17 from .common
import InfoExtractor
, SearchInfoExtractor
18 from ..compat
import functools
# isort: split
19 from ..compat
import (
24 compat_urllib_parse_unquote_plus
,
25 compat_urllib_parse_urlencode
,
26 compat_urllib_parse_urlparse
,
29 from ..jsinterp
import JSInterpreter
73 # any clients starting with _ cannot be explicity requested by the user
76 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
77 'INNERTUBE_CONTEXT': {
80 'clientVersion': '2.20211221.00.00',
83 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
86 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
87 'INNERTUBE_CONTEXT': {
89 'clientName': 'WEB_EMBEDDED_PLAYER',
90 'clientVersion': '1.20211215.00.01',
93 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
96 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
97 'INNERTUBE_HOST': 'music.youtube.com',
98 'INNERTUBE_CONTEXT': {
100 'clientName': 'WEB_REMIX',
101 'clientVersion': '1.20211213.00.00',
104 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
107 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
108 'INNERTUBE_CONTEXT': {
110 'clientName': 'WEB_CREATOR',
111 'clientVersion': '1.20211220.02.00',
114 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
117 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
118 'INNERTUBE_CONTEXT': {
120 'clientName': 'ANDROID',
121 'clientVersion': '16.49',
124 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
125 'REQUIRE_JS_PLAYER': False
127 'android_embedded': {
128 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
129 'INNERTUBE_CONTEXT': {
131 'clientName': 'ANDROID_EMBEDDED_PLAYER',
132 'clientVersion': '16.49',
135 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
136 'REQUIRE_JS_PLAYER': False
139 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
140 'INNERTUBE_CONTEXT': {
142 'clientName': 'ANDROID_MUSIC',
143 'clientVersion': '4.57',
146 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
147 'REQUIRE_JS_PLAYER': False
150 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
151 'INNERTUBE_CONTEXT': {
153 'clientName': 'ANDROID_CREATOR',
154 'clientVersion': '21.47',
157 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
158 'REQUIRE_JS_PLAYER': False
160 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
161 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
163 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
164 'INNERTUBE_CONTEXT': {
167 'clientVersion': '16.46',
168 'deviceModel': 'iPhone14,3',
171 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
172 'REQUIRE_JS_PLAYER': False
175 'INNERTUBE_CONTEXT': {
177 'clientName': 'IOS_MESSAGES_EXTENSION',
178 'clientVersion': '16.46',
179 'deviceModel': 'iPhone14,3',
182 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
183 'REQUIRE_JS_PLAYER': False
186 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
187 'INNERTUBE_CONTEXT': {
189 'clientName': 'IOS_MUSIC',
190 'clientVersion': '4.57',
193 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
194 'REQUIRE_JS_PLAYER': False
197 'INNERTUBE_CONTEXT': {
199 'clientName': 'IOS_CREATOR',
200 'clientVersion': '21.47',
203 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
204 'REQUIRE_JS_PLAYER': False
206 # mweb has 'ultralow' formats
207 # See: https://github.com/yt-dlp/yt-dlp/pull/557
209 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
210 'INNERTUBE_CONTEXT': {
212 'clientName': 'MWEB',
213 'clientVersion': '2.20211221.01.00',
216 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
218 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
219 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
221 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
222 'INNERTUBE_CONTEXT': {
224 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
225 'clientVersion': '2.0',
228 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
233 def _split_innertube_client(client_name
):
234 variant
, *base
= client_name
.rsplit('.', 1)
236 return variant
, base
[0], variant
237 base
, *variant
= client_name
.split('_', 1)
238 return client_name
, base
, variant
[0] if variant
else None
241 def build_innertube_clients():
243 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
245 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
246 priority
= qualities(BASE_CLIENTS
[::-1])
248 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
249 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
250 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
251 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
252 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
254 _
, base_client
, variant
= _split_innertube_client(client
)
255 ytcfg
['priority'] = 10 * priority(base_client
)
258 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
259 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
260 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
261 embedscreen
['priority'] -= 3
262 elif variant
== 'embedded':
263 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
264 ytcfg
['priority'] -= 2
266 ytcfg
['priority'] -= 3
269 build_innertube_clients()
272 class YoutubeBaseInfoExtractor(InfoExtractor
):
273 """Provide base functions for Youtube extractors"""
276 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
277 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
278 r
'browse|oembed|get_video_info|iframe_api|s/player|'
279 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
281 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
283 # _NETRC_MACHINE = 'youtube'
285 # If True it will raise an error if no login info is provided
286 _LOGIN_REQUIRED
= False
289 # invidious-redirect websites
290 r
'(?:www\.)?redirect\.invidious\.io',
291 r
'(?:(?:www|dev)\.)?invidio\.us',
292 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
293 r
'(?:www\.)?invidious\.pussthecat\.org',
294 r
'(?:www\.)?invidious\.zee\.li',
295 r
'(?:www\.)?invidious\.ethibox\.fr',
296 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
297 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
298 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
299 # youtube-dl invidious instances list
300 r
'(?:(?:www|no)\.)?invidiou\.sh',
301 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
302 r
'(?:www\.)?invidious\.kabi\.tk',
303 r
'(?:www\.)?invidious\.mastodon\.host',
304 r
'(?:www\.)?invidious\.zapashcanon\.fr',
305 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
306 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
307 r
'(?:www\.)?invidious\.himiko\.cloud',
308 r
'(?:www\.)?invidious\.reallyancient\.tech',
309 r
'(?:www\.)?invidious\.tube',
310 r
'(?:www\.)?invidiou\.site',
311 r
'(?:www\.)?invidious\.site',
312 r
'(?:www\.)?invidious\.xyz',
313 r
'(?:www\.)?invidious\.nixnet\.xyz',
314 r
'(?:www\.)?invidious\.048596\.xyz',
315 r
'(?:www\.)?invidious\.drycat\.fr',
316 r
'(?:www\.)?inv\.skyn3t\.in',
317 r
'(?:www\.)?tube\.poal\.co',
318 r
'(?:www\.)?tube\.connect\.cafe',
319 r
'(?:www\.)?vid\.wxzm\.sx',
320 r
'(?:www\.)?vid\.mint\.lgbt',
321 r
'(?:www\.)?vid\.puffyan\.us',
322 r
'(?:www\.)?yewtu\.be',
323 r
'(?:www\.)?yt\.elukerio\.org',
324 r
'(?:www\.)?yt\.lelux\.fi',
325 r
'(?:www\.)?invidious\.ggc-project\.de',
326 r
'(?:www\.)?yt\.maisputain\.ovh',
327 r
'(?:www\.)?ytprivate\.com',
328 r
'(?:www\.)?invidious\.13ad\.de',
329 r
'(?:www\.)?invidious\.toot\.koeln',
330 r
'(?:www\.)?invidious\.fdn\.fr',
331 r
'(?:www\.)?watch\.nettohikari\.com',
332 r
'(?:www\.)?invidious\.namazso\.eu',
333 r
'(?:www\.)?invidious\.silkky\.cloud',
334 r
'(?:www\.)?invidious\.exonip\.de',
335 r
'(?:www\.)?invidious\.riverside\.rocks',
336 r
'(?:www\.)?invidious\.blamefran\.net',
337 r
'(?:www\.)?invidious\.moomoo\.de',
338 r
'(?:www\.)?ytb\.trom\.tf',
339 r
'(?:www\.)?yt\.cyberhost\.uk',
340 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
341 r
'(?:www\.)?qklhadlycap4cnod\.onion',
342 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
343 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
344 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
345 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
346 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
347 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
348 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
349 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
350 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
351 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
352 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
353 r
'(?:www\.)?piped\.kavin\.rocks',
354 r
'(?:www\.)?piped\.silkky\.cloud',
355 r
'(?:www\.)?piped\.tokhmi\.xyz',
356 r
'(?:www\.)?piped\.moomoo\.me',
358 r
'(?:www\.)?piped\.syncpundit\.com',
359 r
'(?:www\.)?piped\.mha\.fi',
360 r
'(?:www\.)?piped\.mint\.lgbt',
361 r
'(?:www\.)?piped\.privacy\.com\.de',
364 def _initialize_consent(self
):
365 cookies
= self
._get
_cookies
('https://www.youtube.com/')
366 if cookies
.get('__Secure-3PSID'):
369 consent
= cookies
.get('CONSENT')
371 if 'YES' in consent
.value
:
373 consent_id
= self
._search
_regex
(
374 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
376 consent_id
= random
.randint(100, 999)
377 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
379 def _initialize_pref(self
):
380 cookies
= self
._get
_cookies
('https://www.youtube.com/')
381 pref_cookie
= cookies
.get('PREF')
385 pref
= dict(compat_urlparse
.parse_qsl(pref_cookie
.value
))
387 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
388 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
389 self
._set
_cookie
('.youtube.com', name
='PREF', value
=compat_urllib_parse_urlencode(pref
))
391 def _real_initialize(self
):
392 self
._initialize
_pref
()
393 self
._initialize
_consent
()
394 self
._check
_login
_required
()
396 def _check_login_required(self
):
397 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
398 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
400 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
401 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
403 def _get_default_ytcfg(self, client='web'):
404 return copy.deepcopy(INNERTUBE_CLIENTS[client])
406 def _get_innertube_host(self, client='web'):
407 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
409 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
410 # try_get but with fallback to default ytcfg client values when present
411 _func = lambda y: try_get(y, getter, expected_type)
412 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
414 def _extract_client_name(self, ytcfg, default_client='web'):
415 return self._ytcfg_get_safe(
416 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
417 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), compat_str, default_client)
419 def _extract_client_version(self, ytcfg, default_client='web'):
420 return self._ytcfg_get_safe(
421 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
422 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), compat_str, default_client)
424 def _select_api_hostname(self, req_api_hostname, default_client=None):
425 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
426 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
428 def _extract_api_key(self, ytcfg=None, default_client='web'):
429 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
431 def _extract_context(self, ytcfg=None, default_client='web'):
433 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
434 # Enforce language and tz for extraction
435 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
436 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
441 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
442 time_now = round(time.time())
443 if self._SAPISID is None:
444 yt_cookies = self._get_cookies('https://www.youtube.com')
445 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
446 # See: https://github.com/yt-dlp/yt-dlp/issues/393
447 sapisid_cookie = dict_get(
448 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
449 if sapisid_cookie and sapisid_cookie.value:
450 self._SAPISID = sapisid_cookie.value
451 self.write_debug('Extracted SAPISID cookie')
452 # SAPISID cookie is required if not already present
453 if not yt_cookies.get('SAPISID'):
454 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
456 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
458 self._SAPISID = False
459 if not self._SAPISID:
461 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
462 sapisidhash = hashlib.sha1(
463 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
464 return f'SAPISIDHASH {time_now}_{sapisidhash}'
466 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
467 note='Downloading API JSON', errnote='Unable to download API page',
468 context=None, api_key=None, api_hostname=None, default_client='web'):
470 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
472 real_headers = self.generate_api_headers(default_client=default_client)
473 real_headers.update({'content-type': 'application/json'})
475 real_headers.update(headers)
476 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
477 or api_key or self._extract_api_key(default_client=default_client))
478 return self._download_json(
479 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
480 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
481 data=json.dumps(data).encode('utf8'), headers=real_headers,
482 query={'key': api_key, 'prettyPrint': 'false'})
484 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
485 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
488 def _extract_session_index(*data):
490 Index of current account in account list.
491 See: https://github.com/yt-dlp/yt-dlp/pull/519
494 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
495 if session_index is not None:
499 def _extract_identity_token(self, ytcfg=None, webpage=None):
501 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
505 return self._search_regex(
506 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
507 'identity token
', default=None, fatal=False)
510 def _extract_account_syncid(*args):
512 Extract syncId required to download private playlists of secondary channels
513 @params response and/or ytcfg
516 # ytcfg includes channel_syncid if on secondary channel
517 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
521 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
522 lambda x: x['DATASYNC_ID
']), compat_str) or '').split('||
')
523 if len(sync_ids) >= 2 and sync_ids[1]:
524 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
525 # and just "user_syncid||" for primary channel. We only want the channel_syncid
529 def _extract_visitor_data(*args):
531 Extracts visitorData from an API response or ytcfg
532 Appears to be used to track session state
535 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
538 @functools.cached_property
539 def is_authenticated(self):
540 return bool(self._generate_sapisidhash_header())
542 def extract_ytcfg(self, video_id, webpage):
545 return self._parse_json(
547 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
548 default='{}'), video_id, fatal=False) or {}
550 def generate_api_headers(
551 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
552 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
554 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
556 'X-YouTube-Client-Name': compat_str(
557 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
558 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
560 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
561 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
562 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
564 if session_index
is None:
565 session_index
= self
._extract
_session
_index
(ytcfg
)
566 if account_syncid
or session_index
is not None:
567 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
569 auth
= self
._generate
_sapisidhash
_header
(origin
)
571 headers
['Authorization'] = auth
572 headers
['X-Origin'] = origin
573 return {h: v for h, v in headers.items() if v is not None}
575 def _download_ytcfg(self
, client
, video_id
):
577 'web': 'https://www.youtube.com',
578 'web_music': 'https://music.youtube.com',
579 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
583 webpage
= self
._download
_webpage
(
584 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
585 return self
.extract_ytcfg(video_id
, webpage
) or {}
588 def _build_api_continuation_query(continuation
, ctp
=None):
590 'continuation': continuation
592 # TODO: Inconsistency with clickTrackingParams.
593 # Currently we have a fixed ctp contained within context (from ytcfg)
594 # and a ctp in root query for continuation.
596 query
['clickTracking'] = {'clickTrackingParams': ctp}
600 def _extract_next_continuation_data(cls
, renderer
):
601 next_continuation
= try_get(
602 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
603 lambda x
: x
['continuation']['reloadContinuationData']), dict)
604 if not next_continuation
:
606 continuation
= next_continuation
.get('continuation')
609 ctp
= next_continuation
.get('clickTrackingParams')
610 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
613 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
614 if isinstance(continuation_ep
, dict):
615 continuation
= try_get(
616 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
619 ctp
= continuation_ep
.get('clickTrackingParams')
620 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
623 def _extract_continuation(cls
, renderer
):
624 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
625 if next_continuation
:
626 return next_continuation
629 for key
in ('contents', 'items'):
630 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
632 for content
in contents
:
633 if not isinstance(content
, dict):
635 continuation_ep
= try_get(
636 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
637 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
639 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
644 def _extract_alerts(cls
, data
):
645 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
646 if not isinstance(alert_dict
, dict):
648 for alert
in alert_dict
.values():
649 alert_type
= alert
.get('type')
652 message
= cls
._get
_text
(alert
, 'text')
654 yield alert_type
, message
656 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
659 for alert_type
, alert_message
in alerts
:
660 if alert_type
.lower() == 'error' and fatal
:
661 errors
.append([alert_type
, alert_message
])
663 warnings
.append([alert_type
, alert_message
])
665 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
666 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
668 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
670 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
671 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
673 def _extract_badges(self
, renderer
: dict):
675 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
676 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
678 badges
.add(label
.lower())
682 def _get_text(data
, *path_list
, max_runs
=None):
683 for path
in path_list
or [None]:
687 obj
= traverse_obj(data
, path
, default
=[])
688 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
691 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
694 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
695 if not runs
and isinstance(item
, list):
698 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
699 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
703 def _get_count(self
, data
, *path_list
):
704 count_text
= self
._get
_text
(data
, *path_list
) or ''
705 count
= parse_count(count_text
)
708 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
712 def _extract_thumbnails(data
, *path_list
):
714 Extract thumbnails from thumbnails dict
715 @param path_list: path list to level that contains 'thumbnails' key
718 for path
in path_list
or [()]:
719 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
720 thumbnail_url
= url_or_none(thumbnail
.get('url'))
721 if not thumbnail_url
:
723 # Sometimes youtube gives a wrong thumbnail URL. See:
724 # https://github.com/yt-dlp/yt-dlp/issues/233
725 # https://github.com/ytdl-org/youtube-dl/issues/28023
726 if 'maxresdefault' in thumbnail_url
:
727 thumbnail_url
= thumbnail_url
.split('?')[0]
729 'url': thumbnail_url
,
730 'height': int_or_none(thumbnail
.get('height')),
731 'width': int_or_none(thumbnail
.get('width')),
736 def extract_relative_time(relative_time_text
):
738 Extracts a relative time from string and converts to dt object
739 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
741 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
)
743 start
= mobj
.group('start')
745 return datetime_from_str(start
)
747 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
751 def _extract_time_text(self
, renderer
, *path_list
):
752 """@returns (timestamp, time_text)"""
753 text
= self
._get
_text
(renderer
, *path_list
) or ''
754 dt
= self
.extract_relative_time(text
)
756 if isinstance(dt
, datetime
.datetime
):
757 timestamp
= calendar
.timegm(dt
.timetuple())
759 if timestamp
is None:
761 unified_timestamp(text
) or unified_timestamp(
763 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
764 text
.lower(), 'time text', default
=None)))
766 if text
and timestamp
is None:
767 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
768 return timestamp
, text
770 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
771 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
772 default_client
='web'):
776 retries
= self
.get_param('extractor_retries', 3)
777 if check_get_keys
is None:
779 while count
< retries
:
782 self
.report_warning('%s. Retrying ...' % remove_end(last_error
, '.'))
784 response
= self
._call
_api
(
785 ep
=ep
, fatal
=True, headers
=headers
,
786 video_id
=item_id
, query
=query
,
787 context
=self
._extract
_context
(ytcfg
, default_client
),
788 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
789 api_hostname
=api_hostname
, default_client
=default_client
,
790 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
791 except ExtractorError
as e
:
792 if isinstance(e
.cause
, network_exceptions
):
793 if isinstance(e
.cause
, compat_HTTPError
):
794 first_bytes
= e
.cause
.read(512)
795 if not is_html(first_bytes
):
798 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
799 lambda x
: x
['error']['message'], compat_str
)
801 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
802 # Downloading page may result in intermittent 5xx HTTP error
803 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
804 # We also want to catch all other network exceptions since errors in later pages can be troublesome
805 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
806 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
807 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
813 self
.report_warning(error_to_compat_str(e
))
818 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
819 except ExtractorError
as e
:
820 # YouTube servers may return errors we want to retry on in a 200 OK response
821 # See: https://github.com/yt-dlp/yt-dlp/issues/839
822 if 'unknown error' in e
.msg
.lower():
827 self
.report_warning(error_to_compat_str(e
))
829 if not check_get_keys
or dict_get(response
, check_get_keys
):
831 # Youtube sometimes sends incomplete data
832 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
833 last_error
= 'Incomplete data received'
836 raise ExtractorError(last_error
)
838 self
.report_warning(last_error
)
843 def is_music_url(url
):
844 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
846 def _extract_video(self
, renderer
):
847 video_id
= renderer
.get('videoId')
848 title
= self
._get
_text
(renderer
, 'title')
849 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
850 duration
= parse_duration(self
._get
_text
(
851 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
853 duration
= parse_duration(self
._search
_regex
(
854 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
855 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
856 video_id
, default
=None, group
='duration'))
858 view_count
= self
._get
_count
(renderer
, 'viewCountText')
860 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
861 channel_id
= traverse_obj(
862 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
863 expected_type
=str, get_all
=False)
864 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
865 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
866 overlay_style
= traverse_obj(
867 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
868 get_all
=False, expected_type
=str)
869 badges
= self
._extract
_badges
(renderer
)
870 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
871 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
872 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
873 expected_type
=str)) or ''
874 url
= f
'https://www.youtube.com/watch?v={video_id}'
875 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
876 url
= f
'https://www.youtube.com/shorts/{video_id}'
880 'ie_key': YoutubeIE
.ie_key(),
884 'description': description
,
885 'duration': duration
,
886 'view_count': view_count
,
887 'uploader': uploader
,
888 'channel_id': channel_id
,
889 'thumbnails': thumbnails
,
890 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
891 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
893 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
894 else 'was_live' if 'streamed' in time_text
.lower()
895 else 'is_live' if overlay_style
is not None and overlay_style
== 'LIVE' or 'live now' in badges
897 'release_timestamp': scheduled_timestamp
,
898 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
902 class YoutubeIE(YoutubeBaseInfoExtractor
):
904 _VALID_URL
= r
"""(?x)^
906 (?:https?://|//) # http(s):// or protocol-independent URL
907 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
908 (?:www\.)?deturl\.com/www\.youtube\.com|
909 (?:www\.)?pwnyoutube\.com|
910 (?:www\.)?hooktube\.com|
911 (?:www\.)?yourepeat\.com|
914 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
915 (?:.*?\#/)? # handle anchor (#/) redirect urls
916 (?: # the various things that can precede the ID:
917 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
918 |(?: # or the v= param in all its forms
919 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
920 (?:\?|\#!?) # the params delimiter ? or # or #!
921 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
926 youtu\.be| # just youtu.be/xxxx
927 vid\.plus| # or vid.plus/xxxx
928 zwearz\.com/watch| # or zwearz.com/watch/xxxx
931 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
933 )? # all until now is optional -> you can pass the naked ID
934 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
935 (?(1).+)? # if we found the ID, everything can follow
937 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
940 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
941 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$',
942 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
945 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
946 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
947 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
948 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
949 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
950 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
951 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
952 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
953 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
954 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
955 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
956 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
957 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
958 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
959 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
960 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
961 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
962 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
966 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
967 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
968 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
969 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
970 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
971 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
972 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
974 # Apple HTTP Live Streaming
975 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
976 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
977 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
978 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
979 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
980 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
981 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
982 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
985 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
986 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
987 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
988 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
989 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
990 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
991 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
992 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
993 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
994 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
995 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
996 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
999 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
1000 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
1001 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
1002 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
1003 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
1004 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
1005 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
1008 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1009 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1010 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1011 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1012 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1013 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
1014 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
1015 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1016 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1017 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1018 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1019 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1020 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1021 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1022 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1023 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1024 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1025 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1026 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1027 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1028 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1029 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1032 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
1033 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
1035 # Dash webm audio with opus inside
1036 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
1037 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
1038 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
1041 '_rtmp': {'protocol': 'rtmp'}
,
1043 # av01 video only formats sometimes served with "unknown" codecs
1044 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1045 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'}
,
1046 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'}
,
1047 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'}
,
1048 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'}
,
1049 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'}
,
1050 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1051 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'}
,
1053 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1062 'id': 'BaW_jenozKc',
1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
1067 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1068 'channel': 'Philipp Hagemeister',
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1071 'upload_date': '20121002',
1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1073 'categories': ['Science & Technology'],
1074 'tags': ['youtube-dl'],
1078 'availability': 'public',
1079 'playable_in_embed': True,
1080 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1081 'live_status': 'not_live',
1085 'channel_follower_count': int
1089 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1090 'note': 'Embed-only video (#1746)',
1092 'id': 'yZIXLfi8CZQ',
1094 'upload_date': '20120608',
1095 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1096 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1097 'uploader': 'SET India',
1098 'uploader_id': 'setindia',
1099 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1102 'skip': 'Private video',
1105 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1106 'note': 'Use the first video ID in the URL',
1108 'id': 'BaW_jenozKc',
1110 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1111 'uploader': 'Philipp Hagemeister',
1112 'uploader_id': 'phihag',
1113 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1114 'channel': 'Philipp Hagemeister',
1115 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1116 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1117 'upload_date': '20121002',
1118 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1119 'categories': ['Science & Technology'],
1120 'tags': ['youtube-dl'],
1124 'availability': 'public',
1125 'playable_in_embed': True,
1126 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1127 'live_status': 'not_live',
1129 'channel_follower_count': int
1132 'skip_download': True,
1136 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1137 'note': '256k DASH audio (format 141) via DASH manifest',
1139 'id': 'a9LDPn-MO4I',
1141 'upload_date': '20121002',
1142 'uploader_id': '8KVIDEO',
1143 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1145 'uploader': '8KVIDEO',
1146 'title': 'UHDTV TEST 8K VIDEO.mp4'
1149 'youtube_include_dash_manifest': True,
1152 'skip': 'format 141 not served anymore',
1154 # DASH manifest with encrypted signature
1156 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1158 'id': 'IB3lcPjvWLA',
1160 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1161 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1163 'uploader': 'AfrojackVEVO',
1164 'uploader_id': 'AfrojackVEVO',
1165 'upload_date': '20131011',
1168 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1169 'playable_in_embed': True,
1170 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1172 'track': 'The Spark',
1173 'live_status': 'not_live',
1174 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1175 'channel': 'Afrojack',
1176 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1178 'availability': 'public',
1179 'categories': ['Music'],
1181 'alt_title': 'The Spark',
1182 'channel_follower_count': int
1185 'youtube_include_dash_manifest': True,
1186 'format': '141/bestaudio[ext=m4a]',
1189 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1191 'note': 'Embed allowed age-gate video',
1192 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1194 'id': 'HtVdAasjOgU',
1196 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1197 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1199 'uploader': 'The Witcher',
1200 'uploader_id': 'WitcherGame',
1201 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1202 'upload_date': '20140605',
1204 'categories': ['Gaming'],
1205 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1206 'availability': 'needs_auth',
1207 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1209 'channel': 'The Witcher',
1210 'live_status': 'not_live',
1212 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1213 'playable_in_embed': True,
1215 'channel_follower_count': int
1219 'note': 'Age-gate video with embed allowed in public site',
1220 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1222 'id': 'HsUATh_Nc2U',
1224 'title': 'Godzilla 2 (Official Video)',
1225 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1226 'upload_date': '20200408',
1227 'uploader_id': 'FlyingKitty900',
1228 'uploader': 'FlyingKitty',
1230 'availability': 'needs_auth',
1231 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1232 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1233 'channel': 'FlyingKitty',
1234 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1236 'categories': ['Entertainment'],
1237 'live_status': 'not_live',
1238 'tags': ['Flyingkitty', 'godzilla 2'],
1239 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1242 'playable_in_embed': True,
1243 'channel_follower_count': int
1247 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1248 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1250 'id': 'Tq92D6wQ1mg',
1251 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1253 'upload_date': '20191228',
1254 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1255 'uploader': 'Projekt Melody',
1256 'description': 'md5:17eccca93a786d51bc67646756894066',
1259 'availability': 'needs_auth',
1260 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1261 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1263 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1264 'channel': 'Projekt Melody',
1265 'live_status': 'not_live',
1266 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1267 'playable_in_embed': True,
1268 'categories': ['Entertainment'],
1270 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1271 'channel_follower_count': int
1275 'note': 'Non-Agegated non-embeddable video',
1276 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1278 'id': 'MeJVWBSsPAY',
1280 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1281 'uploader': 'Herr Lurik',
1282 'uploader_id': 'st3in234',
1283 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1284 'upload_date': '20130730',
1285 'track': 'Such mich find mich',
1287 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1289 'playable_in_embed': False,
1290 'creator': 'OOMPH!',
1291 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1293 'alt_title': 'Such mich find mich',
1295 'channel': 'Herr Lurik',
1296 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1297 'categories': ['Music'],
1298 'availability': 'public',
1299 'uploader_url': 'http://www.youtube.com/user/st3in234',
1300 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1301 'live_status': 'not_live',
1303 'channel_follower_count': int
1307 'note': 'Non-bypassable age-gated video',
1308 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1309 'only_matching': True,
1311 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1312 # YouTube Red ad is not captured for creator
1314 'url': '__2ABJjxzNo',
1316 'id': '__2ABJjxzNo',
1319 'upload_date': '20100430',
1320 'uploader_id': 'deadmau5',
1321 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1322 'creator': 'deadmau5',
1323 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1324 'uploader': 'deadmau5',
1325 'title': 'Deadmau5 - Some Chords (HD)',
1326 'alt_title': 'Some Chords',
1327 'availability': 'public',
1329 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1331 'live_status': 'not_live',
1332 'channel': 'deadmau5',
1333 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1335 'track': 'Some Chords',
1336 'artist': 'deadmau5',
1337 'playable_in_embed': True,
1339 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1340 'categories': ['Music'],
1341 'album': 'Some Chords',
1342 'channel_follower_count': int
1344 'expected_warnings': [
1345 'DASH manifest missing',
1348 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1350 'url': 'lqQg6PlCWgI',
1352 'id': 'lqQg6PlCWgI',
1355 'upload_date': '20150827',
1356 'uploader_id': 'olympic',
1357 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1358 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1359 'uploader': 'Olympics',
1360 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1362 'release_timestamp': 1343767800,
1363 'playable_in_embed': True,
1364 'categories': ['Sports'],
1365 'release_date': '20120731',
1366 'channel': 'Olympics',
1367 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1368 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1369 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1371 'availability': 'public',
1372 'live_status': 'was_live',
1374 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1375 'channel_follower_count': int
1378 'skip_download': 'requires avconv',
1383 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1385 'id': '_b-2C3KPAM0',
1387 'stretched_ratio': 16 / 9.,
1389 'upload_date': '20110310',
1390 'uploader_id': 'AllenMeow',
1391 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1392 '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',
1394 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1395 'playable_in_embed': True,
1399 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1400 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1401 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1403 'categories': ['People & Blogs'],
1405 'live_status': 'not_live',
1406 'availability': 'unlisted',
1407 'channel_follower_count': int
1410 # url_encoded_fmt_stream_map is empty string
1412 'url': 'qEJwOuvDf7I',
1414 'id': 'qEJwOuvDf7I',
1416 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1418 'upload_date': '20150404',
1419 'uploader_id': 'spbelect',
1420 'uploader': 'Наблюдатели Петербурга',
1423 'skip_download': 'requires avconv',
1425 'skip': 'This live event has ended.',
1427 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1429 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1431 'id': 'FIl7x6_3R5Y',
1433 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1434 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1436 'upload_date': '20150625',
1437 'uploader_id': 'dorappi2000',
1438 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1439 'uploader': 'dorappi2000',
1440 'formats': 'mincount:31',
1442 'skip': 'not actual anymore',
1444 # DASH manifest with segment_list
1446 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1447 'md5': '8ce563a1d667b599d21064e982ab9e31',
1449 'id': 'CsmdDsKjzN8',
1451 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1452 'uploader': 'Airtek',
1453 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1454 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1455 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1458 'youtube_include_dash_manifest': True,
1459 'format': '135', # bestvideo
1461 'skip': 'This live event has ended.',
1464 # Multifeed videos (multiple cameras), URL is for Main Camera
1465 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1467 'id': 'jvGDaLqkpTg',
1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
1473 'id': 'jvGDaLqkpTg',
1475 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1476 'description': 'md5:e03b909557865076822aa169218d6a5d',
1478 'upload_date': '20161111',
1479 'uploader': 'Team PGP',
1480 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1481 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1485 'id': '3AKt1R1aDnw',
1487 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1488 'description': 'md5:e03b909557865076822aa169218d6a5d',
1490 'upload_date': '20161111',
1491 'uploader': 'Team PGP',
1492 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1493 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1497 'id': 'RtAMM00gpVc',
1499 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1500 'description': 'md5:e03b909557865076822aa169218d6a5d',
1502 'upload_date': '20161111',
1503 'uploader': 'Team PGP',
1504 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1505 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1509 'id': '6N2fdlP3C5U',
1511 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1512 'description': 'md5:e03b909557865076822aa169218d6a5d',
1514 'upload_date': '20161111',
1515 'uploader': 'Team PGP',
1516 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1517 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1521 'skip_download': True,
1523 'skip': 'Not multifeed anymore',
1526 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1527 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1529 'id': 'gVfLd0zydlo',
1530 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1532 'playlist_count': 2,
1533 'skip': 'Not multifeed anymore',
1536 'url': 'https://vid.plus/FlRa-iH7PGw',
1537 'only_matching': True,
1540 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1541 'only_matching': True,
1544 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1545 # Also tests cut-off URL expansion in video description (see
1546 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1547 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1548 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1550 'id': 'lsguqyKfVQg',
1552 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1553 'alt_title': 'Dark Walk',
1554 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1556 'upload_date': '20151119',
1557 'uploader_id': 'IronSoulElf',
1558 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1559 'uploader': 'IronSoulElf',
1560 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1561 'track': 'Dark Walk',
1562 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1563 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1564 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1565 'categories': ['Film & Animation'],
1567 'live_status': 'not_live',
1568 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1569 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1571 'availability': 'public',
1572 'channel': 'IronSoulElf',
1573 'playable_in_embed': True,
1576 'channel_follower_count': int
1579 'skip_download': True,
1583 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1584 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1585 'only_matching': True,
1588 # Video with yt:stretch=17:0
1589 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1591 'id': 'Q39EVAstoRM',
1593 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1594 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1595 'upload_date': '20151107',
1596 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1597 'uploader': 'CH GAMER DROID',
1600 'skip_download': True,
1602 'skip': 'This video does not exist.',
1605 # Video with incomplete 'yt:stretch=16:'
1606 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1607 'only_matching': True,
1610 # Video licensed under Creative Commons
1611 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1613 'id': 'M4gD1WSo5mA',
1615 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1616 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1618 'upload_date': '20150128',
1619 'uploader_id': 'BerkmanCenter',
1620 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1621 'uploader': 'The Berkman Klein Center for Internet & Society',
1622 'license': 'Creative Commons Attribution license (reuse allowed)',
1623 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1624 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1627 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1628 'channel': 'The Berkman Klein Center for Internet & Society',
1629 'availability': 'public',
1631 'categories': ['Education'],
1632 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1633 'live_status': 'not_live',
1634 'playable_in_embed': True,
1635 'channel_follower_count': int
1638 'skip_download': True,
1642 # Channel-like uploader_url
1643 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1645 'id': 'eQcmzGIKrzg',
1647 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1648 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1650 'upload_date': '20151120',
1651 'uploader': 'Bernie Sanders',
1652 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1653 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1654 'license': 'Creative Commons Attribution license (reuse allowed)',
1655 'playable_in_embed': True,
1658 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1660 'availability': 'public',
1661 'categories': ['News & Politics'],
1662 'channel': 'Bernie Sanders',
1663 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1665 'live_status': 'not_live',
1666 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1667 'channel_follower_count': int
1670 'skip_download': True,
1674 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1675 'only_matching': True,
1678 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1679 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1680 'only_matching': True,
1683 # Rental video preview
1684 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1686 'id': 'uGpuVWrhIzE',
1688 'title': 'Piku - Trailer',
1689 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1690 'upload_date': '20150811',
1691 'uploader': 'FlixMatrix',
1692 'uploader_id': 'FlixMatrixKaravan',
1693 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1694 'license': 'Standard YouTube License',
1697 'skip_download': True,
1699 'skip': 'This video is not available.',
1702 # YouTube Red video with episode data
1703 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1705 'id': 'iqKdEhx-dD4',
1707 'title': 'Isolation - Mind Field (Ep 1)',
1708 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1710 'upload_date': '20170118',
1711 'uploader': 'Vsauce',
1712 'uploader_id': 'Vsauce',
1713 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1714 'series': 'Mind Field',
1716 'episode_number': 1,
1717 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1720 'availability': 'public',
1722 'channel': 'Vsauce',
1723 'episode': 'Episode 1',
1724 'categories': ['Entertainment'],
1725 'season': 'Season 1',
1726 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1727 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1729 'playable_in_embed': True,
1730 'live_status': 'not_live',
1731 'channel_follower_count': int
1734 'skip_download': True,
1736 'expected_warnings': [
1737 'Skipping DASH manifest',
1741 # The following content has been identified by the YouTube community
1742 # as inappropriate or offensive to some audiences.
1743 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1745 'id': '6SJNVb0GnPI',
1747 'title': 'Race Differences in Intelligence',
1748 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1750 'upload_date': '20140124',
1751 'uploader': 'New Century Foundation',
1752 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1753 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1756 'skip_download': True,
1758 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1762 'url': '1t24XAntNCY',
1763 'only_matching': True,
1766 # geo restricted to JP
1767 'url': 'sJL6WA-aGkQ',
1768 'only_matching': True,
1771 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1772 'only_matching': True,
1775 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1776 'only_matching': True,
1779 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1780 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1781 'only_matching': True,
1785 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1786 'only_matching': True,
1789 # Video with unsupported adaptive stream type formats
1790 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1792 'id': 'Z4Vy8R84T1U',
1794 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1795 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1797 'upload_date': '20130923',
1798 'uploader': 'Amelia Putri Harwita',
1799 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1800 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1801 'formats': 'maxcount:10',
1804 'skip_download': True,
1805 'youtube_include_dash_manifest': False,
1807 'skip': 'not actual anymore',
1810 # Youtube Music Auto-generated description
1811 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1813 'id': 'MgNrAu2pzNs',
1815 'title': 'Voyeur Girl',
1816 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1817 'upload_date': '20190312',
1818 'uploader': 'Stephen - Topic',
1819 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1820 'artist': 'Stephen',
1821 'track': 'Voyeur Girl',
1822 'album': 'it\'s too much love to know my dear',
1823 'release_date': '20190313',
1824 'release_year': 2019,
1825 'alt_title': 'Voyeur Girl',
1827 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1828 'playable_in_embed': True,
1830 'categories': ['Music'],
1831 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1832 'channel': 'Stephen',
1833 'availability': 'public',
1834 'creator': 'Stephen',
1836 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1838 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1840 'live_status': 'not_live',
1841 'channel_follower_count': int
1844 'skip_download': True,
1848 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1849 'only_matching': True,
1852 # invalid -> valid video id redirection
1853 'url': 'DJztXj2GPfl',
1855 'id': 'DJztXj2GPfk',
1857 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1858 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1859 'upload_date': '20090125',
1860 'uploader': 'Prochorowka',
1861 'uploader_id': 'Prochorowka',
1862 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1863 'artist': 'Panjabi MC',
1864 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1865 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1868 'skip_download': True,
1870 'skip': 'Video unavailable',
1873 # empty description results in an empty string
1874 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1876 'id': 'x41yOUIvK2k',
1878 'title': 'IMG 3456',
1880 'upload_date': '20170613',
1881 'uploader_id': 'ElevageOrVert',
1882 'uploader': 'ElevageOrVert',
1884 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1885 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1887 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1889 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1890 'availability': 'public',
1892 'categories': ['Pets & Animals'],
1894 'playable_in_embed': True,
1895 'live_status': 'not_live',
1896 'channel': 'ElevageOrVert',
1897 'channel_follower_count': int
1900 'skip_download': True,
1904 # with '};' inside yt initial data (see [1])
1905 # see [2] for an example with '};' inside ytInitialPlayerResponse
1906 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1907 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1908 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1910 'id': 'CHqg6qOn4no',
1912 'title': 'Part 77 Sort a list of simple types in c#',
1913 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1914 'upload_date': '20130831',
1915 'uploader_id': 'kudvenkat',
1916 'uploader': 'kudvenkat',
1917 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1919 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1920 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1921 'live_status': 'not_live',
1922 'categories': ['Education'],
1923 'availability': 'public',
1924 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1926 'playable_in_embed': True,
1930 'channel': 'kudvenkat',
1931 'channel_follower_count': int
1934 'skip_download': True,
1938 # another example of '};' in ytInitialData
1939 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1940 'only_matching': True,
1943 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1944 'only_matching': True,
1947 # https://github.com/ytdl-org/youtube-dl/pull/28094
1948 'url': 'OtqTfy26tG0',
1950 'id': 'OtqTfy26tG0',
1952 'title': 'Burn Out',
1953 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1954 'upload_date': '20141120',
1955 'uploader': 'The Cinematic Orchestra - Topic',
1956 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1957 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1958 'artist': 'The Cinematic Orchestra',
1959 'track': 'Burn Out',
1960 'album': 'Every Day',
1962 'live_status': 'not_live',
1963 'alt_title': 'Burn Out',
1967 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1968 'creator': 'The Cinematic Orchestra',
1969 'channel': 'The Cinematic Orchestra',
1970 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1971 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1972 'availability': 'public',
1973 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1974 'categories': ['Music'],
1975 'playable_in_embed': True,
1976 'channel_follower_count': int
1979 'skip_download': True,
1983 # controversial video, only works with bpctr when authenticated with cookies
1984 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1985 'only_matching': True,
1988 # controversial video, requires bpctr/contentCheckOk
1989 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1991 'id': 'SZJvDhaSDnc',
1993 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1994 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1995 'uploader': 'CBS Mornings',
1996 'uploader_id': 'CBSThisMorning',
1997 'upload_date': '20140716',
1998 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2000 'categories': ['News & Politics'],
2001 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2003 'channel': 'CBS Mornings',
2004 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2005 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2007 'availability': 'needs_auth',
2008 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2010 'live_status': 'not_live',
2011 'playable_in_embed': True,
2012 'channel_follower_count': int
2016 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2017 'url': 'cBvYw8_A0vQ',
2019 'id': 'cBvYw8_A0vQ',
2021 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2022 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2023 'upload_date': '20201120',
2024 'uploader': 'Walk around Japan',
2025 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2026 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2028 'categories': ['Travel & Events'],
2029 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2031 'channel': 'Walk around Japan',
2032 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2033 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2035 'availability': 'public',
2036 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2037 'live_status': 'not_live',
2038 'playable_in_embed': True,
2039 'channel_follower_count': int
2042 'skip_download': True,
2045 # Has multiple audio streams
2046 'url': 'WaOKSUlf4TM',
2047 'only_matching': True
2049 # Requires Premium: has format 141 when requested using YTM url
2050 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2051 'only_matching': True
2053 # multiple subtitles with same lang_code
2054 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2055 'only_matching': True,
2057 # Force use android client fallback
2058 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2060 'id': 'YOelRv7fMxY',
2061 'title': 'DIGGING A SECRET TUNNEL Part 1',
2063 'upload_date': '20210624',
2064 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2065 'uploader': 'colinfurze',
2066 'uploader_id': 'colinfurze',
2067 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2068 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2070 'categories': ['Entertainment'],
2071 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2073 'channel': 'colinfurze',
2074 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2075 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2077 'availability': 'public',
2079 'live_status': 'not_live',
2080 'playable_in_embed': True,
2081 'channel_follower_count': int
2084 'format': '17', # 3gp format available on android
2085 'extractor_args': {'youtube': {'player_client': ['android']}
},
2089 # Skip download of additional client configs (remix client config in this case)
2090 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2091 'only_matching': True,
2093 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
2097 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2098 'only_matching': True,
2100 'note': 'Storyboards',
2101 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2103 'id': '5KLPxDtMqe8',
2106 'title': 'Your Brain is Plastic',
2107 'uploader_id': 'scishow',
2108 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2109 'upload_date': '20140324',
2110 'uploader': 'SciShow',
2112 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2113 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2115 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2116 'playable_in_embed': True,
2118 'uploader_url': 'http://www.youtube.com/user/scishow',
2119 'availability': 'public',
2120 'channel': 'SciShow',
2121 'live_status': 'not_live',
2123 'categories': ['Education'],
2125 'channel_follower_count': int
2126 }, 'params': {'format': 'mhtml', 'skip_download': True}
2128 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2129 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2131 'id': '2NUZ8W2llS4',
2133 'title': 'The NP that test your phone performance 🙂',
2134 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2135 'uploader': 'Leon Nguyen',
2136 'uploader_id': 'VNSXIII',
2137 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2138 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2139 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2143 'categories': ['Gaming'],
2145 'playable_in_embed': True,
2146 'live_status': 'not_live',
2147 'upload_date': '20220103',
2149 'availability': 'public',
2150 'channel': 'Leon Nguyen',
2151 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2152 'channel_follower_count': int
2155 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2156 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2158 'id': 'mzZzzBU6lrM',
2160 'title': 'I Met GeorgeNotFound In Real Life...',
2161 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2162 'uploader': 'Quackity',
2163 'uploader_id': 'QuackityHQ',
2164 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2165 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2166 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2170 'categories': ['Entertainment'],
2172 'playable_in_embed': True,
2173 'live_status': 'not_live',
2174 'release_timestamp': 1641172509,
2175 'release_date': '20220103',
2176 'upload_date': '20220103',
2178 'availability': 'public',
2179 'channel': 'Quackity',
2180 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2181 'channel_follower_count': int
2184 { # continuous livestream. Microformat upload date should be preferred.
2185 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2186 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2188 'id': 'kgx4WGK0oNU',
2189 '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}',
2191 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2192 'availability': 'public',
2194 'release_timestamp': 1637975704,
2195 'upload_date': '20210619',
2196 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2197 'live_status': 'is_live',
2198 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2199 'uploader': '阿鲍Abao',
2200 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2201 'channel': 'Abao in Tokyo',
2202 'channel_follower_count': int,
2203 'release_date': '20211127',
2205 'categories': ['People & Blogs'],
2207 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2209 'playable_in_embed': True,
2210 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2212 'params': {'skip_download': True}
2214 # Story. Requires specific player params to work.
2215 # Note: stories get removed after some period of time
2216 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2218 'id': 'vv8qTUWmulI',
2220 'availability': 'unlisted',
2222 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2223 'upload_date': '20220526',
2224 'categories': ['Education'],
2226 'channel': 'IT\'S HISTORY',
2228 'uploader_id': 'BlastfromthePast',
2230 'uploader': 'IT\'S HISTORY',
2231 'playable_in_embed': True,
2233 'live_status': 'not_live',
2235 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2236 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2237 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2240 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2242 'id': 'tjjjtzRLHvA',
2244 'title': 'ハッシュタグ無し };if window.ytcsi',
2245 'upload_date': '20220323',
2247 'availability': 'unlisted',
2248 'channel': 'nao20010128nao',
2249 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2251 'uploader': 'nao20010128nao',
2252 'uploader_id': 'nao20010128nao',
2253 'categories': ['Music'],
2256 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2257 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2258 'live_status': 'not_live',
2259 'playable_in_embed': True,
2260 'channel_follower_count': int,
2263 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2269 def suitable(cls
, url
):
2270 from ..utils
import parse_qs
2273 if qs
.get('list', [None])[0]:
2275 return super().suitable(url
)
2277 def __init__(self
, *args
, **kwargs
):
2278 super().__init
__(*args
, **kwargs
)
2279 self
._code
_cache
= {}
2280 self
._player
_cache
= {}
2282 def _prepare_live_from_start_formats(self
, formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
):
2283 lock
= threading
.Lock()
2286 start_time
= time
.time()
2287 formats
= [f
for f
in formats
if f
.get('is_from_start')]
2289 def refetch_manifest(format_id
, delay
):
2290 nonlocal formats
, start_time
, is_live
2291 if time
.time() <= start_time
+ delay
:
2294 _
, _
, prs
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
2295 video_details
= traverse_obj(
2296 prs
, (..., 'videoDetails'), expected_type
=dict, default
=[])
2297 microformats
= traverse_obj(
2298 prs
, (..., 'microformat', 'playerMicroformatRenderer'),
2299 expected_type
=dict, default
=[])
2300 _
, is_live
, _
, formats
= self
._list
_formats
(video_id
, microformats
, video_details
, prs
, player_url
)
2301 start_time
= time
.time()
2303 def mpd_feed(format_id
, delay
):
2305 @returns (manifest_url, manifest_stream_number, is_live) or None
2308 refetch_manifest(format_id
, delay
)
2310 f
= next((f
for f
in formats
if f
['format_id'] == format_id
), None)
2313 self
.to_screen(f
'{video_id}: Video is no longer live')
2315 self
.report_warning(
2316 f
'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2318 return f
['manifest_url'], f
['manifest_stream_number'], is_live
2322 f
['protocol'] = 'http_dash_segments_generator'
2323 f
['fragments'] = functools
.partial(
2324 self
._live
_dash
_fragments
, f
['format_id'], live_start_time
, mpd_feed
)
2326 def _live_dash_fragments(self
, format_id
, live_start_time
, mpd_feed
, ctx
):
2327 FETCH_SPAN
, MAX_DURATION
= 5, 432000
2329 mpd_url
, stream_number
, is_live
= None, None, True
2332 download_start_time
= ctx
.get('start') or time
.time()
2334 lack_early_segments
= download_start_time
- (live_start_time
or download_start_time
) > MAX_DURATION
2335 if lack_early_segments
:
2336 self
.report_warning(bug_reports_message(
2337 'Starting download from the last 120 hours of the live stream since '
2338 'YouTube does not have data before that. If you think this is wrong,'), only_once
=True)
2339 lack_early_segments
= True
2341 known_idx
, no_fragment_score
, last_segment_url
= begin_index
, 0, None
2342 fragments
, fragment_base_url
= None, None
2344 def _extract_sequence_from_mpd(refresh_sequence
, immediate
):
2345 nonlocal mpd_url
, stream_number
, is_live
, no_fragment_score
, fragments
, fragment_base_url
2346 # Obtain from MPD's maximum seq value
2347 old_mpd_url
= mpd_url
2348 last_error
= ctx
.pop('last_error', None)
2349 expire_fast
= immediate
or last_error
and isinstance(last_error
, compat_HTTPError
) and last_error
.code
== 403
2350 mpd_url
, stream_number
, is_live
= (mpd_feed(format_id
, 5 if expire_fast
else 18000)
2351 or (mpd_url
, stream_number
, False))
2352 if not refresh_sequence
:
2353 if expire_fast
and not is_live
:
2354 return False, last_seq
2355 elif old_mpd_url
== mpd_url
:
2356 return True, last_seq
2358 fmts
, _
= self
._extract
_mpd
_formats
_and
_subtitles
(
2359 mpd_url
, None, note
=False, errnote
=False, fatal
=False)
2360 except ExtractorError
:
2363 no_fragment_score
+= 2
2364 return False, last_seq
2365 fmt_info
= next(x
for x
in fmts
if x
['manifest_stream_number'] == stream_number
)
2366 fragments
= fmt_info
['fragments']
2367 fragment_base_url
= fmt_info
['fragment_base_url']
2368 assert fragment_base_url
2370 _last_seq
= int(re
.search(r
'(?:/|^)sq/(\d+)', fragments
[-1]['path']).group(1))
2371 return True, _last_seq
2374 fetch_time
= time
.time()
2375 if no_fragment_score
> 30:
2377 if last_segment_url
:
2378 # Obtain from "X-Head-Seqnum" header value from each segment
2380 urlh
= self
._request
_webpage
(
2381 last_segment_url
, None, note
=False, errnote
=False, fatal
=False)
2382 except ExtractorError
:
2384 last_seq
= try_get(urlh
, lambda x
: int_or_none(x
.headers
['X-Head-Seqnum']))
2385 if last_seq
is None:
2386 no_fragment_score
+= 2
2387 last_segment_url
= None
2390 should_continue
, last_seq
= _extract_sequence_from_mpd(True, no_fragment_score
> 15)
2391 no_fragment_score
+= 2
2392 if not should_continue
:
2395 if known_idx
> last_seq
:
2396 last_segment_url
= None
2401 if begin_index
< 0 and known_idx
< 0:
2402 # skip from the start when it's negative value
2403 known_idx
= last_seq
+ begin_index
2404 if lack_early_segments
:
2405 known_idx
= max(known_idx
, last_seq
- int(MAX_DURATION
// fragments
[-1]['duration']))
2407 for idx
in range(known_idx
, last_seq
):
2408 # do not update sequence here or you'll get skipped some part of it
2409 should_continue
, _
= _extract_sequence_from_mpd(False, False)
2410 if not should_continue
:
2412 raise ExtractorError('breaking out of outer loop')
2413 last_segment_url
= urljoin(fragment_base_url
, 'sq/%d' % idx
)
2415 'url': last_segment_url
,
2416 'fragment_count': last_seq
,
2418 if known_idx
== last_seq
:
2419 no_fragment_score
+= 5
2421 no_fragment_score
= 0
2422 known_idx
= last_seq
2423 except ExtractorError
:
2426 time
.sleep(max(0, FETCH_SPAN
+ fetch_time
- time
.time()))
2428 def _extract_player_url(self
, *ytcfgs
, webpage
=None):
2429 player_url
= traverse_obj(
2430 ytcfgs
, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2431 get_all
=False, expected_type
=compat_str
)
2434 return urljoin('https://www.youtube.com', player_url
)
2436 def _download_player_url(self
, video_id
, fatal
=False):
2437 res
= self
._download
_webpage
(
2438 'https://www.youtube.com/iframe_api',
2439 note
='Downloading iframe API JS', video_id
=video_id
, fatal
=fatal
)
2441 player_version
= self
._search
_regex
(
2442 r
'player\\?/([0-9a-fA-F]{8})\\?/', res
, 'player version', fatal
=fatal
)
2444 return f
'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2446 def _signature_cache_id(self
, example_sig
):
2447 """ Return a string representation of a signature """
2448 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
2451 def _extract_player_info(cls
, player_url
):
2452 for player_re
in cls
._PLAYER
_INFO
_RE
:
2453 id_m
= re
.search(player_re
, player_url
)
2457 raise ExtractorError('Cannot identify player %r' % player_url
)
2458 return id_m
.group('id')
2460 def _load_player(self
, video_id
, player_url
, fatal
=True):
2461 player_id
= self
._extract
_player
_info
(player_url
)
2462 if player_id
not in self
._code
_cache
:
2463 code
= self
._download
_webpage
(
2464 player_url
, video_id
, fatal
=fatal
,
2465 note
='Downloading player ' + player_id
,
2466 errnote
='Download of %s failed' % player_url
)
2468 self
._code
_cache
[player_id
] = code
2469 return self
._code
_cache
.get(player_id
)
2471 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
2472 player_id
= self
._extract
_player
_info
(player_url
)
2474 # Read from filesystem cache
2475 func_id
= f
'js_{player_id}_{self._signature_cache_id(example_sig)}'
2476 assert os
.path
.basename(func_id
) == func_id
2478 cache_spec
= self
.cache
.load('youtube-sigfuncs', func_id
)
2479 if cache_spec
is not None:
2480 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
2482 code
= self
._load
_player
(video_id
, player_url
)
2484 res
= self
._parse
_sig
_js
(code
)
2486 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2487 cache_res
= res(test_string
)
2488 cache_spec
= [ord(c
) for c
in cache_res
]
2490 self
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
2493 def _print_sig_code(self
, func
, example_sig
):
2494 if not self
.get_param('youtube_print_sig_code'):
2497 def gen_sig_code(idxs
):
2498 def _genslice(start
, end
, step
):
2499 starts
= '' if start
== 0 else str(start
)
2500 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
2501 steps
= '' if step
== 1 else (':%d' % step
)
2502 return f
's[{starts}{ends}{steps}]'
2505 # Quelch pyflakes warnings - start will be set when step is set
2506 start
= '(Never used)'
2507 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
2508 if step
is not None:
2509 if i
- prev
== step
:
2511 yield _genslice(start
, prev
, step
)
2514 if i
- prev
in [-1, 1]:
2519 yield 's[%d]' % prev
2523 yield _genslice(start
, i
, step
)
2525 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
2526 cache_res
= func(test_string
)
2527 cache_spec
= [ord(c
) for c
in cache_res
]
2528 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
2529 signature_id_tuple
= '(%s)' % (
2530 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
2531 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2532 ' return %s\n') % (signature_id_tuple
, expr_code
)
2533 self
.to_screen('Extracted signature function:\n' + code
)
2535 def _parse_sig_js(self
, jscode
):
2536 funcname
= self
._search
_regex
(
2537 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2538 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2539 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2540 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2541 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}\(a,\d+\)',
2542 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\(\s*""\s*\)',
2543 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2545 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2546 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2547 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2548 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2549 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2550 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2551 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
2552 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
2553 jscode, 'Initial JS player signature function name
', group='sig
')
2555 jsi = JSInterpreter(jscode)
2556 initial_function = jsi.extract_function(funcname)
2557 return lambda s: initial_function([s])
2559 def _decrypt_signature(self, s, video_id, player_url):
2560 """Turn the encrypted s field into a working signature"""
2562 player_id = (player_url, self._signature_cache_id(s))
2563 if player_id not in self._player_cache:
2564 func = self._extract_signature_function(video_id, player_url, s)
2565 self._player_cache[player_id] = func
2566 func = self._player_cache[player_id]
2567 self._print_sig_code(func, s)
2569 except Exception as e:
2570 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2572 def _decrypt_nsig(self, s, video_id, player_url):
2573 """Turn the encrypted n field into a working signature"""
2574 if player_url is None:
2575 raise ExtractorError('Cannot decrypt nsig without player_url
')
2576 player_url = urljoin('https
://www
.youtube
.com
', player_url)
2578 sig_id = ('nsig_value
', s)
2579 if sig_id in self._player_cache:
2580 return self._player_cache[sig_id]
2583 player_id = ('nsig
', player_url)
2584 if player_id not in self._player_cache:
2585 self._player_cache[player_id] = self._extract_n_function(video_id, player_url)
2586 func = self._player_cache[player_id]
2587 self._player_cache[sig_id] = func(s)
2588 self.write_debug(f'Decrypted nsig {s}
=> {self._player_cache[sig_id]}
')
2589 return self._player_cache[sig_id]
2590 except Exception as e:
2591 raise ExtractorError(traceback.format_exc(), cause=e, video_id=video_id)
2593 def _extract_n_function_name(self, jscode):
2594 nfunc, idx = self._search_regex(
2595 r'\
.get\
("n"\
)\
)&&\
(b
=(?P
<nfunc
>[a
-zA
-Z0
-9$
]+)(?
:\
[(?P
<idx
>\d
+)\
])?\
([a
-zA
-Z0
-9]\
)',
2596 jscode, 'Initial JS player n function name
', group=('nfunc
', 'idx
'))
2599 return json.loads(js_to_json(self._search_regex(
2600 rf'var {re.escape(nfunc)}\s
*=\s
*(\
[.+?\
]);', jscode,
2601 f'Initial JS player n function
list ({nfunc}
.{idx}
)')))[int(idx)]
2603 def _extract_n_function(self, video_id, player_url):
2604 player_id = self._extract_player_info(player_url)
2605 func_code = self.cache.load('youtube
-nsig
', player_id)
2608 jsi = JSInterpreter(func_code)
2610 jscode = self._load_player(video_id, player_url)
2611 funcname = self._extract_n_function_name(jscode)
2612 jsi = JSInterpreter(jscode)
2613 func_code = jsi.extract_function_code(funcname)
2614 self.cache.store('youtube
-nsig
', player_id, func_code)
2616 if self.get_param('youtube_print_sig_code
'):
2617 self.to_screen(f'Extracted nsig function
from {player_id}
:\n{func_code[1]}
\n')
2619 return lambda s: jsi.extract_function_from_code(*func_code)([s])
2621 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2623 Extract signatureTimestamp (sts)
2624 Required to tell API what sig/player version is in use.
2627 if isinstance(ytcfg, dict):
2628 sts = int_or_none(ytcfg.get('STS
'))
2631 # Attempt to extract from player
2632 if player_url is None:
2633 error_msg = 'Cannot extract signature timestamp without player_url
.'
2635 raise ExtractorError(error_msg)
2636 self.report_warning(error_msg)
2638 code = self._load_player(video_id, player_url, fatal=fatal)
2640 sts = int_or_none(self._search_regex(
2641 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
2642 'JS player signature timestamp
', group='sts
', fatal=fatal))
2645 def _mark_watched(self, video_id, player_responses):
2646 for is_full, key in enumerate(('videostatsPlaybackUrl
', 'videostatsWatchtimeUrl
')):
2647 label = 'fully
' if is_full else ''
2648 url = get_first(player_responses, ('playbackTracking
', key, 'baseUrl
'),
2649 expected_type=url_or_none)
2651 self.report_warning(f'Unable to mark {label}watched
')
2653 parsed_url = compat_urlparse.urlparse(url)
2654 qs = compat_urlparse.parse_qs(parsed_url.query)
2656 # cpn generation algorithm is reverse engineered from base.js.
2657 # In fact it works even with dummy cpn.
2658 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
2659 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2661 # # more consistent results setting it to right before the end
2662 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2667 'cmt
': video_length,
2668 'el
': 'detailpage
', # otherwise defaults to "shorts"
2672 # these seem to mark watchtime "history" in the real world
2673 # they're required
, so send
in a single value
2679 url
= compat_urlparse
.urlunparse(
2680 parsed_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
2682 self
._download
_webpage
(
2683 url
, video_id
, f
'Marking {label}watched',
2684 'Unable to mark watched', fatal
=False)
2687 def _extract_urls(webpage
):
2688 # Embedded YouTube player
2690 unescapeHTML(mobj
.group('url'))
2691 for mobj
in re
.finditer(r
'''(?x)
2701 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
2702 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
2705 # lazyYT YouTube embed
2706 entries.extend(list(map(
2708 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
2710 # Wordpress "YouTube Video Importer" plugin
2711 matches = re.findall(r'''(?x
)<div
[^
>]+
2712 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2713 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
2714 entries.extend(m[-1] for m in matches)
2719 def _extract_url(webpage):
2720 urls = YoutubeIE._extract_urls(webpage)
2721 return urls[0] if urls else None
2724 def extract_id(cls, url):
2725 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2727 raise ExtractorError('Invalid URL: %s' % url)
2728 return mobj.group('id')
2730 def _extract_chapters_from_json(self, data, duration):
2731 chapter_list = traverse_obj(
2733 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2734 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2735 ), expected_type=list)
2737 return self._extract_chapters(
2739 chapter_time=lambda chapter: float_or_none(
2740 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2741 chapter_title=lambda chapter: traverse_obj(
2742 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2745 def _extract_chapters_from_engagement_panel(self, data, duration):
2746 content_list = traverse_obj(
2748 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2749 expected_type=list, default=[])
2750 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2751 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2753 return next(filter(None, (
2754 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2755 chapter_time, chapter_title, duration)
2756 for contents in content_list)), [])
2758 def _extract_chapters_from_description(self, description, duration):
2759 return self._extract_chapters(
2760 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2761 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2762 duration=duration, strict=False)
2764 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2768 'start_time': chapter_time(chapter),
2769 'title': chapter_title(chapter),
2770 } for chapter in chapter_list or []]
2772 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2774 chapters = [{'start_time': 0, 'title': '<Untitled>'}]
2775 for idx, chapter in enumerate(chapter_list):
2776 if chapter['start_time'] is None or not chapter['title']:
2777 self.report_warning(f'Incomplete chapter {idx}')
2778 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2779 chapters[-1]['end_time'] = chapter['start_time']
2780 chapters.append(chapter)
2782 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2783 chapters[-1]['end_time'] = duration
2784 return chapters if len(chapters) > 1 and chapters[1]['start_time'] else chapters[1:]
2786 def _extract_comment(self, comment_renderer, parent=None):
2787 comment_id = comment_renderer.get('commentId')
2791 text = self._get_text(comment_renderer, 'contentText')
2793 # note: timestamp is an estimate calculated from the current time and time_text
2794 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2795 author = self._get_text(comment_renderer, 'authorText')
2796 author_id = try_get(comment_renderer,
2797 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2799 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2800 lambda x: x['likeCount']), compat_str)) or 0
2801 author_thumbnail = try_get(comment_renderer,
2802 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2804 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2805 is_favorited = 'creatorHeart' in (try_get(
2806 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2810 'timestamp': timestamp,
2811 'time_text': time_text,
2812 'like_count': votes,
2813 'is_favorited': is_favorited,
2815 'author_id': author_id,
2816 'author_thumbnail': author_thumbnail,
2817 'author_is_uploader': author_is_uploader,
2818 'parent': parent or 'root'
2821 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2823 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2825 def extract_header(contents):
2826 _continuation = None
2827 for content in contents:
2828 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2829 expected_comment_count = self._get_count(
2830 comments_header_renderer, 'countText', 'commentsCount')
2832 if expected_comment_count:
2833 tracker['est_total'] = expected_comment_count
2834 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2835 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2837 sort_menu_item = try_get(
2838 comments_header_renderer,
2839 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2840 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2842 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2843 if not _continuation:
2846 sort_text = str_or_none(sort_menu_item.get('title'))
2848 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2849 self.to_screen('Sorting comments by %s' % sort_text.lower())
2851 return _continuation
2853 def extract_thread(contents):
2855 tracker['current_page_thread'] = 0
2856 for content in contents:
2857 if not parent and tracker['total_parent_comments'] >= max_parents:
2859 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2860 comment_renderer = get_first(
2861 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2862 expected_type=dict, default={})
2864 comment = self._extract_comment(comment_renderer, parent)
2868 tracker['running_total'] += 1
2869 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2872 # Attempt to get the replies
2873 comment_replies_renderer = try_get(
2874 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2876 if comment_replies_renderer:
2877 tracker['current_page_thread'] += 1
2878 comment_entries_iter = self._comment_entries(
2879 comment_replies_renderer, ytcfg, video_id,
2880 parent=comment.get('id'), tracker=tracker)
2881 yield from itertools.islice(comment_entries_iter, min(
2882 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2884 # Keeps track of counts across recursive calls
2889 current_page_thread=0,
2890 total_parent_comments=0,
2891 total_reply_comments=0)
2894 # YouTube comments have a max depth of 2
2895 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2897 self._downloader.deprecation_warning(
2898 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2899 if max_depth == 1 and parent:
2902 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2903 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2905 continuation = self._extract_continuation(root_continuation_data)
2908 is_forced_continuation = False
2909 is_first_continuation = parent is None
2910 if is_first_continuation and not continuation:
2911 # Sometimes you can get comments by generating the continuation yourself,
2912 # even if YouTube initially reports them being disabled - e.g. stories comments.
2913 # Note: if the comment section is actually disabled, YouTube may return a response with
2914 # required check_get_keys missing. So we will disable that check initially in this case.
2915 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2916 is_forced_continuation = True
2918 for page_num in itertools.count(0):
2919 if not continuation:
2921 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2922 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
2924 if is_first_continuation:
2925 note_prefix = 'Downloading comment section API JSON'
2927 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2928 tracker['current_page_thread'], comment_prog_str)
2930 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2931 ' ' if parent else '', ' replies' if parent else '',
2932 page_num, comment_prog_str)
2934 response = self._extract_response(
2935 item_id=None, query=continuation,
2936 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2937 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2938 is_forced_continuation = False
2939 continuation_contents = traverse_obj(
2940 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2943 for continuation_section in continuation_contents:
2944 continuation_items = traverse_obj(
2945 continuation_section,
2946 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2947 get_all=False, expected_type=list) or []
2948 if is_first_continuation:
2949 continuation = extract_header(continuation_items)
2950 is_first_continuation = False
2955 for entry in extract_thread(continuation_items):
2959 continuation = self._extract_continuation({'contents': continuation_items})
2963 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
2964 if message and not parent and tracker['running_total'] == 0:
2965 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
2968 def _generate_comment_continuation(video_id):
2970 Generates initial comment section continuation token from given video id
2972 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
2973 return base64.b64encode(token.encode()).decode()
2975 def _get_comments(self, ytcfg, video_id, contents, webpage):
2976 """Entry for comment extraction"""
2977 def _real_comment_extract(contents):
2979 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
2980 if item.get('sectionIdentifier') == 'comment-item-section'), None)
2981 yield from self._comment_entries(renderer, ytcfg, video_id)
2983 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
2984 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
2987 def _get_checkok_params():
2988 return {'contentCheckOk': True, 'racyCheckOk': True}
2991 def _generate_player_context(cls, sts=None):
2993 'html5Preference': 'HTML5_PREF_WANTS',
2996 context['signatureTimestamp'] = sts
2998 'playbackContext': {
2999 'contentPlaybackContext': context
3001 **cls._get_checkok_params()
3005 def _is_agegated(player_response):
3006 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3009 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3010 AGE_GATE_REASONS = (
3011 'confirm your age', 'age-restricted', 'inappropriate', # reason
3012 'age_verification_required', 'age_check_required', # status
3014 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3017 def _is_unplayable(player_response):
3018 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3020 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
3022 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3023 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3024 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3025 headers = self.generate_api_headers(
3026 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3029 'videoId': video_id,
3030 'params': '8AEB' # enable stories
3032 yt_query.update(self._generate_player_context(sts))
3033 return self._extract_response(
3034 item_id=video_id, ep='player', query=yt_query,
3035 ytcfg=player_ytcfg, headers=headers, fatal=True,
3036 default_client=client,
3037 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3040 def _get_requested_clients(self, url, smuggled_data):
3041 requested_clients = []
3042 default = ['android', 'web']
3043 allowed_clients = sorted(
3044 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3045 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3046 for client in self._configuration_arg('player_client'):
3047 if client in allowed_clients:
3048 requested_clients.append(client)
3049 elif client == 'default':
3050 requested_clients.extend(default)
3051 elif client == 'all':
3052 requested_clients.extend(allowed_clients)
3054 self.report_warning(f'Skipping unsupported client {client}')
3055 if not requested_clients:
3056 requested_clients = default
3058 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3059 requested_clients.extend(
3060 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3062 return orderedSet(requested_clients)
3064 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
3067 initial_pr = self._search_json(
3068 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3070 all_clients = set(clients)
3071 clients = clients[::-1]
3074 def append_client(*client_names):
3075 """ Append the first client name that exists but not already used """
3076 for client_name in client_names:
3077 actual_client = _split_innertube_client(client_name)[0]
3078 if actual_client in INNERTUBE_CLIENTS:
3079 if actual_client not in all_clients:
3080 clients.append(client_name)
3081 all_clients.add(actual_client)
3084 # Android player_response does not have microFormats which are needed for
3085 # extraction of some data. So we return the initial_pr with formats
3086 # stripped out even if not requested by the user
3087 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3089 pr = dict(initial_pr)
3090 pr['streamingData'] = None
3094 tried_iframe_fallback = False
3097 client, base_client, variant = _split_innertube_client(clients.pop())
3098 player_ytcfg = master_ytcfg if client == 'web' else {}
3099 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3100 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3102 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3103 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3104 if 'js' in self._configuration_arg('player_skip'):
3105 require_js_player = False
3108 if not player_url and not tried_iframe_fallback and require_js_player:
3109 player_url = self._download_player_url(video_id)
3110 tried_iframe_fallback = True
3113 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3114 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3115 except ExtractorError as e:
3117 self.report_warning(last_error)
3124 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3125 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3126 append_client(f'{base_client}_creator')
3127 elif self._is_agegated(pr):
3128 if variant == 'tv_embedded':
3129 append_client(f'{base_client}_embedded')
3131 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3136 self.report_warning(last_error)
3137 return prs, player_url
3139 def _extract_formats(self, streaming_data, video_id, player_url, is_live, duration):
3140 itags, stream_ids = {}, []
3141 itag_qualities, res_qualities = {}, {}
3143 # Normally tiny is the smallest video-only formats. But
3144 # audio-only formats with unknown quality may get tagged as tiny
3146 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3147 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3149 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3151 for fmt in streaming_formats:
3152 if fmt.get('targetDurationSec'):
3155 itag = str_or_none(fmt.get('itag'))
3156 audio_track = fmt.get('audioTrack') or {}
3157 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3158 if stream_id in stream_ids:
3161 quality = fmt.get('quality')
3162 height = int_or_none(fmt.get('height'))
3163 if quality == 'tiny' or not quality:
3164 quality = fmt.get('audioQuality', '').lower() or quality
3165 # The 3gp format (17) in android client has a quality of "small
",
3166 # but is actually worse than other formats
3171 itag_qualities[itag] = quality
3173 res_qualities[height] = quality
3174 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3175 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3176 # number of fragment that would subsequently requested with (`&sq=N`)
3177 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3180 fmt_url = fmt.get('url')
3182 sc = compat_parse_qs(fmt.get('signatureCipher'))
3183 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3184 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3185 if not all((sc, fmt_url, player_url, encrypted_sig)):
3188 fmt_url += '&%s=%s' % (
3189 traverse_obj(sc, ('sp', -1)) or 'signature',
3190 self._decrypt_signature(encrypted_sig, video_id, player_url)
3192 except ExtractorError as e:
3193 self.report_warning('Signature extraction failed: Some formats may be missing', only_once=True)
3194 self.write_debug(e, only_once=True)
3197 query = parse_qs(fmt_url)
3201 fmt_url = update_url_query(fmt_url, {
3202 'n': self._decrypt_nsig(query['n'][0], video_id, player_url)})
3203 except ExtractorError as e:
3204 self.report_warning(
3205 'nsig extraction failed: You may experience throttling for some formats\n'
3206 f'n = {query["n"][0]} ; player = {player_url}', only_once=True)
3207 self.write_debug(e, only_once=True)
3211 itags[itag] = 'https'
3212 stream_ids.append(stream_id)
3214 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3215 language_preference = (
3216 10 if audio_track.get('audioIsDefault') and 10
3217 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3219 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3220 # Eg: 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3221 # Make sure to avoid false positives with small duration differences.
3222 # Eg: __2ABJjxzNo, ySuUZEjARPY
3223 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3225 self.report_warning(
3226 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3228 'asr': int_or_none(fmt.get('audioSampleRate')),
3229 'filesize': int_or_none(fmt.get('contentLength')),
3231 'format_note': join_nonempty(
3232 '%s%s' % (audio_track.get('displayName') or '',
3233 ' (default)' if language_preference > 0 else ''),
3234 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3235 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3236 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3237 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3238 'fps': int_or_none(fmt.get('fps')) or None,
3240 'quality': q(quality),
3241 'has_drm': bool(fmt.get('drmFamilies')),
3244 'width': int_or_none(fmt.get('width')),
3245 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3246 'desc' if language_preference < -1 else ''),
3247 'language_preference': language_preference,
3248 # Strictly de-prioritize damaged and 3gp formats
3249 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3251 mime_mobj = re.match(
3252 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3254 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3255 dct.update(parse_codecs(mime_mobj.group(2)))
3256 no_audio = dct.get('acodec
') == 'none
'
3257 no_video = dct.get('vcodec
') == 'none
'
3262 if no_audio or no_video:
3263 dct['downloader_options
'] = {
3264 # Youtube throttles chunks >~10M
3265 'http_chunk_size
': 10485760,
3268 dct['container
'] = dct['ext
'] + '_dash
'
3271 live_from_start = is_live and self.get_param('live_from_start
')
3272 skip_manifests = self._configuration_arg('skip
')
3273 if not self.get_param('youtube_include_hls_manifest
', True):
3274 skip_manifests.append('hls
')
3275 if not self.get_param('youtube_include_dash_manifest
', True):
3276 skip_manifests.append('dash
')
3277 get_dash = 'dash
' not in skip_manifests and (
3278 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3279 get_hls = not live_from_start and 'hls
' not in skip_manifests
3281 def process_manifest_format(f, proto, itag):
3283 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3285 itag = f'{itag}
-{proto}
'
3287 f['format_id
'] = itag
3290 f['quality
'] = next((
3292 for val, qdict in ((f.get('format_id
', '').split('-')[0], itag_qualities), (f.get('height
'), res_qualities))
3293 if val in qdict), -1)
3296 for sd in streaming_data:
3297 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3298 if hls_manifest_url:
3299 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4
', fatal=False):
3300 if process_manifest_format(f, 'hls
', self._search_regex(
3301 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3304 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3305 if dash_manifest_url:
3306 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
3307 if process_manifest_format(f, 'dash
', f['format_id
']):
3308 f['filesize
'] = int_or_none(self._search_regex(
3309 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3311 f['is_from_start
'] = True
3315 def _extract_storyboard(self, player_responses, duration):
3317 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3318 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3322 for i, args in enumerate(spec):
3323 args = args.split('#')
3324 counts
= list(map(int_or_none
, args
[:5]))
3325 if len(args
) != 8 or not all(counts
):
3326 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3328 width
, height
, frame_count
, cols
, rows
= counts
3331 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3332 fragment_count
= frame_count
/ (cols
* rows
)
3333 fragment_duration
= duration
/ fragment_count
3335 'format_id': f
'sb{i}',
3336 'format_note': 'storyboard',
3338 'protocol': 'mhtml',
3345 'url': url
.replace('$M', str(j
)),
3346 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3347 } for j
in range(math
.ceil(fragment_count
))],
3350 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3352 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3353 webpage
= self
._download
_webpage
(
3354 webpage_url
+ '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id
, fatal
=False)
3356 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3358 player_responses
, player_url
= self
._extract
_player
_responses
(
3359 self
._get
_requested
_clients
(url
, smuggled_data
),
3360 video_id
, webpage
, master_ytcfg
)
3362 return webpage
, master_ytcfg
, player_responses
, player_url
3364 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3365 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3366 is_live
= get_first(video_details
, 'isLive')
3368 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3370 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3371 formats
= list(self
._extract
_formats
(streaming_data
, video_id
, player_url
, is_live
, duration
))
3373 return live_broadcast_details
, is_live
, streaming_data
, formats
3375 def _real_extract(self
, url
):
3376 url
, smuggled_data
= unsmuggle_url(url
, {})
3377 video_id
= self
._match
_id
(url
)
3379 base_url
= self
.http_scheme() + '//www.youtube.com/'
3380 webpage_url
= base_url
+ 'watch?v=' + video_id
3382 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3384 playability_statuses
= traverse_obj(
3385 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3387 trailer_video_id
= get_first(
3388 playability_statuses
,
3389 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3391 if trailer_video_id
:
3392 return self
.url_result(
3393 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3395 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3396 if webpage
else (lambda x
: None))
3398 video_details
= traverse_obj(
3399 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3400 microformats
= traverse_obj(
3401 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3402 expected_type
=dict, default
=[])
3404 get_first(video_details
, 'title')
3405 or self
._get
_text
(microformats
, (..., 'title'))
3406 or search_meta(['og:title', 'twitter:title', 'title']))
3407 video_description
= get_first(video_details
, 'shortDescription')
3409 multifeed_metadata_list
= get_first(
3411 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3413 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3414 if self
.get_param('noplaylist'):
3415 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3419 for feed
in multifeed_metadata_list
.split(','):
3420 # Unquote should take place before split on comma (,) since textual
3421 # fields may contain comma as well (see
3422 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3423 feed_data
= compat_parse_qs(
3424 compat_urllib_parse_unquote_plus(feed
))
3426 def feed_entry(name
):
3428 feed_data
, lambda x
: x
[name
][0], compat_str
)
3430 feed_id
= feed_entry('id')
3433 feed_title
= feed_entry('title')
3436 title
+= ' (%s)' % feed_title
3438 '_type': 'url_transparent',
3439 'ie_key': 'Youtube',
3441 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3442 {'force_singlefeed': True}
),
3445 feed_ids
.append(feed_id
)
3447 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3448 % (', '.join(feed_ids
), video_id
))
3449 return self
.playlist_result(
3450 entries
, video_id
, video_title
, video_description
)
3452 duration
= int_or_none(
3453 get_first(video_details
, 'lengthSeconds')
3454 or get_first(microformats
, 'lengthSeconds')
3455 or parse_duration(search_meta('duration'))) or None
3457 if get_first(video_details
, 'isPostLiveDvr'):
3458 self
.write_debug('Video is in Post-Live Manifestless mode')
3459 if duration
or 0 > 4 * 3600:
3460 self
.report_warning(
3461 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3462 'This is a known issue and patches are welcome')
3464 live_broadcast_details
, is_live
, streaming_data
, formats
= self
._list
_formats
(
3465 video_id
, microformats
, video_details
, player_responses
, player_url
, duration
)
3468 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3469 self
.report_drm(video_id
)
3471 playability_statuses
,
3472 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3473 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3474 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3476 if subreason
== 'The uploader has not made this video available in your country.':
3477 countries
= get_first(microformats
, 'availableCountries')
3479 regions_allowed
= search_meta('regionsAllowed')
3480 countries
= regions_allowed
.split(',') if regions_allowed
else None
3481 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3482 reason
+= f
'. {subreason}'
3484 self
.raise_no_formats(reason
, expected
=True)
3486 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3487 if not keywords
and webpage
:
3489 unescapeHTML(m
.group('content'))
3490 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3491 for keyword
in keywords
:
3492 if keyword
.startswith('yt:stretch='):
3493 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3495 # NB: float is intentional for forcing float division
3496 w
, h
= (float(v
) for v
in mobj
.groups())
3500 if f
.get('vcodec') != 'none':
3501 f
['stretched_ratio'] = ratio
3503 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3504 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3507 'url': thumbnail_url
,
3509 original_thumbnails
= thumbnails
.copy()
3511 # The best resolution thumbnails sometimes does not appear in the webpage
3512 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3513 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3515 # While the *1,*2,*3 thumbnails are just below their correspnding "*default" variants
3516 # in resolution, these are not the custom thumbnail. So de-prioritize them
3517 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3518 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3520 n_thumbnail_names
= len(thumbnail_names
)
3522 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3523 video_id
=video_id
, name
=name
, ext
=ext
,
3524 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3525 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3526 for thumb
in thumbnails
:
3527 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3528 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3529 self
._remove
_duplicate
_formats
(thumbnails
)
3530 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3532 category
= get_first(microformats
, 'category') or search_meta('genre')
3533 channel_id
= str_or_none(
3534 get_first(video_details
, 'channelId')
3535 or get_first(microformats
, 'externalChannelId')
3536 or search_meta('channelId'))
3537 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3539 live_content
= get_first(video_details
, 'isLiveContent')
3540 is_upcoming
= get_first(video_details
, 'isUpcoming')
3542 if is_upcoming
or live_content
is False:
3544 if is_upcoming
is None and (live_content
or is_live
):
3546 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3547 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3548 if not duration
and live_end_time
and live_start_time
:
3549 duration
= live_end_time
- live_start_time
3551 if is_live
and self
.get_param('live_from_start'):
3552 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3554 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3556 # Source is given priority since formats that throttle are given lower source_preference
3557 # When throttling issue is fully fixed, remove this
3558 self
._sort
_formats
(formats
, ('quality', 'res', 'fps', 'hdr:12', 'source', 'codec:vp9.2', 'lang', 'proto'))
3562 'title': video_title
,
3564 'thumbnails': thumbnails
,
3565 # The best thumbnail that we are sure exists. Prevents unnecessary
3566 # URL checking if user don't care about getting the best possible thumbnail
3567 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3568 'description': video_description
,
3569 'uploader': get_first(video_details
, 'author'),
3570 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3571 'uploader_url': owner_profile_url
,
3572 'channel_id': channel_id
,
3573 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3574 'duration': duration
,
3575 'view_count': int_or_none(
3576 get_first((video_details
, microformats
), (..., 'viewCount'))
3577 or search_meta('interactionCount')),
3578 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3579 'age_limit': 18 if (
3580 get_first(microformats
, 'isFamilySafe') is False
3581 or search_meta('isFamilyFriendly') == 'false'
3582 or search_meta('og:restrictions:age') == '18+') else 0,
3583 'webpage_url': webpage_url
,
3584 'categories': [category
] if category
else None,
3586 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3588 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3589 else None if is_live
is None or is_upcoming
is None
3591 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3592 'release_timestamp': live_start_time
,
3595 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3597 def get_lang_code(track
):
3598 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3599 or track
.get('languageCode'))
3601 # Converted into dicts to remove duplicates
3603 get_lang_code(sub
): sub
3604 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3605 translation_languages
= {
3606 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3607 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3609 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3610 lang_subs
= container
.setdefault(lang_code
, [])
3611 for fmt
in self
._SUBTITLE
_FORMATS
:
3617 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3621 subtitles
, automatic_captions
= {}, {}
3622 for lang_code
, caption_track
in captions
.items():
3623 base_url
= caption_track
.get('baseUrl')
3624 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3627 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3628 if caption_track
.get('kind') != 'asr':
3632 subtitles
, base_url
, lang_code
, lang_name
, {})
3633 if not caption_track
.get('isTranslatable'):
3635 for trans_code
, trans_name
in translation_languages
.items():
3638 orig_trans_code
= trans_code
3639 if caption_track
.get('kind') != 'asr':
3640 if 'translated_subs' in self
._configuration
_arg
('skip'):
3642 trans_code
+= f
'-{lang_code}'
3643 trans_name
+= format_field(lang_name
, None, ' from %s')
3644 # Add an "-orig" label to the original language so that it can be distinguished.
3645 # The subs are returned without "-orig" as well for compatibility
3646 if lang_code
== f
'a-{orig_trans_code}':
3648 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3649 # Setting tlang=lang returns damaged subtitles.
3650 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3651 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3652 info
['automatic_captions'] = automatic_captions
3653 info
['subtitles'] = subtitles
3655 parsed_url
= compat_urllib_parse_urlparse(url
)
3656 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3657 query
= compat_parse_qs(component
)
3658 for k
, v
in query
.items():
3659 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3661 if d_k
not in info
and k
in s_ks
:
3662 info
[d_k
] = parse_duration(query
[k
][0])
3664 # Youtube Music Auto-generated description
3665 if video_description
:
3668 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3670 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3671 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3672 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3673 .+\nAuto-generated\ by\ YouTube\.\s*$
3674 ''', video_description
)
3676 release_year
= mobj
.group('release_year')
3677 release_date
= mobj
.group('release_date')
3679 release_date
= release_date
.replace('-', '')
3680 if not release_year
:
3681 release_year
= release_date
[:4]
3683 'album': mobj
.group('album'.strip()),
3684 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3685 'track': mobj
.group('track').strip(),
3686 'release_date': release_date
,
3687 'release_year': int_or_none(release_year
),
3692 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3693 if not initial_data
:
3694 query
= {'videoId': video_id}
3695 query
.update(self
._get
_checkok
_params
())
3696 initial_data
= self
._extract
_response
(
3697 item_id
=video_id
, ep
='next', fatal
=False,
3698 ytcfg
=master_ytcfg
, query
=query
,
3699 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3700 note
='Downloading initial data API JSON')
3702 info
['comment_count'] = traverse_obj(initial_data
, (
3703 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3704 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3706 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3707 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3708 ), expected_type
=int_or_none
, get_all
=False)
3710 try: # This will error if there is no livechat
3711 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3712 except (KeyError, IndexError, TypeError):
3715 info
.setdefault('subtitles', {})['live_chat'] = [{
3716 # url is needed to set cookies
3717 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3718 'video_id': video_id
,
3720 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3724 info
['chapters'] = (
3725 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3726 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3727 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3730 contents
= traverse_obj(
3731 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3732 expected_type
=list, default
=[])
3734 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3736 stl
= vpir
.get('superTitleLink')
3738 stl
= self
._get
_text
(stl
)
3741 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3742 info
['location'] = stl
3744 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3747 'series': mobj
.group(1),
3748 'season_number': int(mobj
.group(2)),
3749 'episode_number': int(mobj
.group(3)),
3751 for tlb
in (try_get(
3753 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3755 tbr
= tlb
.get('toggleButtonRenderer') or {}
3756 for getter
, regex
in [(
3757 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3758 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3759 lambda x
: x
['accessibility'],
3760 lambda x
: x
['accessibilityData']['accessibilityData'],
3761 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3762 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3764 mobj
= re
.match(regex
, label
)
3766 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3768 sbr_tooltip
= try_get(
3769 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3771 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3773 'like_count': str_to_int(like_count
),
3774 'dislike_count': str_to_int(dislike_count
),
3776 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3778 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3780 'channel': self
._get
_text
(vor
, 'title'),
3781 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3785 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3787 multiple_songs
= False
3789 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3790 multiple_songs
= True
3793 mrr
= row
.get('metadataRowRenderer') or {}
3794 mrr_title
= mrr
.get('title')
3797 mrr_title
= self
._get
_text
(mrr
, 'title')
3798 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3799 if mrr_title
== 'License':
3800 info
['license'] = mrr_contents_text
3801 elif not multiple_songs
:
3802 if mrr_title
== 'Album':
3803 info
['album'] = mrr_contents_text
3804 elif mrr_title
== 'Artist':
3805 info
['artist'] = mrr_contents_text
3806 elif mrr_title
== 'Song':
3807 info
['track'] = mrr_contents_text
3810 'channel': 'uploader',
3811 'channel_id': 'uploader_id',
3812 'channel_url': 'uploader_url',
3815 # The upload date for scheduled, live and past live streams / premieres in microformats
3816 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3817 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3819 unified_strdate(get_first(microformats
, 'uploadDate'))
3820 or unified_strdate(search_meta('uploadDate')))
3821 if not upload_date
or (not info
.get('is_live') and not info
.get('was_live') and info
.get('live_status') != 'is_upcoming'):
3822 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3823 info
['upload_date'] = upload_date
3825 for to
, frm
in fallbacks
.items():
3826 if not info
.get(to
):
3827 info
[to
] = info
.get(frm
)
3829 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3834 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3835 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3836 is_membersonly
= None
3838 if initial_data
and is_private
is not None:
3839 is_membersonly
= False
3841 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3842 badge_labels
= set()
3843 for content
in contents
:
3844 if not isinstance(content
, dict):
3846 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3847 for badge_label
in badge_labels
:
3848 if badge_label
.lower() == 'members only':
3849 is_membersonly
= True
3850 elif badge_label
.lower() == 'premium':
3852 elif badge_label
.lower() == 'unlisted':
3855 info
['availability'] = self
._availability
(
3856 is_private
=is_private
,
3857 needs_premium
=is_premium
,
3858 needs_subscription
=is_membersonly
,
3859 needs_auth
=info
['age_limit'] >= 18,
3860 is_unlisted
=None if is_private
is None else is_unlisted
)
3862 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
3864 self
.mark_watched(video_id
, player_responses
)
3869 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
3872 def passthrough_smuggled_data(func
):
3873 def _smuggle(entries
, smuggled_data
):
3874 for entry
in entries
:
3875 # TODO: Convert URL to music.youtube instead.
3876 # Do we need to passthrough any other smuggled_data?
3877 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
3880 @functools.wraps(func
)
3881 def wrapper(self
, url
):
3882 url
, smuggled_data
= unsmuggle_url(url
, {})
3883 if self
.is_music_url(url
):
3884 smuggled_data
['is_music_url'] = True
3885 info_dict
= func(self
, url
, smuggled_data
)
3886 if smuggled_data
and info_dict
.get('entries'):
3887 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
3891 def _extract_channel_id(self
, webpage
):
3892 channel_id
= self
._html
_search
_meta
(
3893 'channelId', webpage
, 'channel id', default
=None)
3896 channel_url
= self
._html
_search
_meta
(
3897 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3898 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3899 'twitter:app:url:googleplay'), webpage
, 'channel url')
3900 return self
._search
_regex
(
3901 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3902 channel_url
, 'channel id')
3905 def _extract_basic_item_renderer(item
):
3906 # Modified from _extract_grid_item_renderer
3907 known_basic_renderers
= (
3908 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3910 for key
, renderer
in item
.items():
3911 if not isinstance(renderer
, dict):
3913 elif key
in known_basic_renderers
:
3915 elif key
.startswith('grid') and key
.endswith('Renderer'):
3918 def _grid_entries(self
, grid_renderer
):
3919 for item
in grid_renderer
['items']:
3920 if not isinstance(item
, dict):
3922 renderer
= self
._extract
_basic
_item
_renderer
(item
)
3923 if not isinstance(renderer
, dict):
3925 title
= self
._get
_text
(renderer
, 'title')
3928 playlist_id
= renderer
.get('playlistId')
3930 yield self
.url_result(
3931 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
3932 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
3936 video_id
= renderer
.get('videoId')
3938 yield self
._extract
_video
(renderer
)
3941 channel_id
= renderer
.get('channelId')
3943 yield self
.url_result(
3944 'https://www.youtube.com/channel/%s' % channel_id
,
3945 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
3947 # generic endpoint URL support
3948 ep_url
= urljoin('https://www.youtube.com/', try_get(
3949 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3952 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
3953 if ie
.suitable(ep_url
):
3954 yield self
.url_result(
3955 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
3958 def _music_reponsive_list_entry(self
, renderer
):
3959 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
3961 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
3962 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
3963 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
3965 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
3967 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
3968 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
3969 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
3970 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
3971 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
3973 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
3974 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
3976 def _shelf_entries_from_content(self
, shelf_renderer
):
3977 content
= shelf_renderer
.get('content')
3978 if not isinstance(content
, dict):
3980 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
3982 # TODO: add support for nested playlists so each shelf is processed
3983 # as separate playlist
3984 # TODO: this includes only first N items
3985 yield from self
._grid
_entries
(renderer
)
3986 renderer
= content
.get('horizontalListRenderer')
3991 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
3993 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3995 shelf_url
= urljoin('https://www.youtube.com', ep
)
3997 # Skipping links to another channels, note that checking for
3998 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4000 if skip_channels
and '/channels?' in shelf_url
:
4002 title
= self
._get
_text
(shelf_renderer
, 'title')
4003 yield self
.url_result(shelf_url
, video_title
=title
)
4004 # Shelf may not contain shelf URL, fallback to extraction from content
4005 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4007 def _playlist_entries(self
, video_list_renderer
):
4008 for content
in video_list_renderer
['contents']:
4009 if not isinstance(content
, dict):
4011 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4012 if not isinstance(renderer
, dict):
4014 video_id
= renderer
.get('videoId')
4017 yield self
._extract
_video
(renderer
)
4019 def _rich_entries(self
, rich_grid_renderer
):
4021 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4022 video_id
= renderer
.get('videoId')
4025 yield self
._extract
_video
(renderer
)
4027 def _video_entry(self
, video_renderer
):
4028 video_id
= video_renderer
.get('videoId')
4030 return self
._extract
_video
(video_renderer
)
4032 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4033 url
= urljoin('https://youtube.com', traverse_obj(
4034 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4036 return self
.url_result(
4037 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4039 def _post_thread_entries(self
, post_thread_renderer
):
4040 post_renderer
= try_get(
4041 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4042 if not post_renderer
:
4045 video_renderer
= try_get(
4046 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4047 video_id
= video_renderer
.get('videoId')
4049 entry
= self
._extract
_video
(video_renderer
)
4052 # playlist attachment
4053 playlist_id
= try_get(
4054 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], compat_str
)
4056 yield self
.url_result(
4057 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4058 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4059 # inline video links
4060 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4062 if not isinstance(run
, dict):
4065 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], compat_str
)
4068 if not YoutubeIE
.suitable(ep_url
):
4070 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4071 if video_id
== ep_video_id
:
4073 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4075 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4076 contents
= post_thread_continuation
.get('contents')
4077 if not isinstance(contents
, list):
4079 for content
in contents
:
4080 renderer
= content
.get('backstagePostThreadRenderer')
4081 if isinstance(renderer
, dict):
4082 yield from self
._post
_thread
_entries
(renderer
)
4084 renderer
= content
.get('videoRenderer')
4085 if isinstance(renderer
, dict):
4086 yield self
._video
_entry
(renderer
)
4089 def _rich_grid_entries(self, contents):
4090 for content in contents:
4091 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4093 entry = self._video_entry(video_renderer)
4098 def _extract_entries(self
, parent_renderer
, continuation_list
):
4099 # continuation_list is modified in-place with continuation_list = [continuation_token]
4100 continuation_list
[:] = [None]
4101 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4102 for content
in contents
:
4103 if not isinstance(content
, dict):
4105 is_renderer
= traverse_obj(
4106 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4109 renderer
= content
.get('richItemRenderer')
4111 for entry
in self
._rich
_entries
(renderer
):
4113 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4115 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4116 for isr_content
in isr_contents
:
4117 if not isinstance(isr_content
, dict):
4121 'playlistVideoListRenderer': self
._playlist
_entries
,
4122 'gridRenderer': self
._grid
_entries
,
4123 'reelShelfRenderer': self
._grid
_entries
,
4124 'shelfRenderer': self
._shelf
_entries
,
4125 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4126 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4127 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4128 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4129 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4130 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4132 for key
, renderer
in isr_content
.items():
4133 if key
not in known_renderers
:
4135 for entry
in known_renderers
[key
](renderer
):
4138 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4141 if not continuation_list
[0]:
4142 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4144 if not continuation_list
[0]:
4145 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4147 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4148 continuation_list
= [None]
4149 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4150 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4154 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4155 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4156 yield from extract_entries(parent_renderer
)
4157 continuation
= continuation_list
[0]
4159 for page_num
in itertools
.count(1):
4160 if not continuation
:
4162 headers
= self
.generate_api_headers(
4163 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4164 response
= self
._extract
_response
(
4165 item_id
=f
'{item_id} page {page_num}',
4166 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4167 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4171 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4172 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4173 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4175 known_continuation_renderers
= {
4176 'playlistVideoListContinuation': self
._playlist
_entries
,
4177 'gridContinuation': self
._grid
_entries
,
4178 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4179 'sectionListContinuation': extract_entries
, # for feeds
4181 continuation_contents
= try_get(
4182 response
, lambda x
: x
['continuationContents'], dict) or {}
4183 continuation_renderer
= None
4184 for key
, value
in continuation_contents
.items():
4185 if key
not in known_continuation_renderers
:
4187 continuation_renderer
= value
4188 continuation_list
= [None]
4189 yield from known_continuation_renderers
[key
](continuation_renderer
)
4190 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4192 if continuation_renderer
:
4196 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4197 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4198 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4199 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4200 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4201 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4202 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4203 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4205 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4206 continuation_items
= try_get(
4207 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4208 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4209 video_items_renderer
= None
4210 for key
, value
in continuation_item
.items():
4211 if key
not in known_renderers
:
4213 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4214 continuation_list
= [None]
4215 yield from known_renderers
[key
][0](video_items_renderer
)
4216 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4218 if video_items_renderer
:
4223 def _extract_selected_tab(tabs
, fatal
=True):
4225 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4226 if renderer
.get('selected') is True:
4230 raise ExtractorError('Unable to find selected tab')
4232 def _extract_uploader(self
, data
):
4234 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4236 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4238 owner_text
= owner
.get('text')
4239 uploader
['uploader'] = self
._search
_regex
(
4240 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4241 uploader
['uploader_id'] = try_get(
4242 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], compat_str
)
4243 uploader
['uploader_url'] = urljoin(
4244 'https://www.youtube.com/',
4245 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str
))
4246 return {k: v for k, v in uploader.items() if v is not None}
4248 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4249 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4252 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4253 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4255 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4257 channel_name
= renderer
.get('title')
4258 channel_url
= renderer
.get('channelUrl')
4259 channel_id
= renderer
.get('externalId')
4262 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4265 title
= renderer
.get('title')
4266 description
= renderer
.get('description', '')
4267 playlist_id
= channel_id
4268 tags
= renderer
.get('keywords', '').split()
4270 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4271 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4272 def _get_uncropped(url
):
4273 return url_or_none((url
or '').split('=')[0] + '=s0')
4275 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4276 if avatar_thumbnails
:
4277 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4278 if uncropped_avatar
:
4279 avatar_thumbnails
.append({
4280 'url': uncropped_avatar
,
4281 'id': 'avatar_uncropped',
4285 channel_banners
= self
._extract
_thumbnails
(
4286 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4287 for banner
in channel_banners
:
4288 banner
['preference'] = -10
4291 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4292 if uncropped_banner
:
4293 channel_banners
.append({
4294 'url': uncropped_banner
,
4295 'id': 'banner_uncropped',
4299 primary_thumbnails
= self
._extract
_thumbnails
(
4300 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4302 if playlist_id
is None:
4303 playlist_id
= item_id
4305 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4306 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4308 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4309 title
+= format_field(selected_tab
, 'title', ' - %s')
4310 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4313 'playlist_id': playlist_id
,
4314 'playlist_title': title
,
4315 'playlist_description': description
,
4316 'uploader': channel_name
,
4317 'uploader_id': channel_id
,
4318 'uploader_url': channel_url
,
4319 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4321 'view_count': self
._get
_count
(playlist_stats
, 1),
4322 'availability': self
._extract
_availability
(data
),
4323 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4324 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4325 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4328 metadata
.update(self
._extract
_uploader
(data
))
4330 'channel': metadata
['uploader'],
4331 'channel_id': metadata
['uploader_id'],
4332 'channel_url': metadata
['uploader_url']})
4333 return self
.playlist_result(
4335 selected_tab
, playlist_id
, ytcfg
,
4336 self
._extract
_account
_syncid
(ytcfg
, data
),
4337 self
._extract
_visitor
_data
(data
, ytcfg
)),
4340 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4341 first_id
= last_id
= response
= None
4342 for page_num
in itertools
.count(1):
4343 videos
= list(self
._playlist
_entries
(playlist
))
4346 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4347 if start
>= len(videos
):
4349 yield from videos
[start
:]
4350 first_id
= first_id
or videos
[0]['id']
4351 last_id
= videos
[-1]['id']
4352 watch_endpoint
= try_get(
4353 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4354 headers
= self
.generate_api_headers(
4355 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4356 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4358 'playlistId': playlist_id
,
4359 'videoId': watch_endpoint
.get('videoId') or last_id
,
4360 'index': watch_endpoint
.get('index') or len(videos
),
4361 'params': watch_endpoint
.get('params') or 'OAE%3D'
4363 response
= self
._extract
_response
(
4364 item_id
='%s page %d' % (playlist_id
, page_num
),
4365 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4366 check_get_keys
='contents'
4369 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4371 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4372 title
= playlist
.get('title') or try_get(
4373 data
, lambda x
: x
['titleText']['simpleText'], compat_str
)
4374 playlist_id
= playlist
.get('playlistId') or item_id
4376 # Delegating everything except mix playlists to regular tab-based playlist URL
4377 playlist_url
= urljoin(url
, try_get(
4378 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4381 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4382 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4383 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4385 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4386 return self
.url_result(
4387 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4390 return self
.playlist_result(
4391 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4392 playlist_id
=playlist_id
, playlist_title
=title
)
4394 def _extract_availability(self
, data
):
4396 Gets the availability of a given playlist/tab.
4397 Note: Unless YouTube tells us explicitly, we do not assume it is public
4398 @param data: response
4400 is_private
= is_unlisted
= None
4401 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4402 badge_labels
= self
._extract
_badges
(renderer
)
4404 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4405 privacy_dropdown_entries
= try_get(
4406 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4407 for renderer_dict
in privacy_dropdown_entries
:
4408 is_selected
= try_get(
4409 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4412 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4414 badge_labels
.add(label
.lower())
4417 for badge_label
in badge_labels
:
4418 if badge_label
== 'unlisted':
4420 elif badge_label
== 'private':
4422 elif badge_label
== 'public':
4423 is_unlisted
= is_private
= False
4424 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4427 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4428 sidebar_renderer
= try_get(
4429 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4430 for item
in sidebar_renderer
:
4431 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4435 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4437 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4439 browse_id
= params
= None
4440 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4443 menu_renderer
= try_get(
4444 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4445 for menu_item
in menu_renderer
:
4446 if not isinstance(menu_item
, dict):
4448 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4450 nav_item_renderer
, lambda x
: x
['text']['simpleText'], compat_str
)
4451 if not text
or text
.lower() != 'show unavailable videos':
4453 browse_endpoint
= try_get(
4454 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4455 browse_id
= browse_endpoint
.get('browseId')
4456 params
= browse_endpoint
.get('params')
4459 headers
= self
.generate_api_headers(
4460 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4461 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4463 'params': params
or 'wgYCCAA=',
4464 'browseId': browse_id
or 'VL%s' % item_id
4466 return self
._extract
_response
(
4467 item_id
=item_id
, headers
=headers
, query
=query
,
4468 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4469 note
='Downloading API JSON with unavailable videos')
4471 @functools.cached_property
4472 def skip_webpage(self
):
4473 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4475 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4476 retries
= self
.get_param('extractor_retries', 3)
4478 webpage
= data
= last_error
= None
4479 while count
< retries
:
4481 # Sometimes youtube returns a webpage with incomplete ytInitialData
4482 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4484 self
.report_warning('%s. Retrying ...' % last_error
)
4486 webpage
= self
._download
_webpage
(
4488 note
='Downloading webpage%s' % (' (retry #%d)' % count
if count
else '',))
4489 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4490 except ExtractorError
as e
:
4491 if isinstance(e
.cause
, network_exceptions
):
4492 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
4493 last_error
= error_to_compat_str(e
.cause
or e
.msg
)
4498 self
.report_warning(error_to_compat_str(e
))
4502 self
._extract
_and
_report
_alerts
(data
)
4503 except ExtractorError
as e
:
4506 self
.report_warning(error_to_compat_str(e
))
4509 if dict_get(data
, ('contents', 'currentVideoEndpoint', 'onResponseReceivedActions')):
4512 last_error
= 'Incomplete yt initial data received'
4513 if count
>= retries
:
4515 raise ExtractorError(last_error
)
4516 self
.report_warning(last_error
)
4519 return webpage
, data
4521 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4522 """Use if failed to extract ytcfg (and data) from initial webpage"""
4523 if not ytcfg
and self
.is_authenticated
:
4524 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4525 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4526 raise ExtractorError(
4527 f
'{msg}. If you are not downloading private content, or '
4528 'your cookies are only for the first account and channel,'
4529 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4531 self
.report_warning(msg
, only_once
=True)
4533 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4535 if not self
.skip_webpage
:
4536 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4537 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4538 # Reject webpage data if redirected to home page without explicitly requesting
4539 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4540 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4541 if (url
!= 'https://www.youtube.com/feed/recommended'
4542 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4543 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4544 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4546 raise ExtractorError(msg
, expected
=True)
4547 self
.report_warning(msg
, only_once
=True)
4549 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4550 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4553 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4554 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4555 resolve_response
= self
._extract
_response
(
4556 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4557 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4558 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4559 for ep_key
, ep
in endpoints
.items():
4560 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4562 return self
._extract
_response
(
4563 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4564 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4565 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4566 err_note
= 'Failed to resolve url (does the playlist exist?)'
4568 raise ExtractorError(err_note
, expected
=True)
4569 self
.report_warning(err_note
, item_id
)
4571 _SEARCH_PARAMS
= None
4573 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4574 data
= {'query': query}
4575 if params
is NO_DEFAULT
:
4576 params
= self
._SEARCH
_PARAMS
4578 data
['params'] = params
4581 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4582 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4584 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4585 ('continuationContents', ),
4587 display_id
= f
'query "{query}"'
4588 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4589 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4590 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4592 continuation_list
= [None]
4594 for page_num
in itertools
.count(1):
4595 data
.update(continuation_list
[0] or {})
4596 headers
= self
.generate_api_headers(
4597 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4598 search
= self
._extract
_response
(
4599 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4600 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4601 slr_contents
= traverse_obj(search
, *content_keys
)
4602 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4603 if not continuation_list
[0]:
4607 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4608 IE_DESC
= 'YouTube Tabs'
4609 _VALID_URL
= r
'''(?x:
4613 youtube(?:kids)?\.com|
4617 (?P<channel_type>channel|c|user|browse)/|
4620 (?:playlist|watch)\?.*?\blist=
4622 (?!(?:%(reserved_names)s)\b) # Direct URLs
4626 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4627 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4629 IE_NAME
= 'youtube:tab'
4632 'note': 'playlists, multipage',
4633 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4634 'playlist_mincount': 94,
4636 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4637 'title': 'Igor Kleiner - Playlists',
4638 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4639 'uploader': 'Igor Kleiner',
4640 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4641 'channel': 'Igor Kleiner',
4642 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4643 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4644 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4645 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4646 'channel_follower_count': int
4649 'note': 'playlists, multipage, different order',
4650 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4651 'playlist_mincount': 94,
4653 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4654 'title': 'Igor Kleiner - Playlists',
4655 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4656 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4657 'uploader': 'Igor Kleiner',
4658 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4659 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4660 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4661 'channel': 'Igor Kleiner',
4662 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4663 'channel_follower_count': int
4666 'note': 'playlists, series',
4667 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4668 'playlist_mincount': 5,
4670 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4671 'title': '3Blue1Brown - Playlists',
4672 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4673 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4674 'uploader': '3Blue1Brown',
4675 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4676 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4677 'channel': '3Blue1Brown',
4678 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4679 'tags': ['Mathematics'],
4680 'channel_follower_count': int
4683 'note': 'playlists, singlepage',
4684 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4685 'playlist_mincount': 4,
4687 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4688 'title': 'ThirstForScience - Playlists',
4689 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4690 'uploader': 'ThirstForScience',
4691 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4692 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4693 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4694 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4696 'channel': 'ThirstForScience',
4697 'channel_follower_count': int
4700 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4701 'only_matching': True,
4703 'note': 'basic, single video playlist',
4704 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4706 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4707 'uploader': 'Sergey M.',
4708 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4709 'title': 'youtube-dl public playlist',
4713 'modified_date': '20201130',
4714 'channel': 'Sergey M.',
4715 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4716 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4717 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4719 'playlist_count': 1,
4721 'note': 'empty playlist',
4722 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4724 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4725 'uploader': 'Sergey M.',
4726 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4727 'title': 'youtube-dl empty playlist',
4729 'channel': 'Sergey M.',
4731 'modified_date': '20160902',
4732 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4733 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4734 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4736 'playlist_count': 0,
4739 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4741 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4742 'title': 'lex will - Home',
4743 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4744 'uploader': 'lex will',
4745 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4746 'channel': 'lex will',
4747 'tags': ['bible', 'history', 'prophesy'],
4748 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4749 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4750 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4751 'channel_follower_count': int
4753 'playlist_mincount': 2,
4755 'note': 'Videos tab',
4756 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4758 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4759 'title': 'lex will - Videos',
4760 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4761 'uploader': 'lex will',
4762 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4763 'tags': ['bible', 'history', 'prophesy'],
4764 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4765 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4766 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4767 'channel': 'lex will',
4768 'channel_follower_count': int
4770 'playlist_mincount': 975,
4772 'note': 'Videos tab, sorted by popular',
4773 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4775 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4776 'title': 'lex will - Videos',
4777 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4778 'uploader': 'lex will',
4779 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4780 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4781 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4782 'channel': 'lex will',
4783 'tags': ['bible', 'history', 'prophesy'],
4784 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4785 'channel_follower_count': int
4787 'playlist_mincount': 199,
4789 'note': 'Playlists tab',
4790 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4792 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4793 'title': 'lex will - Playlists',
4794 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4795 'uploader': 'lex will',
4796 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4797 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4798 'channel': 'lex will',
4799 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4800 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4801 'tags': ['bible', 'history', 'prophesy'],
4802 'channel_follower_count': int
4804 'playlist_mincount': 17,
4806 'note': 'Community tab',
4807 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4809 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4810 'title': 'lex will - Community',
4811 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4812 'uploader': 'lex will',
4813 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4814 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4815 'channel': 'lex will',
4816 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4817 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4818 'tags': ['bible', 'history', 'prophesy'],
4819 'channel_follower_count': int
4821 'playlist_mincount': 18,
4823 'note': 'Channels tab',
4824 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4826 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4827 'title': 'lex will - Channels',
4828 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4829 'uploader': 'lex will',
4830 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4831 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4832 'channel': 'lex will',
4833 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4834 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4835 'tags': ['bible', 'history', 'prophesy'],
4836 'channel_follower_count': int
4838 'playlist_mincount': 12,
4840 'note': 'Search tab',
4841 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4842 'playlist_mincount': 40,
4844 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4845 'title': '3Blue1Brown - Search - linear algebra',
4846 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4847 'uploader': '3Blue1Brown',
4848 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4849 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4850 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4851 'tags': ['Mathematics'],
4852 'channel': '3Blue1Brown',
4853 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4854 'channel_follower_count': int
4857 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4858 'only_matching': True,
4860 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4861 'only_matching': True,
4863 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4864 'only_matching': True,
4866 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4867 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4869 'title': '29C3: Not my department',
4870 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4871 'uploader': 'Christiaan008',
4872 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4873 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4875 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4877 'modified_date': '20150605',
4878 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4879 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4880 'channel': 'Christiaan008',
4882 'playlist_count': 96,
4884 'note': 'Large playlist',
4885 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4887 'title': 'Uploads from Cauchemar',
4888 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4889 'uploader': 'Cauchemar',
4890 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4891 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4893 'modified_date': r
're:\d{8}',
4894 'channel': 'Cauchemar',
4895 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4898 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4900 'playlist_mincount': 1123,
4901 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4903 'note': 'even larger playlist, 8832 videos',
4904 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4905 'only_matching': True,
4907 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4908 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4910 'title': 'Uploads from Interstellar Movie',
4911 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4912 'uploader': 'Interstellar Movie',
4913 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4914 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4917 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4918 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4919 'channel': 'Interstellar Movie',
4921 'modified_date': r
're:\d{8}',
4923 'playlist_mincount': 21,
4925 'note': 'Playlist with "show unavailable videos" button',
4926 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4928 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4929 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4930 'uploader': 'Phim Siêu Nhân Nhật Bản',
4931 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4933 'channel': 'Phim Siêu Nhân Nhật Bản',
4935 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4937 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4938 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4939 'modified_date': r
're:\d{8}',
4941 'playlist_mincount': 200,
4942 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4944 'note': 'Playlist with unavailable videos in page 7',
4945 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
4947 'title': 'Uploads from BlankTV',
4948 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
4949 'uploader': 'BlankTV',
4950 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4951 'channel': 'BlankTV',
4952 'channel_url': 'https://www.youtube.com/c/blanktv',
4953 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
4956 'uploader_url': 'https://www.youtube.com/c/blanktv',
4957 'modified_date': r
're:\d{8}',
4960 'playlist_mincount': 1000,
4961 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4963 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
4964 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4966 'title': 'Data Analysis with Dr Mike Pound',
4967 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
4968 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4969 'uploader': 'Computerphile',
4970 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
4971 'uploader_url': 'https://www.youtube.com/user/Computerphile',
4974 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
4975 'channel_url': 'https://www.youtube.com/user/Computerphile',
4976 'channel': 'Computerphile',
4978 'playlist_mincount': 11,
4980 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4981 'only_matching': True,
4983 'note': 'Playlist URL that does not actually serve a playlist',
4984 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
4986 'id': 'FqZTN594JQw',
4988 'title': "Smiley's People 01 detective, Adventure Series, Action",
4989 'uploader': 'STREEM',
4990 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
4991 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
4992 'upload_date': '20150526',
4993 'license': 'Standard YouTube License',
4994 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
4995 'categories': ['People & Blogs'],
5001 'skip_download': True,
5003 'skip': 'This video is not available.',
5004 'add_ie': [YoutubeIE
.ie_key()],
5006 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5007 'only_matching': True,
5009 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5010 'only_matching': True,
5012 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5014 'id': 'GgL890LIznQ', # This will keep changing
5017 'uploader': 'Sky News',
5018 'uploader_id': 'skynews',
5019 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5020 'upload_date': r
're:\d{8}',
5022 'categories': ['News & Politics'],
5025 'release_timestamp': 1642502819,
5026 'channel': 'Sky News',
5027 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5030 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5031 'playable_in_embed': True,
5032 'release_date': '20220118',
5033 'availability': 'public',
5034 'live_status': 'is_live',
5035 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5036 'channel_follower_count': int
5039 'skip_download': True,
5041 'expected_warnings': ['Ignoring subtitle tracks found in '],
5043 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5045 'id': 'a48o2S1cPoo',
5047 'title': 'The Young Turks - Live Main Show',
5048 'uploader': 'The Young Turks',
5049 'uploader_id': 'TheYoungTurks',
5050 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5051 'upload_date': '20150715',
5052 'license': 'Standard YouTube License',
5053 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5054 'categories': ['News & Politics'],
5055 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5059 'skip_download': True,
5061 'only_matching': True,
5063 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5064 'only_matching': True,
5066 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5067 'only_matching': True,
5069 'note': 'A channel that is not live. Should raise error',
5070 'url': 'https://www.youtube.com/user/numberphile/live',
5071 'only_matching': True,
5073 'url': 'https://www.youtube.com/feed/trending',
5074 'only_matching': True,
5076 'url': 'https://www.youtube.com/feed/library',
5077 'only_matching': True,
5079 'url': 'https://www.youtube.com/feed/history',
5080 'only_matching': True,
5082 'url': 'https://www.youtube.com/feed/subscriptions',
5083 'only_matching': True,
5085 'url': 'https://www.youtube.com/feed/watch_later',
5086 'only_matching': True,
5088 'note': 'Recommended - redirects to home page.',
5089 'url': 'https://www.youtube.com/feed/recommended',
5090 'only_matching': True,
5092 'note': 'inline playlist with not always working continuations',
5093 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5094 'only_matching': True,
5096 'url': 'https://www.youtube.com/course',
5097 'only_matching': True,
5099 'url': 'https://www.youtube.com/zsecurity',
5100 'only_matching': True,
5102 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5103 'only_matching': True,
5105 'url': 'https://www.youtube.com/TheYoungTurks/live',
5106 'only_matching': True,
5108 'url': 'https://www.youtube.com/hashtag/cctv9',
5114 'playlist_mincount': 350,
5116 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5117 'only_matching': True,
5119 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5120 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5121 'only_matching': True
5123 'note': '/browse/ should redirect to /channel/',
5124 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5125 'only_matching': True
5127 'note': 'VLPL, should redirect to playlist?list=PL...',
5128 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5130 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5131 'uploader': 'NoCopyrightSounds',
5132 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5133 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5134 'title': 'NCS Releases',
5135 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5136 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5137 'modified_date': r
're:\d{8}',
5139 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5141 'channel': 'NoCopyrightSounds',
5143 'playlist_mincount': 166,
5144 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5146 'note': 'Topic, should redirect to playlist?list=UU...',
5147 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5149 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5150 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5151 'title': 'Uploads from Royalty Free Music - Topic',
5152 'uploader': 'Royalty Free Music - Topic',
5154 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5155 'channel': 'Royalty Free Music - Topic',
5157 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5158 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5159 'modified_date': r
're:\d{8}',
5160 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5163 'expected_warnings': [
5164 'The URL does not have a videos tab',
5165 r
'[Uu]navailable videos (are|will be) hidden',
5167 'playlist_mincount': 101,
5169 'note': 'Topic without a UU playlist',
5170 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5172 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5173 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5176 'expected_warnings': [
5177 'the playlist redirect gave error',
5179 'playlist_mincount': 9,
5181 'note': 'Youtube music Album',
5182 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5184 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5185 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5189 'availability': 'unlisted',
5190 'modified_date': r
're:\d{8}',
5192 'playlist_count': 50,
5194 'note': 'unlisted single video playlist',
5195 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5197 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5198 'uploader': 'colethedj',
5199 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5200 'title': 'yt-dlp unlisted playlist test',
5201 'availability': 'unlisted',
5203 'modified_date': '20211208',
5204 'channel': 'colethedj',
5207 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5208 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5209 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5211 'playlist_count': 1,
5213 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5214 'url': 'https://www.youtube.com/feed/recommended',
5216 'id': 'recommended',
5217 'title': 'recommended',
5220 'playlist_mincount': 50,
5222 'skip_download': True,
5223 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5226 'note': 'API Fallback: /videos tab, sorted by oldest first',
5227 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5229 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5230 'title': 'Cody\'sLab - Videos',
5231 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5232 'uploader': 'Cody\'sLab',
5233 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5234 'channel': 'Cody\'sLab',
5235 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5237 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5238 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5239 'channel_follower_count': int
5241 'playlist_mincount': 650,
5243 'skip_download': True,
5244 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5247 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5248 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5250 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5251 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5252 'title': 'Uploads from Royalty Free Music - Topic',
5253 'uploader': 'Royalty Free Music - Topic',
5254 'modified_date': r
're:\d{8}',
5255 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5257 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5259 'channel': 'Royalty Free Music - Topic',
5261 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5263 'expected_warnings': [
5264 'does not have a videos tab',
5265 r
'[Uu]navailable videos (are|will be) hidden',
5267 'playlist_mincount': 101,
5269 'skip_download': True,
5270 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5273 'note': 'non-standard redirect to regional channel',
5274 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5275 'only_matching': True
5277 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5278 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5280 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5281 'modified_date': '20220407',
5282 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5284 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5285 'uploader': 'pukkandan',
5286 'availability': 'unlisted',
5287 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5288 'channel': 'pukkandan',
5289 'description': 'Test for collaborative playlist',
5290 'title': 'yt-dlp test - collaborative playlist',
5291 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5293 'playlist_mincount': 2
5297 def suitable(cls
, url
):
5298 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5300 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5302 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5303 def _real_extract(self
, url
, smuggled_data
):
5304 item_id
= self
._match
_id
(url
)
5305 url
= compat_urlparse
.urlunparse(
5306 compat_urlparse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5307 compat_opts
= self
.get_param('compat_opts', [])
5310 mobj
= self
._URL
_RE
.match(url
).groupdict()
5311 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5314 mobj
, redirect_warning
= get_mobj(url
), None
5315 # Youtube returns incomplete data if tabname is not lower case
5316 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5318 if smuggled_data
.get('is_music_url'):
5319 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5320 item_id
= item_id
[2:]
5321 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5322 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5323 mdata
= self
._extract
_tab
_endpoint
(
5324 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5325 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5326 get_all
=False, expected_type
=compat_str
)
5328 raise ExtractorError('Failed to resolve album to playlist')
5329 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5330 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5331 pre
= f
'https://www.youtube.com/channel/{item_id}'
5333 original_tab_name
= tab
5334 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5335 # Home URLs should redirect to /videos/
5336 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5337 'To download only the videos in the home page, add a "/featured" to the URL')
5340 url
= ''.join((pre
, tab
, post
))
5341 mobj
= get_mobj(url
)
5343 # Handle both video/playlist URLs
5345 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5347 if not video_id
and mobj
['not_channel'].startswith('watch'):
5349 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5350 raise ExtractorError('Unable to recognize tab page')
5351 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5352 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5353 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5354 mobj
= get_mobj(url
)
5356 if video_id
and playlist_id
:
5357 if self
.get_param('noplaylist'):
5358 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5359 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5360 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5361 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5363 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5365 # YouTube may provide a non-standard redirect to the regional channel
5366 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5367 redirect_url
= traverse_obj(
5368 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5369 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5370 redirect_url
= ''.join((
5371 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5372 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5373 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5375 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5377 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5378 selected_tab_name
= selected_tab
.get('title', '').lower()
5379 if selected_tab_name
== 'home':
5380 selected_tab_name
= 'featured'
5381 requested_tab_name
= mobj
['tab'][1:]
5382 if 'no-youtube-channel-redirect' not in compat_opts
:
5383 if requested_tab_name
== 'live':
5384 # Live tab should have redirected to the video
5385 raise ExtractorError('The channel is not currently live', expected
=True)
5386 if requested_tab_name
not in ('', selected_tab_name
):
5387 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5388 if not original_tab_name
:
5389 if item_id
[:2] == 'UC':
5390 # Topic channels don't have /videos. Use the equivalent playlist instead
5391 pl_id
= f
'UU{item_id[2:]}'
5392 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5394 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5395 except ExtractorError
:
5396 redirect_warning
+= ' and the playlist redirect gave error'
5398 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5399 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5400 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5401 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5403 raise ExtractorError(redirect_warning
, expected
=True)
5405 if redirect_warning
:
5406 self
.to_screen(redirect_warning
)
5407 self
.write_debug(f
'Final URL: {url}')
5409 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5410 if 'no-youtube-unavailable-videos' not in compat_opts
:
5411 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5412 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5413 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5415 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5417 playlist
= traverse_obj(
5418 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5420 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5422 video_id
= traverse_obj(
5423 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5425 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5426 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5427 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5428 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5430 raise ExtractorError('Unable to recognize tab page')
5433 class YoutubePlaylistIE(InfoExtractor
):
5434 IE_DESC
= 'YouTube playlists'
5435 _VALID_URL
= r
'''(?x)(?:
5440 youtube(?:kids)?\.com|
5445 (?P<id>%(playlist_id)s)
5447 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5448 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5450 IE_NAME
= 'youtube:playlist'
5452 'note': 'issue #673',
5453 'url': 'PLBB231211A4F62143',
5455 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5456 'id': 'PLBB231211A4F62143',
5457 'uploader': 'Wickman',
5458 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5459 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5461 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5462 'modified_date': r
're:\d{8}',
5463 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5464 'channel': 'Wickman',
5466 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5468 'playlist_mincount': 29,
5470 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5472 'title': 'YDL_safe_search',
5473 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5475 'playlist_count': 2,
5476 'skip': 'This playlist is private',
5479 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5480 'playlist_count': 4,
5483 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5484 'uploader': 'milan',
5485 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5487 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5489 'modified_date': '20140919',
5492 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5493 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5495 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5497 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5498 'playlist_mincount': 654,
5500 'title': '2018 Chinese New Singles (11/6 updated)',
5501 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5503 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5504 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5507 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5509 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5510 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5511 'modified_date': r
're:\d{8}',
5513 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5515 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5516 'only_matching': True,
5518 # music album playlist
5519 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5520 'only_matching': True,
5524 def suitable(cls
, url
):
5525 if YoutubeTabIE
.suitable(url
):
5527 from ..utils
import parse_qs
5529 if qs
.get('v', [None])[0]:
5531 return super().suitable(url
)
5533 def _real_extract(self
, url
):
5534 playlist_id
= self
._match
_id
(url
)
5535 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5536 url
= update_url_query(
5537 'https://www.youtube.com/playlist',
5538 parse_qs(url
) or {'list': playlist_id}
)
5540 url
= smuggle_url(url
, {'is_music_url': True}
)
5541 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5544 class YoutubeYtBeIE(InfoExtractor
):
5545 IE_DESC
= 'youtu.be'
5546 _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}
5548 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5550 'id': 'yeWKywCrFtk',
5552 'title': 'Small Scale Baler and Braiding Rugs',
5553 'uploader': 'Backus-Page House Museum',
5554 'uploader_id': 'backuspagemuseum',
5555 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5556 'upload_date': '20161008',
5557 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5558 'categories': ['Nonprofits & Activism'],
5562 'playable_in_embed': True,
5563 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5564 'channel': 'Backus-Page House Museum',
5565 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5566 'live_status': 'not_live',
5568 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5569 'availability': 'public',
5574 'skip_download': True,
5577 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5578 'only_matching': True,
5581 def _real_extract(self
, url
):
5582 mobj
= self
._match
_valid
_url
(url
)
5583 video_id
= mobj
.group('id')
5584 playlist_id
= mobj
.group('playlist_id')
5585 return self
.url_result(
5586 update_url_query('https://www.youtube.com/watch', {
5588 'list': playlist_id
,
5589 'feature': 'youtu.be',
5590 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5593 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5594 IE_DESC
= 'YouTube livestream embeds'
5595 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5597 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5598 'only_matching': True,
5601 def _real_extract(self
, url
):
5602 channel_id
= self
._match
_id
(url
)
5603 return self
.url_result(
5604 f
'https://www.youtube.com/channel/{channel_id}/live',
5605 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5608 class YoutubeYtUserIE(InfoExtractor
):
5609 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5610 IE_NAME
= 'youtube:user'
5611 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5613 'url': 'ytuser:phihag',
5614 'only_matching': True,
5617 def _real_extract(self
, url
):
5618 user_id
= self
._match
_id
(url
)
5619 return self
.url_result(
5620 'https://www.youtube.com/user/%s/videos' % user_id
,
5621 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5624 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5625 IE_NAME
= 'youtube:favorites'
5626 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5627 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5628 _LOGIN_REQUIRED
= True
5631 'only_matching': True,
5633 'url': ':ytfavorites',
5634 'only_matching': True,
5637 def _real_extract(self
, url
):
5638 return self
.url_result(
5639 'https://www.youtube.com/playlist?list=LL',
5640 ie
=YoutubeTabIE
.ie_key())
5643 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5644 IE_NAME
= 'youtube:notif'
5645 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5646 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5647 _LOGIN_REQUIRED
= True
5650 'only_matching': True,
5652 'url': ':ytnotifications',
5653 'only_matching': True,
5656 def _extract_notification_menu(self
, response
, continuation_list
):
5657 notification_list
= traverse_obj(
5659 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5660 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5661 expected_type
=list) or []
5662 continuation_list
[0] = None
5663 for item
in notification_list
:
5664 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5667 continuation
= item
.get('continuationItemRenderer')
5669 continuation_list
[0] = continuation
5671 def _extract_notification_renderer(self
, notification
):
5672 video_id
= traverse_obj(
5673 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5674 url
= f
'https://www.youtube.com/watch?v={video_id}'
5677 browse_ep
= traverse_obj(
5678 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5679 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5680 post_id
= self
._search
_regex
(
5681 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5682 'post id', default
=None)
5683 if not channel_id
or not post_id
:
5685 # The direct /post url redirects to this in the browser
5686 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5688 channel
= traverse_obj(
5689 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5691 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5692 if notification_title
:
5693 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5694 # TODO: handle recommended videos
5695 title
= self
._search
_regex
(
5696 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5697 'video title', default
=None)
5698 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5699 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5704 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5705 'video_id': video_id
,
5707 'channel_id': channel_id
,
5709 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5710 'upload_date': upload_date
,
5713 def _notification_menu_entries(self
, ytcfg
):
5714 continuation_list
= [None]
5716 for page
in itertools
.count(1):
5717 ctoken
= traverse_obj(
5718 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5719 response
= self
._extract
_response
(
5720 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5721 ep
='notification/get_notification_menu', check_get_keys
='actions',
5722 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5723 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5724 if not continuation_list
[0]:
5727 def _real_extract(self
, url
):
5728 display_id
= 'notifications'
5729 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5730 self
._report
_playlist
_authcheck
(ytcfg
)
5731 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5734 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5735 IE_DESC
= 'YouTube search'
5736 IE_NAME
= 'youtube:search'
5737 _SEARCH_KEY
= 'ytsearch'
5738 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5740 'url': 'ytsearch5:youtube-dl test video',
5741 'playlist_count': 5,
5743 'id': 'youtube-dl test video',
5744 'title': 'youtube-dl test video',
5749 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5750 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5751 _SEARCH_KEY
= 'ytsearchdate'
5752 IE_DESC
= 'YouTube search, newest videos first'
5753 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5755 'url': 'ytsearchdate5:youtube-dl test video',
5756 'playlist_count': 5,
5758 'id': 'youtube-dl test video',
5759 'title': 'youtube-dl test video',
5764 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5765 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5766 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5767 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5769 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5770 'playlist_mincount': 5,
5772 'id': 'youtube-dl test video',
5773 'title': 'youtube-dl test video',
5776 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5777 'playlist_mincount': 5,
5783 'url': 'https://www.youtube.com/results?search_query=%23cats',
5784 'playlist_mincount': 1,
5789 'url': r
're:https://(www\.)?youtube\.com/hashtag/cats',
5794 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5795 'only_matching': True,
5798 def _real_extract(self
, url
):
5800 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5801 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5804 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5805 IE_DESC
= 'YouTube music search URLs with selectable sections (Eg: #songs)'
5806 IE_NAME
= 'youtube:music:search_url'
5807 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5809 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5810 'playlist_count': 16,
5812 'id': 'royalty free music',
5813 'title': 'royalty free music',
5816 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5817 'playlist_mincount': 30,
5819 'id': 'royalty free music - songs',
5820 'title': 'royalty free music - songs',
5822 'params': {'extract_flat': 'in_playlist'}
5824 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5825 'playlist_mincount': 30,
5827 'id': 'royalty free music - community playlists',
5828 'title': 'royalty free music - community playlists',
5830 'params': {'extract_flat': 'in_playlist'}
5834 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5835 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5836 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5837 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5838 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5839 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5842 def _real_extract(self
, url
):
5844 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5845 params
= qs
.get('sp', (None,))[0]
5847 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5849 section
= compat_urllib_parse_unquote_plus((url
.split('#') + [''])[1]).lower()
5850 params
= self
._SECTIONS
.get(section
)
5853 title
= join_nonempty(query
, section
, delim
=' - ')
5854 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5857 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5859 Base class for feed extractors
5860 Subclasses must re-define the _FEED_NAME property.
5862 _LOGIN_REQUIRED
= True
5863 _FEED_NAME
= 'feeds'
5865 def _real_initialize(self
):
5866 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
5870 return f
'youtube:{self._FEED_NAME}'
5872 def _real_extract(self
, url
):
5873 return self
.url_result(
5874 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
5877 class YoutubeWatchLaterIE(InfoExtractor
):
5878 IE_NAME
= 'youtube:watchlater'
5879 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5880 _VALID_URL
= r
':ytwatchlater'
5882 'url': ':ytwatchlater',
5883 'only_matching': True,
5886 def _real_extract(self
, url
):
5887 return self
.url_result(
5888 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
5891 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
5892 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
5893 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5894 _FEED_NAME
= 'recommended'
5895 _LOGIN_REQUIRED
= False
5898 'only_matching': True,
5900 'url': ':ytrecommended',
5901 'only_matching': True,
5903 'url': 'https://youtube.com',
5904 'only_matching': True,
5908 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
5909 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5910 _VALID_URL
= r
':ytsub(?:scription)?s?'
5911 _FEED_NAME
= 'subscriptions'
5914 'only_matching': True,
5916 'url': ':ytsubscriptions',
5917 'only_matching': True,
5921 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
5922 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
5923 _VALID_URL
= r
':ythis(?:tory)?'
5924 _FEED_NAME
= 'history'
5926 'url': ':ythistory',
5927 'only_matching': True,
5931 class YoutubeStoriesIE(InfoExtractor
):
5932 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
5933 IE_NAME
= 'youtube:stories'
5934 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
5936 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
5937 'only_matching': True,
5940 def _real_extract(self
, url
):
5941 playlist_id
= f
'RLTD{self._match_id(url)}'
5942 return self
.url_result(
5943 f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
5944 ie
=YoutubeTabIE
, video_id
=playlist_id
)
5947 class YoutubeTruncatedURLIE(InfoExtractor
):
5948 IE_NAME
= 'youtube:truncated_url'
5949 IE_DESC
= False # Do not list
5950 _VALID_URL
= r
'''(?x)
5952 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
5955 annotation_id=annotation_[^&]+|
5961 attribution_link\?a=[^&]+
5967 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
5968 'only_matching': True,
5970 'url': 'https://www.youtube.com/watch?',
5971 'only_matching': True,
5973 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
5974 'only_matching': True,
5976 'url': 'https://www.youtube.com/watch?feature=foo',
5977 'only_matching': True,
5979 'url': 'https://www.youtube.com/watch?hl=en-GB',
5980 'only_matching': True,
5982 'url': 'https://www.youtube.com/watch?t=2372',
5983 'only_matching': True,
5986 def _real_extract(self
, url
):
5987 raise ExtractorError(
5988 'Did you forget to quote the URL? Remember that & is a meta '
5989 'character in most shells, so you want to put the URL in quotes, '
5991 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
5992 ' or simply youtube-dl BaW_jenozKc .',
5996 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
5997 IE_NAME
= 'youtube:clip'
5998 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6000 # FIXME: Other metadata should be extracted from the clip, not from the base video
6001 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6003 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6005 'section_start': 29.0,
6006 'section_end': 39.7,
6011 def _real_extract(self
, url
):
6012 clip_id
= self
._match
_id
(url
)
6013 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6015 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6017 raise ExtractorError('Unable to find video ID')
6019 clip_data
= traverse_obj(data
, (
6020 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6021 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6022 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6023 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6026 '_type': 'url_transparent',
6027 'url': f
'https://www.youtube.com/watch?v={video_id}',
6028 'ie_key': YoutubeIE
.ie_key(),
6030 'section_start': int(clip_data
['startTimeMs']) / 1000,
6031 'section_end': int(clip_data
['endTimeMs']) / 1000,
6035 class YoutubeTruncatedIDIE(InfoExtractor
):
6036 IE_NAME
= 'youtube:truncated_id'
6037 IE_DESC
= False # Do not list
6038 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6041 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6042 'only_matching': True,
6045 def _real_extract(self
, url
):
6046 video_id
= self
._match
_id
(url
)
6047 raise ExtractorError(
6048 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',