_upcoming is None
3360 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3361 'release_timestamp': live_start_time,
3364 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3366 def get_lang_code(track):
3367 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3368 or track.get('languageCode'))
3370 # Converted into dicts to remove duplicates
3372 get_lang_code(sub): sub
3373 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3374 translation_languages = {
3375 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3376 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3378 def process_language(container, base_url, lang_code, sub_name, query):
3379 lang_subs = container.setdefault(lang_code, [])
3380 for fmt in self._SUBTITLE_FORMATS:
3386 'url': update_url_query(base_url, query),
3390 subtitles, automatic_captions = {}, {}
3391 for lang_code, caption_track in captions.items():
3392 base_url = caption_track.get('baseUrl')
3395 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3396 if caption_track.get('kind') != 'asr':
3400 subtitles, base_url, lang_code, lang_name, {})
3401 if not caption_track.get('isTranslatable'):
3403 for trans_code, trans_name in translation_languages.items():
3406 if caption_track.get('kind') != 'asr':
3407 trans_code += f'-{lang_code}'
3408 trans_name += format_field(lang_name, template=' from %s')
3410 automatic_captions, base_url, trans_code, trans_name, {'tlang': trans_code})
3411 info['automatic_captions'] = automatic_captions
3412 info['subtitles'] = subtitles
3414 parsed_url = compat_urllib_parse_urlparse(url)
3415 for component in [parsed_url.fragment, parsed_url.query]:
3416 query = compat_parse_qs(component)
3417 for k, v in query.items():
3418 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3420 if d_k not in info and k in s_ks:
3421 info[d_k] = parse_duration(query[k][0])
3423 # Youtube Music Auto-generated description
3424 if video_description:
3425 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)
3427 release_year = mobj.group('release_year')
3428 release_date = mobj.group('release_date')
3430 release_date = release_date.replace('-', '')
3431 if not release_year:
3432 release_year = release_date[:4]
3434 'album': mobj.group('album'.strip()),
3435 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3436 'track': mobj.group('track').strip(),
3437 'release_date': release_date,
3438 'release_year': int_or_none(release_year),
3443 initial_data = self._extract_yt_initial_variable(
3444 webpage, self._YT_INITIAL_DATA_RE, video_id,
3446 if not initial_data:
3447 query = {'videoId': video_id}
3448 query.update(self._get_checkok_params())
3449 initial_data = self._extract_response(
3450 item_id=video_id, ep='next', fatal=False,
3451 ytcfg=master_ytcfg, query=query,
3452 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3453 note='Downloading initial data API JSON')
3456 # This will error if there is no livechat
3457 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3458 info.setdefault('subtitles', {})['live_chat'] = [{
3459 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3460 'video_id': video_id,
3462 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3464 except (KeyError, IndexError, TypeError):
3468 info['chapters'] = (
3469 self._extract_chapters_from_json(initial_data, duration)
3470 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3475 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
3477 for content in contents:
3478 vpir = content.get('videoPrimaryInfoRenderer')
3480 stl = vpir.get('superTitleLink')
3482 stl = self._get_text(stl)
3485 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3486 info['location'] = stl
3488 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3491 'series': mobj.group(1),
3492 'season_number': int(mobj.group(2)),
3493 'episode_number': int(mobj.group(3)),
3495 for tlb in (try_get(
3497 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3499 tbr = tlb.get('toggleButtonRenderer') or {}
3500 for getter, regex in [(
3501 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3502 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3503 lambda x: x['accessibility'],
3504 lambda x: x['accessibilityData']['accessibilityData'],
3505 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3506 label = (try_get(tbr, getter, dict) or {}).get('label')
3508 mobj = re.match(regex, label)
3510 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3512 sbr_tooltip = try_get(
3513 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3515 like_count, dislike_count = sbr_tooltip.split(' / ')
3517 'like_count': str_to_int(like_count),
3518 'dislike_count': str_to_int(dislike_count),
3520 vsir = content.get('videoSecondaryInfoRenderer')
3522 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3524 'channel': self._get_text(vor, 'title'),
3525 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3529 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3531 multiple_songs = False
3533 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3534 multiple_songs = True
3537 mrr = row.get('metadataRowRenderer') or {}
3538 mrr_title = mrr.get('title')
3541 mrr_title = self._get_text(mrr, 'title')
3542 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3543 if mrr_title == 'License':
3544 info['license'] = mrr_contents_text
3545 elif not multiple_songs:
3546 if mrr_title == 'Album':
3547 info['album'] = mrr_contents_text
3548 elif mrr_title == 'Artist':
3549 info['artist'] = mrr_contents_text
3550 elif mrr_title == 'Song':
3551 info['track'] = mrr_contents_text
3554 'channel': 'uploader',
3555 'channel_id': 'uploader_id',
3556 'channel_url': 'uploader_url',
3558 for to, frm in fallbacks.items():
3559 if not info.get(to):
3560 info[to] = info.get(frm)
3562 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3567 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3568 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3569 is_membersonly = None
3571 if initial_data and is_private is not None:
3572 is_membersonly = False
3574 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3575 badge_labels = set()
3576 for content in contents:
3577 if not isinstance(content, dict):
3579 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3580 for badge_label in badge_labels:
3581 if badge_label.lower() == 'members only':
3582 is_membersonly = True
3583 elif badge_label.lower() == 'premium':
3585 elif badge_label.lower() == 'unlisted':
3588 info['availability'] = self._availability(
3589 is_private=is_private,
3590 needs_premium=is_premium,
3591 needs_subscription=is_membersonly,
3592 needs_auth=info['age_limit'] >= 18,
3593 is_unlisted=None if is_private is None else is_unlisted)
3595 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3597 self.mark_watched(video_id, player_responses)
3602 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3604 def _extract_channel_id(self, webpage):
3605 channel_id = self._html_search_meta(
3606 'channelId', webpage, 'channel id', default=None)
3609 channel_url = self._html_search_meta(
3610 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3611 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3612 'twitter:app:url:googleplay'), webpage, 'channel url')
3613 return self._search_regex(
3614 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3615 channel_url, 'channel id')
3618 def _extract_basic_item_renderer(item):
3619 # Modified from _extract_grid_item_renderer
3620 known_basic_renderers = (
3621 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3623 for key, renderer in item.items():
3624 if not isinstance(renderer, dict):
3626 elif key in known_basic_renderers:
3628 elif key.startswith('grid') and key.endswith('Renderer'):
3631 def _grid_entries(self, grid_renderer):
3632 for item in grid_renderer['items']:
3633 if not isinstance(item, dict):
3635 renderer = self._extract_basic_item_renderer(item)
3636 if not isinstance(renderer, dict):
3638 title = self._get_text(renderer, 'title')
3641 playlist_id = renderer.get('playlistId')
3643 yield self.url_result(
3644 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3645 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3649 video_id = renderer.get('videoId')
3651 yield self._extract_video(renderer)
3654 channel_id = renderer.get('channelId')
3656 yield self.url_result(
3657 'https://www.youtube.com/channel/%s' % channel_id,
3658 ie=YoutubeTabIE.ie_key(), video_title=title)
3660 # generic endpoint URL support
3661 ep_url = urljoin('https://www.youtube.com/', try_get(
3662 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3665 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3666 if ie.suitable(ep_url):
3667 yield self.url_result(
3668 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3671 def _shelf_entries_from_content(self, shelf_renderer):
3672 content = shelf_renderer.get('content')
3673 if not isinstance(content, dict):
3675 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3677 # TODO: add support for nested playlists so each shelf is processed
3678 # as separate playlist
3679 # TODO: this includes only first N items
3680 for entry in self._grid_entries(renderer):
3682 renderer = content.get('horizontalListRenderer')
3687 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3689 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3691 shelf_url = urljoin('https://www.youtube.com', ep)
3693 # Skipping links to another channels, note that checking for
3694 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3696 if skip_channels and '/channels?' in shelf_url:
3698 title = self._get_text(shelf_renderer, 'title')
3699 yield self.url_result(shelf_url, video_title=title)
3700 # Shelf may not contain shelf URL, fallback to extraction from content
3701 for entry in self._shelf_entries_from_content(shelf_renderer):
3704 def _playlist_entries(self, video_list_renderer):
3705 for content in video_list_renderer['contents']:
3706 if not isinstance(content, dict):
3708 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3709 if not isinstance(renderer, dict):
3711 video_id = renderer.get('videoId')
3714 yield self._extract_video(renderer)
3716 def _rich_entries(self, rich_grid_renderer):
3718 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3719 video_id = renderer.get('videoId')
3722 yield self._extract_video(renderer)
3724 def _video_entry(self, video_renderer):
3725 video_id = video_renderer.get('videoId')
3727 return self._extract_video(video_renderer)
3729 def _post_thread_entries(self, post_thread_renderer):
3730 post_renderer = try_get(
3731 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3732 if not post_renderer:
3735 video_renderer = try_get(
3736 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3737 video_id = video_renderer.get('videoId')
3739 entry = self._extract_video(video_renderer)
3742 # playlist attachment
3743 playlist_id = try_get(
3744 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3746 yield self.url_result(
3747 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3748 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3749 # inline video links
3750 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3752 if not isinstance(run, dict):
3755 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3758 if not YoutubeIE.suitable(ep_url):
3760 ep_video_id = YoutubeIE._match_id(ep_url)
3761 if video_id == ep_video_id:
3763 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3765 def _post_thread_continuation_entries(self, post_thread_continuation):
3766 contents = post_thread_continuation.get('contents')
3767 if not isinstance(contents, list):
3769 for content in contents:
3770 renderer = content.get('backstagePostThreadRenderer')
3771 if not isinstance(renderer, dict):
3773 for entry in self._post_thread_entries(renderer):
3777 def _rich_grid_entries(self
, contents
):
3778 for content
in contents
:
3779 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3781 entry
= self
._video
_entry
(video_renderer
)
3785 def _extract_entries(self, parent_renderer, continuation_list):
3786 # continuation_list is modified in-place with continuation_list = [continuation_token]
3787 continuation_list[:] = [None]
3788 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3789 for content in contents:
3790 if not isinstance(content, dict):
3792 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3794 renderer = content.get('richItemRenderer')
3796 for entry in self._rich_entries(renderer):
3798 continuation_list[0] = self._extract_continuation(parent_renderer)
3800 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3801 for isr_content in isr_contents:
3802 if not isinstance(isr_content, dict):
3806 'playlistVideoListRenderer': self._playlist_entries,
3807 'gridRenderer': self._grid_entries,
3808 'shelfRenderer': lambda x: self._shelf_entries(x),
3809 'backstagePostThreadRenderer': self._post_thread_entries,
3810 'videoRenderer': lambda x: [self._video_entry(x)],
3811 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
3812 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
3814 for key, renderer in isr_content.items():
3815 if key not in known_renderers:
3817 for entry in known_renderers[key](renderer):
3820 continuation_list[0] = self._extract_continuation(renderer)
3823 if not continuation_list[0]:
3824 continuation_list[0] = self._extract_continuation(is_renderer)
3826 if not continuation_list[0]:
3827 continuation_list[0] = self._extract_continuation(parent_renderer)
3829 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
3830 continuation_list = [None]
3831 extract_entries = lambda x: self._extract_entries(x, continuation_list)
3832 tab_content = try_get(tab, lambda x: x['content'], dict)
3836 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3837 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3838 for entry in extract_entries(parent_renderer):
3840 continuation = continuation_list[0]
3842 for page_num in itertools.count(1):
3843 if not continuation:
3845 headers = self.generate_api_headers(
3846 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
3847 response = self._extract_response(
3848 item_id='%s page %s' % (item_id, page_num),
3849 query=continuation, headers=headers, ytcfg=ytcfg,
3850 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3854 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
3855 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
3856 visitor_data = self._extract_visitor_data(response) or visitor_data
3858 known_continuation_renderers = {
3859 'playlistVideoListContinuation': self._playlist_entries,
3860 'gridContinuation': self._grid_entries,
3861 'itemSectionContinuation': self._post_thread_continuation_entries,
3862 'sectionListContinuation': extract_entries, # for feeds
3864 continuation_contents = try_get(
3865 response, lambda x: x['continuationContents'], dict) or {}
3866 continuation_renderer = None
3867 for key, value in continuation_contents.items():
3868 if key not in known_continuation_renderers:
3870 continuation_renderer = value
3871 continuation_list = [None]
3872 for entry in known_continuation_renderers[key](continuation_renderer):
3874 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3876 if continuation_renderer:
3880 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3881 'gridVideoRenderer': (self._grid_entries, 'items'),
3882 'gridChannelRenderer': (self._grid_entries, 'items'),
3883 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3884 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3885 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3886 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3888 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3889 continuation_items = try_get(
3890 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3891 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3892 video_items_renderer = None
3893 for key, value in continuation_item.items():
3894 if key not in known_renderers:
3896 video_items_renderer = {known_renderers[key][1]: continuation_items}
3897 continuation_list = [None]
3898 for entry in known_renderers[key][0](video_items_renderer):
3900 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3902 if video_items_renderer:
3907 def _extract_selected_tab(tabs):
3909 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3910 if renderer.get('selected') is True:
3913 raise ExtractorError('Unable to find selected tab')
3916 def _extract_uploader(cls, data):
3918 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3920 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3922 uploader['uploader'] = owner.get('text')
3923 uploader['uploader_id'] = try_get(
3924 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3925 uploader['uploader_url'] = urljoin(
3926 'https://www.youtube.com/',
3927 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3928 return {k: v for k, v in uploader.items() if v is not None}
3930 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
3931 playlist_id = title = description = channel_url = channel_name = channel_id = None
3934 selected_tab = self._extract_selected_tab(tabs)
3935 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3937 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3939 channel_name = renderer.get('title')
3940 channel_url = renderer.get('channelUrl')
3941 channel_id = renderer.get('externalId')
3944 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3947 title = renderer.get('title')
3948 description = renderer.get('description', '')
3949 playlist_id = channel_id
3950 tags = renderer.get('keywords', '').split()
3952 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
3953 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
3954 def _get_uncropped(url):
3955 return url_or_none((url or '').split('=')[0] + '=s0')
3957 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
3958 if avatar_thumbnails:
3959 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
3960 if uncropped_avatar:
3961 avatar_thumbnails.append({
3962 'url': uncropped_avatar,
3963 'id': 'avatar_uncropped',
3967 channel_banners = self._extract_thumbnails(
3968 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
3969 for banner in channel_banners:
3970 banner['preference'] = -10
3973 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
3974 if uncropped_banner:
3975 channel_banners.append({
3976 'url': uncropped_banner,
3977 'id': 'banner_uncropped',
3981 primary_thumbnails = self._extract_thumbnails(
3982 primary_sidebar_renderer, ('thumbnailRenderer', 'playlistVideoThumbnailRenderer', 'thumbnail'))
3984 if playlist_id is None:
3985 playlist_id = item_id
3987 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
3988 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
3990 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
3991 title += format_field(selected_tab, 'title', ' - %s')
3992 title += format_field(selected_tab, 'expandedText', ' - %s')
3995 'playlist_id': playlist_id,
3996 'playlist_title': title,
3997 'playlist_description': description,
3998 'uploader': channel_name,
3999 'uploader_id': channel_id,
4000 'uploader_url': channel_url,
4001 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4003 'view_count': self._get_count(playlist_stats, 1),
4004 'availability': self._extract_availability(data),
4005 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4006 'playlist_count': self._get_count(playlist_stats, 0),
4007 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4010 metadata.update(self._extract_uploader(data))
4012 'channel': metadata['uploader'],
4013 'channel_id': metadata['uploader_id'],
4014 'channel_url': metadata['uploader_url']})
4015 return self.playlist_result(
4017 selected_tab, playlist_id, ytcfg,
4018 self._extract_account_syncid(ytcfg, data),
4019 self._extract_visitor_data(data, ytcfg)),
4022 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4023 first_id = last_id = response = None
4024 for page_num in itertools.count(1):
4025 videos = list(self._playlist_entries(playlist))
4028 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4029 if start >= len(videos):
4031 for video in videos[start:]:
4032 if video['id'] == first_id:
4033 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4036 first_id = first_id or videos[0]['id']
4037 last_id = videos[-1]['id']
4038 watch_endpoint = try_get(
4039 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4040 headers = self.generate_api_headers(
4041 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4042 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4044 'playlistId': playlist_id,
4045 'videoId': watch_endpoint.get('videoId') or last_id,
4046 'index': watch_endpoint.get('index') or len(videos),
4047 'params': watch_endpoint.get('params') or 'OAE%3D'
4049 response = self._extract_response(
4050 item_id='%s page %d' % (playlist_id, page_num),
4051 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4052 check_get_keys='contents'
4055 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4057 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4058 title = playlist.get('title') or try_get(
4059 data, lambda x: x['titleText']['simpleText'], compat_str)
4060 playlist_id = playlist.get('playlistId') or item_id
4062 # Delegating everything except mix playlists to regular tab-based playlist URL
4063 playlist_url = urljoin(url, try_get(
4064 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4066 if playlist_url and playlist_url != url:
4067 return self.url_result(
4068 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4071 return self.playlist_result(
4072 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4073 playlist_id=playlist_id, playlist_title=title)
4075 def _extract_availability(self, data):
4077 Gets the availability of a given playlist/tab.
4078 Note: Unless YouTube tells us explicitly, we do not assume it is public
4079 @param data: response
4081 is_private = is_unlisted = None
4082 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4083 badge_labels = self._extract_badges(renderer)
4085 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4086 privacy_dropdown_entries = try_get(
4087 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4088 for renderer_dict in privacy_dropdown_entries:
4089 is_selected = try_get(
4090 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4093 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4095 badge_labels.add(label.lower())
4098 for badge_label in badge_labels:
4099 if badge_label == 'unlisted':
4101 elif badge_label == 'private':
4103 elif badge_label == 'public':
4104 is_unlisted = is_private = False
4105 return self._availability(is_private, False, False, False, is_unlisted)
4108 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4109 sidebar_renderer = try_get(
4110 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4111 for item in sidebar_renderer:
4112 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4116 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4118 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4120 browse_id = params = None
4121 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4124 menu_renderer = try_get(
4125 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4126 for menu_item in menu_renderer:
4127 if not isinstance(menu_item, dict):
4129 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4131 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4132 if not text or text.lower() != 'show unavailable videos':
4134 browse_endpoint = try_get(
4135 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4136 browse_id = browse_endpoint.get('browseId')
4137 params = browse_endpoint.get('params')
4140 headers = self.generate_api_headers(
4141 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4142 visitor_data=self._extract_visitor_data(data, ytcfg))
4144 'params': params or 'wgYCCAA=',
4145 'browseId': browse_id or 'VL%s' % item_id
4147 return self._extract_response(
4148 item_id=item_id, headers=headers, query=query,
4149 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4150 note='Downloading API JSON with unavailable videos')
4152 def _extract_webpage(self, url, item_id, fatal=True):
4153 retries = self.get_param('extractor_retries', 3)
4155 webpage = data = last_error = None
4156 while count < retries:
4158 # Sometimes youtube returns a webpage with incomplete ytInitialData
4159 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4161 self.report_warning('%s. Retrying ...' % last_error)
4163 webpage = self._download_webpage(
4165 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4166 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4167 except ExtractorError as e:
4168 if isinstance(e.cause, network_exceptions):
4169 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4170 last_error = error_to_compat_str(e.cause or e.msg)
4175 self.report_warning(error_to_compat_str(e))
4179 self._extract_and_report_alerts(data)
4180 except ExtractorError as e:
4183 self.report_warning(error_to_compat_str(e))
4186 if dict_get(data, ('contents', 'currentVideoEndpoint')):
4189 last_error = 'Incomplete yt initial data received'
4190 if count >= retries:
4192 raise ExtractorError(last_error)
4193 self.report_warning(last_error)
4196 return webpage, data
4198 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4200 if 'webpage' not in self._configuration_arg('skip'):
4201 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4202 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4204 if not ytcfg and self.is_authenticated:
4205 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download.'
4206 if 'authcheck' not in self._configuration_arg('skip') and fatal:
4207 raise ExtractorError(
4208 msg + ' If you are not downloading private content, or your cookies are only for the first account and channel,'
4209 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4211 self.report_warning(msg, only_once=True)
4212 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4215 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4216 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4217 resolve_response = self._extract_response(
4218 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4219 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4220 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4221 for ep_key, ep in endpoints.items():
4222 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4224 return self._extract_response(
4225 item_id=item_id, query=params, ep=ep, headers=headers,
4226 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4227 check_get_keys=('contents', 'currentVideoEndpoint'))
4228 err_note = 'Failed to resolve url (does the playlist exist?)'
4230 raise ExtractorError(err_note, expected=True)
4231 self.report_warning(err_note, item_id)
4234 def _smuggle_data(entries, data):
4235 for entry in entries:
4237 entry['url'] = smuggle_url(entry['url'], data)
4240 _SEARCH_PARAMS = None
4242 def _search_results(self, query, params=NO_DEFAULT):
4243 data = {'query': query}
4244 if params is NO_DEFAULT:
4245 params = self._SEARCH_PARAMS
4247 data['params'] = params
4248 continuation_list = [None]
4249 for page_num in itertools.count(1):
4250 data.update(continuation_list[0] or {})
4251 search = self._extract_response(
4252 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4253 check_get_keys=('contents', 'onResponseReceivedCommands'))
4254 slr_contents = try_get(
4256 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4257 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4259 yield from self._extract_entries({'contents': slr_contents}, continuation_list)
4260 if not continuation_list[0]:
4264 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4265 IE_DESC = 'YouTube Tabs'
4266 _VALID_URL = r'''(?x
:
4270 youtube(?
:kids
)?\
.com|
4274 (?P
<channel_type
>channel|c|user|browse
)/|
4277 (?
:playlist|watch
)\?.*?
\blist
=
4279 (?
!(?
:%(reserved_names)s)\b) # Direct URLs
4283 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4284 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4286 IE_NAME = 'youtube:tab'
4289 'note': 'playlists, multipage',
4290 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4291 'playlist_mincount': 94,
4293 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4294 'title': 'Igor Kleiner - Playlists',
4295 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4296 'uploader': 'Igor Kleiner',
4297 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4298 'channel': 'Igor Kleiner',
4299 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4300 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4301 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4302 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4303 'channel_follower_count': int
4306 'note': 'playlists, multipage, different order',
4307 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4308 'playlist_mincount': 94,
4310 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4311 'title': 'Igor Kleiner - Playlists',
4312 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4313 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4314 'uploader': 'Igor Kleiner',
4315 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4316 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4317 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4318 'channel': 'Igor Kleiner',
4319 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4320 'channel_follower_count': int
4323 'note': 'playlists, series',
4324 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4325 'playlist_mincount': 5,
4327 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4328 'title': '3Blue1Brown - Playlists',
4329 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4330 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4331 'uploader': '3Blue1Brown',
4332 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4333 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4334 'channel': '3Blue1Brown',
4335 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4336 'tags': ['Mathematics'],
4337 'channel_follower_count': int
4340 'note': 'playlists, singlepage',
4341 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4342 'playlist_mincount': 4,
4344 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4345 'title': 'ThirstForScience - Playlists',
4346 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4347 'uploader': 'ThirstForScience',
4348 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4349 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4350 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4351 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4353 'channel': 'ThirstForScience',
4354 'channel_follower_count': int
4357 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4358 'only_matching': True,
4360 'note': 'basic, single video playlist',
4361 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4363 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4364 'uploader': 'Sergey M.',
4365 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4366 'title': 'youtube-dl public playlist',
4370 'modified_date': '20201130',
4371 'channel': 'Sergey M.',
4372 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4373 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4374 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4376 'playlist_count': 1,
4378 'note': 'empty playlist',
4379 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4381 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4382 'uploader': 'Sergey M.',
4383 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4384 'title': 'youtube-dl empty playlist',
4386 'channel': 'Sergey M.',
4388 'modified_date': '20160902',
4389 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4390 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4391 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4393 'playlist_count': 0,
4396 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4398 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4399 'title': 'lex will - Home',
4400 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4401 'uploader': 'lex will',
4402 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4403 'channel': 'lex will',
4404 'tags': ['bible', 'history', 'prophesy'],
4405 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4406 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4407 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4408 'channel_follower_count': int
4410 'playlist_mincount': 2,
4412 'note': 'Videos tab',
4413 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4415 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4416 'title': 'lex will - Videos',
4417 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4418 'uploader': 'lex will',
4419 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4420 'tags': ['bible', 'history', 'prophesy'],
4421 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4422 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4423 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4424 'channel': 'lex will',
4425 'channel_follower_count': int
4427 'playlist_mincount': 975,
4429 'note': 'Videos tab, sorted by popular',
4430 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4432 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4433 'title': 'lex will - Videos',
4434 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4435 'uploader': 'lex will',
4436 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4437 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4438 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4439 'channel': 'lex will',
4440 'tags': ['bible', 'history', 'prophesy'],
4441 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4442 'channel_follower_count': int
4444 'playlist_mincount': 199,
4446 'note': 'Playlists tab',
4447 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4449 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4450 'title': 'lex will - Playlists',
4451 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4452 'uploader': 'lex will',
4453 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4454 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4455 'channel': 'lex will',
4456 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4457 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4458 'tags': ['bible', 'history', 'prophesy'],
4459 'channel_follower_count': int
4461 'playlist_mincount': 17,
4463 'note': 'Community tab',
4464 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4466 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4467 'title': 'lex will - Community',
4468 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4469 'uploader': 'lex will',
4470 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4471 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4472 'channel': 'lex will',
4473 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4474 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4475 'tags': ['bible', 'history', 'prophesy'],
4476 'channel_follower_count': int
4478 'playlist_mincount': 18,
4480 'note': 'Channels tab',
4481 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4483 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4484 'title': 'lex will - Channels',
4485 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4486 'uploader': 'lex will',
4487 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4488 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4489 'channel': 'lex will',
4490 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4491 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4492 'tags': ['bible', 'history', 'prophesy'],
4493 'channel_follower_count': int
4495 'playlist_mincount': 12,
4497 'note': 'Search tab',
4498 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4499 'playlist_mincount': 40,
4501 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4502 'title': '3Blue1Brown - Search - linear algebra',
4503 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4504 'uploader': '3Blue1Brown',
4505 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4506 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4507 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4508 'tags': ['Mathematics'],
4509 'channel': '3Blue1Brown',
4510 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4511 'channel_follower_count': int
4514 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4515 'only_matching': True,
4517 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4518 'only_matching': True,
4520 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4521 'only_matching': True,
4523 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4524 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4526 'title': '29C3: Not my department',
4527 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4528 'uploader': 'Christiaan008',
4529 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4530 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4532 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4534 'modified_date': '20150605',
4535 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4536 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4537 'channel': 'Christiaan008',
4539 'playlist_count': 96,
4541 'note': 'Large playlist',
4542 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4544 'title': 'Uploads from Cauchemar',
4545 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4546 'uploader': 'Cauchemar',
4547 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4548 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4550 'modified_date': r're:\d{8}',
4551 'channel': 'Cauchemar',
4552 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4555 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4557 'playlist_mincount': 1123,
4558 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4560 'note': 'even larger playlist, 8832 videos',
4561 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4562 'only_matching': True,
4564 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4565 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4567 'title': 'Uploads from Interstellar Movie',
4568 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4569 'uploader': 'Interstellar Movie',
4570 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4571 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4574 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4575 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4576 'channel': 'Interstellar Movie',
4578 'modified_date': r're:\d{8}',
4580 'playlist_mincount': 21,
4582 'note': 'Playlist with "show unavailable videos" button',
4583 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4585 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4586 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4587 'uploader': 'Phim Siêu Nhân Nhật Bản',
4588 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4590 'channel': 'Phim Siêu Nhân Nhật Bản',
4592 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4594 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4595 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4596 'modified_date': r're:\d{8}',
4598 'playlist_mincount': 200,
4599 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4601 'note': 'Playlist with unavailable videos in page 7',
4602 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4604 'title': 'Uploads from BlankTV',
4605 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4606 'uploader': 'BlankTV',
4607 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4608 'channel': 'BlankTV',
4609 'channel_url': 'https://www.youtube.com/c/blanktv',
4610 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4613 'uploader_url': 'https://www.youtube.com/c/blanktv',
4614 'modified_date': r're:\d{8}',
4617 'playlist_mincount': 1000,
4618 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4620 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4621 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4623 'title': 'Data Analysis with Dr Mike Pound',
4624 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4625 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4626 'uploader': 'Computerphile',
4627 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4628 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4631 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4632 'channel_url': 'https://www.youtube.com/user/Computerphile',
4633 'channel': 'Computerphile',
4635 'playlist_mincount': 11,
4637 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4638 'only_matching': True,
4640 'note': 'Playlist URL that does not actually serve a playlist',
4641 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4643 'id': 'FqZTN594JQw',
4645 'title': "Smiley's People 01 detective, Adventure Series, Action",
4646 'uploader': 'STREEM',
4647 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4648 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4649 'upload_date': '20150526',
4650 'license': 'Standard YouTube License',
4651 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4652 'categories': ['People & Blogs'],
4658 'skip_download': True,
4660 'skip': 'This video is not available.',
4661 'add_ie': [YoutubeIE.ie_key()],
4663 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4664 'only_matching': True,
4666 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4667 'only_matching': True,
4669 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4671 'id': 'GgL890LIznQ', # This will keep changing
4674 'uploader': 'Sky News',
4675 'uploader_id': 'skynews',
4676 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4677 'upload_date': r're:\d{8}',
4679 'categories': ['News & Politics'],
4682 'release_timestamp': 1642502819,
4683 'channel': 'Sky News',
4684 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4687 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4688 'playable_in_embed': True,
4689 'release_date': '20220118',
4690 'availability': 'public',
4691 'live_status': 'is_live',
4692 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4693 'channel_follower_count': int
4696 'skip_download': True,
4698 'expected_warnings': ['Ignoring subtitle tracks found in '],
4700 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4702 'id': 'a48o2S1cPoo',
4704 'title': 'The Young Turks - Live Main Show',
4705 'uploader': 'The Young Turks',
4706 'uploader_id': 'TheYoungTurks',
4707 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4708 'upload_date': '20150715',
4709 'license': 'Standard YouTube License',
4710 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4711 'categories': ['News & Politics'],
4712 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4716 'skip_download': True,
4718 'only_matching': True,
4720 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4721 'only_matching': True,
4723 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4724 'only_matching': True,
4726 'note': 'A channel that is not live. Should raise error',
4727 'url': 'https://www.youtube.com/user/numberphile/live',
4728 'only_matching': True,
4730 'url': 'https://www.youtube.com/feed/trending',
4731 'only_matching': True,
4733 'url': 'https://www.youtube.com/feed/library',
4734 'only_matching': True,
4736 'url': 'https://www.youtube.com/feed/history',
4737 'only_matching': True,
4739 'url': 'https://www.youtube.com/feed/subscriptions',
4740 'only_matching': True,
4742 'url': 'https://www.youtube.com/feed/watch_later',
4743 'only_matching': True,
4745 'note': 'Recommended - redirects to home page.',
4746 'url': 'https://www.youtube.com/feed/recommended',
4747 'only_matching': True,
4749 'note': 'inline playlist with not always working continuations',
4750 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4751 'only_matching': True,
4753 'url': 'https://www.youtube.com/course',
4754 'only_matching': True,
4756 'url': 'https://www.youtube.com/zsecurity',
4757 'only_matching': True,
4759 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4760 'only_matching': True,
4762 'url': 'https://www.youtube.com/TheYoungTurks/live',
4763 'only_matching': True,
4765 'url': 'https://www.youtube.com/hashtag/cctv9',
4771 'playlist_mincount': 350,
4773 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
4774 'only_matching': True,
4776 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
4777 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4778 'only_matching': True
4780 'note': '/browse/ should redirect to /channel/',
4781 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
4782 'only_matching': True
4784 'note': 'VLPL, should redirect to playlist?list=PL...',
4785 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4787 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
4788 'uploader': 'NoCopyrightSounds',
4789 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
4790 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4791 'title': 'NCS Releases',
4792 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4793 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
4794 'modified_date': r're:\d{8}',
4796 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
4798 'channel': 'NoCopyrightSounds',
4800 'playlist_mincount': 166,
4801 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4803 'note': 'Topic, should redirect to playlist?list=UU...',
4804 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4806 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4807 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4808 'title': 'Uploads from Royalty Free Music - Topic',
4809 'uploader': 'Royalty Free Music - Topic',
4811 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4812 'channel': 'Royalty Free Music - Topic',
4814 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4815 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4816 'modified_date': r're:\d{8}',
4817 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4820 'expected_warnings': [
4821 'The URL does not have a videos tab',
4822 r'[Uu]navailable videos (are|will be) hidden',
4824 'playlist_mincount': 101,
4826 'note': 'Topic without a UU playlist',
4827 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
4829 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
4830 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
4833 'expected_warnings': [
4834 'the playlist redirect gave error',
4836 'playlist_mincount': 9,
4838 'note': 'Youtube music Album',
4839 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
4841 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
4842 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
4846 'availability': 'unlisted',
4847 'modified_date': r're:\d{8}',
4849 'playlist_count': 50,
4851 'note': 'unlisted single video playlist',
4852 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4854 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4855 'uploader': 'colethedj',
4856 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
4857 'title': 'yt-dlp unlisted playlist test',
4858 'availability': 'unlisted',
4860 'modified_date': '20211208',
4861 'channel': 'colethedj',
4864 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4865 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
4866 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
4868 'playlist_count': 1,
4870 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
4871 'url': 'https://www.youtube.com/feed/recommended',
4873 'id': 'recommended',
4874 'title': 'recommended',
4877 'playlist_mincount': 50,
4879 'skip_download': True,
4880 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4883 'note': 'API Fallback: /videos tab, sorted by oldest first',
4884 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
4886 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4887 'title': 'Cody\'sLab - Videos',
4888 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
4889 'uploader': 'Cody\'sLab',
4890 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4891 'channel': 'Cody\'sLab',
4892 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
4894 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4895 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
4896 'channel_follower_count': int
4898 'playlist_mincount': 650,
4900 'skip_download': True,
4901 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4904 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
4905 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
4907 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
4908 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4909 'title': 'Uploads from Royalty Free Music - Topic',
4910 'uploader': 'Royalty Free Music - Topic',
4911 'modified_date': r're:\d{8}',
4912 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
4914 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4916 'channel': 'Royalty Free Music - Topic',
4918 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
4920 'expected_warnings': [
4921 'does not have a videos tab',
4922 r'[Uu]navailable videos (are|will be) hidden',
4924 'playlist_mincount': 101,
4926 'skip_download': True,
4927 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
4932 def suitable(cls, url):
4933 return False if YoutubeIE.suitable(url) else super(
4934 YoutubeTabIE, cls).suitable(url)
4936 def _real_extract(self, url):
4937 url, smuggled_data = unsmuggle_url(url, {})
4938 if self.is_music_url(url):
4939 smuggled_data['is_music_url'] = True
4940 info_dict = self.__real_extract(url, smuggled_data)
4941 if info_dict.get('entries'):
4942 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4945 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
4947 def __real_extract(self, url, smuggled_data):
4948 item_id = self._match_id(url)
4949 url = compat_urlparse.urlunparse(
4950 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4951 compat_opts = self.get_param('compat_opts', [])
4954 mobj = self._URL_RE.match(url).groupdict()
4955 mobj.update((k, '') for k, v in mobj.items() if v is None)
4958 mobj, redirect_warning = get_mobj(url), None
4959 # Youtube returns incomplete data if tabname is not lower case
4960 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4962 if smuggled_data.get('is_music_url'):
4963 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
4964 item_id = item_id[2:]
4965 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
4966 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
4967 mdata = self._extract_tab_endpoint(
4968 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
4969 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
4970 get_all=False, expected_type=compat_str)
4972 raise ExtractorError('Failed to resolve album to playlist')
4973 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
4974 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
4975 pre = f'https://www.youtube.com/channel/{item_id}'
4977 original_tab_name = tab
4978 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4979 # Home URLs should redirect to /videos/
4980 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
4981 'To download only the videos in the home page, add a "/featured" to the URL')
4984 url = ''.join((pre, tab, post))
4985 mobj = get_mobj(url)
4987 # Handle both video/playlist URLs
4989 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
4991 if not video_id and mobj['not_channel'].startswith('watch'):
4993 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4994 raise ExtractorError('Unable to recognize tab page')
4995 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4996 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
4997 url = f'https://www.youtube.com/playlist?list={playlist_id}'
4998 mobj = get_mobj(url)
5000 if video_id and playlist_id:
5001 if self.get_param('noplaylist'):
5002 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5003 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5004 ie=YoutubeIE.ie_key(), video_id=video_id)
5005 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5007 data, ytcfg = self._extract_data(url, item_id)
5009 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5011 selected_tab = self._extract_selected_tab(tabs)
5012 selected_tab_name = selected_tab.get('title', '').lower()
5013 if selected_tab_name == 'home':
5014 selected_tab_name = 'featured'
5015 requested_tab_name = mobj['tab'][1:]
5016 if 'no-youtube-channel-redirect' not in compat_opts:
5017 if requested_tab_name == 'live':
5018 # Live tab should have redirected to the video
5019 raise ExtractorError('The channel is not currently live', expected=True)
5020 if requested_tab_name not in ('', selected_tab_name):
5021 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5022 if not original_tab_name:
5023 if item_id[:2] == 'UC':
5024 # Topic channels don't have /videos. Use the equivalent playlist instead
5025 pl_id = f'UU{item_id[2:]}'
5026 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5028 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5029 except ExtractorError:
5030 redirect_warning += ' and the playlist redirect gave error'
5032 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5033 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5034 if selected_tab_name and selected_tab_name != requested_tab_name:
5035 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5037 raise ExtractorError(redirect_warning, expected=True)
5039 if redirect_warning:
5040 self.to_screen(redirect_warning)
5041 self.write_debug(f'Final URL: {url}')
5043 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5044 if 'no-youtube-unavailable-videos' not in compat_opts:
5045 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5046 self._extract_and_report_alerts(data, only_once=True)
5047 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5049 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5051 playlist = traverse_obj(
5052 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5054 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5056 video_id = traverse_obj(
5057 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5059 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5060 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5061 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5062 ie=YoutubeIE.ie_key(), video_id=video_id)
5064 raise ExtractorError('Unable to recognize tab page')
5067 class YoutubePlaylistIE(InfoExtractor):
5068 IE_DESC = 'YouTube playlists'
5069 _VALID_URL = r'''(?x
)(?
:
5074 youtube(?
:kids
)?\
.com|
5079 (?P
<id>%(playlist_id)s)
5081 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5082 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5084 IE_NAME = 'youtube:playlist'
5086 'note': 'issue #673',
5087 'url': 'PLBB231211A4F62143',
5089 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5090 'id': 'PLBB231211A4F62143',
5091 'uploader': 'Wickman',
5092 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5093 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5095 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5096 'modified_date': r're:\d{8}',
5097 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5098 'channel': 'Wickman',
5100 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5102 'playlist_mincount': 29,
5104 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5106 'title': 'YDL_safe_search',
5107 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5109 'playlist_count': 2,
5110 'skip': 'This playlist is private',
5113 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5114 'playlist_count': 4,
5117 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5118 'uploader': 'milan',
5119 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5121 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5123 'modified_date': '20140919',
5126 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5127 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5129 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5131 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5132 'playlist_mincount': 654,
5134 'title': '2018 Chinese New Singles (11/6 updated)',
5135 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5137 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5138 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5141 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5143 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5144 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5145 'modified_date': r're:\d{8}',
5147 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5149 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5150 'only_matching': True,
5152 # music album playlist
5153 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5154 'only_matching': True,
5158 def suitable(cls, url):
5159 if YoutubeTabIE.suitable(url):
5161 from ..utils import parse_qs
5163 if qs.get('v', [None])[0]:
5165 return super(YoutubePlaylistIE, cls).suitable(url)
5167 def _real_extract(self, url):
5168 playlist_id = self._match_id(url)
5169 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5170 url = update_url_query(
5171 'https://www.youtube.com/playlist',
5172 parse_qs(url) or {'list': playlist_id})
5174 url = smuggle_url(url, {'is_music_url': True})
5175 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5178 class YoutubeYtBeIE(InfoExtractor):
5179 IE_DESC = 'youtu.be'
5180 _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}
5182 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5184 'id': 'yeWKywCrFtk',
5186 'title': 'Small Scale Baler and Braiding Rugs',
5187 'uploader': 'Backus-Page House Museum',
5188 'uploader_id': 'backuspagemuseum',
5189 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5190 'upload_date': '20161008',
5191 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5192 'categories': ['Nonprofits & Activism'],
5196 'playable_in_embed': True,
5197 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5198 'channel': 'Backus-Page House Museum',
5199 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5200 'live_status': 'not_live',
5202 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5203 'availability': 'public',
5208 'skip_download': True,
5211 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5212 'only_matching': True,
5215 def _real_extract(self, url):
5216 mobj = self._match_valid_url(url)
5217 video_id = mobj.group('id')
5218 playlist_id = mobj.group('playlist_id')
5219 return self.url_result(
5220 update_url_query('https://www.youtube.com/watch', {
5222 'list': playlist_id,
5223 'feature': 'youtu.be',
5224 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5227 class YoutubeLivestreamEmbedIE(InfoExtractor):
5228 IE_DESC = 'YouTube livestream embeds'
5229 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5231 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5232 'only_matching': True,
5235 def _real_extract(self, url):
5236 channel_id = self._match_id(url)
5237 return self.url_result(
5238 f'https://www.youtube.com/channel/{channel_id}/live',
5239 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5242 class YoutubeYtUserIE(InfoExtractor):
5243 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5244 IE_NAME = 'youtube:user'
5245 _VALID_URL = r'ytuser:(?P<id>.+)'
5247 'url': 'ytuser:phihag',
5248 'only_matching': True,
5251 def _real_extract(self, url):
5252 user_id = self._match_id(url)
5253 return self.url_result(
5254 'https://www.youtube.com/user/%s/videos' % user_id,
5255 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5258 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5259 IE_NAME = 'youtube:favorites'
5260 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5261 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5262 _LOGIN_REQUIRED = True
5265 'only_matching': True,
5267 'url': ':ytfavorites',
5268 'only_matching': True,
5271 def _real_extract(self, url):
5272 return self.url_result(
5273 'https://www.youtube.com/playlist?list=LL',
5274 ie=YoutubeTabIE.ie_key())
5277 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5278 IE_DESC = 'YouTube search'
5279 IE_NAME = 'youtube:search'
5280 _SEARCH_KEY = 'ytsearch'
5281 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5285 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5286 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5287 _SEARCH_KEY = 'ytsearchdate'
5288 IE_DESC = 'YouTube search, newest videos first'
5289 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5292 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5293 IE_DESC = 'YouTube search URLs with sorting and filter support'
5294 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5295 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
5297 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5298 'playlist_mincount': 5,
5300 'id': 'youtube-dl test video',
5301 'title': 'youtube-dl test video',
5304 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5305 'playlist_mincount': 5,
5312 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5313 'only_matching': True,
5316 def _real_extract(self, url):
5318 query = (qs.get('search_query') or qs.get('q'))[0]
5319 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5322 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
5324 Base class for feed extractors
5325 Subclasses must define the _FEED_NAME property.
5327 _LOGIN_REQUIRED = True
5332 return 'youtube:%s' % self._FEED_NAME
5334 def _real_extract(self, url):
5335 return self.url_result(
5336 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
5337 ie=YoutubeTabIE.ie_key())
5340 class YoutubeWatchLaterIE(InfoExtractor):
5341 IE_NAME = 'youtube:watchlater'
5342 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5343 _VALID_URL = r':ytwatchlater'
5345 'url': ':ytwatchlater',
5346 'only_matching': True,
5349 def _real_extract(self, url):
5350 return self.url_result(
5351 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5354 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5355 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5356 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5357 _FEED_NAME = 'recommended'
5358 _LOGIN_REQUIRED = False
5361 'only_matching': True,
5363 'url': ':ytrecommended',
5364 'only_matching': True,
5366 'url': 'https://youtube.com',
5367 'only_matching': True,
5371 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5372 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5373 _VALID_URL = r':ytsub(?:scription)?s?'
5374 _FEED_NAME = 'subscriptions'
5377 'only_matching': True,
5379 'url': ':ytsubscriptions',
5380 'only_matching': True,
5384 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5385 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5386 _VALID_URL = r':ythis(?:tory)?'
5387 _FEED_NAME = 'history'
5389 'url': ':ythistory',
5390 'only_matching': True,
5394 class YoutubeTruncatedURLIE(InfoExtractor):
5395 IE_NAME = 'youtube:truncated_url'
5396 IE_DESC = False # Do not list
5397 _VALID_URL = r'''(?x
)
5399 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
5402 annotation_id
=annotation_
[^
&]+|
5408 attribution_link
\?a
=[^
&]+
5414 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5415 'only_matching': True,
5417 'url': 'https://www.youtube.com/watch?',
5418 'only_matching': True,
5420 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5421 'only_matching': True,
5423 'url': 'https://www.youtube.com/watch?feature=foo',
5424 'only_matching': True,
5426 'url': 'https://www.youtube.com/watch?hl=en-GB',
5427 'only_matching': True,
5429 'url': 'https://www.youtube.com/watch?t=2372',
5430 'only_matching': True,
5433 def _real_extract(self, url):
5434 raise ExtractorError(
5435 'Did you forget to quote the URL? Remember that & is a meta '
5436 'character in most shells, so you want to put the URL in quotes, '
5438 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5439 ' or simply youtube-dl BaW_jenozKc .',
5443 class YoutubeClipIE(InfoExtractor):
5444 IE_NAME = 'youtube:clip'
5445 IE_DESC = False # Do not list
5446 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5448 def _real_extract(self, url):
5449 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5450 return self.url_result(url, 'Generic')
5453 class YoutubeTruncatedIDIE(InfoExtractor):
5454 IE_NAME = 'youtube:truncated_id'
5455 IE_DESC = False # Do not list
5456 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5459 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5460 'only_matching': True,
5463 def _real_extract(self, url):
5464 video_id = self._match_id(url)
5465 raise ExtractorError(
5466 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),