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
76 # any clients starting with _ cannot be explicity requested by the user
79 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
80 'INNERTUBE_CONTEXT': {
83 'clientVersion': '2.20211221.00.00',
86 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
89 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
90 'INNERTUBE_CONTEXT': {
92 'clientName': 'WEB_EMBEDDED_PLAYER',
93 'clientVersion': '1.20211215.00.01',
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
99 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
100 'INNERTUBE_HOST': 'music.youtube.com',
101 'INNERTUBE_CONTEXT': {
103 'clientName': 'WEB_REMIX',
104 'clientVersion': '1.20211213.00.00',
107 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
110 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
111 'INNERTUBE_CONTEXT': {
113 'clientName': 'WEB_CREATOR',
114 'clientVersion': '1.20211220.02.00',
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
120 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
121 'INNERTUBE_CONTEXT': {
123 'clientName': 'ANDROID',
124 'clientVersion': '16.49',
127 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
128 'REQUIRE_JS_PLAYER': False
130 'android_embedded': {
131 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
132 'INNERTUBE_CONTEXT': {
134 'clientName': 'ANDROID_EMBEDDED_PLAYER',
135 'clientVersion': '16.49',
138 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
139 'REQUIRE_JS_PLAYER': False
142 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
143 'INNERTUBE_CONTEXT': {
145 'clientName': 'ANDROID_MUSIC',
146 'clientVersion': '4.57',
149 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
150 'REQUIRE_JS_PLAYER': False
153 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
154 'INNERTUBE_CONTEXT': {
156 'clientName': 'ANDROID_CREATOR',
157 'clientVersion': '21.47',
160 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
161 'REQUIRE_JS_PLAYER': False
163 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
164 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
166 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
167 'INNERTUBE_CONTEXT': {
170 'clientVersion': '16.46',
171 'deviceModel': 'iPhone14,3',
174 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
175 'REQUIRE_JS_PLAYER': False
178 'INNERTUBE_CONTEXT': {
180 'clientName': 'IOS_MESSAGES_EXTENSION',
181 'clientVersion': '16.46',
182 'deviceModel': 'iPhone14,3',
185 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
186 'REQUIRE_JS_PLAYER': False
189 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
190 'INNERTUBE_CONTEXT': {
192 'clientName': 'IOS_MUSIC',
193 'clientVersion': '4.57',
196 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
197 'REQUIRE_JS_PLAYER': False
200 'INNERTUBE_CONTEXT': {
202 'clientName': 'IOS_CREATOR',
203 'clientVersion': '21.47',
206 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
207 'REQUIRE_JS_PLAYER': False
209 # mweb has 'ultralow' formats
210 # See: https://github.com/yt-dlp/yt-dlp/pull/557
212 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
213 'INNERTUBE_CONTEXT': {
215 'clientName': 'MWEB',
216 'clientVersion': '2.20211221.01.00',
219 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
221 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
222 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
224 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
225 'INNERTUBE_CONTEXT': {
227 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
228 'clientVersion': '2.0',
231 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
236 def _split_innertube_client(client_name
):
237 variant
, *base
= client_name
.rsplit('.', 1)
239 return variant
, base
[0], variant
240 base
, *variant
= client_name
.split('_', 1)
241 return client_name
, base
, variant
[0] if variant
else None
244 def build_innertube_clients():
246 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
248 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
249 priority
= qualities(BASE_CLIENTS
[::-1])
251 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
252 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
253 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
254 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
255 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
257 _
, base_client
, variant
= _split_innertube_client(client
)
258 ytcfg
['priority'] = 10 * priority(base_client
)
261 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
262 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
263 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
264 embedscreen
['priority'] -= 3
265 elif variant
== 'embedded':
266 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
267 ytcfg
['priority'] -= 2
269 ytcfg
['priority'] -= 3
272 build_innertube_clients()
275 class YoutubeBaseInfoExtractor(InfoExtractor
):
276 """Provide base functions for Youtube extractors"""
279 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
280 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
281 r
'browse|oembed|get_video_info|iframe_api|s/player|'
282 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
284 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
286 # _NETRC_MACHINE = 'youtube'
288 # If True it will raise an error if no login info is provided
289 _LOGIN_REQUIRED
= False
292 # invidious-redirect websites
293 r
'(?:www\.)?redirect\.invidious\.io',
294 r
'(?:(?:www|dev)\.)?invidio\.us',
295 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
296 r
'(?:www\.)?invidious\.pussthecat\.org',
297 r
'(?:www\.)?invidious\.zee\.li',
298 r
'(?:www\.)?invidious\.ethibox\.fr',
299 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
300 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
301 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
302 # youtube-dl invidious instances list
303 r
'(?:(?:www|no)\.)?invidiou\.sh',
304 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
305 r
'(?:www\.)?invidious\.kabi\.tk',
306 r
'(?:www\.)?invidious\.mastodon\.host',
307 r
'(?:www\.)?invidious\.zapashcanon\.fr',
308 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
309 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
310 r
'(?:www\.)?invidious\.himiko\.cloud',
311 r
'(?:www\.)?invidious\.reallyancient\.tech',
312 r
'(?:www\.)?invidious\.tube',
313 r
'(?:www\.)?invidiou\.site',
314 r
'(?:www\.)?invidious\.site',
315 r
'(?:www\.)?invidious\.xyz',
316 r
'(?:www\.)?invidious\.nixnet\.xyz',
317 r
'(?:www\.)?invidious\.048596\.xyz',
318 r
'(?:www\.)?invidious\.drycat\.fr',
319 r
'(?:www\.)?inv\.skyn3t\.in',
320 r
'(?:www\.)?tube\.poal\.co',
321 r
'(?:www\.)?tube\.connect\.cafe',
322 r
'(?:www\.)?vid\.wxzm\.sx',
323 r
'(?:www\.)?vid\.mint\.lgbt',
324 r
'(?:www\.)?vid\.puffyan\.us',
325 r
'(?:www\.)?yewtu\.be',
326 r
'(?:www\.)?yt\.elukerio\.org',
327 r
'(?:www\.)?yt\.lelux\.fi',
328 r
'(?:www\.)?invidious\.ggc-project\.de',
329 r
'(?:www\.)?yt\.maisputain\.ovh',
330 r
'(?:www\.)?ytprivate\.com',
331 r
'(?:www\.)?invidious\.13ad\.de',
332 r
'(?:www\.)?invidious\.toot\.koeln',
333 r
'(?:www\.)?invidious\.fdn\.fr',
334 r
'(?:www\.)?watch\.nettohikari\.com',
335 r
'(?:www\.)?invidious\.namazso\.eu',
336 r
'(?:www\.)?invidious\.silkky\.cloud',
337 r
'(?:www\.)?invidious\.exonip\.de',
338 r
'(?:www\.)?invidious\.riverside\.rocks',
339 r
'(?:www\.)?invidious\.blamefran\.net',
340 r
'(?:www\.)?invidious\.moomoo\.de',
341 r
'(?:www\.)?ytb\.trom\.tf',
342 r
'(?:www\.)?yt\.cyberhost\.uk',
343 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
344 r
'(?:www\.)?qklhadlycap4cnod\.onion',
345 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
346 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
347 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
348 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
349 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
350 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
351 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
352 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
353 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
354 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
357 def _initialize_consent(self
):
358 cookies
= self
._get
_cookies
('https://www.youtube.com/')
359 if cookies
.get('__Secure-3PSID'):
362 consent
= cookies
.get('CONSENT')
364 if 'YES' in consent
.value
:
366 consent_id
= self
._search
_regex
(
367 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
369 consent_id
= random
.randint(100, 999)
370 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
372 def _initialize_pref(self
):
373 cookies
= self
._get
_cookies
('https://www.youtube.com/')
374 pref_cookie
= cookies
.get('PREF')
378 pref
= dict(compat_urlparse
.parse_qsl(pref_cookie
.value
))
380 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
381 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
382 self
._set
_cookie
('.youtube.com', name
='PREF', value
=compat_urllib_parse_urlencode(pref
))
384 def _real_initialize(self
):
385 self
._initialize
_pref
()
386 self
._initialize
_consent
()
387 self
._check
_login
_required
()
389 def _check_login_required(self
):
390 if (self
._LOGIN
_REQUIRED
391 and self
.get_param('cookiefile') is None
392 and self
.get_param('cookiesfrombrowser') is None):
393 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
395 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
396 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
397 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
399 def _get_default_ytcfg(self, client='web'):
400 return copy.deepcopy(INNERTUBE_CLIENTS[client])
402 def _get_innertube_host(self, client='web'):
403 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
405 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
406 # try_get but with fallback to default ytcfg client values when present
407 _func = lambda y: try_get(y, getter, expected_type)
408 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
410 def _extract_client_name(self, ytcfg, default_client='web'):
411 return self._ytcfg_get_safe(
412 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
413 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
415 def _extract_client_version(self, ytcfg, default_client='web'):
416 return self._ytcfg_get_safe(
417 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
418 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
420 def _extract_api_key(self, ytcfg=None, default_client='web'):
421 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
423 def _extract_context(self, ytcfg=None, default_client='web'):
425 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
426 # Enforce language and tz for extraction
427 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
428 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
433 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
434 time_now = round(time.time())
435 if self._SAPISID is None:
436 yt_cookies = self._get_cookies('https://www.youtube.com')
437 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
438 # See: https://github.com/yt-dlp/yt-dlp/issues/393
439 sapisid_cookie = dict_get(
440 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
441 if sapisid_cookie and sapisid_cookie.value:
442 self._SAPISID = sapisid_cookie.value
443 self.write_debug('Extracted SAPISID cookie')
444 # SAPISID cookie is required if not already present
445 if not yt_cookies.get('SAPISID'):
446 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
448 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
450 self._SAPISID = False
451 if not self._SAPISID:
453 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
454 sapisidhash = hashlib.sha1(
455 f'{time_now} {self._SAPISID} {origin}'.encode('utf-8')).hexdigest()
456 return f'SAPISIDHASH {time_now}_{sapisidhash}'
458 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
459 note='Downloading API JSON', errnote='Unable to download API page',
460 context=None, api_key=None, api_hostname=None, default_client='web'):
462 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
464 real_headers = self.generate_api_headers(default_client=default_client)
465 real_headers.update({'content-type': 'application/json'})
467 real_headers.update(headers)
468 return self._download_json(
469 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
470 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
471 data=json.dumps(data).encode('utf8'), headers=real_headers,
472 query={'key': api_key or self._extract_api_key(), 'prettyPrint': 'false'})
474 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
475 data = self._search_regex(
476 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
477 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data', fatal=fatal)
479 return self._parse_json(data, item_id, fatal=fatal)
482 def _extract_session_index(*data):
484 Index of current account in account list.
485 See: https://github.com/yt-dlp/yt-dlp/pull/519
488 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
489 if session_index is not None:
493 def _extract_identity_token(self, ytcfg=None, webpage=None):
495 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
499 return self._search_regex(
500 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
501 'identity token
', default=None, fatal=False)
504 def _extract_account_syncid(*args):
506 Extract syncId required to download private playlists of secondary channels
507 @params response and/or ytcfg
510 # ytcfg includes channel_syncid if on secondary channel
511 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
515 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
516 lambda x: x['DATASYNC_ID
']), compat_str) or '').split('||
')
517 if len(sync_ids) >= 2 and sync_ids[1]:
518 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
519 # and just "user_syncid||" for primary channel. We only want the channel_syncid
523 def _extract_visitor_data(*args):
525 Extracts visitorData from an API response or ytcfg
526 Appears to be used to track session state
529 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
533 def is_authenticated(self):
534 return bool(self._generate_sapisidhash_header())
536 def extract_ytcfg(self, video_id, webpage):
539 return self._parse_json(
541 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
542 default='{}'), video_id, fatal=False) or {}
544 def generate_api_headers(
545 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
546 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
548 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(default_client
))
550 'X-YouTube-Client-Name': compat_str(
551 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
552 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
554 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
555 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
556 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
558 if session_index
is None:
559 session_index
= self
._extract
_session
_index
(ytcfg
)
560 if account_syncid
or session_index
is not None:
561 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
563 auth
= self
._generate
_sapisidhash
_header
(origin
)
565 headers
['Authorization'] = auth
566 headers
['X-Origin'] = origin
567 return {h: v for h, v in headers.items() if v is not None}
569 def _download_ytcfg(self
, client
, video_id
):
571 'web': 'https://www.youtube.com',
572 'web_music': 'https://music.youtube.com',
573 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
577 webpage
= self
._download
_webpage
(
578 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
579 return self
.extract_ytcfg(video_id
, webpage
) or {}
582 def _build_api_continuation_query(continuation
, ctp
=None):
584 'continuation': continuation
586 # TODO: Inconsistency with clickTrackingParams.
587 # Currently we have a fixed ctp contained within context (from ytcfg)
588 # and a ctp in root query for continuation.
590 query
['clickTracking'] = {'clickTrackingParams': ctp}
594 def _extract_next_continuation_data(cls
, renderer
):
595 next_continuation
= try_get(
596 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
597 lambda x
: x
['continuation']['reloadContinuationData']), dict)
598 if not next_continuation
:
600 continuation
= next_continuation
.get('continuation')
603 ctp
= next_continuation
.get('clickTrackingParams')
604 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
607 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
608 if isinstance(continuation_ep
, dict):
609 continuation
= try_get(
610 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
613 ctp
= continuation_ep
.get('clickTrackingParams')
614 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
617 def _extract_continuation(cls
, renderer
):
618 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
619 if next_continuation
:
620 return next_continuation
623 for key
in ('contents', 'items'):
624 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
626 for content
in contents
:
627 if not isinstance(content
, dict):
629 continuation_ep
= try_get(
630 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
631 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
633 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
638 def _extract_alerts(cls
, data
):
639 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
640 if not isinstance(alert_dict
, dict):
642 for alert
in alert_dict
.values():
643 alert_type
= alert
.get('type')
646 message
= cls
._get
_text
(alert
, 'text')
648 yield alert_type
, message
650 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
653 for alert_type
, alert_message
in alerts
:
654 if alert_type
.lower() == 'error' and fatal
:
655 errors
.append([alert_type
, alert_message
])
657 warnings
.append([alert_type
, alert_message
])
659 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
660 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
), only_once
=only_once
)
662 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
664 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
665 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
667 def _extract_badges(self
, renderer
: dict):
669 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
670 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
672 badges
.add(label
.lower())
676 def _get_text(data
, *path_list
, max_runs
=None):
677 for path
in path_list
or [None]:
681 obj
= traverse_obj(data
, path
, default
=[])
682 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
685 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
688 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
689 if not runs
and isinstance(item
, list):
692 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
693 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
697 def _get_count(self
, data
, *path_list
):
698 count_text
= self
._get
_text
(data
, *path_list
) or ''
699 count
= parse_count(count_text
)
702 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
706 def _extract_thumbnails(data
, *path_list
):
708 Extract thumbnails from thumbnails dict
709 @param path_list: path list to level that contains 'thumbnails' key
712 for path
in path_list
or [()]:
713 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
714 thumbnail_url
= url_or_none(thumbnail
.get('url'))
715 if not thumbnail_url
:
717 # Sometimes youtube gives a wrong thumbnail URL. See:
718 # https://github.com/yt-dlp/yt-dlp/issues/233
719 # https://github.com/ytdl-org/youtube-dl/issues/28023
720 if 'maxresdefault' in thumbnail_url
:
721 thumbnail_url
= thumbnail_url
.split('?')[0]
723 'url': thumbnail_url
,
724 'height': int_or_none(thumbnail
.get('height')),
725 'width': int_or_none(thumbnail
.get('width')),
730 def extract_relative_time(relative_time_text
):
732 Extracts a relative time from string and converts to dt object
733 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
735 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
)
737 start
= mobj
.group('start')
739 return datetime_from_str(start
)
741 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
745 def _extract_time_text(self
, renderer
, *path_list
):
746 """@returns (timestamp, time_text)"""
747 text
= self
._get
_text
(renderer
, *path_list
) or ''
748 dt
= self
.extract_relative_time(text
)
750 if isinstance(dt
, datetime
.datetime
):
751 timestamp
= calendar
.timegm(dt
.timetuple())
753 if timestamp
is None:
755 unified_timestamp(text
) or unified_timestamp(
757 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
758 text
.lower(), 'time text', default
=None)))
760 if text
and timestamp
is None:
761 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
762 return timestamp
, text
764 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
765 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
766 default_client
='web'):
770 retries
= self
.get_param('extractor_retries', 3)
771 if check_get_keys
is None:
773 while count
< retries
:
776 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
778 response
= self
._call
_api
(
779 ep
=ep
, fatal
=True, headers
=headers
,
780 video_id
=item_id
, query
=query
,
781 context
=self
._extract
_context
(ytcfg
, default_client
),
782 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
783 api_hostname
=api_hostname
, default_client
=default_client
,
784 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
785 except ExtractorError
as e
:
786 if isinstance(e
.cause
, network_exceptions
):
787 if isinstance(e
.cause
, compat_HTTPError
):
788 first_bytes
= e
.cause
.read(512)
789 if not is_html(first_bytes
):
792 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
793 lambda x
: x
['error']['message'], compat_str
)
795 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
796 # Downloading page may result in intermittent 5xx HTTP error
797 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
798 # We also want to catch all other network exceptions since errors in later pages can be troublesome
799 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
800 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
801 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
807 self
.report_warning(error_to_compat_str(e
))
812 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
813 except ExtractorError
as e
:
814 # YouTube servers may return errors we want to retry on in a 200 OK response
815 # See: https://github.com/yt-dlp/yt-dlp/issues/839
816 if 'unknown error' in e
.msg
.lower():
821 self
.report_warning(error_to_compat_str(e
))
823 if not check_get_keys
or dict_get(response
, check_get_keys
):
825 # Youtube sometimes sends incomplete data
826 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
827 last_error
= 'Incomplete data received'
830 raise ExtractorError(last_error
)
832 self
.report_warning(last_error
)
837 def is_music_url(url
):
838 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
840 def _extract_video(self
, renderer
):
841 video_id
= renderer
.get('videoId')
842 title
= self
._get
_text
(renderer
, 'title')
843 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
844 duration
= parse_duration(self
._get
_text
(
845 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
847 duration
= parse_duration(self
._search
_regex
(
848 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
849 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
850 video_id
, default
=None, group
='duration'))
852 view_count
= self
._get
_count
(renderer
, 'viewCountText')
854 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
855 channel_id
= traverse_obj(
856 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
857 expected_type
=str, get_all
=False)
858 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
859 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
860 overlay_style
= traverse_obj(
861 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
862 get_all
=False, expected_type
=str)
863 badges
= self
._extract
_badges
(renderer
)
864 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
865 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
866 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
867 expected_type
=str)) or ''
868 url
= f
'https://www.youtube.com/watch?v={video_id}'
869 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
870 url
= f
'https://www.youtube.com/shorts/{video_id}'
874 'ie_key': YoutubeIE
.ie_key(),
878 'description': description
,
879 'duration': duration
,
880 'view_count': view_count
,
881 'uploader': uploader
,
882 'channel_id': channel_id
,
883 'thumbnails': thumbnails
,
884 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
885 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
887 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
888 else 'was_live' if 'streamed' in time_text
.lower()
889 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
891 'release_timestamp': scheduled_timestamp
,
892 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
896 class YoutubeIE(YoutubeBaseInfoExtractor
):
898 _VALID_URL
= r
"""(?x)^
900 (?:https?://|//) # http(s):// or protocol-independent URL
901 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
902 (?:www\.)?deturl\.com/www\.youtube\.com|
903 (?:www\.)?pwnyoutube\.com|
904 (?:www\.)?hooktube\.com|
905 (?:www\.)?yourepeat\.com|
908 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
909 (?:.*?\#/)? # handle anchor (#/) redirect urls
910 (?: # the various things that can precede the ID:
911 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
912 |(?: # or the v= param in all its forms
913 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
914 (?:\?|\#!?) # the params delimiter ? or # or #!
915 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
920 youtu\.be| # just youtu.be/xxxx
921 vid\.plus| # or vid.plus/xxxx
922 zwearz\.com/watch| # or zwearz.com/watch/xxxx
925 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
927 )? # all until now is optional -> you can pass the naked ID
928 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
929 (?(1).+)? # if we found the ID, everything can follow
931 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
934 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
935 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$',
936 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
939 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
940 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
941 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
942 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
943 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
944 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
945 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
946 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
947 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
948 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
949 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
950 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
951 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
952 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
953 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
954 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
955 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
956 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
960 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
961 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
962 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
963 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
964 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
965 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
966 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
968 # Apple HTTP Live Streaming
969 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
970 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
971 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
972 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
973 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
974 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
975 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
976 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
979 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
980 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
981 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
982 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
983 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
984 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
985 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
986 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
987 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
988 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
989 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
990 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
993 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
994 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
995 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
996 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
997 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
998 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
999 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
1002 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1003 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1004 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1005 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1006 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1007 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1008 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
1009 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1010 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1011 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1012 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1013 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1014 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1015 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1016 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1017 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1018 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1019 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1020 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1021 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1022 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1023 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1026 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
1027 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
1029 # Dash webm audio with opus inside
1030 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
1031 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
1032 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
1035 '_rtmp': {'protocol': 'rtmp'}
,
1037 # av01 video only formats sometimes served with "unknown" codecs
1038 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1039 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1040 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}
,
1041 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}
,
1042 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}
,
1043 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}
,
1044 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1045 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1047 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1054 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1056 'id': 'BaW_jenozKc',
1058 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1059 'uploader': 'Philipp Hagemeister',
1060 'uploader_id': 'phihag',
1061 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1062 'channel': 'Philipp Hagemeister',
1063 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1064 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1065 'upload_date': '20121002',
1066 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1067 'categories': ['Science & Technology'],
1068 'tags': ['youtube-dl'],
1072 'availability': 'public',
1073 'playable_in_embed': True,
1074 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1075 'live_status': 'not_live',
1079 'channel_follower_count': int
1083 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1084 'note': 'Embed-only video (#1746)',
1086 'id': 'yZIXLfi8CZQ',
1088 'upload_date': '20120608',
1089 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1090 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1091 'uploader': 'SET India',
1092 'uploader_id': 'setindia',
1093 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1096 'skip': 'Private video',
1099 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1100 'note': 'Use the first video ID in the URL',
1102 'id': 'BaW_jenozKc',
1104 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1105 'uploader': 'Philipp Hagemeister',
1106 'uploader_id': 'phihag',
1107 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1108 'channel': 'Philipp Hagemeister',
1109 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1110 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1111 'upload_date': '20121002',
1112 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1113 'categories': ['Science & Technology'],
1114 'tags': ['youtube-dl'],
1118 'availability': 'public',
1119 'playable_in_embed': True,
1120 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1121 'live_status': 'not_live',
1123 'channel_follower_count': int
1126 'skip_download': True,
1130 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1131 'note': '256k DASH audio (format 141) via DASH manifest',
1133 'id': 'a9LDPn-MO4I',
1135 'upload_date': '20121002',
1136 'uploader_id': '8KVIDEO',
1137 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1139 'uploader': '8KVIDEO',
1140 'title': 'UHDTV TEST 8K VIDEO.mp4'
1143 'youtube_include_dash_manifest': True,
1146 'skip': 'format 141 not served anymore',
1148 # DASH manifest with encrypted signature
1150 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1152 'id': 'IB3lcPjvWLA',
1154 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1155 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1157 'uploader': 'AfrojackVEVO',
1158 'uploader_id': 'AfrojackVEVO',
1159 'upload_date': '20131011',
1162 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1163 'playable_in_embed': True,
1164 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1166 'track': 'The Spark',
1167 'live_status': 'not_live',
1168 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1169 'channel': 'Afrojack',
1170 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1172 'availability': 'public',
1173 'categories': ['Music'],
1175 'alt_title': 'The Spark',
1176 'channel_follower_count': int
1179 'youtube_include_dash_manifest': True,
1180 'format': '141/bestaudio[ext=m4a]',
1183 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1185 'note': 'Embed allowed age-gate video',
1186 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1188 'id': 'HtVdAasjOgU',
1190 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1191 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1193 'uploader': 'The Witcher',
1194 'uploader_id': 'WitcherGame',
1195 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1196 'upload_date': '20140605',
1198 'categories': ['Gaming'],
1199 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1200 'availability': 'needs_auth',
1201 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1203 'channel': 'The Witcher',
1204 'live_status': 'not_live',
1206 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1207 'playable_in_embed': True,
1209 'channel_follower_count': int
1213 'note': 'Age-gate video with embed allowed in public site',
1214 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1216 'id': 'HsUATh_Nc2U',
1218 'title': 'Godzilla 2 (Official Video)',
1219 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1220 'upload_date': '20200408',
1221 'uploader_id': 'FlyingKitty900',
1222 'uploader': 'FlyingKitty',
1224 'availability': 'needs_auth',
1225 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1226 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1227 'channel': 'FlyingKitty',
1228 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1230 'categories': ['Entertainment'],
1231 'live_status': 'not_live',
1232 'tags': ['Flyingkitty', 'godzilla 2'],
1233 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1236 'playable_in_embed': True,
1237 'channel_follower_count': int
1241 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1242 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1244 'id': 'Tq92D6wQ1mg',
1245 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1247 'upload_date': '20191228',
1248 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1249 'uploader': 'Projekt Melody',
1250 'description': 'md5:17eccca93a786d51bc67646756894066',
1253 'availability': 'needs_auth',
1254 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1255 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1258 'channel': 'Projekt Melody',
1259 'live_status': 'not_live',
1260 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1261 'playable_in_embed': True,
1262 'categories': ['Entertainment'],
1264 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1265 'channel_follower_count': int
1269 'note': 'Non-Agegated non-embeddable video',
1270 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1272 'id': 'MeJVWBSsPAY',
1274 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1275 'uploader': 'Herr Lurik',
1276 'uploader_id': 'st3in234',
1277 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1278 'upload_date': '20130730',
1279 'track': 'Such mich find mich',
1281 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1283 'playable_in_embed': False,
1284 'creator': 'OOMPH!',
1285 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1287 'alt_title': 'Such mich find mich',
1289 'channel': 'Herr Lurik',
1290 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1291 'categories': ['Music'],
1292 'availability': 'public',
1293 'uploader_url': 'http://www.youtube.com/user/st3in234',
1294 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1295 'live_status': 'not_live',
1297 'channel_follower_count': int
1301 'note': 'Non-bypassable age-gated video',
1302 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1303 'only_matching': True,
1305 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1306 # YouTube Red ad is not captured for creator
1308 'url': '__2ABJjxzNo',
1310 'id': '__2ABJjxzNo',
1313 'upload_date': '20100430',
1314 'uploader_id': 'deadmau5',
1315 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1316 'creator': 'deadmau5',
1317 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1318 'uploader': 'deadmau5',
1319 'title': 'Deadmau5 - Some Chords (HD)',
1320 'alt_title': 'Some Chords',
1321 'availability': 'public',
1323 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1325 'live_status': 'not_live',
1326 'channel': 'deadmau5',
1327 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1329 'track': 'Some Chords',
1330 'artist': 'deadmau5',
1331 'playable_in_embed': True,
1333 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1334 'categories': ['Music'],
1335 'album': 'Some Chords',
1336 'channel_follower_count': int
1338 'expected_warnings': [
1339 'DASH manifest missing',
1342 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1344 'url': 'lqQg6PlCWgI',
1346 'id': 'lqQg6PlCWgI',
1349 'upload_date': '20150827',
1350 'uploader_id': 'olympic',
1351 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1352 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1353 'uploader': 'Olympics',
1354 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1356 'release_timestamp': 1343767800,
1357 'playable_in_embed': True,
1358 'categories': ['Sports'],
1359 'release_date': '20120731',
1360 'channel': 'Olympics',
1361 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1362 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1363 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1365 'availability': 'public',
1366 'live_status': 'was_live',
1368 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1369 'channel_follower_count': int
1372 'skip_download': 'requires avconv',
1377 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1379 'id': '_b-2C3KPAM0',
1381 'stretched_ratio': 16 / 9.,
1383 'upload_date': '20110310',
1384 'uploader_id': 'AllenMeow',
1385 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1386 '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',
1388 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1389 'playable_in_embed': True,
1393 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1394 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1395 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1397 'categories': ['People & Blogs'],
1399 'live_status': 'not_live',
1400 'availability': 'unlisted',
1401 'channel_follower_count': int
1404 # url_encoded_fmt_stream_map is empty string
1406 'url': 'qEJwOuvDf7I',
1408 'id': 'qEJwOuvDf7I',
1410 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1412 'upload_date': '20150404',
1413 'uploader_id': 'spbelect',
1414 'uploader': 'Наблюдатели Петербурга',
1417 'skip_download': 'requires avconv',
1419 'skip': 'This live event has ended.',
1421 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1423 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1425 'id': 'FIl7x6_3R5Y',
1427 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1428 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1430 'upload_date': '20150625',
1431 'uploader_id': 'dorappi2000',
1432 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1433 'uploader': 'dorappi2000',
1434 'formats': 'mincount:31',
1436 'skip': 'not actual anymore',
1438 # DASH manifest with segment_list
1440 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1441 'md5': '8ce563a1d667b599d21064e982ab9e31',
1443 'id': 'CsmdDsKjzN8',
1445 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1446 'uploader': 'Airtek',
1447 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1448 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1449 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1452 'youtube_include_dash_manifest': True,
1453 'format': '135', # bestvideo
1455 'skip': 'This live event has ended.',
1458 # Multifeed videos (multiple cameras), URL is for Main Camera
1459 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1461 'id': 'jvGDaLqkpTg',
1462 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1463 'description': 'md5:e03b909557865076822aa169218d6a5d',
1467 'id': 'jvGDaLqkpTg',
1469 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1470 'description': 'md5:e03b909557865076822aa169218d6a5d',
1472 'upload_date': '20161111',
1473 'uploader': 'Team PGP',
1474 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1475 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1479 'id': '3AKt1R1aDnw',
1481 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1482 'description': 'md5:e03b909557865076822aa169218d6a5d',
1484 'upload_date': '20161111',
1485 'uploader': 'Team PGP',
1486 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1487 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1491 'id': 'RtAMM00gpVc',
1493 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1494 'description': 'md5:e03b909557865076822aa169218d6a5d',
1496 'upload_date': '20161111',
1497 'uploader': 'Team PGP',
1498 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1499 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1503 'id': '6N2fdlP3C5U',
1505 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1506 'description': 'md5:e03b909557865076822aa169218d6a5d',
1508 'upload_date': '20161111',
1509 'uploader': 'Team PGP',
1510 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1511 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1515 'skip_download': True,
1517 'skip': 'Not multifeed anymore',
1520 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1521 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1523 'id': 'gVfLd0zydlo',
1524 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1526 'playlist_count': 2,
1527 'skip': 'Not multifeed anymore',
1530 'url': 'https://vid.plus/FlRa-iH7PGw',
1531 'only_matching': True,
1534 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1535 'only_matching': True,
1538 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1539 # Also tests cut-off URL expansion in video description (see
1540 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1541 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1542 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1544 'id': 'lsguqyKfVQg',
1546 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1547 'alt_title': 'Dark Walk',
1548 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1550 'upload_date': '20151119',
1551 'uploader_id': 'IronSoulElf',
1552 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1553 'uploader': 'IronSoulElf',
1554 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1555 'track': 'Dark Walk',
1556 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1557 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1558 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1559 'categories': ['Film & Animation'],
1561 'live_status': 'not_live',
1562 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1563 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1565 'availability': 'public',
1566 'channel': 'IronSoulElf',
1567 'playable_in_embed': True,
1570 'channel_follower_count': int
1573 'skip_download': True,
1577 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1578 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1579 'only_matching': True,
1582 # Video with yt:stretch=17:0
1583 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1585 'id': 'Q39EVAstoRM',
1587 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1588 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1589 'upload_date': '20151107',
1590 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1591 'uploader': 'CH GAMER DROID',
1594 'skip_download': True,
1596 'skip': 'This video does not exist.',
1599 # Video with incomplete 'yt:stretch=16:'
1600 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1601 'only_matching': True,
1604 # Video licensed under Creative Commons
1605 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1607 'id': 'M4gD1WSo5mA',
1609 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1610 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1612 'upload_date': '20150128',
1613 'uploader_id': 'BerkmanCenter',
1614 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1615 'uploader': 'The Berkman Klein Center for Internet & Society',
1616 'license': 'Creative Commons Attribution license (reuse allowed)',
1617 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1618 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1621 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1622 'channel': 'The Berkman Klein Center for Internet & Society',
1623 'availability': 'public',
1625 'categories': ['Education'],
1626 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1627 'live_status': 'not_live',
1628 'playable_in_embed': True,
1629 'channel_follower_count': int
1632 'skip_download': True,
1636 # Channel-like uploader_url
1637 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1639 'id': 'eQcmzGIKrzg',
1641 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1642 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1644 'upload_date': '20151120',
1645 'uploader': 'Bernie Sanders',
1646 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1647 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1648 'license': 'Creative Commons Attribution license (reuse allowed)',
1649 'playable_in_embed': True,
1652 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1654 'availability': 'public',
1655 'categories': ['News & Politics'],
1656 'channel': 'Bernie Sanders',
1657 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1659 'live_status': 'not_live',
1660 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1661 'channel_follower_count': int
1664 'skip_download': True,
1668 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1669 'only_matching': True,
1672 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1673 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1674 'only_matching': True,
1677 # Rental video preview
1678 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1680 'id': 'uGpuVWrhIzE',
1682 'title': 'Piku - Trailer',
1683 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1684 'upload_date': '20150811',
1685 'uploader': 'FlixMatrix',
1686 'uploader_id': 'FlixMatrixKaravan',
1687 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1688 'license': 'Standard YouTube License',
1691 'skip_download': True,
1693 'skip': 'This video is not available.',
1696 # YouTube Red video with episode data
1697 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1699 'id': 'iqKdEhx-dD4',
1701 'title': 'Isolation - Mind Field (Ep 1)',
1702 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1704 'upload_date': '20170118',
1705 'uploader': 'Vsauce',
1706 'uploader_id': 'Vsauce',
1707 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1708 'series': 'Mind Field',
1710 'episode_number': 1,
1711 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1714 'availability': 'public',
1716 'channel': 'Vsauce',
1717 'episode': 'Episode 1',
1718 'categories': ['Entertainment'],
1719 'season': 'Season 1',
1720 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1721 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1723 'playable_in_embed': True,
1724 'live_status': 'not_live',
1725 'channel_follower_count': int
1728 'skip_download': True,
1730 'expected_warnings': [
1731 'Skipping DASH manifest',
1735 # The following content has been identified by the YouTube community
1736 # as inappropriate or offensive to some audiences.
1737 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1739 'id': '6SJNVb0GnPI',
1741 'title': 'Race Differences in Intelligence',
1742 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1744 'upload_date': '20140124',
1745 'uploader': 'New Century Foundation',
1746 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1747 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1750 'skip_download': True,
1752 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1756 'url': '1t24XAntNCY',
1757 'only_matching': True,
1760 # geo restricted to JP
1761 'url': 'sJL6WA-aGkQ',
1762 'only_matching': True,
1765 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1766 'only_matching': True,
1769 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1770 'only_matching': True,
1773 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1774 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1775 'only_matching': True,
1779 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1780 'only_matching': True,
1783 # Video with unsupported adaptive stream type formats
1784 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1786 'id': 'Z4Vy8R84T1U',
1788 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1789 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1791 'upload_date': '20130923',
1792 'uploader': 'Amelia Putri Harwita',
1793 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1794 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1795 'formats': 'maxcount:10',
1798 'skip_download': True,
1799 'youtube_include_dash_manifest': False,
1801 'skip': 'not actual anymore',
1804 # Youtube Music Auto-generated description
1805 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1807 'id': 'MgNrAu2pzNs',
1809 'title': 'Voyeur Girl',
1810 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1811 'upload_date': '20190312',
1812 'uploader': 'Stephen - Topic',
1813 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1814 'artist': 'Stephen',
1815 'track': 'Voyeur Girl',
1816 'album': 'it\'s too much love to know my dear',
1817 'release_date': '20190313',
1818 'release_year': 2019,
1819 'alt_title': 'Voyeur Girl',
1821 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1822 'playable_in_embed': True,
1824 'categories': ['Music'],
1825 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1826 'channel': 'Stephen',
1827 'availability': 'public',
1828 'creator': 'Stephen',
1830 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1832 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1834 'live_status': 'not_live',
1835 'channel_follower_count': int
1838 'skip_download': True,
1842 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1843 'only_matching': True,
1846 # invalid -> valid video id redirection
1847 'url': 'DJztXj2GPfl',
1849 'id': 'DJztXj2GPfk',
1851 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1852 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1853 'upload_date': '20090125',
1854 'uploader': 'Prochorowka',
1855 'uploader_id': 'Prochorowka',
1856 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1857 'artist': 'Panjabi MC',
1858 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1859 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1862 'skip_download': True,
1864 'skip': 'Video unavailable',
1867 # empty description results in an empty string
1868 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1870 'id': 'x41yOUIvK2k',
1872 'title': 'IMG 3456',
1874 'upload_date': '20170613',
1875 'uploader_id': 'ElevageOrVert',
1876 'uploader': 'ElevageOrVert',
1878 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1879 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1881 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1883 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1884 'availability': 'public',
1886 'categories': ['Pets & Animals'],
1888 'playable_in_embed': True,
1889 'live_status': 'not_live',
1890 'channel': 'ElevageOrVert',
1891 'channel_follower_count': int
1894 'skip_download': True,
1898 # with '};' inside yt initial data (see [1])
1899 # see [2] for an example with '};' inside ytInitialPlayerResponse
1900 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1901 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1902 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1904 'id': 'CHqg6qOn4no',
1906 'title': 'Part 77 Sort a list of simple types in c#',
1907 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1908 'upload_date': '20130831',
1909 'uploader_id': 'kudvenkat',
1910 'uploader': 'kudvenkat',
1911 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1913 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1914 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1915 'live_status': 'not_live',
1916 'categories': ['Education'],
1917 'availability': 'public',
1918 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1920 'playable_in_embed': True,
1924 'channel': 'kudvenkat',
1925 'channel_follower_count': int
1928 'skip_download': True,
1932 # another example of '};' in ytInitialData
1933 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1934 'only_matching': True,
1937 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1938 'only_matching': True,
1941 # https://github.com/ytdl-org/youtube-dl/pull/28094
1942 'url': 'OtqTfy26tG0',
1944 'id': 'OtqTfy26tG0',
1946 'title': 'Burn Out',
1947 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1948 'upload_date': '20141120',
1949 'uploader': 'The Cinematic Orchestra - Topic',
1950 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1951 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1952 'artist': 'The Cinematic Orchestra',
1953 'track': 'Burn Out',
1954 'album': 'Every Day',
1956 'live_status': 'not_live',
1957 'alt_title': 'Burn Out',
1961 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1962 'creator': 'The Cinematic Orchestra',
1963 'channel': 'The Cinematic Orchestra',
1964 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1965 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1966 'availability': 'public',
1967 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1968 'categories': ['Music'],
1969 'playable_in_embed': True,
1970 'channel_follower_count': int
1973 'skip_download': True,
1977 # controversial video, only works with bpctr when authenticated with cookies
1978 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1979 'only_matching': True,
1982 # controversial video, requires bpctr/contentCheckOk
1983 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1985 'id': 'SZJvDhaSDnc',
1987 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1988 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1989 'uploader': 'CBS Mornings',
1990 'uploader_id': 'CBSThisMorning',
1991 'upload_date': '20140716',
1992 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1994 'categories': ['News & Politics'],
1995 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1997 'channel': 'CBS Mornings',
1998 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
1999 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2001 'availability': 'needs_auth',
2002 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2004 'live_status': 'not_live',
2005 'playable_in_embed': True,
2006 'channel_follower_count': int
2010 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2011 'url': 'cBvYw8_A0vQ',
2013 'id': 'cBvYw8_A0vQ',
2015 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2016 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2017 'upload_date': '20201120',
2018 'uploader': 'Walk around Japan',
2019 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2020 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2022 'categories': ['Travel & Events'],
2023 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2025 'channel': 'Walk around Japan',
2026 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2027 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2029 'availability': 'public',
2030 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2031 'live_status': 'not_live',
2032 'playable_in_embed': True,
2033 'channel_follower_count': int
2036 'skip_download': True,
2039 # Has multiple audio streams
2040 'url': 'WaOKSUlf4TM',
2041 'only_matching': True
2043 # Requires Premium: has format 141 when requested using YTM url
2044 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2045 'only_matching': True
2047 # multiple subtitles with same lang_code
2048 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2049 'only_matching': True,
2051 # Force use android client fallback
2052 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2054 'id': 'YOelRv7fMxY',
2055 'title': 'DIGGING A SECRET TUNNEL Part 1',
2057 'upload_date': '20210624',
2058 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2059 'uploader': 'colinfurze',
2060 'uploader_id': 'colinfurze',
2061 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2062 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2064 'categories': ['Entertainment'],
2065 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2067 'channel': 'colinfurze',
2068 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2069 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2071 'availability': 'public',
2073 'live_status': 'not_live',
2074 'playable_in_embed': True,
2075 'channel_follower_count': int
2078 'format': '17', # 3gp format available on android
2079 'extractor_args': {'youtube': {'player_client': ['android']}
},
2083 # Skip download of additional client configs (remix client config in this case)
2084 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2085 'only_matching': True,
2087 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
2091 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2092 'only_matching': True,
2094 'note': 'Storyboards',
2095 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2097 'id': '5KLPxDtMqe8',
2100 'title': 'Your Brain is Plastic',
2101 'uploader_id': 'scishow',
2102 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2103 'upload_date': '20140324',
2104 'uploader': 'SciShow',
2106 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2107 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2109 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2110 'playable_in_embed': True,
2112 'uploader_url': 'http://www.youtube.com/user/scishow',
2113 'availability': 'public',
2114 'channel': 'SciShow',
2115 'live_status': 'not_live',
2117 'categories': ['Education'],
2119 'channel_follower_count': int
2120 }, 'params': {'format': 'mhtml', 'skip_download': True}
2122 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2123 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2125 'id': '2NUZ8W2llS4',
2127 'title': 'The NP that test your phone performance 🙂',
2128 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2129 'uploader': 'Leon Nguyen',
2130 'uploader_id': 'VNSXIII',
2131 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2132 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2133 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2137 'categories': ['Gaming'],
2139 'playable_in_embed': True,
2140 'live_status': 'not_live',
2141 'upload_date': '20220103',
2143 'availability': 'public',
2144 'channel': 'Leon Nguyen',
2145 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2146 'channel_follower_count': int
2149 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2150 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2152 'id': 'mzZzzBU6lrM',
2154 'title': 'I Met GeorgeNotFound In Real Life...',
2155 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2156 'uploader': 'Quackity',
2157 'uploader_id': 'QuackityHQ',
2158 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2159 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2160 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2164 'categories': ['Entertainment'],
2166 'playable_in_embed': True,
2167 'live_status': 'not_live',
2168 'release_timestamp': 1641172509,
2169 'release_date': '20220103',
2170 'upload_date': '20220103',
2172 'availability': 'public',
2173 'channel': 'Quackity',
2174 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2175 'channel_follower_count': int
2178 { # continuous livestream. Microformat upload date should be preferred.
2179 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2180 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2182 'id': 'kgx4WGK0oNU',
2183 'title': r
're:jazz\/lofi hip hop radio🌱chill beats to relax\/study to \[LIVE 24\/7\] \d{4}-\d{2}-\d{2} \d{2}:\d{2}',
2185 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2186 'availability': 'public',
2188 'release_timestamp': 1637975704,
2189 'upload_date': '20210619',
2190 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2191 'live_status': 'is_live',
2192 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2193 'uploader': '阿鲍Abao',
2194 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2195 'channel': 'Abao in Tokyo',
2196 'channel_follower_count': int,
2197 'release_date': '20211127',
2199 'categories': ['People & Blogs'],
2201 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2203 'playable_in_embed': True,
2204 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2206 'params': {'skip_download': True}
2211 def suitable(cls
, url
):
2212 from ..utils
import parse_qs
2215 if qs
.get('list', [None])[0]:
2217 return super(YoutubeIE
, cls
).suitable(url
)
2219 def __init__(self
, *args
, **kwargs
):
2220 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
2221 self
._code
_cache
= {}
2222 self
._player
_cache
= {}
2224 def _prepare_live_from_start_formats(self
, formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
):
2225 lock
= threading
.Lock()
2228 start_time
= time
.time()
2229 formats
= [f
for f
in formats
if f
.get('is_from_start')]
2231 def refetch_manifest(format_id
, delay
):
2232 nonlocal formats
, start_time
, is_live
2233 if time
.time() <= start_time
+ delay
:
2236 _
, _
, prs
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
2237 video_details
= traverse_obj(
2238 prs
, (..., 'videoDetails'), expected_type
=dict, default
=[])
2239 microformats
= traverse_obj(
2240 prs
, (..., 'microformat', 'playerMicroformatRenderer'),
2241 expected_type
=dict, default
=[])
2242 _
, is_live
, _
, formats
= self
._list
_formats
(video_id
, microformats
, video_details
, prs
, player_url
)
2243 start_time
= time
.time()
2245 def mpd_feed(format_id
, delay
):
2247 @returns (manifest_url, manifest_stream_number, is_live) or None
2250 refetch_manifest(format_id
, delay
)
2252 f
= next((f
for f
in formats
if f
['format_id'] == format_id
), None)
2255 self
.to_screen(f
'{video_id}: Video is no longer live')
2257 self
.report_warning(
2258 f
'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2260 return f
['manifest_url'], f
['manifest_stream_number'], is_live
2264 f
['protocol'] = 'http_dash_segments_generator'
2265 f
['fragments'] = functools
.partial(
2266 self
._live
_dash
_fragments
, f
['format_id'], live_start_time
, mpd_feed
)
2268 def _live_dash_fragments(self
, format_id
, live_start_time
, mpd_feed
, ctx
):
2269 FETCH_SPAN
, MAX_DURATION
= 5, 432000
2271 mpd_url
, stream_number
, is_live
= None, None, True
2274 download_start_time
= ctx
.get('start') or time
.time()
2276 lack_early_segments
= download_start_time
- (live_start_time
or download_start_time
) > MAX_DURATION
2277 if lack_early_segments
:
2278 self
.report_warning(bug_reports_message(
2279 'Starting download from the last 120 hours of the live stream since '
2280 'YouTube does not have data before that. If you think this is wrong,'), only_once
=True)
2281 lack_early_segments
= True
2283 known_idx
, no_fragment_score
, last_segment_url
= begin_index
, 0, None
2284 fragments
, fragment_base_url
= None, None
2286 def _extract_sequence_from_mpd(refresh_sequence
, immediate
):
2287 nonlocal mpd_url
, stream_number
, is_live
, no_fragment_score
, fragments
, fragment_base_url
2288 # Obtain from MPD's maximum seq value
2289 old_mpd_url
= mpd_url
2290 last_error
= ctx
.pop('last_error', None)
2291 expire_fast
= immediate
or last_error
and isinstance(last_error
, compat_HTTPError
) and last_error
.code
== 403
2292 mpd_url
, stream_number
, is_live
= (mpd_feed(format_id
, 5 if expire_fast
else 18000)
2293 or (mpd_url
, stream_number
, False))
2294 if not refresh_sequence
:
2295 if expire_fast
and not is_live
:
2296 return False, last_seq
2297 elif old_mpd_url
== mpd_url
:
2298 return True, last_seq
2300 fmts
, _
= self
._extract
_mpd
_formats
_and
_subtitles
(
2301 mpd_url
, None, note
=False, errnote
=False, fatal
=False)
2302 except ExtractorError
:
2305 no_fragment_score
+= 2
2306 return False, last_seq
2307 fmt_info
= next(x
for x
in fmts
if x
['manifest_stream_number'] == stream_number
)
2308 fragments
= fmt_info
['fragments']
2309 fragment_base_url
= fmt_info
['fragment_base_url']
2310 assert fragment_base_url
2312 _last_seq
= int(re
.search(r
'(?:/|^)sq/(\d+)', fragments
[-1]['path']).group(1))
2313 return True, _last_seq
2316 fetch_time
= time
.time()
2317 if no_fragment_score
> 30:
2319 if last_segment_url
:
2320 # Obtain from "X-Head-Seqnum" header value from each segment
2322 urlh
= self
._request
_webpage
(
2323 last_segment_url
, None, note
=False, errnote
=False, fatal
=False)
2324 except ExtractorError
:
2326 last_seq
= try_get(urlh
, lambda x
: int_or_none(x
.headers
['X-Head-Seqnum']))
2327 if last_seq
is None:
2328 no_fragment_score
+= 2
2329 last_segment_url
= None
2332 should_continue
, last_seq
= _extract_sequence_from_mpd(True, no_fragment_score
> 15)
2333 no_fragment_score
+= 2
2334 if not should_continue
:
2337 if known_idx
> last_seq
:
2338 last_segment_url
= None
2343 if begin_index
< 0 and known_idx
< 0:
2344 # skip from the start when it's negative value
2345 known_idx
= last_seq
+ begin_index
2346 if lack_early_segments
:
2347 known_idx
= max(known_idx
, last_seq
- int(MAX_DURATION
// fragments
[-1]['duration']))
2349 for idx
in range(known_idx
, last_seq
):
2350 # do not update sequence here or you'll get skipped some part of it
2351 should_continue
, _
= _extract_sequence_from_mpd(False, False)
2352 if not should_continue
:
2354 raise ExtractorError('breaking out of outer loop')
2355 last_segment_url
= urljoin(fragment_base_url
, 'sq/%d' % idx
)
2357 'url': last_segment_url
,
2359 if known_idx
== last_seq
:
2360 no_fragment_score
+= 5
2362 no_fragment_score
= 0
2363 known_idx
= last_seq
2364 except ExtractorError
:
2367 time
.sleep(max(0, FETCH_SPAN
+ fetch_time
- time
.time()))
2369 def _extract_player_url(self
, *ytcfgs
, webpage
=None):
2370 player_url
= traverse_obj(
2371 ytcfgs
, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2372 get_all
=False, expected_type
=compat_str
)
2375 return urljoin('https://www.youtube.com', player_url
)
2377 def _download_player_url(self
, video_id
, fatal
=False):
2378 res
= self
._download
_webpage
(
2379 'https://www.youtube.com/iframe_api',
2380 note
='Downloading iframe API JS', video_id
=video_id
, fatal
=fatal
)
2382 player_version
= self
._search
_regex
(
2383 r
'player\\?/([0-9a-fA-F]{8})\\?/', res
, 'player version', fatal
=fatal
)
2385 return f
'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2387 def _signature_cache_id(self
, example_sig
):
2388 """ Return a string representation of a signature """
2389 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
2392 def _extract_player_info(cls
, player_url
):
2393 for player_re
in cls
._PLAYER
_INFO
_RE
:
2394 id_m
= re
.search(player_re
, player_url
)
2398 raise ExtractorError('Cannot identify player %r' % player_url
)
2399 return id_m
.group('id')
2401 def _load_player(self
, video_id
, player_url
, fatal
=True):
2402 player_id
= self
._extract
_player
_info
(player_url
)
2403 if player_id
not in self
._code
_cache
:
2404 code
= self
._download
_webpage
(
2405 player_url
, video_id
, fatal
=fatal
,
2406 note
='Downloading player ' + player_id
,
2407 errnote
='Download of %s failed' % player_url
)
2409 self
._code
_cache
[player_id
] = code
2410 return self
._code
_cache
.get(player_id
)
2412 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
2413 player_id
= self
._extract
_player
_info
(player_url
)
2415 # Read from filesystem cache
2416 func_id
= 'js_%s_%s' % (
2417 player_id
, self
._signature
_cache
_id
(example_sig
))
2418 assert os
.path
.basename(func_id
) == func_id
2420 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
2421 if cache_spec
is not None:
2422 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
2424 code
= self
._load
_player
(video_id
, player_url
)
2426 res
= self
._parse
_sig
_js
(code
)
2428 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2429 cache_res
= res(test_string
)
2430 cache_spec
= [ord(c
) for c
in cache_res
]
2432 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
2435 def _print_sig_code(self
, func
, example_sig
):
2436 if not self
.get_param('youtube_print_sig_code'):
2439 def gen_sig_code(idxs
):
2440 def _genslice(start
, end
, step
):
2441 starts
= '' if start
== 0 else str(start
)
2442 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
2443 steps
= '' if step
== 1 else (':%d' % step
)
2444 return 's[%s%s%s]' % (starts
, ends
, steps
)
2447 # Quelch pyflakes warnings - start will be set when step is set
2448 start
= '(Never used)'
2449 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
2450 if step
is not None:
2451 if i
- prev
== step
:
2453 yield _genslice(start
, prev
, step
)
2456 if i
- prev
in [-1, 1]:
2461 yield 's[%d]' % prev
2465 yield _genslice(start
, i
, step
)
2467 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2468 cache_res
= func(test_string
)
2469 cache_spec
= [ord(c
) for c
in cache_res
]
2470 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
2471 signature_id_tuple
= '(%s)' % (
2472 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
2473 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2474 ' return %s\n') % (signature_id_tuple
, expr_code
)
2475 self
.to_screen('Extracted signature function:\n' + code
)
2477 def _parse_sig_js(self
, jscode
):
2478 funcname
= self
._search
_regex
(
2479 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2480 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2481 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2482 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2483 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}\(a,\d+\)',
2484 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\(\s*""\s*\)',
2485 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2487 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2488 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2489 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2490 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2491 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2492 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2493 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2494 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
2495 jscode, 'Initial JS player signature function name
', group='sig
')
2497 jsi = JSInterpreter(jscode)
2498 initial_function = jsi.extract_function(funcname)
2499 return lambda s: initial_function([s])
2501 def _decrypt_signature(self, s, video_id, player_url):
2502 """Turn the encrypted s field into a working signature"""
2504 if player_url is None:
2505 raise ExtractorError('Cannot decrypt signature without player_url
')
2508 player_id = (player_url, self._signature_cache_id(s))
2509 if player_id not in self._player_cache:
2510 func = self._extract_signature_function(
2511 video_id, player_url, s
2513 self._player_cache[player_id] = func
2514 func = self._player_cache[player_id]
2515 self._print_sig_code(func, s)
2517 except Exception as e:
2518 raise ExtractorError('Signature extraction failed
: ' + traceback.format_exc(), cause=e)
2520 def _decrypt_nsig(self, s, video_id, player_url):
2521 """Turn the encrypted n field into a working signature"""
2522 if player_url is None:
2523 raise ExtractorError('Cannot decrypt nsig without player_url
')
2524 player_url = urljoin('https
://www
.youtube
.com
', player_url)
2526 sig_id = ('nsig_value
', s)
2527 if sig_id in self._player_cache:
2528 return self._player_cache[sig_id]
2531 player_id = ('nsig
', player_url)
2532 if player_id not in self._player_cache:
2533 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2534 func = self._player_cache[player_id]
2535 self._player_cache[sig_id] = func(s)
2536 self.write_debug(f'Decrypted nsig {s}
=> {self._player_cache[sig_id]}
')
2537 return self._player_cache[sig_id]
2538 except Exception as e:
2539 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2541 def _extract_n_function_name(self, jscode):
2542 nfunc, idx = self._search_regex(
2543 r'\
.get\
("n"\
)\
)&&\
(b
=(?P
<nfunc
>[a
-zA
-Z0
-9$
]+)(?
:\
[(?P
<idx
>\d
+)\
])?\
([a
-zA
-Z0
-9]\
)',
2544 jscode, 'Initial JS player n function name
', group=('nfunc
', 'idx
'))
2547 return json.loads(js_to_json(self._search_regex(
2548 rf'var {re.escape(nfunc)}\s
*=\s
*(\
[.+?\
]);', jscode,
2549 f'Initial JS player n function
list ({nfunc}
.{idx}
)')))[int(idx)]
2551 def _extract_n_function(self, video_id, player_url):
2552 player_id = self._extract_player_info(player_url)
2553 func_code = self._downloader.cache.load('youtube
-nsig
', player_id)
2556 jsi = JSInterpreter(func_code)
2558 jscode = self._load_player(video_id, player_url)
2559 funcname = self._extract_n_function_name(jscode)
2560 jsi = JSInterpreter(jscode)
2561 func_code = jsi.extract_function_code(funcname)
2562 self._downloader.cache.store('youtube
-nsig
', player_id, func_code)
2564 if self.get_param('youtube_print_sig_code
'):
2565 self.to_screen(f'Extracted nsig function
from {player_id}
:\n{func_code[1]}
\n')
2567 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2569 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2571 Extract signatureTimestamp (sts)
2572 Required to tell API what sig/player version is in use.
2575 if isinstance(ytcfg, dict):
2576 sts = int_or_none(ytcfg.get('STS
'))
2579 # Attempt to extract from player
2580 if player_url is None:
2581 error_msg = 'Cannot extract signature timestamp without player_url
.'
2583 raise ExtractorError(error_msg)
2584 self.report_warning(error_msg)
2586 code = self._load_player(video_id, player_url, fatal=fatal)
2588 sts = int_or_none(self._search_regex(
2589 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
2590 'JS player signature timestamp
', group='sts
', fatal=fatal))
2593 def _mark_watched(self, video_id, player_responses):
2594 playback_url = get_first(
2595 player_responses, ('playbackTracking
', 'videostatsPlaybackUrl
', 'baseUrl
'),
2596 expected_type=url_or_none)
2597 if not playback_url:
2598 self.report_warning('Unable to mark watched
')
2600 parsed_playback_url = compat_urlparse.urlparse(playback_url)
2601 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
2603 # cpn generation algorithm is reverse engineered from base.js.
2604 # In fact it works even with dummy cpn.
2605 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
2606 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2612 playback_url = compat_urlparse.urlunparse(
2613 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2615 self._download_webpage(
2616 playback_url, video_id, 'Marking watched
',
2617 'Unable to mark watched
', fatal=False)
2620 def _extract_urls(webpage):
2621 # Embedded YouTube player
2623 unescapeHTML(mobj.group('url
'))
2624 for mobj in re.finditer(r'''(?x)
2634 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2635 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2638 # lazyYT YouTube embed
2639 entries.extend(list(map(
2641 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
2643 # Wordpress "YouTube Video Importer
" plugin
2644 matches = re.findall(r'''(?x)<div[^>]+
2645 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
2646 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
2647 entries.extend(m[-1] for m in matches)
2652 def _extract_url(webpage):
2653 urls = YoutubeIE._extract_urls(webpage)
2654 return urls[0] if urls else None
2657 def extract_id(cls, url):
2658 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2660 raise ExtractorError('Invalid URL: %s' % url)
2661 return mobj.group('id')
2663 def _extract_chapters_from_json(self, data, duration):
2664 chapter_list = traverse_obj(
2666 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2667 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2668 ), expected_type=list)
2670 return self._extract_chapters(
2672 chapter_time=lambda chapter: float_or_none(
2673 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2674 chapter_title=lambda chapter: traverse_obj(
2675 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2678 def _extract_chapters_from_engagement_panel(self, data, duration):
2679 content_list = traverse_obj(
2681 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2682 expected_type=list, default=[])
2683 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2684 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2688 self._extract_chapters(
2689 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2690 chapter_time, chapter_title, duration)
2691 for contents in content_list
2694 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2696 last_chapter = {'start_time': 0}
2697 for idx, chapter in enumerate(chapter_list or []):
2698 title = chapter_title(chapter)
2699 start_time = chapter_time(chapter)
2700 if start_time is None:
2702 last_chapter['end_time'] = start_time
2703 if start_time < last_chapter['start_time']:
2706 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2708 self.report_warning(f'Invalid start time for chapter "{title}"')
2710 last_chapter = {'start_time': start_time, 'title': title}
2711 chapters.append(last_chapter)
2712 last_chapter['end_time'] = duration
2715 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2716 return self._parse_json(self._search_regex(
2717 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2718 regex), webpage, name, default='{}'), video_id, fatal=False)
2720 def _extract_comment(self, comment_renderer, parent=None):
2721 comment_id = comment_renderer.get('commentId')
2725 text = self._get_text(comment_renderer, 'contentText')
2727 # note: timestamp is an estimate calculated from the current time and time_text
2728 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2729 author = self._get_text(comment_renderer, 'authorText')
2730 author_id = try_get(comment_renderer,
2731 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2733 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2734 lambda x: x['likeCount']), compat_str)) or 0
2735 author_thumbnail = try_get(comment_renderer,
2736 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2738 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2739 is_favorited = 'creatorHeart' in (try_get(
2740 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2744 'timestamp': timestamp,
2745 'time_text': time_text,
2746 'like_count': votes,
2747 'is_favorited': is_favorited,
2749 'author_id': author_id,
2750 'author_thumbnail': author_thumbnail,
2751 'author_is_uploader': author_is_uploader,
2752 'parent': parent or 'root'
2755 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2757 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2759 def extract_header(contents):
2760 _continuation = None
2761 for content in contents:
2762 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2763 expected_comment_count = self._get_count(
2764 comments_header_renderer, 'countText', 'commentsCount')
2766 if expected_comment_count:
2767 tracker['est_total'] = expected_comment_count
2768 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2769 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2771 sort_menu_item = try_get(
2772 comments_header_renderer,
2773 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2774 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2776 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2777 if not _continuation:
2780 sort_text = str_or_none(sort_menu_item.get('title'))
2782 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2783 self.to_screen('Sorting comments by %s' % sort_text.lower())
2785 return _continuation
2787 def extract_thread(contents):
2789 tracker['current_page_thread'] = 0
2790 for content in contents:
2791 if not parent and tracker['total_parent_comments'] >= max_parents:
2793 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2794 comment_renderer = get_first(
2795 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2796 expected_type=dict, default={})
2798 comment = self._extract_comment(comment_renderer, parent)
2802 tracker['running_total'] += 1
2803 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2806 # Attempt to get the replies
2807 comment_replies_renderer = try_get(
2808 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2810 if comment_replies_renderer:
2811 tracker['current_page_thread'] += 1
2812 comment_entries_iter = self._comment_entries(
2813 comment_replies_renderer, ytcfg, video_id,
2814 parent=comment.get('id'), tracker=tracker)
2815 for reply_comment in itertools.islice(comment_entries_iter, min(max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments']))):
2818 # Keeps track of counts across recursive calls
2823 current_page_thread=0,
2824 total_parent_comments=0,
2825 total_reply_comments=0)
2828 # YouTube comments have a max depth of 2
2829 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2831 self._downloader.deprecation_warning(
2832 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2833 if max_depth == 1 and parent:
2836 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2837 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2839 continuation = self._extract_continuation(root_continuation_data)
2840 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2841 if message and not parent:
2842 self.report_warning(message, video_id=video_id)
2845 is_first_continuation = parent is None
2847 for page_num in itertools.count(0):
2848 if not continuation:
2850 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2851 comment_prog_str = f"({tracker['running_total']}/{tracker['est_total']})"
2853 if is_first_continuation:
2854 note_prefix = 'Downloading comment section API JSON'
2856 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2857 tracker['current_page_thread'], comment_prog_str)
2859 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2860 ' ' if parent else '', ' replies' if parent else '',
2861 page_num, comment_prog_str)
2863 response = self._extract_response(
2864 item_id=None, query=continuation,
2865 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2866 check_get_keys='onResponseReceivedEndpoints')
2868 continuation_contents = traverse_obj(
2869 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2872 for continuation_section in continuation_contents:
2873 continuation_items = traverse_obj(
2874 continuation_section,
2875 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2876 get_all=False, expected_type=list) or []
2877 if is_first_continuation:
2878 continuation = extract_header(continuation_items)
2879 is_first_continuation = False
2884 for entry in extract_thread(continuation_items):
2888 continuation = self._extract_continuation({'contents': continuation_items})
2892 def _get_comments(self, ytcfg, video_id, contents, webpage):
2893 """Entry for comment extraction"""
2894 def _real_comment_extract(contents):
2896 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2897 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2898 yield from self._comment_entries(renderer, ytcfg, video_id)
2900 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2901 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2904 def _get_checkok_params():
2905 return {'contentCheckOk': True, 'racyCheckOk': True}
2908 def _generate_player_context(cls, sts=None):
2910 'html5Preference': 'HTML5_PREF_WANTS',
2913 context['signatureTimestamp'] = sts
2915 'playbackContext': {
2916 'contentPlaybackContext': context
2918 **cls._get_checkok_params()
2922 def _is_agegated(player_response):
2923 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
2926 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2927 AGE_GATE_REASONS = (
2928 'confirm your age', 'age-restricted', 'inappropriate', # reason
2929 'age_verification_required', 'age_check_required', # status
2931 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
2934 def _is_unplayable(player_response):
2935 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
2937 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
2939 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2940 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2941 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
2942 headers = self.generate_api_headers(
2943 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
2945 yt_query = {'videoId': video_id}
2946 yt_query.update(self._generate_player_context(sts))
2947 return self._extract_response(
2948 item_id=video_id, ep='player', query=yt_query,
2949 ytcfg=player_ytcfg, headers=headers, fatal=True,
2950 default_client=client,
2951 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2954 def _get_requested_clients(self, url, smuggled_data):
2955 requested_clients = []
2956 default = ['android', 'web']
2957 allowed_clients = sorted(
2958 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2959 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2960 for client in self._configuration_arg('player_client'):
2961 if client in allowed_clients:
2962 requested_clients.append(client)
2963 elif client == 'default':
2964 requested_clients.extend(default)
2965 elif client == 'all':
2966 requested_clients.extend(allowed_clients)
2968 self.report_warning(f'Skipping unsupported client {client}')
2969 if not requested_clients:
2970 requested_clients = default
2972 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2973 requested_clients.extend(
2974 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
2976 return orderedSet(requested_clients)
2978 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
2981 initial_pr = self._extract_yt_initial_variable(
2982 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2983 video_id, 'initial player response')
2985 all_clients = set(clients)
2986 clients = clients[::-1]
2989 def append_client(*client_names):
2990 """ Append the first client name that exists but not already used """
2991 for client_name in client_names:
2992 actual_client = _split_innertube_client(client_name)[0]
2993 if actual_client in INNERTUBE_CLIENTS:
2994 if actual_client not in all_clients:
2995 clients.append(client_name)
2996 all_clients.add(actual_client)
2999 # Android player_response does not have microFormats which are needed for
3000 # extraction of some data. So we return the initial_pr with formats
3001 # stripped out even if not requested by the user
3002 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3004 pr = dict(initial_pr)
3005 pr['streamingData'] = None
3009 tried_iframe_fallback = False
3012 client, base_client, variant = _split_innertube_client(clients.pop())
3013 player_ytcfg = master_ytcfg if client == 'web' else {}
3014 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3015 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3017 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3018 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3019 if 'js' in self._configuration_arg('player_skip'):
3020 require_js_player = False
3023 if not player_url and not tried_iframe_fallback and require_js_player:
3024 player_url = self._download_player_url(video_id)
3025 tried_iframe_fallback = True
3028 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3029 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3030 except ExtractorError as e:
3032 self.report_warning(last_error)
3039 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3040 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3041 append_client(f'{base_client}_creator')
3042 elif self._is_agegated(pr):
3043 if variant == 'tv_embedded':
3044 append_client(f'{base_client}_embedded')
3046 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3051 self.report_warning(last_error)
3052 return prs, player_url
3054 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
3055 itags, stream_ids = {}, []
3056 itag_qualities, res_qualities = {}, {}
3058 # Normally tiny is the smallest video-only formats. But
3059 # audio-only formats with unknown quality may get tagged as tiny
3061 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3062 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3064 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3066 for fmt in streaming_formats:
3067 if fmt.get('targetDurationSec'):
3070 itag = str_or_none(fmt.get('itag'))
3071 audio_track = fmt.get('audioTrack') or {}
3072 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3073 if stream_id in stream_ids:
3076 quality = fmt.get('quality')
3077 height = int_or_none(fmt.get('height'))
3078 if quality == 'tiny' or not quality:
3079 quality = fmt.get('audioQuality', '').lower() or quality
3080 # The 3gp format (17) in android client has a quality of "small",
3081 # but is actually worse than other formats
3086 itag_qualities[itag] = quality
3088 res_qualities[height] = quality
3089 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3090 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3091 # number of fragment that would subsequently requested with (`&sq=N`)
3092 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3095 fmt_url = fmt.get('url')
3097 sc = compat_parse_qs(fmt.get('signatureCipher'))
3098 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3099 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3100 if not (sc and fmt_url and encrypted_sig):
3104 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
3105 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
3106 fmt_url += '&' + sp + '=' + signature
3108 query = parse_qs(fmt_url)
3112 fmt_url = update_url_query(fmt_url, {
3113 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3114 except ExtractorError as e:
3115 self.report_warning(
3116 f'nsig extraction failed: You may experience throttling for some formats\n'
3117 f'n = {query["n"][0]} ; player = {player_url}\n{e}', only_once=True)
3121 itags[itag] = 'https'
3122 stream_ids.append(stream_id)
3124 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3125 language_preference = (
3126 10 if audio_track.get('audioIsDefault') and 10
3127 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3129 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3130 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3131 # Make sure to avoid false positives with small duration differences.
3132 # Eg: __2ABJjxzNo, ySuUZEjARPY
3133 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3135 self.report_warning(f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3137 'asr': int_or_none(fmt.get('audioSampleRate')),
3138 'filesize': int_or_none(fmt.get('contentLength')),
3140 'format_note': join_nonempty(
3141 '%s%s' % (audio_track.get('displayName') or '',
3142 ' (default)' if language_preference > 0 else ''),
3143 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3144 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3145 'source_preference': -10 if throttled else -1,
3146 'fps': int_or_none(fmt.get('fps')) or None,
3148 'quality': q(quality),
3149 'has_drm': bool(fmt.get('drmFamilies')),
3152 'width': int_or_none(fmt.get('width')),
3153 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3154 'desc' if language_preference < -1 else ''),
3155 'language_preference': language_preference,
3156 # Strictly de-prioritize damaged and 3gp formats
3157 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3159 mime_mobj = re.match(
3160 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
3162 dct['ext'] = mimetype2ext(mime_mobj.group(1))
3163 dct.update(parse_codecs(mime_mobj.group(2)))
3164 no_audio = dct.get('acodec') == 'none'
3165 no_video = dct.get('vcodec') == 'none'
3170 if no_audio or no_video:
3171 dct['downloader_options'] = {
3172 # Youtube throttles chunks >~10M
3173 'http_chunk_size': 10485760,
3176 dct['container'] = dct['ext'] + '_dash'
3179 live_from_start = is_live and self.get_param('live_from_start')
3180 skip_manifests = self._configuration_arg('skip')
3181 if not self.get_param('youtube_include_hls_manifest', True):
3182 skip_manifests.append('hls')
3183 get_dash = 'dash' not in skip_manifests and (
3184 not is_live or live_from_start or self._configuration_arg('include_live_dash'))
3185 get_hls = not live_from_start and 'hls' not in skip_manifests
3187 def process_manifest_format(f, proto, itag):
3189 if itags[itag] == proto or f'{itag}-{proto}' in itags:
3191 itag = f'{itag}-{proto}'
3193 f['format_id'] = itag
3196 f['quality'] = next((
3198 for val, qdict in ((f.get('format_id', '').split('-')[0], itag_qualities), (f.get('height'), res_qualities))
3199 if val in qdict), -1)
3202 for sd in streaming_data:
3203 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
3204 if hls_manifest_url:
3205 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
3206 if process_manifest_format(f, 'hls', self._search_regex(
3207 r'/itag/(\d+)', f['url'], 'itag', default=None)):
3210 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
3211 if dash_manifest_url:
3212 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3213 if process_manifest_format(f, 'dash', f['format_id']):
3214 f['filesize'] = int_or_none(self._search_regex(
3215 r'/clen/(\d+)', f.get('fragment_base_url') or f['url'], 'file size', default=None))
3217 f['is_from_start'] = True
3221 def _extract_storyboard(self, player_responses, duration):
3223 player_responses, ('storyboards', 'playerStoryboardSpecRenderer', 'spec'), default='').split('|')[::-1]
3224 base_url = url_or_none(urljoin('https://i.ytimg.com/', spec.pop() or None))
3228 for i, args in enumerate(spec):
3229 args = args.split('#')
3230 counts = list(map(int_or_none, args[:5]))
3231 if len(args) != 8 or not all(counts):
3232 self.report_warning(f'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3234 width, height, frame_count, cols, rows = counts
3237 url = base_url.replace('$L', str(L - i)).replace('$N', N) + f'&sigh={sigh}'
3238 fragment_count = frame_count / (cols * rows)
3239 fragment_duration = duration / fragment_count
3241 'format_id': f'sb{i}',
3242 'format_note': 'storyboard',
3244 'protocol': 'mhtml',
3251 'url': url.replace('$M', str(j)),
3252 'duration': min(fragment_duration, duration - (j * fragment_duration)),
3253 } for j in range(math.ceil(fragment_count))],
3256 def _download_player_responses(self, url, smuggled_data, video_id, webpage_url):
3258 if 'webpage' not in self._configuration_arg('player_skip'):
3259 webpage = self._download_webpage(
3260 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
3262 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
3264 player_responses, player_url = self._extract_player_responses(
3265 self._get_requested_clients(url, smuggled_data),
3266 video_id, webpage, master_ytcfg)
3268 return webpage, master_ytcfg, player_responses, player_url
3270 def _list_formats(self, video_id, microformats, video_details, player_responses, player_url, duration=None):
3271 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
3272 is_live = get_first(video_details, 'isLive')
3274 is_live = get_first(live_broadcast_details, 'isLiveNow')
3276 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
3277 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live, duration))
3279 return live_broadcast_details, is_live, streaming_data, formats
3281 def _real_extract(self, url):
3282 url, smuggled_data = unsmuggle_url(url, {})
3283 video_id = self._match_id(url)
3285 base_url = self.http_scheme() + '//www.youtube.com/'
3286 webpage_url = base_url + 'watch?v=' + video_id
3288 webpage, master_ytcfg, player_responses, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
3290 playability_statuses = traverse_obj(
3291 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
3293 trailer_video_id = get_first(
3294 playability_statuses,
3295 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3297 if trailer_video_id:
3298 return self.url_result(
3299 trailer_video_id, self.ie_key(), trailer_video_id)
3301 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
3302 if webpage else (lambda x: None))
3304 video_details = traverse_obj(
3305 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
3306 microformats = traverse_obj(
3307 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
3308 expected_type=dict, default=[])
3310 get_first(video_details, 'title')
3311 or self._get_text(microformats, (..., 'title'))
3312 or search_meta(['og:title', 'twitter:title', 'title']))
3313 video_description = get_first(video_details, 'shortDescription')
3315 multifeed_metadata_list = get_first(
3317 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3319 if multifeed_metadata_list and not smuggled_data.get('force_singlefeed'):
3320 if self.get_param('noplaylist'):
3321 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3325 for feed in multifeed_metadata_list.split(','):
3326 # Unquote should take place before split on comma (,) since textual
3327 # fields may contain comma as well (see
3328 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3329 feed_data = compat_parse_qs(
3330 compat_urllib_parse_unquote_plus(feed))
3332 def feed_entry(name):
3334 feed_data, lambda x: x[name][0], compat_str)
3336 feed_id = feed_entry('id')
3339 feed_title = feed_entry('title')
3342 title += ' (%s)' % feed_title
3344 '_type': 'url_transparent',
3345 'ie_key': 'Youtube',
3347 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
3348 {'force_singlefeed': True}),
3351 feed_ids.append(feed_id)
3353 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3354 % (', '.join(feed_ids), video_id))
3355 return self.playlist_result(
3356 entries, video_id, video_title, video_description)
3358 duration = int_or_none(
3359 get_first(video_details, 'lengthSeconds')
3360 or get_first(microformats, 'lengthSeconds')
3361 or parse_duration(search_meta('duration'))) or None
3363 live_broadcast_details, is_live, streaming_data, formats = self._list_formats(
3364 video_id, microformats, video_details, player_responses, player_url, duration)
3367 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
3368 self.report_drm(video_id)
3370 playability_statuses,
3371 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
3372 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
3373 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
3375 if subreason == 'The uploader has not made this video available in your country.':
3376 countries = get_first(microformats, 'availableCountries')
3378 regions_allowed = search_meta('regionsAllowed')
3379 countries = regions_allowed.split(',') if regions_allowed else None
3380 self.raise_geo_restricted(subreason, countries, metadata_available=True)
3381 reason += f'. {subreason}'
3383 self.raise_no_formats(reason, expected=True)
3385 keywords = get_first(video_details, 'keywords', expected_type=list) or []
3386 if not keywords and webpage:
3388 unescapeHTML(m.group('content'))
3389 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
3390 for keyword in keywords:
3391 if keyword.startswith('yt:stretch='):
3392 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
3394 # NB: float is intentional for forcing float division
3395 w, h = (float(v) for v in mobj.groups())
3399 if f.get('vcodec') != 'none':
3400 f['stretched_ratio'] = ratio
3402 thumbnails = self._extract_thumbnails((video_details, microformats), (..., ..., 'thumbnail'))
3403 thumbnail_url = search_meta(['og:image', 'twitter:image'])
3406 'url': thumbnail_url,
3408 original_thumbnails = thumbnails.copy()
3410 # The best resolution thumbnails sometimes does not appear in the webpage
3411 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
3412 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3414 'maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3',
3415 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
3416 'mqdefault', 'mq1', 'mq2', 'mq3',
3417 'default', '1', '2', '3'
3419 n_thumbnail_names = len(thumbnail_names)
3421 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3422 video_id=video_id, name=name, ext=ext,
3423 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
3424 } for name in thumbnail_names for ext in ('webp', 'jpg'))
3425 for thumb in thumbnails:
3426 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
3427 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
3428 self._remove_duplicate_formats(thumbnails)
3429 self._downloader._sort_thumbnails(original_thumbnails)
3431 category = get_first(microformats, 'category') or search_meta('genre')
3432 channel_id = str_or_none(
3433 get_first(video_details, 'channelId')
3434 or get_first(microformats, 'externalChannelId')
3435 or search_meta('channelId'))
3436 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
3438 live_content = get_first(video_details, 'isLiveContent')
3439 is_upcoming = get_first(video_details, 'isUpcoming')
3441 if is_upcoming or live_content is False:
3443 if is_upcoming is None and (live_content or is_live):
3445 live_start_time = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
3446 live_end_time = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
3447 if not duration and live_end_time and live_start_time:
3448 duration = live_end_time - live_start_time
3450 if is_live and self.get_param('live_from_start'):
3451 self._prepare_live_from_start_formats(formats, video_id, live_start_time, url, webpage_url, smuggled_data)
3453 formats.extend(self._extract_storyboard(player_responses, duration))
3455 # Source is given priority since formats that throttle are given lower source_preference
3456 # When throttling issue is fully fixed, remove this
3457 self._sort_formats(formats, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3461 'title': video_title,
3463 'thumbnails': thumbnails,
3464 # The best thumbnail that we are sure exists. Prevents unnecessary
3465 # URL checking if user don't care about getting the best possible thumbnail
3466 'thumbnail': traverse_obj(original_thumbnails, (-1, 'url')),
3467 'description': video_description,
3468 'uploader': get_first(video_details, 'author'),
3469 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
3470 'uploader_url': owner_profile_url,
3471 'channel_id': channel_id,
3472 'channel_url': format_field(channel_id, template='https://www.youtube.com/channel/%s'),
3473 'duration': duration,
3474 'view_count': int_or_none(
3475 get_first((video_details, microformats), (..., 'viewCount'))
3476 or search_meta('interactionCount')),
3477 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
3478 'age_limit': 18 if (
3479 get_first(microformats, 'isFamilySafe') is False
3480 or search_meta('isFamilyFriendly') == 'false'
3481 or search_meta('og:restrictions:age') == '18+') else 0,
3482 'webpage_url': webpage_url,
3483 'categories': [category] if category else None,
3485 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
3487 'was_live': (False if is_live or is_upcoming or live_content is False
3488 else None if is_live is None or is_upcoming is None
3490 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
3491 'release_timestamp': live_start_time,
3494 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
3496 def get_lang_code(track):
3497 return (remove_start(track.get('vssId') or '', '.').replace('.', '-')
3498 or track.get('languageCode'))
3500 # Converted into dicts to remove duplicates
3502 get_lang_code(sub): sub
3503 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
3504 translation_languages = {
3505 lang.get('languageCode'): self._get_text(lang.get('languageName'), max_runs=1)
3506 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
3508 def process_language(container, base_url, lang_code, sub_name, query):
3509 lang_subs = container.setdefault(lang_code, [])
3510 for fmt in self._SUBTITLE_FORMATS:
3516 'url': urljoin('https://www.youtube.com', update_url_query(base_url, query)),
3520 subtitles, automatic_captions = {}, {}
3521 for lang_code, caption_track in captions.items():
3522 base_url = caption_track.get('baseUrl')
3523 orig_lang = parse_qs(base_url).get('lang', [None])[-1]
3526 lang_name = self._get_text(caption_track, 'name', max_runs=1)
3527 if caption_track.get('kind') != 'asr':
3531 subtitles, base_url, lang_code, lang_name, {})
3532 if not caption_track.get('isTranslatable'):
3534 for trans_code, trans_name in translation_languages.items():
3537 orig_trans_code = trans_code
3538 if caption_track.get('kind') != 'asr':
3539 if 'translated_subs' in self._configuration_arg('skip'):
3541 trans_code += f'-{lang_code}'
3542 trans_name += format_field(lang_name, template=' from %s')
3543 # Add an "-orig" label to the original language so that it can be distinguished.
3544 # The subs are returned without "-orig" as well for compatibility
3545 if lang_code == f'a-{orig_trans_code}':
3547 automatic_captions, base_url, f'{trans_code}-orig', f'{trans_name} (Original)', {})
3548 # Setting tlang=lang returns damaged subtitles.
3549 process_language(automatic_captions, base_url, trans_code, trans_name,
3550 {} if orig_lang == orig_trans_code else {'tlang': trans_code})
3551 info['automatic_captions'] = automatic_captions
3552 info['subtitles'] = subtitles
3554 parsed_url = compat_urllib_parse_urlparse(url)
3555 for component in [parsed_url.fragment, parsed_url.query]:
3556 query = compat_parse_qs(component)
3557 for k, v in query.items():
3558 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
3560 if d_k not in info and k in s_ks:
3561 info[d_k] = parse_duration(query[k][0])
3563 # Youtube Music Auto-generated description
3564 if video_description:
3565 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)
3567 release_year = mobj.group('release_year')
3568 release_date = mobj.group('release_date')
3570 release_date = release_date.replace('-', '')
3571 if not release_year:
3572 release_year = release_date[:4]
3574 'album': mobj.group('album'.strip()),
3575 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
3576 'track': mobj.group('track').strip(),
3577 'release_date': release_date,
3578 'release_year': int_or_none(release_year),
3583 initial_data = self._extract_yt_initial_variable(
3584 webpage, self._YT_INITIAL_DATA_RE, video_id,
3586 if not initial_data:
3587 query = {'videoId': video_id}
3588 query.update(self._get_checkok_params())
3589 initial_data = self._extract_response(
3590 item_id=video_id, ep='next', fatal=False,
3591 ytcfg=master_ytcfg, query=query,
3592 headers=self.generate_api_headers(ytcfg=master_ytcfg),
3593 note='Downloading initial data API JSON')
3596 # This will error if there is no livechat
3597 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3598 info.setdefault('subtitles', {})['live_chat'] = [{
3599 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
3600 'video_id': video_id,
3602 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
3604 except (KeyError, IndexError, TypeError):
3608 info['chapters'] = (
3609 self._extract_chapters_from_json(initial_data, duration)
3610 or self._extract_chapters_from_engagement_panel(initial_data, duration)
3613 contents = traverse_obj(
3614 initial_data, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3615 expected_type=list, default=[])
3617 vpir = get_first(contents, 'videoPrimaryInfoRenderer')
3619 stl = vpir.get('superTitleLink')
3621 stl = self._get_text(stl)
3624 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3625 info['location'] = stl
3627 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
3630 'series': mobj.group(1),
3631 'season_number': int(mobj.group(2)),
3632 'episode_number': int(mobj.group(3)),
3634 for tlb in (try_get(
3636 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3638 tbr = tlb.get('toggleButtonRenderer') or {}
3639 for getter, regex in [(
3640 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3641 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3642 lambda x: x['accessibility'],
3643 lambda x: x['accessibilityData']['accessibilityData'],
3644 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3645 label = (try_get(tbr, getter, dict) or {}).get('label')
3647 mobj = re.match(regex, label)
3649 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3651 sbr_tooltip = try_get(
3652 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3654 like_count, dislike_count = sbr_tooltip.split(' / ')
3656 'like_count': str_to_int(like_count),
3657 'dislike_count': str_to_int(dislike_count),
3659 vsir = get_first(contents, 'videoSecondaryInfoRenderer')
3661 vor = traverse_obj(vsir, ('owner', 'videoOwnerRenderer'))
3663 'channel': self._get_text(vor, 'title'),
3664 'channel_follower_count': self._get_count(vor, 'subscriberCountText')})
3668 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3670 multiple_songs = False
3672 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3673 multiple_songs = True
3676 mrr = row.get('metadataRowRenderer') or {}
3677 mrr_title = mrr.get('title')
3680 mrr_title = self._get_text(mrr, 'title')
3681 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3682 if mrr_title == 'License':
3683 info['license'] = mrr_contents_text
3684 elif not multiple_songs:
3685 if mrr_title == 'Album':
3686 info['album'] = mrr_contents_text
3687 elif mrr_title == 'Artist':
3688 info['artist'] = mrr_contents_text
3689 elif mrr_title == 'Song':
3690 info['track'] = mrr_contents_text
3693 'channel': 'uploader',
3694 'channel_id': 'uploader_id',
3695 'channel_url': 'uploader_url',
3698 # The upload date for scheduled, live and past live streams / premieres in microformats
3699 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3700 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3702 unified_strdate(get_first(microformats, 'uploadDate'))
3703 or unified_strdate(search_meta('uploadDate')))
3704 if not upload_date or (not info.get('is_live') and not info.get('was_live') and info.get('live_status') != 'is_upcoming'):
3705 upload_date = strftime_or_none(self._extract_time_text(vpir, 'dateText')[0], '%Y%m%d')
3706 info['upload_date'] = upload_date
3708 for to, frm in fallbacks.items():
3709 if not info.get(to):
3710 info[to] = info.get(frm)
3712 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3717 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3718 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3719 is_membersonly = None
3721 if initial_data and is_private is not None:
3722 is_membersonly = False
3724 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3725 badge_labels = set()
3726 for content in contents:
3727 if not isinstance(content, dict):
3729 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3730 for badge_label in badge_labels:
3731 if badge_label.lower() == 'members only':
3732 is_membersonly = True
3733 elif badge_label.lower() == 'premium':
3735 elif badge_label.lower() == 'unlisted':
3738 info['availability'] = self._availability(
3739 is_private=is_private,
3740 needs_premium=is_premium,
3741 needs_subscription=is_membersonly,
3742 needs_auth=info['age_limit'] >= 18,
3743 is_unlisted=None if is_private is None else is_unlisted)
3745 info['__post_extractor'] = self.extract_comments(master_ytcfg, video_id, contents, webpage)
3747 self.mark_watched(video_id, player_responses)
3752 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor):
3755 def passthrough_smuggled_data(func):
3756 def _smuggle(entries, smuggled_data):
3757 for entry in entries:
3758 # TODO: Convert URL to music.youtube instead.
3759 # Do we need to passthrough any other smuggled_data?
3760 entry['url'] = smuggle_url(entry['url'], smuggled_data)
3763 @functools.wraps(func)
3764 def wrapper(self, url):
3765 url, smuggled_data = unsmuggle_url(url, {})
3766 if self.is_music_url(url):
3767 smuggled_data['is_music_url'] = True
3768 info_dict = func(self, url, smuggled_data)
3769 if smuggled_data and info_dict.get('entries'):
3770 info_dict['entries'] = _smuggle(info_dict['entries'], smuggled_data)
3774 def _extract_channel_id(self, webpage):
3775 channel_id = self._html_search_meta(
3776 'channelId', webpage, 'channel id', default=None)
3779 channel_url = self._html_search_meta(
3780 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3781 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3782 'twitter:app:url:googleplay'), webpage, 'channel url')
3783 return self._search_regex(
3784 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3785 channel_url, 'channel id')
3788 def _extract_basic_item_renderer(item):
3789 # Modified from _extract_grid_item_renderer
3790 known_basic_renderers = (
3791 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3793 for key, renderer in item.items():
3794 if not isinstance(renderer, dict):
3796 elif key in known_basic_renderers:
3798 elif key.startswith('grid') and key.endswith('Renderer'):
3801 def _grid_entries(self, grid_renderer):
3802 for item in grid_renderer['items']:
3803 if not isinstance(item, dict):
3805 renderer = self._extract_basic_item_renderer(item)
3806 if not isinstance(renderer, dict):
3808 title = self._get_text(renderer, 'title')
3811 playlist_id = renderer.get('playlistId')
3813 yield self.url_result(
3814 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3815 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3819 video_id = renderer.get('videoId')
3821 yield self._extract_video(renderer)
3824 channel_id = renderer.get('channelId')
3826 yield self.url_result(
3827 'https://www.youtube.com/channel/%s' % channel_id,
3828 ie=YoutubeTabIE.ie_key(), video_title=title)
3830 # generic endpoint URL support
3831 ep_url = urljoin('https://www.youtube.com/', try_get(
3832 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3835 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3836 if ie.suitable(ep_url):
3837 yield self.url_result(
3838 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3841 def _music_reponsive_list_entry(self, renderer):
3842 video_id = traverse_obj(renderer, ('playlistItemData', 'videoId'))
3844 return self.url_result(f'https://music.youtube.com/watch?v={video_id}',
3845 ie=YoutubeIE.ie_key(), video_id=video_id)
3846 playlist_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3848 video_id = traverse_obj(renderer, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3850 return self.url_result(f'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3851 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3852 return self.url_result(f'https://music.youtube.com/playlist?list={playlist_id}',
3853 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3854 browse_id = traverse_obj(renderer, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3856 return self.url_result(f'https://music.youtube.com/browse/{browse_id}',
3857 ie=YoutubeTabIE.ie_key(), video_id=browse_id)
3859 def _shelf_entries_from_content(self, shelf_renderer):
3860 content = shelf_renderer.get('content')
3861 if not isinstance(content, dict):
3863 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3865 # TODO: add support for nested playlists so each shelf is processed
3866 # as separate playlist
3867 # TODO: this includes only first N items
3868 for entry in self._grid_entries(renderer):
3870 renderer = content.get('horizontalListRenderer')
3875 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3877 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3879 shelf_url = urljoin('https://www.youtube.com', ep)
3881 # Skipping links to another channels, note that checking for
3882 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3884 if skip_channels and '/channels?' in shelf_url:
3886 title = self._get_text(shelf_renderer, 'title')
3887 yield self.url_result(shelf_url, video_title=title)
3888 # Shelf may not contain shelf URL, fallback to extraction from content
3889 for entry in self._shelf_entries_from_content(shelf_renderer):
3892 def _playlist_entries(self, video_list_renderer):
3893 for content in video_list_renderer['contents']:
3894 if not isinstance(content, dict):
3896 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3897 if not isinstance(renderer, dict):
3899 video_id = renderer.get('videoId')
3902 yield self._extract_video(renderer)
3904 def _rich_entries(self, rich_grid_renderer):
3906 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3907 video_id = renderer.get('videoId')
3910 yield self._extract_video(renderer)
3912 def _video_entry(self, video_renderer):
3913 video_id = video_renderer.get('videoId')
3915 return self._extract_video(video_renderer)
3917 def _hashtag_tile_entry(self, hashtag_tile_renderer):
3918 url = urljoin('https://youtube.com', traverse_obj(
3919 hashtag_tile_renderer, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
3921 return self.url_result(
3922 url, ie=YoutubeTabIE.ie_key(), title=self._get_text(hashtag_tile_renderer, 'hashtag'))
3924 def _post_thread_entries(self, post_thread_renderer):
3925 post_renderer = try_get(
3926 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3927 if not post_renderer:
3930 video_renderer = try_get(
3931 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3932 video_id = video_renderer.get('videoId')
3934 entry = self._extract_video(video_renderer)
3937 # playlist attachment
3938 playlist_id = try_get(
3939 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3941 yield self.url_result(
3942 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3943 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3944 # inline video links
3945 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3947 if not isinstance(run, dict):
3950 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3953 if not YoutubeIE.suitable(ep_url):
3955 ep_video_id = YoutubeIE._match_id(ep_url)
3956 if video_id == ep_video_id:
3958 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3960 def _post_thread_continuation_entries(self, post_thread_continuation):
3961 contents = post_thread_continuation.get('contents')
3962 if not isinstance(contents, list):
3964 for content in contents:
3965 renderer = content.get('backstagePostThreadRenderer')
3966 if not isinstance(renderer, dict):
3968 for entry in self._post_thread_entries(renderer):
3972 def _rich_grid_entries(self
, contents
):
3973 for content
in contents
:
3974 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3976 entry
= self
._video
_entry
(video_renderer
)
3981 def _extract_entries(self, parent_renderer, continuation_list):
3982 # continuation_list is modified in-place with continuation_list = [continuation_token]
3983 continuation_list[:] = [None]
3984 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3985 for content in contents:
3986 if not isinstance(content, dict):
3988 is_renderer = traverse_obj(
3989 content, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
3992 renderer = content.get('richItemRenderer')
3994 for entry in self._rich_entries(renderer):
3996 continuation_list[0] = self._extract_continuation(parent_renderer)
3998 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3999 for isr_content in isr_contents:
4000 if not isinstance(isr_content, dict):
4004 'playlistVideoListRenderer': self._playlist_entries,
4005 'gridRenderer': self._grid_entries,
4006 'reelShelfRenderer': self._grid_entries,
4007 'shelfRenderer': self._shelf_entries,
4008 'musicResponsiveListItemRenderer': lambda x: [self._music_reponsive_list_entry(x)],
4009 'backstagePostThreadRenderer': self._post_thread_entries,
4010 'videoRenderer': lambda x: [self._video_entry(x)],
4011 'playlistRenderer': lambda x: self._grid_entries({'items': [{'playlistRenderer': x}]}),
4012 'channelRenderer': lambda x: self._grid_entries({'items': [{'channelRenderer': x}]}),
4013 'hashtagTileRenderer': lambda x: [self._hashtag_tile_entry(x)]
4015 for key, renderer in isr_content.items():
4016 if key not in known_renderers:
4018 for entry in known_renderers[key](renderer):
4021 continuation_list[0] = self._extract_continuation(renderer)
4024 if not continuation_list[0]:
4025 continuation_list[0] = self._extract_continuation(is_renderer)
4027 if not continuation_list[0]:
4028 continuation_list[0] = self._extract_continuation(parent_renderer)
4030 def _entries(self, tab, item_id, ytcfg, account_syncid, visitor_data):
4031 continuation_list = [None]
4032 extract_entries = lambda x: self._extract_entries(x, continuation_list)
4033 tab_content = try_get(tab, lambda x: x['content'], dict)
4037 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
4038 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
4039 for entry in extract_entries(parent_renderer):
4041 continuation = continuation_list[0]
4043 for page_num in itertools.count(1):
4044 if not continuation:
4046 headers = self.generate_api_headers(
4047 ytcfg=ytcfg, account_syncid=account_syncid, visitor_data=visitor_data)
4048 response = self._extract_response(
4049 item_id='%s page %s' % (item_id, page_num),
4050 query=continuation, headers=headers, ytcfg=ytcfg,
4051 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4055 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4056 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4057 visitor_data = self._extract_visitor_data(response) or visitor_data
4059 known_continuation_renderers = {
4060 'playlistVideoListContinuation': self._playlist_entries,
4061 'gridContinuation': self._grid_entries,
4062 'itemSectionContinuation': self._post_thread_continuation_entries,
4063 'sectionListContinuation': extract_entries, # for feeds
4065 continuation_contents = try_get(
4066 response, lambda x: x['continuationContents'], dict) or {}
4067 continuation_renderer = None
4068 for key, value in continuation_contents.items():
4069 if key not in known_continuation_renderers:
4071 continuation_renderer = value
4072 continuation_list = [None]
4073 for entry in known_continuation_renderers[key](continuation_renderer):
4075 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
4077 if continuation_renderer:
4081 'videoRenderer': (self._grid_entries, 'items'), # for membership tab
4082 'gridPlaylistRenderer': (self._grid_entries, 'items'),
4083 'gridVideoRenderer': (self._grid_entries, 'items'),
4084 'gridChannelRenderer': (self._grid_entries, 'items'),
4085 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
4086 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
4087 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
4088 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
4090 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4091 continuation_items = try_get(
4092 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
4093 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
4094 video_items_renderer = None
4095 for key, value in continuation_item.items():
4096 if key not in known_renderers:
4098 video_items_renderer = {known_renderers[key][1]: continuation_items}
4099 continuation_list = [None]
4100 for entry in known_renderers[key][0](video_items_renderer):
4102 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
4104 if video_items_renderer:
4109 def _extract_selected_tab(tabs, fatal=True):
4111 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
4112 if renderer.get('selected') is True:
4116 raise ExtractorError('Unable to find selected tab')
4118 def _extract_uploader(self, data):
4120 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
4122 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4124 owner_text = owner.get('text')
4125 uploader['uploader'] = self._search_regex(
4126 r'^by (.+) and \d+ others?$', owner_text, 'uploader', default=owner_text)
4127 uploader['uploader_id'] = try_get(
4128 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
4129 uploader['uploader_url'] = urljoin(
4130 'https://www.youtube.com/',
4131 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
4132 return {k: v for k, v in uploader.items() if v is not None}
4134 def _extract_from_tabs(self, item_id, ytcfg, data, tabs):
4135 playlist_id = title = description = channel_url = channel_name = channel_id = None
4138 selected_tab = self._extract_selected_tab(tabs)
4139 primary_sidebar_renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4141 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
4143 channel_name = renderer.get('title')
4144 channel_url = renderer.get('channelUrl')
4145 channel_id = renderer.get('externalId')
4148 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
4151 title = renderer.get('title')
4152 description = renderer.get('description', '')
4153 playlist_id = channel_id
4154 tags = renderer.get('keywords', '').split()
4156 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4157 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4158 def _get_uncropped(url):
4159 return url_or_none((url or '').split('=')[0] + '=s0')
4161 avatar_thumbnails = self._extract_thumbnails(renderer, 'avatar')
4162 if avatar_thumbnails:
4163 uncropped_avatar = _get_uncropped(avatar_thumbnails[0]['url'])
4164 if uncropped_avatar:
4165 avatar_thumbnails.append({
4166 'url': uncropped_avatar,
4167 'id': 'avatar_uncropped',
4171 channel_banners = self._extract_thumbnails(
4172 data, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4173 for banner in channel_banners:
4174 banner['preference'] = -10
4177 uncropped_banner = _get_uncropped(channel_banners[0]['url'])
4178 if uncropped_banner:
4179 channel_banners.append({
4180 'url': uncropped_banner,
4181 'id': 'banner_uncropped',
4185 primary_thumbnails = self._extract_thumbnails(
4186 primary_sidebar_renderer, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4188 if playlist_id is None:
4189 playlist_id = item_id
4191 playlist_stats = traverse_obj(primary_sidebar_renderer, 'stats')
4192 last_updated_unix, _ = self._extract_time_text(playlist_stats, 2)
4194 title = self._get_text(data, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4195 title += format_field(selected_tab, 'title', ' - %s')
4196 title += format_field(selected_tab, 'expandedText', ' - %s')
4199 'playlist_id': playlist_id,
4200 'playlist_title': title,
4201 'playlist_description': description,
4202 'uploader': channel_name,
4203 'uploader_id': channel_id,
4204 'uploader_url': channel_url,
4205 'thumbnails': primary_thumbnails + avatar_thumbnails + channel_banners,
4207 'view_count': self._get_count(playlist_stats, 1),
4208 'availability': self._extract_availability(data),
4209 'modified_date': strftime_or_none(last_updated_unix, '%Y%m%d'),
4210 'playlist_count': self._get_count(playlist_stats, 0),
4211 'channel_follower_count': self._get_count(data, ('header', ..., 'subscriberCountText')),
4214 metadata.update(self._extract_uploader(data))
4216 'channel': metadata['uploader'],
4217 'channel_id': metadata['uploader_id'],
4218 'channel_url': metadata['uploader_url']})
4219 return self.playlist_result(
4221 selected_tab, playlist_id, ytcfg,
4222 self._extract_account_syncid(ytcfg, data),
4223 self._extract_visitor_data(data, ytcfg)),
4226 def _extract_mix_playlist(self, playlist, playlist_id, data, ytcfg):
4227 first_id = last_id = response = None
4228 for page_num in itertools.count(1):
4229 videos = list(self._playlist_entries(playlist))
4232 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
4233 if start >= len(videos):
4235 for video in videos[start:]:
4236 if video['id'] == first_id:
4237 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
4240 first_id = first_id or videos[0]['id']
4241 last_id = videos[-1]['id']
4242 watch_endpoint = try_get(
4243 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4244 headers = self.generate_api_headers(
4245 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4246 visitor_data=self._extract_visitor_data(response, data, ytcfg))
4248 'playlistId': playlist_id,
4249 'videoId': watch_endpoint.get('videoId') or last_id,
4250 'index': watch_endpoint.get('index') or len(videos),
4251 'params': watch_endpoint.get('params') or 'OAE%3D'
4253 response = self._extract_response(
4254 item_id='%s page %d' % (playlist_id, page_num),
4255 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4256 check_get_keys='contents'
4259 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4261 def _extract_from_playlist(self, item_id, url, data, playlist, ytcfg):
4262 title = playlist.get('title') or try_get(
4263 data, lambda x: x['titleText']['simpleText'], compat_str)
4264 playlist_id = playlist.get('playlistId') or item_id
4266 # Delegating everything except mix playlists to regular tab-based playlist URL
4267 playlist_url = urljoin(url, try_get(
4268 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4270 if playlist_url and playlist_url != url:
4271 return self.url_result(
4272 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4275 return self.playlist_result(
4276 self._extract_mix_playlist(playlist, playlist_id, data, ytcfg),
4277 playlist_id=playlist_id, playlist_title=title)
4279 def _extract_availability(self, data):
4281 Gets the availability of a given playlist/tab.
4282 Note: Unless YouTube tells us explicitly, we do not assume it is public
4283 @param data: response
4285 is_private = is_unlisted = None
4286 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4287 badge_labels = self._extract_badges(renderer)
4289 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4290 privacy_dropdown_entries = try_get(
4291 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4292 for renderer_dict in privacy_dropdown_entries:
4293 is_selected = try_get(
4294 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4297 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4299 badge_labels.add(label.lower())
4302 for badge_label in badge_labels:
4303 if badge_label == 'unlisted':
4305 elif badge_label == 'private':
4307 elif badge_label == 'public':
4308 is_unlisted = is_private = False
4309 return self._availability(is_private, False, False, False, is_unlisted)
4312 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4313 sidebar_renderer = try_get(
4314 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4315 for item in sidebar_renderer:
4316 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4320 def _reload_with_unavailable_videos(self, item_id, data, ytcfg):
4322 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4324 browse_id = params = None
4325 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4328 menu_renderer = try_get(
4329 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4330 for menu_item in menu_renderer:
4331 if not isinstance(menu_item, dict):
4333 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4335 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4336 if not text or text.lower() != 'show unavailable videos':
4338 browse_endpoint = try_get(
4339 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4340 browse_id = browse_endpoint.get('browseId')
4341 params = browse_endpoint.get('params')
4344 headers = self.generate_api_headers(
4345 ytcfg=ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4346 visitor_data=self._extract_visitor_data(data, ytcfg))
4348 'params': params or 'wgYCCAA=',
4349 'browseId': browse_id or 'VL%s' % item_id
4351 return self._extract_response(
4352 item_id=item_id, headers=headers, query=query,
4353 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4354 note='Downloading API JSON with unavailable videos')
4357 def skip_webpage(self):
4358 return 'webpage' in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key())
4360 def _extract_webpage(self, url, item_id, fatal=True):
4361 retries = self.get_param('extractor_retries', 3)
4363 webpage = data = last_error = None
4364 while count < retries:
4366 # Sometimes youtube returns a webpage with incomplete ytInitialData
4367 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4369 self.report_warning('%s. Retrying ...' % last_error)
4371 webpage = self._download_webpage(
4373 note='Downloading webpage%s' % (' (retry #%d)' % count if count else '',))
4374 data = self.extract_yt_initial_data(item_id, webpage or '', fatal=fatal) or {}
4375 except ExtractorError as e:
4376 if isinstance(e.cause, network_exceptions):
4377 if not isinstance(e.cause, compat_HTTPError) or e.cause.code not in (403, 429):
4378 last_error = error_to_compat_str(e.cause or e.msg)
4383 self.report_warning(error_to_compat_str(e))
4387 self._extract_and_report_alerts(data)
4388 except ExtractorError as e:
4391 self.report_warning(error_to_compat_str(e))
4394 if dict_get(data, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4397 last_error = 'Incomplete yt initial data received'
4398 if count >= retries:
4400 raise ExtractorError(last_error)
4401 self.report_warning(last_error)
4404 return webpage, data
4406 def _report_playlist_authcheck(self, ytcfg, fatal=True):
4407 """Use if failed to extract ytcfg (and data) from initial webpage"""
4408 if not ytcfg and self.is_authenticated:
4409 msg = 'Playlists that require authentication may not extract correctly without a successful webpage download'
4410 if 'authcheck' not in self._configuration_arg('skip', ie_key=YoutubeTabIE.ie_key()) and fatal:
4411 raise ExtractorError(
4412 f'{msg}. If you are not downloading private content, or '
4413 'your cookies are only for the first account and channel,'
4414 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4416 self.report_warning(msg, only_once=True)
4418 def _extract_data(self, url, item_id, ytcfg=None, fatal=True, webpage_fatal=False, default_client='web'):
4420 if not self.skip_webpage:
4421 webpage, data = self._extract_webpage(url, item_id, fatal=webpage_fatal)
4422 ytcfg = ytcfg or self.extract_ytcfg(item_id, webpage)
4423 # Reject webpage data if redirected to home page without explicitly requesting
4424 selected_tab = self._extract_selected_tab(traverse_obj(
4425 data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list, default=[]), fatal=False) or {}
4426 if (url != 'https://www.youtube.com/feed/recommended'
4427 and selected_tab.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4428 and 'no-youtube-channel-redirect' not in self.get_param('compat_opts', [])):
4429 msg = 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4431 raise ExtractorError(msg, expected=True)
4432 self.report_warning(msg, only_once=True)
4434 self._report_playlist_authcheck(ytcfg, fatal=fatal)
4435 data = self._extract_tab_endpoint(url, item_id, ytcfg, fatal=fatal, default_client=default_client)
4438 def _extract_tab_endpoint(self, url, item_id, ytcfg=None, fatal=True, default_client='web'):
4439 headers = self.generate_api_headers(ytcfg=ytcfg, default_client=default_client)
4440 resolve_response = self._extract_response(
4441 item_id=item_id, query={'url': url}, check_get_keys='endpoint', headers=headers, ytcfg=ytcfg, fatal=fatal,
4442 ep='navigation/resolve_url', note='Downloading API parameters API JSON', default_client=default_client)
4443 endpoints = {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4444 for ep_key, ep in endpoints.items():
4445 params = try_get(resolve_response, lambda x: x['endpoint'][ep_key], dict)
4447 return self._extract_response(
4448 item_id=item_id, query=params, ep=ep, headers=headers,
4449 ytcfg=ytcfg, fatal=fatal, default_client=default_client,
4450 check_get_keys=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4451 err_note = 'Failed to resolve url (does the playlist exist?)'
4453 raise ExtractorError(err_note, expected=True)
4454 self.report_warning(err_note, item_id)
4456 _SEARCH_PARAMS = None
4458 def _search_results(self, query, params=NO_DEFAULT, default_client='web'):
4459 data = {'query': query}
4460 if params is NO_DEFAULT:
4461 params = self._SEARCH_PARAMS
4463 data['params'] = params
4466 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4467 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4469 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4470 ('continuationContents', ),
4472 display_id = f'query "{query}"'
4473 check_get_keys = tuple(set(keys[0] for keys in content_keys))
4474 ytcfg = self._download_ytcfg(default_client, display_id) if not self.skip_webpage else {}
4475 self._report_playlist_authcheck(ytcfg, fatal=False)
4477 continuation_list = [None]
4479 for page_num in itertools.count(1):
4480 data.update(continuation_list[0] or {})
4481 headers = self.generate_api_headers(
4482 ytcfg=ytcfg, visitor_data=self._extract_visitor_data(search), default_client=default_client)
4483 search = self._extract_response(
4484 item_id=f'{display_id} page {page_num}', ep='search', query=data,
4485 default_client=default_client, check_get_keys=check_get_keys, ytcfg=ytcfg, headers=headers)
4486 slr_contents = traverse_obj(search, *content_keys)
4487 yield from self._extract_entries({'contents': list(variadic(slr_contents))}, continuation_list)
4488 if not continuation_list[0]:
4492 class YoutubeTabIE(YoutubeTabBaseInfoExtractor):
4493 IE_DESC = 'YouTube Tabs'
4494 _VALID_URL = r'''(?x
:
4498 youtube(?
:kids
)?\
.com|
4502 (?P
<channel_type
>channel|c|user|browse
)/|
4505 (?
:playlist|watch
)\?.*?
\blist
=
4507 (?
!(?
:%(reserved_names)s)\b) # Direct URLs
4511 'reserved_names': YoutubeBaseInfoExtractor._RESERVED_NAMES,
4512 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
4514 IE_NAME = 'youtube:tab'
4517 'note': 'playlists, multipage',
4518 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4519 'playlist_mincount': 94,
4521 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4522 'title': 'Igor Kleiner - Playlists',
4523 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4524 'uploader': 'Igor Kleiner',
4525 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4526 'channel': 'Igor Kleiner',
4527 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4528 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4529 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4530 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4531 'channel_follower_count': int
4534 'note': 'playlists, multipage, different order',
4535 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4536 'playlist_mincount': 94,
4538 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4539 'title': 'Igor Kleiner - Playlists',
4540 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4541 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4542 'uploader': 'Igor Kleiner',
4543 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4544 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4545 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4546 'channel': 'Igor Kleiner',
4547 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4548 'channel_follower_count': int
4551 'note': 'playlists, series',
4552 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4553 'playlist_mincount': 5,
4555 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4556 'title': '3Blue1Brown - Playlists',
4557 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4558 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4559 'uploader': '3Blue1Brown',
4560 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4561 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4562 'channel': '3Blue1Brown',
4563 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4564 'tags': ['Mathematics'],
4565 'channel_follower_count': int
4568 'note': 'playlists, singlepage',
4569 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4570 'playlist_mincount': 4,
4572 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4573 'title': 'ThirstForScience - Playlists',
4574 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4575 'uploader': 'ThirstForScience',
4576 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4577 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4578 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4579 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4581 'channel': 'ThirstForScience',
4582 'channel_follower_count': int
4585 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4586 'only_matching': True,
4588 'note': 'basic, single video playlist',
4589 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4591 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4592 'uploader': 'Sergey M.',
4593 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4594 'title': 'youtube-dl public playlist',
4598 'modified_date': '20201130',
4599 'channel': 'Sergey M.',
4600 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4601 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4602 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4604 'playlist_count': 1,
4606 'note': 'empty playlist',
4607 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4609 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4610 'uploader': 'Sergey M.',
4611 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4612 'title': 'youtube-dl empty playlist',
4614 'channel': 'Sergey M.',
4616 'modified_date': '20160902',
4617 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4618 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4619 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4621 'playlist_count': 0,
4624 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4626 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4627 'title': 'lex will - Home',
4628 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4629 'uploader': 'lex will',
4630 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4631 'channel': 'lex will',
4632 'tags': ['bible', 'history', 'prophesy'],
4633 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4634 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4635 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4636 'channel_follower_count': int
4638 'playlist_mincount': 2,
4640 'note': 'Videos tab',
4641 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4643 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4644 'title': 'lex will - Videos',
4645 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4646 'uploader': 'lex will',
4647 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4648 'tags': ['bible', 'history', 'prophesy'],
4649 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4650 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4651 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4652 'channel': 'lex will',
4653 'channel_follower_count': int
4655 'playlist_mincount': 975,
4657 'note': 'Videos tab, sorted by popular',
4658 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4660 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4661 'title': 'lex will - Videos',
4662 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4663 'uploader': 'lex will',
4664 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4665 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4666 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4667 'channel': 'lex will',
4668 'tags': ['bible', 'history', 'prophesy'],
4669 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4670 'channel_follower_count': int
4672 'playlist_mincount': 199,
4674 'note': 'Playlists tab',
4675 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4677 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4678 'title': 'lex will - Playlists',
4679 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4680 'uploader': 'lex will',
4681 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4682 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4683 'channel': 'lex will',
4684 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4685 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4686 'tags': ['bible', 'history', 'prophesy'],
4687 'channel_follower_count': int
4689 'playlist_mincount': 17,
4691 'note': 'Community tab',
4692 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4694 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4695 'title': 'lex will - Community',
4696 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4697 'uploader': 'lex will',
4698 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4699 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4700 'channel': 'lex will',
4701 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4702 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4703 'tags': ['bible', 'history', 'prophesy'],
4704 'channel_follower_count': int
4706 'playlist_mincount': 18,
4708 'note': 'Channels tab',
4709 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4711 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4712 'title': 'lex will - Channels',
4713 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4714 'uploader': 'lex will',
4715 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4716 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4717 'channel': 'lex will',
4718 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4719 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4720 'tags': ['bible', 'history', 'prophesy'],
4721 'channel_follower_count': int
4723 'playlist_mincount': 12,
4725 'note': 'Search tab',
4726 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4727 'playlist_mincount': 40,
4729 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4730 'title': '3Blue1Brown - Search - linear algebra',
4731 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4732 'uploader': '3Blue1Brown',
4733 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4734 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4735 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4736 'tags': ['Mathematics'],
4737 'channel': '3Blue1Brown',
4738 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4739 'channel_follower_count': int
4742 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4743 'only_matching': True,
4745 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4746 'only_matching': True,
4748 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4749 'only_matching': True,
4751 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4752 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4754 'title': '29C3: Not my department',
4755 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4756 'uploader': 'Christiaan008',
4757 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4758 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4760 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4762 'modified_date': '20150605',
4763 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4764 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4765 'channel': 'Christiaan008',
4767 'playlist_count': 96,
4769 'note': 'Large playlist',
4770 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4772 'title': 'Uploads from Cauchemar',
4773 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4774 'uploader': 'Cauchemar',
4775 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4776 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4778 'modified_date': r're:\d{8}',
4779 'channel': 'Cauchemar',
4780 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4783 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4785 'playlist_mincount': 1123,
4786 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4788 'note': 'even larger playlist, 8832 videos',
4789 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4790 'only_matching': True,
4792 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4793 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4795 'title': 'Uploads from Interstellar Movie',
4796 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4797 'uploader': 'Interstellar Movie',
4798 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4799 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4802 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4803 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4804 'channel': 'Interstellar Movie',
4806 'modified_date': r're:\d{8}',
4808 'playlist_mincount': 21,
4810 'note': 'Playlist with "show unavailable videos" button',
4811 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4813 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4814 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4815 'uploader': 'Phim Siêu Nhân Nhật Bản',
4816 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4818 'channel': 'Phim Siêu Nhân Nhật Bản',
4820 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4822 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4823 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4824 'modified_date': r're:\d{8}',
4826 'playlist_mincount': 200,
4827 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4829 'note': 'Playlist with unavailable videos in page 7',
4830 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4832 'title': 'Uploads from BlankTV',
4833 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4834 'uploader': 'BlankTV',
4835 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4836 'channel': 'BlankTV',
4837 'channel_url': 'https://www.youtube.com/c/blanktv',
4838 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4841 'uploader_url': 'https://www.youtube.com/c/blanktv',
4842 'modified_date': r're:\d{8}',
4845 'playlist_mincount': 1000,
4846 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
4848 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4849 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4851 'title': 'Data Analysis with Dr Mike Pound',
4852 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4853 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4854 'uploader': 'Computerphile',
4855 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4856 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4859 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4860 'channel_url': 'https://www.youtube.com/user/Computerphile',
4861 'channel': 'Computerphile',
4863 'playlist_mincount': 11,
4865 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4866 'only_matching': True,
4868 'note': 'Playlist URL that does not actually serve a playlist',
4869 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4871 'id': 'FqZTN594JQw',
4873 'title': "Smiley's People 01 detective, Adventure Series, Action",
4874 'uploader': 'STREEM',
4875 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4876 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4877 'upload_date': '20150526',
4878 'license': 'Standard YouTube License',
4879 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4880 'categories': ['People & Blogs'],
4886 'skip_download': True,
4888 'skip': 'This video is not available.',
4889 'add_ie': [YoutubeIE.ie_key()],
4891 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
4892 'only_matching': True,
4894 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
4895 'only_matching': True,
4897 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
4899 'id': 'GgL890LIznQ', # This will keep changing
4902 'uploader': 'Sky News',
4903 'uploader_id': 'skynews',
4904 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
4905 'upload_date': r're:\d{8}',
4907 'categories': ['News & Politics'],
4910 'release_timestamp': 1642502819,
4911 'channel': 'Sky News',
4912 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
4915 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
4916 'playable_in_embed': True,
4917 'release_date': '20220118',
4918 'availability': 'public',
4919 'live_status': 'is_live',
4920 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
4921 'channel_follower_count': int
4924 'skip_download': True,
4926 'expected_warnings': ['Ignoring subtitle tracks found in '],
4928 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
4930 'id': 'a48o2S1cPoo',
4932 'title': 'The Young Turks - Live Main Show',
4933 'uploader': 'The Young Turks',
4934 'uploader_id': 'TheYoungTurks',
4935 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
4936 'upload_date': '20150715',
4937 'license': 'Standard YouTube License',
4938 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
4939 'categories': ['News & Politics'],
4940 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
4944 'skip_download': True,
4946 'only_matching': True,
4948 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
4949 'only_matching': True,
4951 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
4952 'only_matching': True,
4954 'note': 'A channel that is not live. Should raise error',
4955 'url': 'https://www.youtube.com/user/numberphile/live',
4956 'only_matching': True,
4958 'url': 'https://www.youtube.com/feed/trending',
4959 'only_matching': True,
4961 'url': 'https://www.youtube.com/feed/library',
4962 'only_matching': True,
4964 'url': 'https://www.youtube.com/feed/history',
4965 'only_matching': True,
4967 'url': 'https://www.youtube.com/feed/subscriptions',
4968 'only_matching': True,
4970 'url': 'https://www.youtube.com/feed/watch_later',
4971 'only_matching': True,
4973 'note': 'Recommended - redirects to home page.',
4974 'url': 'https://www.youtube.com/feed/recommended',
4975 'only_matching': True,
4977 'note': 'inline playlist with not always working continuations',
4978 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
4979 'only_matching': True,
4981 'url': 'https://www.youtube.com/course',
4982 'only_matching': True,
4984 'url': 'https://www.youtube.com/zsecurity',
4985 'only_matching': True,
4987 'url': 'http://www.youtube.com/NASAgovVideo/videos',
4988 'only_matching': True,
4990 'url': 'https://www.youtube.com/TheYoungTurks/live',
4991 'only_matching': True,
4993 'url': 'https://www.youtube.com/hashtag/cctv9',
4999 'playlist_mincount': 350,
5001 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5002 'only_matching': True,
5004 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5005 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5006 'only_matching': True
5008 'note': '/browse/ should redirect to /channel/',
5009 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5010 'only_matching': True
5012 'note': 'VLPL, should redirect to playlist?list=PL...',
5013 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5015 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5016 'uploader': 'NoCopyrightSounds',
5017 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5018 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5019 'title': 'NCS Releases',
5020 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5021 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5022 'modified_date': r're:\d{8}',
5024 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5026 'channel': 'NoCopyrightSounds',
5028 'playlist_mincount': 166,
5029 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5031 'note': 'Topic, should redirect to playlist?list=UU...',
5032 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5034 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5035 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5036 'title': 'Uploads from Royalty Free Music - Topic',
5037 'uploader': 'Royalty Free Music - Topic',
5039 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5040 'channel': 'Royalty Free Music - Topic',
5042 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5043 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5044 'modified_date': r're:\d{8}',
5045 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5048 'expected_warnings': [
5049 'The URL does not have a videos tab',
5050 r'[Uu]navailable videos (are|will be) hidden',
5052 'playlist_mincount': 101,
5054 'note': 'Topic without a UU playlist',
5055 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5057 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5058 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5061 'expected_warnings': [
5062 'the playlist redirect gave error',
5064 'playlist_mincount': 9,
5066 'note': 'Youtube music Album',
5067 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5069 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5070 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5074 'availability': 'unlisted',
5075 'modified_date': r're:\d{8}',
5077 'playlist_count': 50,
5079 'note': 'unlisted single video playlist',
5080 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5082 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5083 'uploader': 'colethedj',
5084 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5085 'title': 'yt-dlp unlisted playlist test',
5086 'availability': 'unlisted',
5088 'modified_date': '20211208',
5089 'channel': 'colethedj',
5092 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5093 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5094 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5096 'playlist_count': 1,
5098 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5099 'url': 'https://www.youtube.com/feed/recommended',
5101 'id': 'recommended',
5102 'title': 'recommended',
5105 'playlist_mincount': 50,
5107 'skip_download': True,
5108 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5111 'note': 'API Fallback: /videos tab, sorted by oldest first',
5112 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5114 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5115 'title': 'Cody\'sLab - Videos',
5116 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5117 'uploader': 'Cody\'sLab',
5118 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5119 'channel': 'Cody\'sLab',
5120 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5122 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5123 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5124 'channel_follower_count': int
5126 'playlist_mincount': 650,
5128 'skip_download': True,
5129 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5132 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5133 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5135 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5136 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5137 'title': 'Uploads from Royalty Free Music - Topic',
5138 'uploader': 'Royalty Free Music - Topic',
5139 'modified_date': r're:\d{8}',
5140 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5142 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5144 'channel': 'Royalty Free Music - Topic',
5146 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5148 'expected_warnings': [
5149 'does not have a videos tab',
5150 r'[Uu]navailable videos (are|will be) hidden',
5152 'playlist_mincount': 101,
5154 'skip_download': True,
5155 'extractor_args': {'youtubetab': {'skip': ['webpage']}}
5158 'note': 'non-standard redirect to regional channel',
5159 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5160 'only_matching': True
5162 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5163 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5165 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5166 'modified_date': '20220407',
5167 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5169 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5170 'uploader': 'pukkandan',
5171 'availability': 'unlisted',
5172 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5173 'channel': 'pukkandan',
5174 'description': 'Test for collaborative playlist',
5175 'title': 'yt-dlp test - collaborative playlist',
5176 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5178 'playlist_mincount': 2
5182 def suitable(cls, url):
5183 return False if YoutubeIE.suitable(url) else super(
5184 YoutubeTabIE, cls).suitable(url)
5186 _URL_RE = re.compile(rf'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5188 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5189 def _real_extract(self, url, smuggled_data):
5190 item_id = self._match_id(url)
5191 url = compat_urlparse.urlunparse(
5192 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
5193 compat_opts = self.get_param('compat_opts', [])
5196 mobj = self._URL_RE.match(url).groupdict()
5197 mobj.update((k, '') for k, v in mobj.items() if v is None)
5200 mobj, redirect_warning = get_mobj(url), None
5201 # Youtube returns incomplete data if tabname is not lower case
5202 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
5204 if smuggled_data.get('is_music_url'):
5205 if item_id[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5206 item_id = item_id[2:]
5207 pre, tab, post, is_channel = f'https://www.youtube.com/playlist?list={item_id}', '', '', False
5208 elif item_id[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5209 mdata = self._extract_tab_endpoint(
5210 f'https://music.youtube.com/channel/{item_id}', item_id, default_client='web_music')
5211 murl = traverse_obj(mdata, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5212 get_all=False, expected_type=compat_str)
5214 raise ExtractorError('Failed to resolve album to playlist')
5215 return self.url_result(murl, ie=YoutubeTabIE.ie_key())
5216 elif mobj['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5217 pre = f'https://www.youtube.com/channel/{item_id}'
5219 original_tab_name = tab
5220 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
5221 # Home URLs should redirect to /videos/
5222 redirect_warning = ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5223 'To download only the videos in the home page, add a "/featured" to the URL')
5226 url = ''.join((pre, tab, post))
5227 mobj = get_mobj(url)
5229 # Handle both video/playlist URLs
5231 video_id, playlist_id = [qs.get(key, [None])[0] for key in ('v', 'list')]
5233 if not video_id and mobj['not_channel'].startswith('watch'):
5235 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5236 raise ExtractorError('Unable to recognize tab page')
5237 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5238 self.report_warning(f'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5239 url = f'https://www.youtube.com/playlist?list={playlist_id}'
5240 mobj = get_mobj(url)
5242 if video_id and playlist_id:
5243 if self.get_param('noplaylist'):
5244 self.to_screen(f'Downloading just video {video_id} because of --no-playlist')
5245 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5246 ie=YoutubeIE.ie_key(), video_id=video_id)
5247 self.to_screen(f'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5249 data, ytcfg = self._extract_data(url, item_id)
5251 # YouTube may provide a non-standard redirect to the regional channel
5252 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5253 redirect_url = traverse_obj(
5254 data, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all=False)
5255 if redirect_url and 'no-youtube-channel-redirect' not in compat_opts:
5256 redirect_url = ''.join((
5257 urljoin('https://www.youtube.com', redirect_url), mobj['tab'], mobj['post']))
5258 self.to_screen(f'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5259 return self.url_result(redirect_url, ie=YoutubeTabIE.ie_key())
5261 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5263 selected_tab = self._extract_selected_tab(tabs)
5264 selected_tab_name = selected_tab.get('title', '').lower()
5265 if selected_tab_name == 'home':
5266 selected_tab_name = 'featured'
5267 requested_tab_name = mobj['tab'][1:]
5268 if 'no-youtube-channel-redirect' not in compat_opts:
5269 if requested_tab_name == 'live':
5270 # Live tab should have redirected to the video
5271 raise ExtractorError('The channel is not currently live', expected=True)
5272 if requested_tab_name not in ('', selected_tab_name):
5273 redirect_warning = f'The channel does not have a {requested_tab_name} tab'
5274 if not original_tab_name:
5275 if item_id[:2] == 'UC':
5276 # Topic channels don't have /videos. Use the equivalent playlist instead
5277 pl_id = f'UU{item_id[2:]}'
5278 pl_url = f'https://www.youtube.com/playlist?list={pl_id}'
5280 data, ytcfg = self._extract_data(pl_url, pl_id, ytcfg=ytcfg, fatal=True, webpage_fatal=True)
5281 except ExtractorError:
5282 redirect_warning += ' and the playlist redirect gave error'
5284 item_id, url, selected_tab_name = pl_id, pl_url, requested_tab_name
5285 redirect_warning += f'. Redirecting to playlist {pl_id} instead'
5286 if selected_tab_name and selected_tab_name != requested_tab_name:
5287 redirect_warning += f'. {selected_tab_name} tab is being downloaded instead'
5289 raise ExtractorError(redirect_warning, expected=True)
5291 if redirect_warning:
5292 self.to_screen(redirect_warning)
5293 self.write_debug(f'Final URL: {url}')
5295 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5296 if 'no-youtube-unavailable-videos' not in compat_opts:
5297 data = self._reload_with_unavailable_videos(item_id, data, ytcfg) or data
5298 self._extract_and_report_alerts(data, only_once=True)
5299 tabs = traverse_obj(data, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type=list)
5301 return self._extract_from_tabs(item_id, ytcfg, data, tabs)
5303 playlist = traverse_obj(
5304 data, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type=dict)
5306 return self._extract_from_playlist(item_id, url, data, playlist, ytcfg)
5308 video_id = traverse_obj(
5309 data, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type=str) or video_id
5311 if mobj['tab'] != '/live': # live tab is expected to redirect to video
5312 self.report_warning(f'Unable to recognize playlist. Downloading just video {video_id}')
5313 return self.url_result(f'https://www.youtube.com/watch?v={video_id}',
5314 ie=YoutubeIE.ie_key(), video_id=video_id)
5316 raise ExtractorError('Unable to recognize tab page')
5319 class YoutubePlaylistIE(InfoExtractor):
5320 IE_DESC = 'YouTube playlists'
5321 _VALID_URL = r'''(?x
)(?
:
5326 youtube(?
:kids
)?\
.com|
5331 (?P
<id>%(playlist_id)s)
5333 'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE,
5334 'invidious': '|'.join(YoutubeBaseInfoExtractor._INVIDIOUS_SITES),
5336 IE_NAME = 'youtube:playlist'
5338 'note': 'issue #673',
5339 'url': 'PLBB231211A4F62143',
5341 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5342 'id': 'PLBB231211A4F62143',
5343 'uploader': 'Wickman',
5344 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5345 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5347 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5348 'modified_date': r're:\d{8}',
5349 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5350 'channel': 'Wickman',
5352 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5354 'playlist_mincount': 29,
5356 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5358 'title': 'YDL_safe_search',
5359 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5361 'playlist_count': 2,
5362 'skip': 'This playlist is private',
5365 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5366 'playlist_count': 4,
5369 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5370 'uploader': 'milan',
5371 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5373 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5375 'modified_date': '20140919',
5378 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5379 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5381 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5383 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5384 'playlist_mincount': 654,
5386 'title': '2018 Chinese New Singles (11/6 updated)',
5387 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5389 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5390 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5393 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5395 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5396 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5397 'modified_date': r're:\d{8}',
5399 'expected_warnings': [r'[Uu]navailable videos (are|will be) hidden'],
5401 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5402 'only_matching': True,
5404 # music album playlist
5405 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5406 'only_matching': True,
5410 def suitable(cls, url):
5411 if YoutubeTabIE.suitable(url):
5413 from ..utils import parse_qs
5415 if qs.get('v', [None])[0]:
5417 return super(YoutubePlaylistIE, cls).suitable(url)
5419 def _real_extract(self, url):
5420 playlist_id = self._match_id(url)
5421 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
5422 url = update_url_query(
5423 'https://www.youtube.com/playlist',
5424 parse_qs(url) or {'list': playlist_id})
5426 url = smuggle_url(url, {'is_music_url': True})
5427 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5430 class YoutubeYtBeIE(InfoExtractor):
5431 IE_DESC = 'youtu.be'
5432 _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}
5434 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5436 'id': 'yeWKywCrFtk',
5438 'title': 'Small Scale Baler and Braiding Rugs',
5439 'uploader': 'Backus-Page House Museum',
5440 'uploader_id': 'backuspagemuseum',
5441 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5442 'upload_date': '20161008',
5443 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5444 'categories': ['Nonprofits & Activism'],
5448 'playable_in_embed': True,
5449 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5450 'channel': 'Backus-Page House Museum',
5451 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5452 'live_status': 'not_live',
5454 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5455 'availability': 'public',
5460 'skip_download': True,
5463 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5464 'only_matching': True,
5467 def _real_extract(self, url):
5468 mobj = self._match_valid_url(url)
5469 video_id = mobj.group('id')
5470 playlist_id = mobj.group('playlist_id')
5471 return self.url_result(
5472 update_url_query('https://www.youtube.com/watch', {
5474 'list': playlist_id,
5475 'feature': 'youtu.be',
5476 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
5479 class YoutubeLivestreamEmbedIE(InfoExtractor):
5480 IE_DESC = 'YouTube livestream embeds'
5481 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5483 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5484 'only_matching': True,
5487 def _real_extract(self, url):
5488 channel_id = self._match_id(url)
5489 return self.url_result(
5490 f'https://www.youtube.com/channel/{channel_id}/live',
5491 ie=YoutubeTabIE.ie_key(), video_id=channel_id)
5494 class YoutubeYtUserIE(InfoExtractor):
5495 IE_DESC = 'YouTube user videos; "ytuser:" prefix'
5496 IE_NAME = 'youtube:user'
5497 _VALID_URL = r'ytuser:(?P<id>.+)'
5499 'url': 'ytuser:phihag',
5500 'only_matching': True,
5503 def _real_extract(self, url):
5504 user_id = self._match_id(url)
5505 return self.url_result(
5506 'https://www.youtube.com/user/%s/videos' % user_id,
5507 ie=YoutubeTabIE.ie_key(), video_id=user_id)
5510 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
5511 IE_NAME = 'youtube:favorites'
5512 IE_DESC = 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5513 _VALID_URL = r':ytfav(?:ou?rite)?s?'
5514 _LOGIN_REQUIRED = True
5517 'only_matching': True,
5519 'url': ':ytfavorites',
5520 'only_matching': True,
5523 def _real_extract(self, url):
5524 return self.url_result(
5525 'https://www.youtube.com/playlist?list=LL',
5526 ie=YoutubeTabIE.ie_key())
5529 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5530 IE_DESC = 'YouTube search'
5531 IE_NAME = 'youtube:search'
5532 _SEARCH_KEY = 'ytsearch'
5533 _SEARCH_PARAMS = 'EgIQAQ%3D%3D' # Videos only
5535 'url': 'ytsearch5:youtube-dl test video',
5536 'playlist_count': 5,
5538 'id': 'youtube-dl test video',
5539 'title': 'youtube-dl test video',
5544 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor, SearchInfoExtractor):
5545 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
5546 _SEARCH_KEY = 'ytsearchdate'
5547 IE_DESC = 'YouTube search, newest videos first'
5548 _SEARCH_PARAMS = 'CAISAhAB' # Videos only, sorted by date
5550 'url': 'ytsearchdate5:youtube-dl test video',
5551 'playlist_count': 5,
5553 'id': 'youtube-dl test video',
5554 'title': 'youtube-dl test video',
5559 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor):
5560 IE_DESC = 'YouTube search URLs with sorting and filter support'
5561 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
5562 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5564 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5565 'playlist_mincount': 5,
5567 'id': 'youtube-dl test video',
5568 'title': 'youtube-dl test video',
5571 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5572 'playlist_mincount': 5,
5578 'url': 'https://www.youtube.com/results?search_query=%23cats',
5579 'playlist_mincount': 1,
5584 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5589 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5590 'only_matching': True,
5593 def _real_extract(self, url):
5595 query = (qs.get('search_query') or qs.get('q'))[0]
5596 return self.playlist_result(self._search_results(query, qs.get('sp', (None,))[0]), query, query)
5599 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor):
5600 IE_DESC = 'YouTube music search URLs with selectable sections (Eg: #songs)'
5601 IE_NAME = 'youtube:music:search_url'
5602 _VALID_URL = r'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5604 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5605 'playlist_count': 16,
5607 'id': 'royalty free music',
5608 'title': 'royalty free music',
5611 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5612 'playlist_mincount': 30,
5614 'id': 'royalty free music - songs',
5615 'title': 'royalty free music - songs',
5617 'params': {'extract_flat': 'in_playlist'}
5619 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5620 'playlist_mincount': 30,
5622 'id': 'royalty free music - community playlists',
5623 'title': 'royalty free music - community playlists',
5625 'params': {'extract_flat': 'in_playlist'}
5629 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5630 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5631 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5632 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5633 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5634 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5637 def _real_extract(self, url):
5639 query = (qs.get('search_query') or qs.get('q'))[0]
5640 params = qs.get('sp', (None,))[0]
5642 section = next((k for k, v in self._SECTIONS.items() if v == params), params)
5644 section = compat_urllib_parse_unquote_plus((url.split('#') + [''])[1]).lower()
5645 params = self._SECTIONS.get(section)
5648 title = join_nonempty(query, section, delim=' - ')
5649 return self.playlist_result(self._search_results(query, params, default_client='web_music'), title, title)
5652 class YoutubeFeedsInfoExtractor(InfoExtractor):
5654 Base class for feed extractors
5655 Subclasses must define the _FEED_NAME property.
5657 _LOGIN_REQUIRED = True
5659 def _real_initialize(self):
5660 YoutubeBaseInfoExtractor._check_login_required(self)
5664 return 'youtube:%s' % self._FEED_NAME
5666 def _real_extract(self, url):
5667 return self.url_result(
5668 f'https://www.youtube.com/feed/{self._FEED_NAME}', ie=YoutubeTabIE.ie_key())
5671 class YoutubeWatchLaterIE(InfoExtractor):
5672 IE_NAME = 'youtube:watchlater'
5673 IE_DESC = 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5674 _VALID_URL = r':ytwatchlater'
5676 'url': ':ytwatchlater',
5677 'only_matching': True,
5680 def _real_extract(self, url):
5681 return self.url_result(
5682 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
5685 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
5686 IE_DESC = 'YouTube recommended videos; ":ytrec" keyword'
5687 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5688 _FEED_NAME = 'recommended'
5689 _LOGIN_REQUIRED = False
5692 'only_matching': True,
5694 'url': ':ytrecommended',
5695 'only_matching': True,
5697 'url': 'https://youtube.com',
5698 'only_matching': True,
5702 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
5703 IE_DESC = 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5704 _VALID_URL = r':ytsub(?:scription)?s?'
5705 _FEED_NAME = 'subscriptions'
5708 'only_matching': True,
5710 'url': ':ytsubscriptions',
5711 'only_matching': True,
5715 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
5716 IE_DESC = 'Youtube watch history; ":ythis" keyword (requires cookies)'
5717 _VALID_URL = r':ythis(?:tory)?'
5718 _FEED_NAME = 'history'
5720 'url': ':ythistory',
5721 'only_matching': True,
5725 class YoutubeTruncatedURLIE(InfoExtractor):
5726 IE_NAME = 'youtube:truncated_url'
5727 IE_DESC = False # Do not list
5728 _VALID_URL = r'''(?x
)
5730 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
5733 annotation_id
=annotation_
[^
&]+|
5739 attribution_link
\?a
=[^
&]+
5745 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5746 'only_matching': True,
5748 'url': 'https://www.youtube.com/watch?',
5749 'only_matching': True,
5751 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5752 'only_matching': True,
5754 'url': 'https://www.youtube.com/watch?feature=foo',
5755 'only_matching': True,
5757 'url': 'https://www.youtube.com/watch?hl=en-GB',
5758 'only_matching': True,
5760 'url': 'https://www.youtube.com/watch?t=2372',
5761 'only_matching': True,
5764 def _real_extract(self, url):
5765 raise ExtractorError(
5766 'Did you forget to quote the URL? Remember that & is a meta '
5767 'character in most shells, so you want to put the URL in quotes, '
5769 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5770 ' or simply youtube-dl BaW_jenozKc .',
5774 class YoutubeClipIE(InfoExtractor):
5775 IE_NAME = 'youtube:clip'
5776 IE_DESC = False # Do not list
5777 _VALID_URL = r'https?://(?:www\.)?youtube\.com/clip/'
5779 def _real_extract(self, url):
5780 self.report_warning('YouTube clips are not currently supported. The entire video will be downloaded instead')
5781 return self.url_result(url, 'Generic')
5784 class YoutubeTruncatedIDIE(InfoExtractor):
5785 IE_NAME = 'youtube:truncated_id'
5786 IE_DESC = False # Do not list
5787 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
5790 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
5791 'only_matching': True,
5794 def _real_extract(self, url):
5795 video_id = self._match_id(url)
5796 raise ExtractorError(
5797 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),