19 from .common
import InfoExtractor
, SearchInfoExtractor
20 from .openload
import PhantomJSwrapper
21 from ..compat
import functools
22 from ..jsinterp
import JSInterpreter
65 # any clients starting with _ cannot be explicitly requested by the user
68 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
69 'INNERTUBE_CONTEXT': {
72 'clientVersion': '2.20220801.00.00',
75 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
78 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
79 'INNERTUBE_CONTEXT': {
81 'clientName': 'WEB_EMBEDDED_PLAYER',
82 'clientVersion': '1.20220731.00.00',
85 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
88 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
89 'INNERTUBE_HOST': 'music.youtube.com',
90 'INNERTUBE_CONTEXT': {
92 'clientName': 'WEB_REMIX',
93 'clientVersion': '1.20220727.01.00',
96 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
99 'INNERTUBE_API_KEY': 'AIzaSyBUPetSUmoZL-OhlxA7wSac5XinrygCqMo',
100 'INNERTUBE_CONTEXT': {
102 'clientName': 'WEB_CREATOR',
103 'clientVersion': '1.20220726.00.00',
106 'INNERTUBE_CONTEXT_CLIENT_NAME': 62,
109 'INNERTUBE_API_KEY': 'AIzaSyA8eiZmM1FaDVjRy-df2KTyQ_vz_yYM39w',
110 'INNERTUBE_CONTEXT': {
112 'clientName': 'ANDROID',
113 'clientVersion': '17.29.34',
114 'androidSdkVersion': 30
117 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
118 'REQUIRE_JS_PLAYER': False
120 'android_embedded': {
121 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
122 'INNERTUBE_CONTEXT': {
124 'clientName': 'ANDROID_EMBEDDED_PLAYER',
125 'clientVersion': '17.29.34',
126 'androidSdkVersion': 30
129 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
130 'REQUIRE_JS_PLAYER': False
133 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
134 'INNERTUBE_CONTEXT': {
136 'clientName': 'ANDROID_MUSIC',
137 'clientVersion': '5.16.51',
138 'androidSdkVersion': 30
141 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
142 'REQUIRE_JS_PLAYER': False
145 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
146 'INNERTUBE_CONTEXT': {
148 'clientName': 'ANDROID_CREATOR',
149 'clientVersion': '22.28.100',
150 'androidSdkVersion': 30
153 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
154 'REQUIRE_JS_PLAYER': False
156 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
157 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
159 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
160 'INNERTUBE_CONTEXT': {
163 'clientVersion': '17.30.1',
164 'deviceModel': 'iPhone14,3',
167 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
168 'REQUIRE_JS_PLAYER': False
171 'INNERTUBE_CONTEXT': {
173 'clientName': 'IOS_MESSAGES_EXTENSION',
174 'clientVersion': '17.30.1',
175 'deviceModel': 'iPhone14,3',
178 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
179 'REQUIRE_JS_PLAYER': False
182 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
183 'INNERTUBE_CONTEXT': {
185 'clientName': 'IOS_MUSIC',
186 'clientVersion': '5.18',
189 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
190 'REQUIRE_JS_PLAYER': False
193 'INNERTUBE_CONTEXT': {
195 'clientName': 'IOS_CREATOR',
196 'clientVersion': '22.29.101',
199 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
200 'REQUIRE_JS_PLAYER': False
202 # mweb has 'ultralow' formats
203 # See: https://github.com/yt-dlp/yt-dlp/pull/557
205 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
206 'INNERTUBE_CONTEXT': {
208 'clientName': 'MWEB',
209 'clientVersion': '2.20220801.00.00',
212 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
214 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
215 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
217 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
218 'INNERTUBE_CONTEXT': {
220 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
221 'clientVersion': '2.0',
224 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
229 def _split_innertube_client(client_name
):
230 variant
, *base
= client_name
.rsplit('.', 1)
232 return variant
, base
[0], variant
233 base
, *variant
= client_name
.split('_', 1)
234 return client_name
, base
, variant
[0] if variant
else None
237 def build_innertube_clients():
239 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
241 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
242 priority
= qualities(BASE_CLIENTS
[::-1])
244 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
245 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
246 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
247 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
248 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
250 _
, base_client
, variant
= _split_innertube_client(client
)
251 ytcfg
['priority'] = 10 * priority(base_client
)
254 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
255 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
256 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
257 embedscreen
['priority'] -= 3
258 elif variant
== 'embedded':
259 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
260 ytcfg
['priority'] -= 2
262 ytcfg
['priority'] -= 3
265 build_innertube_clients()
268 class YoutubeBaseInfoExtractor(InfoExtractor
):
269 """Provide base functions for Youtube extractors"""
272 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
273 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
274 r
'browse|oembed|get_video_info|iframe_api|s/player|'
275 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
277 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
279 # _NETRC_MACHINE = 'youtube'
281 # If True it will raise an error if no login info is provided
282 _LOGIN_REQUIRED
= False
285 # invidious-redirect websites
286 r
'(?:www\.)?redirect\.invidious\.io',
287 r
'(?:(?:www|dev)\.)?invidio\.us',
288 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
289 r
'(?:www\.)?invidious\.pussthecat\.org',
290 r
'(?:www\.)?invidious\.zee\.li',
291 r
'(?:www\.)?invidious\.ethibox\.fr',
292 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
293 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
294 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
295 # youtube-dl invidious instances list
296 r
'(?:(?:www|no)\.)?invidiou\.sh',
297 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
298 r
'(?:www\.)?invidious\.kabi\.tk',
299 r
'(?:www\.)?invidious\.mastodon\.host',
300 r
'(?:www\.)?invidious\.zapashcanon\.fr',
301 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
302 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
303 r
'(?:www\.)?invidious\.himiko\.cloud',
304 r
'(?:www\.)?invidious\.reallyancient\.tech',
305 r
'(?:www\.)?invidious\.tube',
306 r
'(?:www\.)?invidiou\.site',
307 r
'(?:www\.)?invidious\.site',
308 r
'(?:www\.)?invidious\.xyz',
309 r
'(?:www\.)?invidious\.nixnet\.xyz',
310 r
'(?:www\.)?invidious\.048596\.xyz',
311 r
'(?:www\.)?invidious\.drycat\.fr',
312 r
'(?:www\.)?inv\.skyn3t\.in',
313 r
'(?:www\.)?tube\.poal\.co',
314 r
'(?:www\.)?tube\.connect\.cafe',
315 r
'(?:www\.)?vid\.wxzm\.sx',
316 r
'(?:www\.)?vid\.mint\.lgbt',
317 r
'(?:www\.)?vid\.puffyan\.us',
318 r
'(?:www\.)?yewtu\.be',
319 r
'(?:www\.)?yt\.elukerio\.org',
320 r
'(?:www\.)?yt\.lelux\.fi',
321 r
'(?:www\.)?invidious\.ggc-project\.de',
322 r
'(?:www\.)?yt\.maisputain\.ovh',
323 r
'(?:www\.)?ytprivate\.com',
324 r
'(?:www\.)?invidious\.13ad\.de',
325 r
'(?:www\.)?invidious\.toot\.koeln',
326 r
'(?:www\.)?invidious\.fdn\.fr',
327 r
'(?:www\.)?watch\.nettohikari\.com',
328 r
'(?:www\.)?invidious\.namazso\.eu',
329 r
'(?:www\.)?invidious\.silkky\.cloud',
330 r
'(?:www\.)?invidious\.exonip\.de',
331 r
'(?:www\.)?invidious\.riverside\.rocks',
332 r
'(?:www\.)?invidious\.blamefran\.net',
333 r
'(?:www\.)?invidious\.moomoo\.de',
334 r
'(?:www\.)?ytb\.trom\.tf',
335 r
'(?:www\.)?yt\.cyberhost\.uk',
336 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
337 r
'(?:www\.)?qklhadlycap4cnod\.onion',
338 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
339 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
340 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
341 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
342 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
343 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
344 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
345 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
346 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
347 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
348 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
349 r
'(?:www\.)?piped\.kavin\.rocks',
350 r
'(?:www\.)?piped\.silkky\.cloud',
351 r
'(?:www\.)?piped\.tokhmi\.xyz',
352 r
'(?:www\.)?piped\.moomoo\.me',
354 r
'(?:www\.)?piped\.syncpundit\.com',
355 r
'(?:www\.)?piped\.mha\.fi',
356 r
'(?:www\.)?piped\.mint\.lgbt',
357 r
'(?:www\.)?piped\.privacy\.com\.de',
360 def _initialize_consent(self
):
361 cookies
= self
._get
_cookies
('https://www.youtube.com/')
362 if cookies
.get('__Secure-3PSID'):
365 consent
= cookies
.get('CONSENT')
367 if 'YES' in consent
.value
:
369 consent_id
= self
._search
_regex
(
370 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
372 consent_id
= random
.randint(100, 999)
373 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
375 def _initialize_pref(self
):
376 cookies
= self
._get
_cookies
('https://www.youtube.com/')
377 pref_cookie
= cookies
.get('PREF')
381 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
383 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
384 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
385 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
387 def _real_initialize(self
):
388 self
._initialize
_pref
()
389 self
._initialize
_consent
()
390 self
._check
_login
_required
()
392 def _check_login_required(self
):
393 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
394 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
396 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
397 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
399 def _get_default_ytcfg(self, client='web'):
400 return copy.deepcopy(INNERTUBE_CLIENTS[client])
402 def _get_innertube_host(self, client='web'):
403 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
405 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
406 # try_get but with fallback to default ytcfg client values when present
407 _func = lambda y: try_get(y, getter, expected_type)
408 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
410 def _extract_client_name(self, ytcfg, default_client='web'):
411 return self._ytcfg_get_safe(
412 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
413 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
415 def _extract_client_version(self, ytcfg, default_client='web'):
416 return self._ytcfg_get_safe(
417 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
418 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
420 def _select_api_hostname(self, req_api_hostname, default_client=None):
421 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
422 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
424 def _extract_api_key(self, ytcfg=None, default_client='web'):
425 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
427 def _extract_context(self, ytcfg=None, default_client='web'):
429 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
430 # Enforce language and tz for extraction
431 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
432 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
437 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
438 time_now = round(time.time())
439 if self._SAPISID is None:
440 yt_cookies = self._get_cookies('https://www.youtube.com')
441 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
442 # See: https://github.com/yt-dlp/yt-dlp/issues/393
443 sapisid_cookie = dict_get(
444 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
445 if sapisid_cookie and sapisid_cookie.value:
446 self._SAPISID = sapisid_cookie.value
447 self.write_debug('Extracted SAPISID cookie')
448 # SAPISID cookie is required if not already present
449 if not yt_cookies.get('SAPISID'):
450 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
452 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
454 self._SAPISID = False
455 if not self._SAPISID:
457 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
458 sapisidhash = hashlib.sha1(
459 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
460 return f'SAPISIDHASH {time_now}_{sapisidhash}'
462 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
463 note='Downloading API JSON', errnote='Unable to download API page',
464 context=None, api_key=None, api_hostname=None, default_client='web'):
466 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
468 real_headers = self.generate_api_headers(default_client=default_client)
469 real_headers.update({'content-type': 'application/json'})
471 real_headers.update(headers)
472 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
473 or api_key or self._extract_api_key(default_client=default_client))
474 return self._download_json(
475 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
476 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
477 data=json.dumps(data).encode('utf8'), headers=real_headers,
478 query={'key': api_key, 'prettyPrint': 'false'})
480 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
481 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
484 def _extract_session_index(*data):
486 Index of current account in account list.
487 See: https://github.com/yt-dlp/yt-dlp/pull/519
490 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
491 if session_index is not None:
495 def _extract_identity_token(self, ytcfg=None, webpage=None):
497 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
501 return self._search_regex(
502 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
503 'identity token
', default=None, fatal=False)
506 def _extract_account_syncid(*args):
508 Extract syncId required to download private playlists of secondary channels
509 @params response and/or ytcfg
512 # ytcfg includes channel_syncid if on secondary channel
513 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
517 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
518 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
519 if len(sync_ids) >= 2 and sync_ids[1]:
520 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
521 # and just "user_syncid||" for primary channel. We only want the channel_syncid
525 def _extract_visitor_data(*args):
527 Extracts visitorData from an API response or ytcfg
528 Appears to be used to track session state
531 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
534 @functools.cached_property
535 def is_authenticated(self):
536 return bool(self._generate_sapisidhash_header())
538 def extract_ytcfg(self, video_id, webpage):
541 return self._parse_json(
543 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
544 default='{}'), video_id, fatal=False) or {}
546 def generate_api_headers(
547 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
548 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
550 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
552 'X-YouTube-Client-Name': str(
553 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
554 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
556 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
557 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
558 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
)
560 if session_index
is None:
561 session_index
= self
._extract
_session
_index
(ytcfg
)
562 if account_syncid
or session_index
is not None:
563 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
565 auth
= self
._generate
_sapisidhash
_header
(origin
)
567 headers
['Authorization'] = auth
568 headers
['X-Origin'] = origin
569 return {h: v for h, v in headers.items() if v is not None}
571 def _download_ytcfg(self
, client
, video_id
):
573 'web': 'https://www.youtube.com',
574 'web_music': 'https://music.youtube.com',
575 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
579 webpage
= self
._download
_webpage
(
580 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
581 return self
.extract_ytcfg(video_id
, webpage
) or {}
584 def _build_api_continuation_query(continuation
, ctp
=None):
586 'continuation': continuation
588 # TODO: Inconsistency with clickTrackingParams.
589 # Currently we have a fixed ctp contained within context (from ytcfg)
590 # and a ctp in root query for continuation.
592 query
['clickTracking'] = {'clickTrackingParams': ctp}
596 def _extract_next_continuation_data(cls
, renderer
):
597 next_continuation
= try_get(
598 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
599 lambda x
: x
['continuation']['reloadContinuationData']), dict)
600 if not next_continuation
:
602 continuation
= next_continuation
.get('continuation')
605 ctp
= next_continuation
.get('clickTrackingParams')
606 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
609 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
610 if isinstance(continuation_ep
, dict):
611 continuation
= try_get(
612 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
615 ctp
= continuation_ep
.get('clickTrackingParams')
616 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
619 def _extract_continuation(cls
, renderer
):
620 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
621 if next_continuation
:
622 return next_continuation
625 for key
in ('contents', 'items'):
626 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
628 for content
in contents
:
629 if not isinstance(content
, dict):
631 continuation_ep
= try_get(
632 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
633 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
635 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
640 def _extract_alerts(cls
, data
):
641 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
642 if not isinstance(alert_dict
, dict):
644 for alert
in alert_dict
.values():
645 alert_type
= alert
.get('type')
648 message
= cls
._get
_text
(alert
, 'text')
650 yield alert_type
, message
652 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
655 for alert_type
, alert_message
in alerts
:
656 if alert_type
.lower() == 'error' and fatal
:
657 errors
.append([alert_type
, alert_message
])
659 warnings
.append([alert_type
, alert_message
])
661 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
662 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
664 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
666 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
667 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
669 def _extract_badges(self
, renderer
: dict):
671 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
672 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], str)
674 badges
.add(label
.lower())
678 def _get_text(data
, *path_list
, max_runs
=None):
679 for path
in path_list
or [None]:
683 obj
= traverse_obj(data
, path
, default
=[])
684 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
687 text
= try_get(item
, lambda x
: x
['simpleText'], str)
690 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
691 if not runs
and isinstance(item
, list):
694 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
695 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
699 def _get_count(self
, data
, *path_list
):
700 count_text
= self
._get
_text
(data
, *path_list
) or ''
701 count
= parse_count(count_text
)
704 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
708 def _extract_thumbnails(data
, *path_list
):
710 Extract thumbnails from thumbnails dict
711 @param path_list: path list to level that contains 'thumbnails' key
714 for path
in path_list
or [()]:
715 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
716 thumbnail_url
= url_or_none(thumbnail
.get('url'))
717 if not thumbnail_url
:
719 # Sometimes youtube gives a wrong thumbnail URL. See:
720 # https://github.com/yt-dlp/yt-dlp/issues/233
721 # https://github.com/ytdl-org/youtube-dl/issues/28023
722 if 'maxresdefault' in thumbnail_url
:
723 thumbnail_url
= thumbnail_url
.split('?')[0]
725 'url': thumbnail_url
,
726 'height': int_or_none(thumbnail
.get('height')),
727 'width': int_or_none(thumbnail
.get('width')),
732 def extract_relative_time(relative_time_text
):
734 Extracts a relative time from string and converts to dt object
735 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
737 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
)
739 start
= mobj
.group('start')
741 return datetime_from_str(start
)
743 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
747 def _extract_time_text(self
, renderer
, *path_list
):
748 """@returns (timestamp, time_text)"""
749 text
= self
._get
_text
(renderer
, *path_list
) or ''
750 dt
= self
.extract_relative_time(text
)
752 if isinstance(dt
, datetime
.datetime
):
753 timestamp
= calendar
.timegm(dt
.timetuple())
755 if timestamp
is None:
757 unified_timestamp(text
) or unified_timestamp(
759 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
760 text
.lower(), 'time text', default
=None)))
762 if text
and timestamp
is None:
763 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
764 return timestamp
, text
766 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
767 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
768 default_client
='web'):
769 for retry
in self
.RetryManager():
771 response
= self
._call
_api
(
772 ep
=ep
, fatal
=True, headers
=headers
,
773 video_id
=item_id
, query
=query
, note
=note
,
774 context
=self
._extract
_context
(ytcfg
, default_client
),
775 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
776 api_hostname
=api_hostname
, default_client
=default_client
)
777 except ExtractorError
as e
:
778 if not isinstance(e
.cause
, network_exceptions
):
779 return self
._error
_or
_warning
(e
, fatal
=fatal
)
780 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
784 first_bytes
= e
.cause
.read(512)
785 if not is_html(first_bytes
):
788 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
789 lambda x
: x
['error']['message'], str)
791 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
792 # Downloading page may result in intermittent 5xx HTTP error
793 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
794 # We also want to catch all other network exceptions since errors in later pages can be troublesome
795 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
796 if e
.cause
.code
not in (403, 429):
799 return self
._error
_or
_warning
(e
, fatal
=fatal
)
802 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
803 except ExtractorError
as e
:
804 # YouTube servers may return errors we want to retry on in a 200 OK response
805 # See: https://github.com/yt-dlp/yt-dlp/issues/839
806 if 'unknown error' in e
.msg
.lower():
809 return self
._error
_or
_warning
(e
, fatal
=fatal
)
810 # Youtube sometimes sends incomplete data
811 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
812 if not traverse_obj(response
, *variadic(check_get_keys
)):
813 retry
.error
= ExtractorError('Incomplete data received', expected
=True)
819 def is_music_url(url
):
820 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
822 def _extract_video(self
, renderer
):
823 video_id
= renderer
.get('videoId')
824 title
= self
._get
_text
(renderer
, 'title')
825 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
826 duration
= parse_duration(self
._get
_text
(
827 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
829 duration
= parse_duration(self
._search
_regex
(
830 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
831 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
832 video_id
, default
=None, group
='duration'))
834 view_count
= self
._get
_count
(renderer
, 'viewCountText')
836 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
837 channel_id
= traverse_obj(
838 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
839 expected_type
=str, get_all
=False)
840 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
841 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
842 overlay_style
= traverse_obj(
843 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
844 get_all
=False, expected_type
=str)
845 badges
= self
._extract
_badges
(renderer
)
846 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
847 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
848 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
849 expected_type
=str)) or ''
850 url
= f
'https://www.youtube.com/watch?v={video_id}'
851 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
852 url
= f
'https://www.youtube.com/shorts/{video_id}'
856 'ie_key': YoutubeIE
.ie_key(),
860 'description': description
,
861 'duration': duration
,
862 'view_count': view_count
,
863 'uploader': uploader
,
864 'channel_id': channel_id
,
865 'thumbnails': thumbnails
,
866 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
867 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
869 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
870 else 'was_live' if 'streamed' in time_text
.lower()
871 else 'is_live' if overlay_style
== 'LIVE' or 'live now' in badges
873 'release_timestamp': scheduled_timestamp
,
874 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
878 class YoutubeIE(YoutubeBaseInfoExtractor
):
880 _VALID_URL
= r
"""(?x)^
882 (?:https?://|//) # http(s):// or protocol-independent URL
883 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
884 (?:www\.)?deturl\.com/www\.youtube\.com|
885 (?:www\.)?pwnyoutube\.com|
886 (?:www\.)?hooktube\.com|
887 (?:www\.)?yourepeat\.com|
890 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
891 (?:.*?\#/)? # handle anchor (#/) redirect urls
892 (?: # the various things that can precede the ID:
893 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
894 |(?: # or the v= param in all its forms
895 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
896 (?:\?|\#!?) # the params delimiter ? or # or #!
897 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
902 youtu\.be| # just youtu.be/xxxx
903 vid\.plus| # or vid.plus/xxxx
904 zwearz\.com/watch| # or zwearz.com/watch/xxxx
907 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
909 )? # all until now is optional -> you can pass the naked ID
910 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
911 (?(1).+)? # if we found the ID, everything can follow
913 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
915 _EMBED_REGEX
= [r
'''(?x)
925 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
926 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
929 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
930 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$',
931 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
934 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
935 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
936 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
937 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
938 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
939 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
940 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
941 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
942 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
943 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
944 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
945 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
946 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
947 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
948 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
949 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
950 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
951 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
955 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
956 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
957 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
958 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
959 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
960 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
961 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
963 # Apple HTTP Live Streaming
964 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
965 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
966 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
967 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
968 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
969 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
970 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
971 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
974 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
975 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
976 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
977 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
978 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
979 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
980 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
981 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
984 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
985 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
989 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
990 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
991 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
992 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
993 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
994 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
997 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
998 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
999 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1000 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1001 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1002 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1003 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1004 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1005 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1006 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1007 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1008 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1009 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1010 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1011 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1013 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1015 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1016 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1017 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1021 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1022 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1024 # Dash webm audio with opus inside
1025 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1026 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1027 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1030 '_rtmp': {'protocol': 'rtmp'},
1032 # av01 video only formats sometimes served with "unknown" codecs
1033 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1034 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1035 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1036 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1037 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1038 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1039 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1040 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1042 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1049 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1051 'id': 'BaW_jenozKc',
1053 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1054 'uploader': 'Philipp Hagemeister',
1055 'uploader_id': 'phihag',
1056 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1057 'channel': 'Philipp Hagemeister',
1058 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1059 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1060 'upload_date': '20121002',
1061 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1062 'categories': ['Science & Technology'],
1063 'tags': ['youtube-dl'],
1067 'availability': 'public',
1068 'playable_in_embed': True,
1069 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1070 'live_status': 'not_live',
1074 'comment_count': int,
1075 'channel_follower_count': int
1079 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1080 'note': 'Embed-only video (#1746)',
1082 'id': 'yZIXLfi8CZQ',
1084 'upload_date': '20120608',
1085 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1086 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1087 'uploader': 'SET India',
1088 'uploader_id': 'setindia',
1089 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1092 'skip': 'Private video',
1095 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1096 'note': 'Use the first video ID in the URL',
1098 'id': 'BaW_jenozKc',
1100 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1101 'uploader': 'Philipp Hagemeister',
1102 'uploader_id': 'phihag',
1103 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1104 'channel': 'Philipp Hagemeister',
1105 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1106 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1107 'upload_date': '20121002',
1108 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1109 'categories': ['Science & Technology'],
1110 'tags': ['youtube-dl'],
1114 'availability': 'public',
1115 'playable_in_embed': True,
1116 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1117 'live_status': 'not_live',
1119 'comment_count': int,
1120 'channel_follower_count': int
1123 'skip_download': True,
1127 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1128 'note': '256k DASH audio (format 141) via DASH manifest',
1130 'id': 'a9LDPn-MO4I',
1132 'upload_date': '20121002',
1133 'uploader_id': '8KVIDEO',
1134 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1136 'uploader': '8KVIDEO',
1137 'title': 'UHDTV TEST 8K VIDEO.mp4'
1140 'youtube_include_dash_manifest': True,
1143 'skip': 'format 141 not served anymore',
1145 # DASH manifest with encrypted signature
1147 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1149 'id': 'IB3lcPjvWLA',
1151 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1152 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1154 'uploader': 'AfrojackVEVO',
1155 'uploader_id': 'AfrojackVEVO',
1156 'upload_date': '20131011',
1159 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1160 'playable_in_embed': True,
1161 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1163 'track': 'The Spark',
1164 'live_status': 'not_live',
1165 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1166 'channel': 'Afrojack',
1167 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1169 'availability': 'public',
1170 'categories': ['Music'],
1172 'alt_title': 'The Spark',
1173 'channel_follower_count': int
1176 'youtube_include_dash_manifest': True,
1177 'format': '141/bestaudio[ext=m4a]',
1180 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1182 'note': 'Embed allowed age-gate video',
1183 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1185 'id': 'HtVdAasjOgU',
1187 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1188 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1190 'uploader': 'The Witcher',
1191 'uploader_id': 'WitcherGame',
1192 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1193 'upload_date': '20140605',
1195 'categories': ['Gaming'],
1196 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1197 'availability': 'needs_auth',
1198 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1200 'channel': 'The Witcher',
1201 'live_status': 'not_live',
1203 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1204 'playable_in_embed': True,
1206 'channel_follower_count': int
1210 'note': 'Age-gate video with embed allowed in public site',
1211 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1213 'id': 'HsUATh_Nc2U',
1215 'title': 'Godzilla 2 (Official Video)',
1216 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1217 'upload_date': '20200408',
1218 'uploader_id': 'FlyingKitty900',
1219 'uploader': 'FlyingKitty',
1221 'availability': 'needs_auth',
1222 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1223 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1224 'channel': 'FlyingKitty',
1225 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1227 'categories': ['Entertainment'],
1228 'live_status': 'not_live',
1229 'tags': ['Flyingkitty', 'godzilla 2'],
1230 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1233 'playable_in_embed': True,
1234 'channel_follower_count': int
1238 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1239 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1241 'id': 'Tq92D6wQ1mg',
1242 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1244 'upload_date': '20191228',
1245 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1246 'uploader': 'Projekt Melody',
1247 'description': 'md5:17eccca93a786d51bc67646756894066',
1250 'availability': 'needs_auth',
1251 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1252 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1254 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1255 'channel': 'Projekt Melody',
1256 'live_status': 'not_live',
1257 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1258 'playable_in_embed': True,
1259 'categories': ['Entertainment'],
1261 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1262 'comment_count': int,
1263 'channel_follower_count': int
1267 'note': 'Non-Agegated non-embeddable video',
1268 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1270 'id': 'MeJVWBSsPAY',
1272 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1273 'uploader': 'Herr Lurik',
1274 'uploader_id': 'st3in234',
1275 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1276 'upload_date': '20130730',
1277 'track': 'Such mich find mich',
1279 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1281 'playable_in_embed': False,
1282 'creator': 'OOMPH!',
1283 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1285 'alt_title': 'Such mich find mich',
1287 'channel': 'Herr Lurik',
1288 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1289 'categories': ['Music'],
1290 'availability': 'public',
1291 'uploader_url': 'http://www.youtube.com/user/st3in234',
1292 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1293 'live_status': 'not_live',
1295 'channel_follower_count': int
1299 'note': 'Non-bypassable age-gated video',
1300 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1301 'only_matching': True,
1303 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1304 # YouTube Red ad is not captured for creator
1306 'url': '__2ABJjxzNo',
1308 'id': '__2ABJjxzNo',
1311 'upload_date': '20100430',
1312 'uploader_id': 'deadmau5',
1313 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1314 'creator': 'deadmau5',
1315 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1316 'uploader': 'deadmau5',
1317 'title': 'Deadmau5 - Some Chords (HD)',
1318 'alt_title': 'Some Chords',
1319 'availability': 'public',
1321 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1323 'live_status': 'not_live',
1324 'channel': 'deadmau5',
1325 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1327 'track': 'Some Chords',
1328 'artist': 'deadmau5',
1329 'playable_in_embed': True,
1331 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1332 'categories': ['Music'],
1333 'album': 'Some Chords',
1334 'channel_follower_count': int
1336 'expected_warnings': [
1337 'DASH manifest missing',
1340 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1342 'url': 'lqQg6PlCWgI',
1344 'id': 'lqQg6PlCWgI',
1347 'upload_date': '20150827',
1348 'uploader_id': 'olympic',
1349 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1350 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1351 'uploader': 'Olympics',
1352 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1354 'release_timestamp': 1343767800,
1355 'playable_in_embed': True,
1356 'categories': ['Sports'],
1357 'release_date': '20120731',
1358 'channel': 'Olympics',
1359 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1360 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1361 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1363 'availability': 'public',
1364 'live_status': 'was_live',
1366 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1367 'channel_follower_count': int
1370 'skip_download': 'requires avconv',
1375 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1377 'id': '_b-2C3KPAM0',
1379 'stretched_ratio': 16 / 9.,
1381 'upload_date': '20110310',
1382 'uploader_id': 'AllenMeow',
1383 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1384 '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',
1386 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1387 'playable_in_embed': True,
1391 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1392 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1393 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1395 'categories': ['People & Blogs'],
1397 'live_status': 'not_live',
1398 'availability': 'unlisted',
1399 'comment_count': int,
1400 'channel_follower_count': int
1403 # url_encoded_fmt_stream_map is empty string
1405 'url': 'qEJwOuvDf7I',
1407 'id': 'qEJwOuvDf7I',
1409 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1411 'upload_date': '20150404',
1412 'uploader_id': 'spbelect',
1413 'uploader': 'Наблюдатели Петербурга',
1416 'skip_download': 'requires avconv',
1418 'skip': 'This live event has ended.',
1420 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1422 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1424 'id': 'FIl7x6_3R5Y',
1426 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1427 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1429 'upload_date': '20150625',
1430 'uploader_id': 'dorappi2000',
1431 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1432 'uploader': 'dorappi2000',
1433 'formats': 'mincount:31',
1435 'skip': 'not actual anymore',
1437 # DASH manifest with segment_list
1439 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1440 'md5': '8ce563a1d667b599d21064e982ab9e31',
1442 'id': 'CsmdDsKjzN8',
1444 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1445 'uploader': 'Airtek',
1446 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1447 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1448 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1451 'youtube_include_dash_manifest': True,
1452 'format': '135', # bestvideo
1454 'skip': 'This live event has ended.',
1457 # Multifeed videos (multiple cameras), URL is for Main Camera
1458 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1460 'id': 'jvGDaLqkpTg',
1461 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1462 'description': 'md5:e03b909557865076822aa169218d6a5d',
1466 'id': 'jvGDaLqkpTg',
1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
1471 'upload_date': '20161111',
1472 'uploader': 'Team PGP',
1473 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1474 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1478 'id': '3AKt1R1aDnw',
1480 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1481 'description': 'md5:e03b909557865076822aa169218d6a5d',
1483 'upload_date': '20161111',
1484 'uploader': 'Team PGP',
1485 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1486 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1490 'id': 'RtAMM00gpVc',
1492 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1493 'description': 'md5:e03b909557865076822aa169218d6a5d',
1495 'upload_date': '20161111',
1496 'uploader': 'Team PGP',
1497 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1498 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1502 'id': '6N2fdlP3C5U',
1504 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1505 'description': 'md5:e03b909557865076822aa169218d6a5d',
1507 'upload_date': '20161111',
1508 'uploader': 'Team PGP',
1509 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1510 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1514 'skip_download': True,
1516 'skip': 'Not multifeed anymore',
1519 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1520 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1522 'id': 'gVfLd0zydlo',
1523 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1525 'playlist_count': 2,
1526 'skip': 'Not multifeed anymore',
1529 'url': 'https://vid.plus/FlRa-iH7PGw',
1530 'only_matching': True,
1533 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1534 'only_matching': True,
1537 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1538 # Also tests cut-off URL expansion in video description (see
1539 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1540 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1541 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1543 'id': 'lsguqyKfVQg',
1545 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1546 'alt_title': 'Dark Walk',
1547 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1549 'upload_date': '20151119',
1550 'uploader_id': 'IronSoulElf',
1551 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1552 'uploader': 'IronSoulElf',
1553 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1554 'track': 'Dark Walk',
1555 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1556 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1557 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1558 'categories': ['Film & Animation'],
1560 'live_status': 'not_live',
1561 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1562 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1564 'availability': 'public',
1565 'channel': 'IronSoulElf',
1566 'playable_in_embed': True,
1569 'channel_follower_count': int
1572 'skip_download': True,
1576 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1577 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1578 'only_matching': True,
1581 # Video with yt:stretch=17:0
1582 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1584 'id': 'Q39EVAstoRM',
1586 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1587 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1588 'upload_date': '20151107',
1589 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1590 'uploader': 'CH GAMER DROID',
1593 'skip_download': True,
1595 'skip': 'This video does not exist.',
1598 # Video with incomplete 'yt:stretch=16:'
1599 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1600 'only_matching': True,
1603 # Video licensed under Creative Commons
1604 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1606 'id': 'M4gD1WSo5mA',
1608 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1609 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1611 'upload_date': '20150128',
1612 'uploader_id': 'BerkmanCenter',
1613 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1614 'uploader': 'The Berkman Klein Center for Internet & Society',
1615 'license': 'Creative Commons Attribution license (reuse allowed)',
1616 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1617 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1620 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1621 'channel': 'The Berkman Klein Center for Internet & Society',
1622 'availability': 'public',
1624 'categories': ['Education'],
1625 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1626 'live_status': 'not_live',
1627 'playable_in_embed': True,
1628 'comment_count': int,
1629 'channel_follower_count': int
1632 'skip_download': True,
1636 # Channel-like uploader_url
1637 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1639 'id': 'eQcmzGIKrzg',
1641 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1642 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1644 'upload_date': '20151120',
1645 'uploader': 'Bernie Sanders',
1646 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1647 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1648 'license': 'Creative Commons Attribution license (reuse allowed)',
1649 'playable_in_embed': True,
1652 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1654 'availability': 'public',
1655 'categories': ['News & Politics'],
1656 'channel': 'Bernie Sanders',
1657 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1659 'live_status': 'not_live',
1660 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1661 'comment_count': int,
1662 'channel_follower_count': int
1665 'skip_download': True,
1669 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1670 'only_matching': True,
1673 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1674 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1675 'only_matching': True,
1678 # Rental video preview
1679 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1681 'id': 'uGpuVWrhIzE',
1683 'title': 'Piku - Trailer',
1684 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1685 'upload_date': '20150811',
1686 'uploader': 'FlixMatrix',
1687 'uploader_id': 'FlixMatrixKaravan',
1688 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1689 'license': 'Standard YouTube License',
1692 'skip_download': True,
1694 'skip': 'This video is not available.',
1697 # YouTube Red video with episode data
1698 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1700 'id': 'iqKdEhx-dD4',
1702 'title': 'Isolation - Mind Field (Ep 1)',
1703 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1705 'upload_date': '20170118',
1706 'uploader': 'Vsauce',
1707 'uploader_id': 'Vsauce',
1708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1709 'series': 'Mind Field',
1711 'episode_number': 1,
1712 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1715 'availability': 'public',
1717 'channel': 'Vsauce',
1718 'episode': 'Episode 1',
1719 'categories': ['Entertainment'],
1720 'season': 'Season 1',
1721 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1722 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1724 'playable_in_embed': True,
1725 'live_status': 'not_live',
1726 'channel_follower_count': int
1729 'skip_download': True,
1731 'expected_warnings': [
1732 'Skipping DASH manifest',
1736 # The following content has been identified by the YouTube community
1737 # as inappropriate or offensive to some audiences.
1738 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1740 'id': '6SJNVb0GnPI',
1742 'title': 'Race Differences in Intelligence',
1743 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1745 'upload_date': '20140124',
1746 'uploader': 'New Century Foundation',
1747 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1748 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1751 'skip_download': True,
1753 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1757 'url': '1t24XAntNCY',
1758 'only_matching': True,
1761 # geo restricted to JP
1762 'url': 'sJL6WA-aGkQ',
1763 'only_matching': True,
1766 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1767 'only_matching': True,
1770 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1771 'only_matching': True,
1774 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1775 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1776 'only_matching': True,
1780 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1781 'only_matching': True,
1784 # Video with unsupported adaptive stream type formats
1785 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1787 'id': 'Z4Vy8R84T1U',
1789 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1790 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1792 'upload_date': '20130923',
1793 'uploader': 'Amelia Putri Harwita',
1794 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1795 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1796 'formats': 'maxcount:10',
1799 'skip_download': True,
1800 'youtube_include_dash_manifest': False,
1802 'skip': 'not actual anymore',
1805 # Youtube Music Auto-generated description
1806 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1808 'id': 'MgNrAu2pzNs',
1810 'title': 'Voyeur Girl',
1811 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1812 'upload_date': '20190312',
1813 'uploader': 'Stephen - Topic',
1814 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1815 'artist': 'Stephen',
1816 'track': 'Voyeur Girl',
1817 'album': 'it\'s too much love to know my dear',
1818 'release_date': '20190313',
1819 'release_year': 2019,
1820 'alt_title': 'Voyeur Girl',
1822 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1823 'playable_in_embed': True,
1825 'categories': ['Music'],
1826 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1827 'channel': 'Stephen',
1828 'availability': 'public',
1829 'creator': 'Stephen',
1831 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1833 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1835 'live_status': 'not_live',
1836 'channel_follower_count': int
1839 'skip_download': True,
1843 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1844 'only_matching': True,
1847 # invalid -> valid video id redirection
1848 'url': 'DJztXj2GPfl',
1850 'id': 'DJztXj2GPfk',
1852 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1853 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1854 'upload_date': '20090125',
1855 'uploader': 'Prochorowka',
1856 'uploader_id': 'Prochorowka',
1857 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1858 'artist': 'Panjabi MC',
1859 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1860 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1863 'skip_download': True,
1865 'skip': 'Video unavailable',
1868 # empty description results in an empty string
1869 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1871 'id': 'x41yOUIvK2k',
1873 'title': 'IMG 3456',
1875 'upload_date': '20170613',
1876 'uploader_id': 'ElevageOrVert',
1877 'uploader': 'ElevageOrVert',
1879 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1880 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1882 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1884 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1885 'availability': 'public',
1887 'categories': ['Pets & Animals'],
1889 'playable_in_embed': True,
1890 'live_status': 'not_live',
1891 'channel': 'ElevageOrVert',
1892 'channel_follower_count': int
1895 'skip_download': True,
1899 # with '};' inside yt initial data (see [1])
1900 # see [2] for an example with '};' inside ytInitialPlayerResponse
1901 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1902 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1903 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1905 'id': 'CHqg6qOn4no',
1907 'title': 'Part 77 Sort a list of simple types in c#',
1908 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1909 'upload_date': '20130831',
1910 'uploader_id': 'kudvenkat',
1911 'uploader': 'kudvenkat',
1912 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1914 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1915 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1916 'live_status': 'not_live',
1917 'categories': ['Education'],
1918 'availability': 'public',
1919 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1921 'playable_in_embed': True,
1925 'channel': 'kudvenkat',
1926 'comment_count': int,
1927 'channel_follower_count': int
1930 'skip_download': True,
1934 # another example of '};' in ytInitialData
1935 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1936 'only_matching': True,
1939 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1940 'only_matching': True,
1943 # https://github.com/ytdl-org/youtube-dl/pull/28094
1944 'url': 'OtqTfy26tG0',
1946 'id': 'OtqTfy26tG0',
1948 'title': 'Burn Out',
1949 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1950 'upload_date': '20141120',
1951 'uploader': 'The Cinematic Orchestra - Topic',
1952 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1953 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1954 'artist': 'The Cinematic Orchestra',
1955 'track': 'Burn Out',
1956 'album': 'Every Day',
1958 'live_status': 'not_live',
1959 'alt_title': 'Burn Out',
1963 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1964 'creator': 'The Cinematic Orchestra',
1965 'channel': 'The Cinematic Orchestra',
1966 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1967 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1968 'availability': 'public',
1969 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1970 'categories': ['Music'],
1971 'playable_in_embed': True,
1972 'channel_follower_count': int
1975 'skip_download': True,
1979 # controversial video, only works with bpctr when authenticated with cookies
1980 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1981 'only_matching': True,
1984 # controversial video, requires bpctr/contentCheckOk
1985 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1987 'id': 'SZJvDhaSDnc',
1989 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1990 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1991 'uploader': 'CBS Mornings',
1992 'uploader_id': 'CBSThisMorning',
1993 'upload_date': '20140716',
1994 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
1996 'categories': ['News & Politics'],
1997 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
1999 'channel': 'CBS Mornings',
2000 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2001 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2003 'availability': 'needs_auth',
2004 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2006 'live_status': 'not_live',
2007 'playable_in_embed': True,
2008 'channel_follower_count': int
2012 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2013 'url': 'cBvYw8_A0vQ',
2015 'id': 'cBvYw8_A0vQ',
2017 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2018 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2019 'upload_date': '20201120',
2020 'uploader': 'Walk around Japan',
2021 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2022 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2024 'categories': ['Travel & Events'],
2025 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2027 'channel': 'Walk around Japan',
2028 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2029 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2031 'availability': 'public',
2032 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2033 'live_status': 'not_live',
2034 'playable_in_embed': True,
2035 'channel_follower_count': int
2038 'skip_download': True,
2041 # Has multiple audio streams
2042 'url': 'WaOKSUlf4TM',
2043 'only_matching': True
2045 # Requires Premium: has format 141 when requested using YTM url
2046 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2047 'only_matching': True
2049 # multiple subtitles with same lang_code
2050 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2051 'only_matching': True,
2053 # Force use android client fallback
2054 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2056 'id': 'YOelRv7fMxY',
2057 'title': 'DIGGING A SECRET TUNNEL Part 1',
2059 'upload_date': '20210624',
2060 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2061 'uploader': 'colinfurze',
2062 'uploader_id': 'colinfurze',
2063 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2064 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2066 'categories': ['Entertainment'],
2067 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2069 'channel': 'colinfurze',
2070 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2071 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2073 'availability': 'public',
2075 'live_status': 'not_live',
2076 'playable_in_embed': True,
2077 'channel_follower_count': int
2080 'format': '17', # 3gp format available on android
2081 'extractor_args': {'youtube': {'player_client': ['android']}},
2085 # Skip download of additional client configs (remix client config in this case)
2086 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2087 'only_matching': True,
2089 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2093 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2094 'only_matching': True,
2096 'note': 'Storyboards',
2097 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2099 'id': '5KLPxDtMqe8',
2102 'title': 'Your Brain is Plastic',
2103 'uploader_id': 'scishow',
2104 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2105 'upload_date': '20140324',
2106 'uploader': 'SciShow',
2108 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2109 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2111 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2112 'playable_in_embed': True,
2114 'uploader_url': 'http://www.youtube.com/user/scishow',
2115 'availability': 'public',
2116 'channel': 'SciShow',
2117 'live_status': 'not_live',
2119 'categories': ['Education'],
2121 'channel_follower_count': int
2122 }, 'params': {'format': 'mhtml', 'skip_download': True}
2124 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2125 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2127 'id': '2NUZ8W2llS4',
2129 'title': 'The NP that test your phone performance 🙂',
2130 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2131 'uploader': 'Leon Nguyen',
2132 'uploader_id': 'VNSXIII',
2133 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2134 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2135 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2139 'categories': ['Gaming'],
2141 'playable_in_embed': True,
2142 'live_status': 'not_live',
2143 'upload_date': '20220103',
2145 'availability': 'public',
2146 'channel': 'Leon Nguyen',
2147 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2148 'comment_count': int,
2149 'channel_follower_count': int
2152 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2153 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2155 'id': 'mzZzzBU6lrM',
2157 'title': 'I Met GeorgeNotFound In Real Life...',
2158 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2159 'uploader': 'Quackity',
2160 'uploader_id': 'QuackityHQ',
2161 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2162 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2163 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2167 'categories': ['Entertainment'],
2169 'playable_in_embed': True,
2170 'live_status': 'not_live',
2171 'release_timestamp': 1641172509,
2172 'release_date': '20220103',
2173 'upload_date': '20220103',
2175 'availability': 'public',
2176 'channel': 'Quackity',
2177 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2178 'channel_follower_count': int
2181 { # continuous livestream. Microformat upload date should be preferred.
2182 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2183 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2185 'id': 'kgx4WGK0oNU',
2186 '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}',
2188 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2189 'availability': 'public',
2191 'release_timestamp': 1637975704,
2192 'upload_date': '20210619',
2193 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2194 'live_status': 'is_live',
2195 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2196 'uploader': '阿鲍Abao',
2197 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2198 'channel': 'Abao in Tokyo',
2199 'channel_follower_count': int,
2200 'release_date': '20211127',
2202 'categories': ['People & Blogs'],
2204 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2206 'playable_in_embed': True,
2207 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2209 'params': {'skip_download': True}
2211 # Story. Requires specific player params to work.
2212 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2214 'id': 'vv8qTUWmulI',
2216 'availability': 'unlisted',
2218 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2219 'upload_date': '20220526',
2220 'categories': ['Education'],
2222 'channel': 'IT\'S HISTORY',
2224 'uploader_id': 'BlastfromthePast',
2226 'uploader': 'IT\'S HISTORY',
2227 'playable_in_embed': True,
2229 'live_status': 'not_live',
2231 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2232 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2233 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2235 'skip': 'stories get removed after some period of time',
2237 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2239 'id': 'tjjjtzRLHvA',
2241 'title': 'ハッシュタグ無し };if window.ytcsi',
2242 'upload_date': '20220323',
2244 'availability': 'unlisted',
2245 'channel': 'nao20010128nao',
2246 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2248 'uploader': 'nao20010128nao',
2249 'uploader_id': 'nao20010128nao',
2250 'categories': ['Music'],
2253 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2254 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2255 'live_status': 'not_live',
2256 'playable_in_embed': True,
2257 'channel_follower_count': int,
2260 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2263 'note': '6 channel audio',
2264 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2265 'only_matching': True,
2270 # YouTube <object> embed
2272 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2273 'md5': '873c81d308b979f0e23ee7e620b312a3',
2275 'id': 'msN87y-iEx0',
2277 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2278 'upload_date': '20080526',
2279 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2280 'uploader': 'Christopher Sykes',
2281 'uploader_id': 'ChristopherJSykes',
2283 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2284 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2285 'playable_in_embed': True,
2286 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2288 'comment_count': int,
2289 'channel': 'Christopher Sykes',
2290 'live_status': 'not_live',
2291 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2292 'availability': 'public',
2295 'categories': ['Science & Technology'],
2296 'channel_follower_count': int,
2297 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2300 'skip_download': True,
2306 def suitable(cls, url):
2307 from ..utils import parse_qs
2310 if qs.get('list', [None])[0]:
2312 return super().suitable(url)
2314 def __init__(self, *args, **kwargs):
2315 super().__init__(*args, **kwargs)
2316 self._code_cache = {}
2317 self._player_cache = {}
2319 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2320 lock = threading.Lock()
2323 start_time = time.time()
2324 formats = [f for f in formats if f.get('is_from_start')]
2326 def refetch_manifest(format_id, delay):
2327 nonlocal formats, start_time, is_live
2328 if time.time() <= start_time + delay:
2331 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2332 video_details = traverse_obj(
2333 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2334 microformats = traverse_obj(
2335 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2336 expected_type=dict, default=[])
2337 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2338 start_time = time.time()
2340 def mpd_feed(format_id, delay):
2342 @returns (manifest_url, manifest_stream_number, is_live) or None
2345 refetch_manifest(format_id, delay)
2347 f = next((f for f in formats if f['format_id'] == format_id), None)
2350 self.to_screen(f'{video_id}: Video is no longer live')
2352 self.report_warning(
2353 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2355 return f['manifest_url'], f['manifest_stream_number'], is_live
2359 f['protocol'] = 'http_dash_segments_generator'
2360 f['fragments'] = functools.partial(
2361 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2363 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2364 FETCH_SPAN, MAX_DURATION = 5, 432000
2366 mpd_url, stream_number, is_live = None, None, True
2369 download_start_time = ctx.get('start') or time.time()
2371 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2372 if lack_early_segments:
2373 self.report_warning(bug_reports_message(
2374 'Starting download from the last 120 hours of the live stream since '
2375 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2376 lack_early_segments = True
2378 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2379 fragments, fragment_base_url = None, None
2381 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2382 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2383 # Obtain from MPD's maximum seq value
2384 old_mpd_url = mpd_url
2385 last_error = ctx.pop('last_error', None)
2386 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2387 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2388 or (mpd_url, stream_number, False))
2389 if not refresh_sequence:
2390 if expire_fast and not is_live:
2391 return False, last_seq
2392 elif old_mpd_url == mpd_url:
2393 return True, last_seq
2395 fmts, _ = self._extract_mpd_formats_and_subtitles(
2396 mpd_url, None, note=False, errnote=False, fatal=False)
2397 except ExtractorError:
2400 no_fragment_score += 2
2401 return False, last_seq
2402 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2403 fragments = fmt_info['fragments']
2404 fragment_base_url = fmt_info['fragment_base_url']
2405 assert fragment_base_url
2407 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2408 return True, _last_seq
2411 fetch_time = time.time()
2412 if no_fragment_score > 30:
2414 if last_segment_url:
2415 # Obtain from "X-Head-Seqnum" header value from each segment
2417 urlh = self._request_webpage(
2418 last_segment_url, None, note=False, errnote=False, fatal=False)
2419 except ExtractorError:
2421 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2422 if last_seq is None:
2423 no_fragment_score += 2
2424 last_segment_url = None
2427 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2428 no_fragment_score += 2
2429 if not should_continue:
2432 if known_idx > last_seq:
2433 last_segment_url = None
2438 if begin_index < 0 and known_idx < 0:
2439 # skip from the start when it's negative value
2440 known_idx = last_seq + begin_index
2441 if lack_early_segments:
2442 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2444 for idx in range(known_idx, last_seq):
2445 # do not update sequence here or you'll get skipped some part of it
2446 should_continue, _ = _extract_sequence_from_mpd(False, False)
2447 if not should_continue:
2449 raise ExtractorError('breaking out of outer loop')
2450 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2452 'url': last_segment_url,
2453 'fragment_count': last_seq,
2455 if known_idx == last_seq:
2456 no_fragment_score += 5
2458 no_fragment_score = 0
2459 known_idx = last_seq
2460 except ExtractorError:
2463 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2465 def _extract_player_url(self, *ytcfgs, webpage=None):
2466 player_url = traverse_obj(
2467 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2468 get_all=False, expected_type=str)
2471 return urljoin('https://www.youtube.com', player_url)
2473 def _download_player_url(self, video_id, fatal=False):
2474 res = self._download_webpage(
2475 'https://www.youtube.com/iframe_api',
2476 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2478 player_version = self._search_regex(
2479 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2481 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2483 def _signature_cache_id(self, example_sig):
2484 """ Return a string representation of a signature """
2485 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2488 def _extract_player_info(cls, player_url):
2489 for player_re in cls._PLAYER_INFO_RE:
2490 id_m = re.search(player_re, player_url)
2494 raise ExtractorError('Cannot identify player %r' % player_url)
2495 return id_m.group('id')
2497 def _load_player(self, video_id, player_url, fatal=True):
2498 player_id = self._extract_player_info(player_url)
2499 if player_id not in self._code_cache:
2500 code = self._download_webpage(
2501 player_url, video_id, fatal=fatal,
2502 note='Downloading player ' + player_id,
2503 errnote='Download of %s failed' % player_url)
2505 self._code_cache[player_id] = code
2506 return self._code_cache.get(player_id)
2508 def _extract_signature_function(self, video_id, player_url, example_sig):
2509 player_id = self._extract_player_info(player_url)
2511 # Read from filesystem cache
2512 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2513 assert os.path.basename(func_id) == func_id
2515 self.write_debug(f'Extracting signature function {func_id}')
2516 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2519 code = self._load_player(video_id, player_url)
2521 res = self._parse_sig_js(code)
2522 test_string = ''.join(map(chr, range(len(example_sig))))
2523 cache_spec = [ord(c) for c in res(test_string)]
2524 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2526 return lambda s: ''.join(s[i] for i in cache_spec)
2528 def _print_sig_code(self, func, example_sig):
2529 if not self.get_param('youtube_print_sig_code'):
2532 def gen_sig_code(idxs):
2533 def _genslice(start, end, step):
2534 starts = '' if start == 0 else str(start)
2535 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2536 steps = '' if step == 1 else (':%d' % step)
2537 return f's[{starts}{ends}{steps}]'
2540 # Quelch pyflakes warnings - start will be set when step is set
2541 start = '(Never used)'
2542 for i, prev in zip(idxs[1:], idxs[:-1]):
2543 if step is not None:
2544 if i - prev == step:
2546 yield _genslice(start, prev, step)
2549 if i - prev in [-1, 1]:
2554 yield 's[%d]' % prev
2558 yield _genslice(start, i, step)
2560 test_string = ''.join(map(chr, range(len(example_sig))))
2561 cache_res = func(test_string)
2562 cache_spec = [ord(c) for c in cache_res]
2563 expr_code = ' + '.join(gen_sig_code(cache_spec))
2564 signature_id_tuple = '(%s)' % (
2565 ', '.join(str(len(p)) for p in example_sig.split('.')))
2566 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2567 ' return %s\n') % (signature_id_tuple, expr_code)
2568 self.to_screen('Extracted signature function:\n' + code)
2570 def _parse_sig_js(self, jscode):
2571 funcname = self._search_regex(
2572 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2573 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2574 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2575 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2576 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}\(a,\d+\)',
2577 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\(\s*""\s*\)',
2578 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2580 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2581 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2582 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2583 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2584 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2585 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2586 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2587 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2588 jscode, 'Initial JS player signature function name', group='sig')
2590 jsi = JSInterpreter(jscode)
2591 initial_function = jsi.extract_function(funcname)
2592 return lambda s: initial_function([s])
2594 def _cached(self, func, *cache_id):
2595 def inner(*args, **kwargs):
2596 if cache_id not in self._player_cache:
2598 self._player_cache[cache_id] = func(*args, **kwargs)
2599 except ExtractorError as e:
2600 self._player_cache[cache_id] = e
2601 except Exception as e:
2602 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2604 ret = self._player_cache[cache_id]
2605 if isinstance(ret, Exception):
2610 def _decrypt_signature(self, s, video_id, player_url):
2611 """Turn the encrypted s field into a working signature"""
2612 extract_sig = self._cached(
2613 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2614 func = extract_sig(video_id, player_url, s)
2615 self._print_sig_code(func, s)
2618 def _decrypt_nsig(self, s, video_id, player_url):
2619 """Turn the encrypted n field into a working signature"""
2620 if player_url is None:
2621 raise ExtractorError('Cannot decrypt nsig without player_url')
2622 player_url = urljoin('https://www.youtube.com', player_url)
2624 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2625 if self.get_param('youtube_print_sig_code'):
2626 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2629 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2630 ret = extract_nsig(jsi, func_code)(s)
2631 except JSInterpreter.Exception as e:
2633 jsi = PhantomJSwrapper(self)
2634 except ExtractorError:
2636 self.report_warning(
2637 f'Native nsig extraction failed: Trying with PhantomJS\n'
2638 f' n = {s} ; player = {player_url}', video_id)
2641 args, func_body = func_code
2643 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2644 video_id=video_id, note='Executing signature code').strip()
2646 self.write_debug(f'Decrypted nsig {s} => {ret}')
2649 def _extract_n_function_code(self, video_id, player_url):
2650 player_id = self._extract_player_info(player_url)
2651 func_code = self.cache.load('youtube-nsig', player_id)
2652 jscode = func_code or self._load_player(video_id, player_url)
2653 jsi = JSInterpreter(jscode)
2656 return jsi, player_id, func_code
2658 funcname, idx = self._search_regex(
2659 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2660 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2662 funcname = json.loads(js_to_json(self._search_regex(
2663 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2664 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2666 func_code = jsi.extract_function_code(funcname)
2667 self.cache.store('youtube-nsig', player_id, func_code)
2668 return jsi, player_id, func_code
2670 def _extract_n_function_from_code(self, jsi, func_code):
2671 func = jsi.extract_function_from_code(*func_code)
2673 def extract_nsig(s):
2676 except JSInterpreter.Exception:
2678 except Exception as e:
2679 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2681 if ret.startswith('enhanced_except_'):
2682 raise JSInterpreter.Exception('Signature function returned an exception')
2687 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2689 Extract signatureTimestamp (sts)
2690 Required to tell API what sig/player version is in use.
2693 if isinstance(ytcfg, dict):
2694 sts = int_or_none(ytcfg.get('STS'))
2697 # Attempt to extract from player
2698 if player_url is None:
2699 error_msg = 'Cannot extract signature timestamp without player_url.'
2701 raise ExtractorError(error_msg)
2702 self.report_warning(error_msg)
2704 code = self._load_player(video_id, player_url, fatal=fatal)
2706 sts = int_or_none(self._search_regex(
2707 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2708 'JS player signature timestamp', group='sts', fatal=fatal))
2711 def _mark_watched(self, video_id, player_responses):
2712 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2713 label = 'fully ' if is_full else ''
2714 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2715 expected_type=url_or_none)
2717 self.report_warning(f'Unable to mark {label}watched')
2719 parsed_url = urllib.parse.urlparse(url)
2720 qs = urllib.parse.parse_qs(parsed_url.query)
2722 # cpn generation algorithm is reverse engineered from base.js.
2723 # In fact it works even with dummy cpn.
2724 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2725 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2727 # # more consistent results setting it to right before the end
2728 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2733 'cmt': video_length,
2734 'el': 'detailpage', # otherwise defaults to "shorts"
2738 # these seem to mark watchtime "history" in the real world
2739 # they're required, so send in a single value
2745 url = urllib.parse.urlunparse(
2746 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2748 self._download_webpage(
2749 url, video_id, f'Marking {label}watched',
2750 'Unable to mark watched', fatal=False)
2753 def _extract_from_webpage(cls, url, webpage):
2754 # Invidious Instances
2755 # https://github.com/yt-dlp/yt-dlp/issues/195
2756 # https://github.com/iv-org/invidious/pull/1730
2758 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2761 yield cls.url_result(mobj.group('url'), cls)
2762 raise cls.StopExtraction()
2764 yield from super()._extract_from_webpage(url, webpage)
2766 # lazyYT YouTube embed
2767 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2768 yield cls.url_result(unescapeHTML(id_), cls, id_)
2770 # Wordpress "YouTube Video Importer" plugin
2771 for m in re.findall(r'''(?x
)<div
[^
>]+
2772 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2773 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
2774 yield cls.url_result(m[-1], cls, m[-1])
2777 def extract_id(cls, url):
2778 video_id = cls.get_temp_id(url)
2780 raise ExtractorError(f'Invalid URL: {url}')
2783 def _extract_chapters_from_json(self, data, duration):
2784 chapter_list = traverse_obj(
2786 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2787 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2788 ), expected_type=list)
2790 return self._extract_chapters(
2792 chapter_time=lambda chapter: float_or_none(
2793 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2794 chapter_title=lambda chapter: traverse_obj(
2795 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2798 def _extract_chapters_from_engagement_panel(self, data, duration):
2799 content_list = traverse_obj(
2801 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2802 expected_type=list, default=[])
2803 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2804 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2806 return next(filter(None, (
2807 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2808 chapter_time, chapter_title, duration)
2809 for contents in content_list)), [])
2811 def _extract_chapters_from_description(self, description, duration):
2812 return self._extract_chapters(
2813 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2814 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2815 duration=duration, strict=False)
2817 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2821 'start_time': chapter_time(chapter),
2822 'title': chapter_title(chapter),
2823 } for chapter in chapter_list or []]
2825 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2827 chapters = [{'start_time': 0}]
2828 for idx, chapter in enumerate(chapter_list):
2829 if chapter['start_time'] is None:
2830 self.report_warning(f'Incomplete chapter {idx}')
2831 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2832 chapters.append(chapter)
2834 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2837 def _extract_comment(self, comment_renderer, parent=None):
2838 comment_id = comment_renderer.get('commentId')
2842 text = self._get_text(comment_renderer, 'contentText')
2844 # note: timestamp is an estimate calculated from the current time and time_text
2845 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2846 author = self._get_text(comment_renderer, 'authorText')
2847 author_id = try_get(comment_renderer,
2848 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2850 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2851 lambda x: x['likeCount']), str)) or 0
2852 author_thumbnail = try_get(comment_renderer,
2853 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2855 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2856 is_favorited = 'creatorHeart' in (try_get(
2857 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2861 'timestamp': timestamp,
2862 'time_text': time_text,
2863 'like_count': votes,
2864 'is_favorited': is_favorited,
2866 'author_id': author_id,
2867 'author_thumbnail': author_thumbnail,
2868 'author_is_uploader': author_is_uploader,
2869 'parent': parent or 'root'
2872 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2874 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2876 def extract_header(contents):
2877 _continuation = None
2878 for content in contents:
2879 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2880 expected_comment_count = self._get_count(
2881 comments_header_renderer, 'countText', 'commentsCount')
2883 if expected_comment_count:
2884 tracker['est_total'] = expected_comment_count
2885 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2886 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2888 sort_menu_item = try_get(
2889 comments_header_renderer,
2890 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2891 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2893 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2894 if not _continuation:
2897 sort_text = str_or_none(sort_menu_item.get('title'))
2899 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2900 self.to_screen('Sorting comments by %s' % sort_text.lower())
2902 return _continuation
2904 def extract_thread(contents):
2906 tracker['current_page_thread'] = 0
2907 for content in contents:
2908 if not parent and tracker['total_parent_comments'] >= max_parents:
2910 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2911 comment_renderer = get_first(
2912 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2913 expected_type=dict, default={})
2915 comment = self._extract_comment(comment_renderer, parent)
2919 tracker['running_total'] += 1
2920 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2923 # Attempt to get the replies
2924 comment_replies_renderer = try_get(
2925 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2927 if comment_replies_renderer:
2928 tracker['current_page_thread'] += 1
2929 comment_entries_iter = self._comment_entries(
2930 comment_replies_renderer, ytcfg, video_id,
2931 parent=comment.get('id'), tracker=tracker)
2932 yield from itertools.islice(comment_entries_iter, min(
2933 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2935 # Keeps track of counts across recursive calls
2940 current_page_thread=0,
2941 total_parent_comments=0,
2942 total_reply_comments=0)
2945 # YouTube comments have a max depth of 2
2946 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2948 self._downloader.deprecation_warning(
2949 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2950 if max_depth == 1 and parent:
2953 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2954 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2956 continuation = self._extract_continuation(root_continuation_data)
2959 is_forced_continuation = False
2960 is_first_continuation = parent is None
2961 if is_first_continuation and not continuation:
2962 # Sometimes you can get comments by generating the continuation yourself,
2963 # even if YouTube initially reports them being disabled - e.g. stories comments.
2964 # Note: if the comment section is actually disabled, YouTube may return a response with
2965 # required check_get_keys missing. So we will disable that check initially in this case.
2966 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2967 is_forced_continuation = True
2969 for page_num in itertools.count(0):
2970 if not continuation:
2972 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2973 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
2975 if is_first_continuation:
2976 note_prefix = 'Downloading comment section API JSON'
2978 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2979 tracker['current_page_thread'], comment_prog_str)
2981 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2982 ' ' if parent else '', ' replies' if parent else '',
2983 page_num, comment_prog_str)
2985 response = self._extract_response(
2986 item_id=None, query=continuation,
2987 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2988 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2989 is_forced_continuation = False
2990 continuation_contents = traverse_obj(
2991 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
2994 for continuation_section in continuation_contents:
2995 continuation_items = traverse_obj(
2996 continuation_section,
2997 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
2998 get_all=False, expected_type=list) or []
2999 if is_first_continuation:
3000 continuation = extract_header(continuation_items)
3001 is_first_continuation = False
3006 for entry in extract_thread(continuation_items):
3010 continuation = self._extract_continuation({'contents': continuation_items})
3014 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3015 if message and not parent and tracker['running_total'] == 0:
3016 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3019 def _generate_comment_continuation(video_id):
3021 Generates initial comment section continuation token from given video id
3023 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3024 return base64.b64encode(token.encode()).decode()
3026 def _get_comments(self, ytcfg, video_id, contents, webpage):
3027 """Entry for comment extraction"""
3028 def _real_comment_extract(contents):
3030 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3031 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3032 yield from self._comment_entries(renderer, ytcfg, video_id)
3034 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3035 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3038 def _get_checkok_params():
3039 return {'contentCheckOk': True, 'racyCheckOk': True}
3042 def _generate_player_context(cls, sts=None):
3044 'html5Preference': 'HTML5_PREF_WANTS',
3047 context['signatureTimestamp'] = sts
3049 'playbackContext': {
3050 'contentPlaybackContext': context
3052 **cls._get_checkok_params()
3056 def _is_agegated(player_response):
3057 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3060 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3061 AGE_GATE_REASONS = (
3062 'confirm your age', 'age-restricted', 'inappropriate', # reason
3063 'age_verification_required', 'age_check_required', # status
3065 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3068 def _is_unplayable(player_response):
3069 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3071 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr):
3073 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3074 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3075 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3076 headers = self.generate_api_headers(
3077 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3080 'videoId': video_id,
3081 'params': '8AEB' # enable stories
3083 yt_query.update(self._generate_player_context(sts))
3084 return self._extract_response(
3085 item_id=video_id, ep='player', query=yt_query,
3086 ytcfg=player_ytcfg, headers=headers, fatal=True,
3087 default_client=client,
3088 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3091 def _get_requested_clients(self, url, smuggled_data):
3092 requested_clients = []
3093 default = ['android', 'web']
3094 allowed_clients = sorted(
3095 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3096 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3097 for client in self._configuration_arg('player_client'):
3098 if client in allowed_clients:
3099 requested_clients.append(client)
3100 elif client == 'default':
3101 requested_clients.extend(default)
3102 elif client == 'all':
3103 requested_clients.extend(allowed_clients)
3105 self.report_warning(f'Skipping unsupported client {client}')
3106 if not requested_clients:
3107 requested_clients = default
3109 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3110 requested_clients.extend(
3111 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3113 return orderedSet(requested_clients)
3115 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg):
3118 initial_pr = self._search_json(
3119 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3121 all_clients = set(clients)
3122 clients = clients[::-1]
3125 def append_client(*client_names):
3126 """ Append the first client name that exists but not already used """
3127 for client_name in client_names:
3128 actual_client = _split_innertube_client(client_name)[0]
3129 if actual_client in INNERTUBE_CLIENTS:
3130 if actual_client not in all_clients:
3131 clients.append(client_name)
3132 all_clients.add(actual_client)
3135 # Android player_response does not have microFormats which are needed for
3136 # extraction of some data. So we return the initial_pr with formats
3137 # stripped out even if not requested by the user
3138 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3140 pr = dict(initial_pr)
3141 pr['streamingData'] = None
3145 tried_iframe_fallback = False
3148 client, base_client, variant = _split_innertube_client(clients.pop())
3149 player_ytcfg = master_ytcfg if client == 'web' else {}
3150 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3151 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3153 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3154 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3155 if 'js' in self._configuration_arg('player_skip'):
3156 require_js_player = False
3159 if not player_url and not tried_iframe_fallback and require_js_player:
3160 player_url = self._download_player_url(video_id)
3161 tried_iframe_fallback = True
3164 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3165 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr)
3166 except ExtractorError as e:
3168 self.report_warning(last_error)
3173 # YouTube may return a different video player response than expected.
3174 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3175 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3176 if pr_video_id and pr_video_id != video_id:
3177 self.report_warning(
3178 f'Skipping player response from {client} client (got player response for video "{pr_video_id}
" instead of "{video_id}
")' + bug_reports_message())
3182 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3183 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3184 append_client(f'{base_client}_creator')
3185 elif self._is_agegated(pr):
3186 if variant == 'tv_embedded':
3187 append_client(f'{base_client}_embedded')
3189 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3194 self.report_warning(last_error)
3195 return prs, player_url
3197 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
3198 itags, stream_ids = {}, []
3199 itag_qualities, res_qualities = {}, {0: -1}
3201 # Normally tiny is the smallest video-only formats. But
3202 # audio-only formats with unknown quality may get tagged as tiny
3204 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3205 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3207 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3209 for fmt in streaming_formats:
3210 if fmt.get('targetDurationSec'):
3213 itag = str_or_none(fmt.get('itag'))
3214 audio_track = fmt.get('audioTrack') or {}
3215 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3216 if stream_id in stream_ids:
3219 quality = fmt.get('quality')
3220 height = int_or_none(fmt.get('height'))
3221 if quality == 'tiny' or not quality:
3222 quality = fmt.get('audioQuality', '').lower() or quality
3223 # The 3gp format (17) in android client has a quality of "small
",
3224 # but is actually worse than other formats
3229 itag_qualities[itag] = quality
3231 res_qualities[height] = quality
3232 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3233 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3234 # number of fragment that would subsequently requested with (`&sq=N`)
3235 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3238 fmt_url = fmt.get('url')
3240 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3241 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3242 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3243 if not all((sc, fmt_url, player_url, encrypted_sig)):
3246 fmt_url += '&%s=%s' % (
3247 traverse_obj(sc, ('sp', -1)) or 'signature',
3248 self._decrypt_signature(encrypted_sig, video_id, player_url)
3250 except ExtractorError as e:
3251 self.report_warning('Signature extraction failed: Some formats may be missing',
3252 video_id=video_id, only_once=True)
3253 self.write_debug(e, only_once=True)
3256 query = parse_qs(fmt_url)
3260 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3261 fmt_url = update_url_query(fmt_url, {
3262 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3264 except ExtractorError as e:
3266 if isinstance(e, JSInterpreter.Exception):
3267 phantomjs_hint = f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} to workaround the issue\n'
3268 self.report_warning(
3269 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3270 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3271 self.write_debug(e, only_once=True)
3275 itags[itag] = 'https'
3276 stream_ids.append(stream_id)
3278 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3279 language_preference = (
3280 10 if audio_track.get('audioIsDefault') and 10
3281 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3283 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3284 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3285 # Make sure to avoid false positives with small duration differences.
3286 # E.g. __2ABJjxzNo, ySuUZEjARPY
3287 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3289 self.report_warning(
3290 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3292 'asr': int_or_none(fmt.get('audioSampleRate')),
3293 'filesize': int_or_none(fmt.get('contentLength')),
3295 'format_note': join_nonempty(
3296 '%s%s' % (audio_track.get('displayName') or '',
3297 ' (default)' if language_preference > 0 else ''),
3298 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3299 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3300 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3301 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3302 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3303 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3304 'fps': int_or_none(fmt.get('fps')) or None,
3305 'audio_channels': fmt.get('audioChannels'),
3307 'quality': q(quality),
3308 'has_drm': bool(fmt.get('drmFamilies')),
3311 'width': int_or_none(fmt.get('width')),
3312 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3313 'desc' if language_preference < -1 else ''),
3314 'language_preference': language_preference,
3315 # Strictly de-prioritize damaged and 3gp formats
3316 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3318 mime_mobj = re.match(
3319 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3321 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3322 dct.update(parse_codecs(mime_mobj.group(2)))
3323 no_audio = dct.get('acodec
') == 'none
'
3324 no_video = dct.get('vcodec
') == 'none
'
3329 if no_audio or no_video:
3330 dct['downloader_options
'] = {
3331 # Youtube throttles chunks >~10M
3332 'http_chunk_size
': 10485760,
3335 dct['container
'] = dct['ext
'] + '_dash
'
3338 live_from_start = is_live and self.get_param('live_from_start
')
3339 skip_manifests = self._configuration_arg('skip
')
3340 if not self.get_param('youtube_include_hls_manifest
', True):
3341 skip_manifests.append('hls
')
3342 if not self.get_param('youtube_include_dash_manifest
', True):
3343 skip_manifests.append('dash
')
3344 get_dash = 'dash
' not in skip_manifests and (
3345 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3346 get_hls = not live_from_start and 'hls
' not in skip_manifests
3348 def process_manifest_format(f, proto, itag):
3350 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3352 itag = f'{itag}
-{proto}
'
3354 f['format_id
'] = itag
3357 f['quality
'] = itag_qualities.get(try_get(f, lambda f: f['format_id
'].split('-')[0]), -1)
3358 if f['quality
'] == -1 and f.get('height
'):
3359 f['quality
'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height
']))])
3363 for sd in streaming_data:
3364 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3365 if hls_manifest_url:
3366 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4
', fatal=False, live=is_live)
3367 subtitles = self._merge_subtitles(subs, subtitles)
3369 if process_manifest_format(f, 'hls
', self._search_regex(
3370 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3373 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3374 if dash_manifest_url:
3375 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3376 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3378 if process_manifest_format(f, 'dash
', f['format_id
']):
3379 f['filesize
'] = int_or_none(self._search_regex(
3380 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3382 f['is_from_start
'] = True
3387 def _extract_storyboard(self, player_responses, duration):
3389 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3390 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3394 for i, args in enumerate(spec):
3395 args = args.split('#')
3396 counts
= list(map(int_or_none
, args
[:5]))
3397 if len(args
) != 8 or not all(counts
):
3398 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3400 width
, height
, frame_count
, cols
, rows
= counts
3403 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3404 fragment_count
= frame_count
/ (cols
* rows
)
3405 fragment_duration
= duration
/ fragment_count
3407 'format_id': f
'sb{i}',
3408 'format_note': 'storyboard',
3410 'protocol': 'mhtml',
3416 'fps': frame_count
/ duration
,
3420 'url': url
.replace('$M', str(j
)),
3421 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3422 } for j
in range(math
.ceil(fragment_count
))],
3425 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3427 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3428 webpage
= self
._download
_webpage
(
3429 webpage_url
+ '&bpctr=9999999999&has_verified=1&pp=8AEB', video_id
, fatal
=False)
3431 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3433 player_responses
, player_url
= self
._extract
_player
_responses
(
3434 self
._get
_requested
_clients
(url
, smuggled_data
),
3435 video_id
, webpage
, master_ytcfg
)
3437 return webpage
, master_ytcfg
, player_responses
, player_url
3439 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3440 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3441 is_live
= get_first(video_details
, 'isLive')
3443 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3445 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3446 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, is_live
, duration
)
3448 return live_broadcast_details
, is_live
, streaming_data
, formats
, subtitles
3450 def _real_extract(self
, url
):
3451 url
, smuggled_data
= unsmuggle_url(url
, {})
3452 video_id
= self
._match
_id
(url
)
3454 base_url
= self
.http_scheme() + '//www.youtube.com/'
3455 webpage_url
= base_url
+ 'watch?v=' + video_id
3457 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3459 playability_statuses
= traverse_obj(
3460 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3462 trailer_video_id
= get_first(
3463 playability_statuses
,
3464 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3466 if trailer_video_id
:
3467 return self
.url_result(
3468 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3470 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3471 if webpage
else (lambda x
: None))
3473 video_details
= traverse_obj(
3474 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3475 microformats
= traverse_obj(
3476 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3477 expected_type
=dict, default
=[])
3479 get_first(video_details
, 'title')
3480 or self
._get
_text
(microformats
, (..., 'title'))
3481 or search_meta(['og:title', 'twitter:title', 'title']))
3482 video_description
= get_first(video_details
, 'shortDescription')
3484 multifeed_metadata_list
= get_first(
3486 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3488 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3489 if self
.get_param('noplaylist'):
3490 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3494 for feed
in multifeed_metadata_list
.split(','):
3495 # Unquote should take place before split on comma (,) since textual
3496 # fields may contain comma as well (see
3497 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3498 feed_data
= urllib
.parse
.parse_qs(
3499 urllib
.parse
.unquote_plus(feed
))
3501 def feed_entry(name
):
3503 feed_data
, lambda x
: x
[name
][0], str)
3505 feed_id
= feed_entry('id')
3508 feed_title
= feed_entry('title')
3511 title
+= ' (%s)' % feed_title
3513 '_type': 'url_transparent',
3514 'ie_key': 'Youtube',
3516 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3517 {'force_singlefeed': True}
),
3520 feed_ids
.append(feed_id
)
3522 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3523 % (', '.join(feed_ids
), video_id
))
3524 return self
.playlist_result(
3525 entries
, video_id
, video_title
, video_description
)
3527 duration
= int_or_none(
3528 get_first(video_details
, 'lengthSeconds')
3529 or get_first(microformats
, 'lengthSeconds')
3530 or parse_duration(search_meta('duration'))) or None
3532 live_broadcast_details
, is_live
, streaming_data
, formats
, automatic_captions
= \
3533 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
)
3536 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3537 self
.report_drm(video_id
)
3539 playability_statuses
,
3540 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3541 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3542 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3544 if subreason
== 'The uploader has not made this video available in your country.':
3545 countries
= get_first(microformats
, 'availableCountries')
3547 regions_allowed
= search_meta('regionsAllowed')
3548 countries
= regions_allowed
.split(',') if regions_allowed
else None
3549 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3550 reason
+= f
'. {subreason}'
3552 self
.raise_no_formats(reason
, expected
=True)
3554 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3555 if not keywords
and webpage
:
3557 unescapeHTML(m
.group('content'))
3558 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3559 for keyword
in keywords
:
3560 if keyword
.startswith('yt:stretch='):
3561 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3563 # NB: float is intentional for forcing float division
3564 w
, h
= (float(v
) for v
in mobj
.groups())
3568 if f
.get('vcodec') != 'none':
3569 f
['stretched_ratio'] = ratio
3571 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3572 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3575 'url': thumbnail_url
,
3577 original_thumbnails
= thumbnails
.copy()
3579 # The best resolution thumbnails sometimes does not appear in the webpage
3580 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3581 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3583 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3584 # in resolution, these are not the custom thumbnail. So de-prioritize them
3585 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3586 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3588 n_thumbnail_names
= len(thumbnail_names
)
3590 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3591 video_id
=video_id
, name
=name
, ext
=ext
,
3592 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3593 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3594 for thumb
in thumbnails
:
3595 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3596 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3597 self
._remove
_duplicate
_formats
(thumbnails
)
3598 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3600 category
= get_first(microformats
, 'category') or search_meta('genre')
3601 channel_id
= str_or_none(
3602 get_first(video_details
, 'channelId')
3603 or get_first(microformats
, 'externalChannelId')
3604 or search_meta('channelId'))
3605 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3607 live_content
= get_first(video_details
, 'isLiveContent')
3608 is_upcoming
= get_first(video_details
, 'isUpcoming')
3610 if is_upcoming
or live_content
is False:
3612 if is_upcoming
is None and (live_content
or is_live
):
3614 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3615 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3616 if not duration
and live_end_time
and live_start_time
:
3617 duration
= live_end_time
- live_start_time
3619 if is_live
and self
.get_param('live_from_start'):
3620 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3622 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3624 # source_preference is lower for throttled/potentially damaged formats
3625 self
._sort
_formats
(formats
, (
3626 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
3630 'title': video_title
,
3632 'thumbnails': thumbnails
,
3633 # The best thumbnail that we are sure exists. Prevents unnecessary
3634 # URL checking if user don't care about getting the best possible thumbnail
3635 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3636 'description': video_description
,
3637 'uploader': get_first(video_details
, 'author'),
3638 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3639 'uploader_url': owner_profile_url
,
3640 'channel_id': channel_id
,
3641 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3642 'duration': duration
,
3643 'view_count': int_or_none(
3644 get_first((video_details
, microformats
), (..., 'viewCount'))
3645 or search_meta('interactionCount')),
3646 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3647 'age_limit': 18 if (
3648 get_first(microformats
, 'isFamilySafe') is False
3649 or search_meta('isFamilyFriendly') == 'false'
3650 or search_meta('og:restrictions:age') == '18+') else 0,
3651 'webpage_url': webpage_url
,
3652 'categories': [category
] if category
else None,
3654 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3656 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3657 else None if is_live
is None or is_upcoming
is None
3659 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3660 'release_timestamp': live_start_time
,
3663 if get_first(video_details
, 'isPostLiveDvr'):
3664 self
.write_debug('Video is in Post-Live Manifestless mode')
3665 info
['live_status'] = 'post_live'
3666 if (duration
or 0) > 4 * 3600:
3667 self
.report_warning(
3668 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3669 'This is a known issue and patches are welcome')
3672 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3674 def get_lang_code(track
):
3675 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3676 or track
.get('languageCode'))
3678 # Converted into dicts to remove duplicates
3680 get_lang_code(sub
): sub
3681 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3682 translation_languages
= {
3683 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3684 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3686 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3687 lang_subs
= container
.setdefault(lang_code
, [])
3688 for fmt
in self
._SUBTITLE
_FORMATS
:
3694 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3698 # NB: Constructing the full subtitle dictionary is slow
3699 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3700 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3701 for lang_code
, caption_track
in captions
.items():
3702 base_url
= caption_track
.get('baseUrl')
3703 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3706 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3707 if caption_track
.get('kind') != 'asr':
3711 subtitles
, base_url
, lang_code
, lang_name
, {})
3712 if not caption_track
.get('isTranslatable'):
3714 for trans_code
, trans_name
in translation_languages
.items():
3717 orig_trans_code
= trans_code
3718 if caption_track
.get('kind') != 'asr':
3719 if not get_translated_subs
:
3721 trans_code
+= f
'-{lang_code}'
3722 trans_name
+= format_field(lang_name
, None, ' from %s')
3723 # Add an "-orig" label to the original language so that it can be distinguished.
3724 # The subs are returned without "-orig" as well for compatibility
3725 if lang_code
== f
'a-{orig_trans_code}':
3727 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3728 # Setting tlang=lang returns damaged subtitles.
3729 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3730 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3732 info
['automatic_captions'] = automatic_captions
3733 info
['subtitles'] = subtitles
3735 parsed_url
= urllib
.parse
.urlparse(url
)
3736 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3737 query
= urllib
.parse
.parse_qs(component
)
3738 for k
, v
in query
.items():
3739 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3741 if d_k
not in info
and k
in s_ks
:
3742 info
[d_k
] = parse_duration(query
[k
][0])
3744 # Youtube Music Auto-generated description
3745 if video_description
:
3748 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3750 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3751 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3752 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3753 .+\nAuto-generated\ by\ YouTube\.\s*$
3754 ''', video_description
)
3756 release_year
= mobj
.group('release_year')
3757 release_date
= mobj
.group('release_date')
3759 release_date
= release_date
.replace('-', '')
3760 if not release_year
:
3761 release_year
= release_date
[:4]
3763 'album': mobj
.group('album'.strip()),
3764 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3765 'track': mobj
.group('track').strip(),
3766 'release_date': release_date
,
3767 'release_year': int_or_none(release_year
),
3772 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3773 if not initial_data
:
3774 query
= {'videoId': video_id}
3775 query
.update(self
._get
_checkok
_params
())
3776 initial_data
= self
._extract
_response
(
3777 item_id
=video_id
, ep
='next', fatal
=False,
3778 ytcfg
=master_ytcfg
, query
=query
,
3779 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3780 note
='Downloading initial data API JSON')
3782 info
['comment_count'] = traverse_obj(initial_data
, (
3783 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3784 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3786 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3787 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3788 ), expected_type
=int_or_none
, get_all
=False)
3790 try: # This will error if there is no livechat
3791 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3792 except (KeyError, IndexError, TypeError):
3795 info
.setdefault('subtitles', {})['live_chat'] = [{
3796 # url is needed to set cookies
3797 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3798 'video_id': video_id
,
3800 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3804 info
['chapters'] = (
3805 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3806 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3807 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3810 contents
= traverse_obj(
3811 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3812 expected_type
=list, default
=[])
3814 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3816 stl
= vpir
.get('superTitleLink')
3818 stl
= self
._get
_text
(stl
)
3821 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3822 info
['location'] = stl
3824 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3827 'series': mobj
.group(1),
3828 'season_number': int(mobj
.group(2)),
3829 'episode_number': int(mobj
.group(3)),
3831 for tlb
in (try_get(
3833 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3835 tbr
= tlb
.get('toggleButtonRenderer') or {}
3836 for getter
, regex
in [(
3837 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3838 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3839 lambda x
: x
['accessibility'],
3840 lambda x
: x
['accessibilityData']['accessibilityData'],
3841 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3842 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3844 mobj
= re
.match(regex
, label
)
3846 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3848 sbr_tooltip
= try_get(
3849 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3851 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3853 'like_count': str_to_int(like_count
),
3854 'dislike_count': str_to_int(dislike_count
),
3856 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3858 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3860 'channel': self
._get
_text
(vor
, 'title'),
3861 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3865 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3867 multiple_songs
= False
3869 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3870 multiple_songs
= True
3873 mrr
= row
.get('metadataRowRenderer') or {}
3874 mrr_title
= mrr
.get('title')
3877 mrr_title
= self
._get
_text
(mrr
, 'title')
3878 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3879 if mrr_title
== 'License':
3880 info
['license'] = mrr_contents_text
3881 elif not multiple_songs
:
3882 if mrr_title
== 'Album':
3883 info
['album'] = mrr_contents_text
3884 elif mrr_title
== 'Artist':
3885 info
['artist'] = mrr_contents_text
3886 elif mrr_title
== 'Song':
3887 info
['track'] = mrr_contents_text
3890 'channel': 'uploader',
3891 'channel_id': 'uploader_id',
3892 'channel_url': 'uploader_url',
3895 # The upload date for scheduled, live and past live streams / premieres in microformats
3896 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3897 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3899 unified_strdate(get_first(microformats
, 'uploadDate'))
3900 or unified_strdate(search_meta('uploadDate')))
3901 if not upload_date
or (not info
.get('is_live') and not info
.get('was_live') and info
.get('live_status') != 'is_upcoming'):
3902 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3903 info
['upload_date'] = upload_date
3905 for to
, frm
in fallbacks
.items():
3906 if not info
.get(to
):
3907 info
[to
] = info
.get(frm
)
3909 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3914 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3915 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3916 is_membersonly
= None
3918 if initial_data
and is_private
is not None:
3919 is_membersonly
= False
3921 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3922 badge_labels
= set()
3923 for content
in contents
:
3924 if not isinstance(content
, dict):
3926 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3927 for badge_label
in badge_labels
:
3928 if badge_label
.lower() == 'members only':
3929 is_membersonly
= True
3930 elif badge_label
.lower() == 'premium':
3932 elif badge_label
.lower() == 'unlisted':
3935 info
['availability'] = self
._availability
(
3936 is_private
=is_private
,
3937 needs_premium
=is_premium
,
3938 needs_subscription
=is_membersonly
,
3939 needs_auth
=info
['age_limit'] >= 18,
3940 is_unlisted
=None if is_private
is None else is_unlisted
)
3942 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
3944 self
.mark_watched(video_id
, player_responses
)
3949 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
3952 def passthrough_smuggled_data(func
):
3953 def _smuggle(entries
, smuggled_data
):
3954 for entry
in entries
:
3955 # TODO: Convert URL to music.youtube instead.
3956 # Do we need to passthrough any other smuggled_data?
3957 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
3960 @functools.wraps(func
)
3961 def wrapper(self
, url
):
3962 url
, smuggled_data
= unsmuggle_url(url
, {})
3963 if self
.is_music_url(url
):
3964 smuggled_data
['is_music_url'] = True
3965 info_dict
= func(self
, url
, smuggled_data
)
3966 if smuggled_data
and info_dict
.get('entries'):
3967 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
3971 def _extract_channel_id(self
, webpage
):
3972 channel_id
= self
._html
_search
_meta
(
3973 'channelId', webpage
, 'channel id', default
=None)
3976 channel_url
= self
._html
_search
_meta
(
3977 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3978 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3979 'twitter:app:url:googleplay'), webpage
, 'channel url')
3980 return self
._search
_regex
(
3981 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3982 channel_url
, 'channel id')
3985 def _extract_basic_item_renderer(item
):
3986 # Modified from _extract_grid_item_renderer
3987 known_basic_renderers
= (
3988 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
3990 for key
, renderer
in item
.items():
3991 if not isinstance(renderer
, dict):
3993 elif key
in known_basic_renderers
:
3995 elif key
.startswith('grid') and key
.endswith('Renderer'):
3998 def _grid_entries(self
, grid_renderer
):
3999 for item
in grid_renderer
['items']:
4000 if not isinstance(item
, dict):
4002 renderer
= self
._extract
_basic
_item
_renderer
(item
)
4003 if not isinstance(renderer
, dict):
4005 title
= self
._get
_text
(renderer
, 'title')
4008 playlist_id
= renderer
.get('playlistId')
4010 yield self
.url_result(
4011 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4012 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4016 video_id
= renderer
.get('videoId')
4018 yield self
._extract
_video
(renderer
)
4021 channel_id
= renderer
.get('channelId')
4023 yield self
.url_result(
4024 'https://www.youtube.com/channel/%s' % channel_id
,
4025 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
4027 # generic endpoint URL support
4028 ep_url
= urljoin('https://www.youtube.com/', try_get(
4029 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4032 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4033 if ie
.suitable(ep_url
):
4034 yield self
.url_result(
4035 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4038 def _music_reponsive_list_entry(self
, renderer
):
4039 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4041 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4042 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4043 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4045 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4047 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4048 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4049 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4050 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4051 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4053 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4054 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4056 def _shelf_entries_from_content(self
, shelf_renderer
):
4057 content
= shelf_renderer
.get('content')
4058 if not isinstance(content
, dict):
4060 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4062 # TODO: add support for nested playlists so each shelf is processed
4063 # as separate playlist
4064 # TODO: this includes only first N items
4065 yield from self
._grid
_entries
(renderer
)
4066 renderer
= content
.get('horizontalListRenderer')
4071 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4073 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4075 shelf_url
= urljoin('https://www.youtube.com', ep
)
4077 # Skipping links to another channels, note that checking for
4078 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4080 if skip_channels
and '/channels?' in shelf_url
:
4082 title
= self
._get
_text
(shelf_renderer
, 'title')
4083 yield self
.url_result(shelf_url
, video_title
=title
)
4084 # Shelf may not contain shelf URL, fallback to extraction from content
4085 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4087 def _playlist_entries(self
, video_list_renderer
):
4088 for content
in video_list_renderer
['contents']:
4089 if not isinstance(content
, dict):
4091 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4092 if not isinstance(renderer
, dict):
4094 video_id
= renderer
.get('videoId')
4097 yield self
._extract
_video
(renderer
)
4099 def _rich_entries(self
, rich_grid_renderer
):
4101 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4102 video_id
= renderer
.get('videoId')
4105 yield self
._extract
_video
(renderer
)
4107 def _video_entry(self
, video_renderer
):
4108 video_id
= video_renderer
.get('videoId')
4110 return self
._extract
_video
(video_renderer
)
4112 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4113 url
= urljoin('https://youtube.com', traverse_obj(
4114 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4116 return self
.url_result(
4117 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4119 def _post_thread_entries(self
, post_thread_renderer
):
4120 post_renderer
= try_get(
4121 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4122 if not post_renderer
:
4125 video_renderer
= try_get(
4126 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4127 video_id
= video_renderer
.get('videoId')
4129 entry
= self
._extract
_video
(video_renderer
)
4132 # playlist attachment
4133 playlist_id
= try_get(
4134 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4136 yield self
.url_result(
4137 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4138 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4139 # inline video links
4140 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4142 if not isinstance(run
, dict):
4145 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4148 if not YoutubeIE
.suitable(ep_url
):
4150 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4151 if video_id
== ep_video_id
:
4153 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4155 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4156 contents
= post_thread_continuation
.get('contents')
4157 if not isinstance(contents
, list):
4159 for content
in contents
:
4160 renderer
= content
.get('backstagePostThreadRenderer')
4161 if isinstance(renderer
, dict):
4162 yield from self
._post
_thread
_entries
(renderer
)
4164 renderer
= content
.get('videoRenderer')
4165 if isinstance(renderer
, dict):
4166 yield self
._video
_entry
(renderer
)
4169 def _rich_grid_entries(self, contents):
4170 for content in contents:
4171 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4173 entry = self._video_entry(video_renderer)
4178 def _extract_entries(self
, parent_renderer
, continuation_list
):
4179 # continuation_list is modified in-place with continuation_list = [continuation_token]
4180 continuation_list
[:] = [None]
4181 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4182 for content
in contents
:
4183 if not isinstance(content
, dict):
4185 is_renderer
= traverse_obj(
4186 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4189 renderer
= content
.get('richItemRenderer')
4191 for entry
in self
._rich
_entries
(renderer
):
4193 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4195 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4196 for isr_content
in isr_contents
:
4197 if not isinstance(isr_content
, dict):
4201 'playlistVideoListRenderer': self
._playlist
_entries
,
4202 'gridRenderer': self
._grid
_entries
,
4203 'reelShelfRenderer': self
._grid
_entries
,
4204 'shelfRenderer': self
._shelf
_entries
,
4205 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4206 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4207 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4208 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4209 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4210 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4212 for key
, renderer
in isr_content
.items():
4213 if key
not in known_renderers
:
4215 for entry
in known_renderers
[key
](renderer
):
4218 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4221 if not continuation_list
[0]:
4222 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4224 if not continuation_list
[0]:
4225 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4227 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4228 continuation_list
= [None]
4229 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4230 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4234 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4235 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4236 yield from extract_entries(parent_renderer
)
4237 continuation
= continuation_list
[0]
4239 for page_num
in itertools
.count(1):
4240 if not continuation
:
4242 headers
= self
.generate_api_headers(
4243 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4244 response
= self
._extract
_response
(
4245 item_id
=f
'{item_id} page {page_num}',
4246 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4247 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4251 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4252 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4253 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4255 known_continuation_renderers
= {
4256 'playlistVideoListContinuation': self
._playlist
_entries
,
4257 'gridContinuation': self
._grid
_entries
,
4258 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4259 'sectionListContinuation': extract_entries
, # for feeds
4261 continuation_contents
= try_get(
4262 response
, lambda x
: x
['continuationContents'], dict) or {}
4263 continuation_renderer
= None
4264 for key
, value
in continuation_contents
.items():
4265 if key
not in known_continuation_renderers
:
4267 continuation_renderer
= value
4268 continuation_list
= [None]
4269 yield from known_continuation_renderers
[key
](continuation_renderer
)
4270 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4272 if continuation_renderer
:
4276 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4277 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4278 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4279 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4280 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4281 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4282 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4283 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4285 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4286 continuation_items
= try_get(
4287 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4288 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4289 video_items_renderer
= None
4290 for key
, value
in continuation_item
.items():
4291 if key
not in known_renderers
:
4293 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4294 continuation_list
= [None]
4295 yield from known_renderers
[key
][0](video_items_renderer
)
4296 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4298 if video_items_renderer
:
4303 def _extract_selected_tab(tabs
, fatal
=True):
4305 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4306 if renderer
.get('selected') is True:
4310 raise ExtractorError('Unable to find selected tab')
4312 def _extract_uploader(self
, data
):
4314 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4316 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4318 owner_text
= owner
.get('text')
4319 uploader
['uploader'] = self
._search
_regex
(
4320 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4321 uploader
['uploader_id'] = try_get(
4322 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], str)
4323 uploader
['uploader_url'] = urljoin(
4324 'https://www.youtube.com/',
4325 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4326 return {k: v for k, v in uploader.items() if v is not None}
4328 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4329 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4332 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4333 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4335 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4337 channel_name
= renderer
.get('title')
4338 channel_url
= renderer
.get('channelUrl')
4339 channel_id
= renderer
.get('externalId')
4342 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4345 title
= renderer
.get('title')
4346 description
= renderer
.get('description', '')
4347 playlist_id
= channel_id
4348 tags
= renderer
.get('keywords', '').split()
4350 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4351 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4352 def _get_uncropped(url
):
4353 return url_or_none((url
or '').split('=')[0] + '=s0')
4355 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4356 if avatar_thumbnails
:
4357 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4358 if uncropped_avatar
:
4359 avatar_thumbnails
.append({
4360 'url': uncropped_avatar
,
4361 'id': 'avatar_uncropped',
4365 channel_banners
= self
._extract
_thumbnails
(
4366 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4367 for banner
in channel_banners
:
4368 banner
['preference'] = -10
4371 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4372 if uncropped_banner
:
4373 channel_banners
.append({
4374 'url': uncropped_banner
,
4375 'id': 'banner_uncropped',
4379 primary_thumbnails
= self
._extract
_thumbnails
(
4380 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4382 if playlist_id
is None:
4383 playlist_id
= item_id
4385 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4386 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4388 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4389 title
+= format_field(selected_tab
, 'title', ' - %s')
4390 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4393 'playlist_id': playlist_id
,
4394 'playlist_title': title
,
4395 'playlist_description': description
,
4396 'uploader': channel_name
,
4397 'uploader_id': channel_id
,
4398 'uploader_url': channel_url
,
4399 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4401 'view_count': self
._get
_count
(playlist_stats
, 1),
4402 'availability': self
._extract
_availability
(data
),
4403 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4404 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4405 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4408 metadata
.update(self
._extract
_uploader
(data
))
4410 'channel': metadata
['uploader'],
4411 'channel_id': metadata
['uploader_id'],
4412 'channel_url': metadata
['uploader_url']})
4413 return self
.playlist_result(
4415 selected_tab
, playlist_id
, ytcfg
,
4416 self
._extract
_account
_syncid
(ytcfg
, data
),
4417 self
._extract
_visitor
_data
(data
, ytcfg
)),
4420 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4421 first_id
= last_id
= response
= None
4422 for page_num
in itertools
.count(1):
4423 videos
= list(self
._playlist
_entries
(playlist
))
4426 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4427 if start
>= len(videos
):
4429 yield from videos
[start
:]
4430 first_id
= first_id
or videos
[0]['id']
4431 last_id
= videos
[-1]['id']
4432 watch_endpoint
= try_get(
4433 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4434 headers
= self
.generate_api_headers(
4435 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4436 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4438 'playlistId': playlist_id
,
4439 'videoId': watch_endpoint
.get('videoId') or last_id
,
4440 'index': watch_endpoint
.get('index') or len(videos
),
4441 'params': watch_endpoint
.get('params') or 'OAE%3D'
4443 response
= self
._extract
_response
(
4444 item_id
='%s page %d' % (playlist_id
, page_num
),
4445 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4446 check_get_keys
='contents'
4449 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4451 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4452 title
= playlist
.get('title') or try_get(
4453 data
, lambda x
: x
['titleText']['simpleText'], str)
4454 playlist_id
= playlist
.get('playlistId') or item_id
4456 # Delegating everything except mix playlists to regular tab-based playlist URL
4457 playlist_url
= urljoin(url
, try_get(
4458 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4461 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4462 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4463 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4465 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4466 return self
.url_result(
4467 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4470 return self
.playlist_result(
4471 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4472 playlist_id
=playlist_id
, playlist_title
=title
)
4474 def _extract_availability(self
, data
):
4476 Gets the availability of a given playlist/tab.
4477 Note: Unless YouTube tells us explicitly, we do not assume it is public
4478 @param data: response
4480 is_private
= is_unlisted
= None
4481 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4482 badge_labels
= self
._extract
_badges
(renderer
)
4484 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4485 privacy_dropdown_entries
= try_get(
4486 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4487 for renderer_dict
in privacy_dropdown_entries
:
4488 is_selected
= try_get(
4489 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4492 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4494 badge_labels
.add(label
.lower())
4497 for badge_label
in badge_labels
:
4498 if badge_label
== 'unlisted':
4500 elif badge_label
== 'private':
4502 elif badge_label
== 'public':
4503 is_unlisted
= is_private
= False
4504 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4507 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4508 sidebar_renderer
= try_get(
4509 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4510 for item
in sidebar_renderer
:
4511 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4515 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4517 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4519 browse_id
= params
= None
4520 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4523 menu_renderer
= try_get(
4524 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4525 for menu_item
in menu_renderer
:
4526 if not isinstance(menu_item
, dict):
4528 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4530 nav_item_renderer
, lambda x
: x
['text']['simpleText'], str)
4531 if not text
or text
.lower() != 'show unavailable videos':
4533 browse_endpoint
= try_get(
4534 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4535 browse_id
= browse_endpoint
.get('browseId')
4536 params
= browse_endpoint
.get('params')
4539 headers
= self
.generate_api_headers(
4540 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4541 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4543 'params': params
or 'wgYCCAA=',
4544 'browseId': browse_id
or 'VL%s' % item_id
4546 return self
._extract
_response
(
4547 item_id
=item_id
, headers
=headers
, query
=query
,
4548 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4549 note
='Downloading API JSON with unavailable videos')
4551 @functools.cached_property
4552 def skip_webpage(self
):
4553 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4555 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4556 webpage
, data
= None, None
4557 for retry
in self
.RetryManager(fatal
=fatal
):
4559 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
4560 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4561 except ExtractorError
as e
:
4562 if isinstance(e
.cause
, network_exceptions
):
4563 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4566 self
._error
_or
_warning
(e
, fatal
=fatal
)
4570 self
._extract
_and
_report
_alerts
(data
)
4571 except ExtractorError
as e
:
4572 self
._error
_or
_warning
(e
, fatal
=fatal
)
4575 # Sometimes youtube returns a webpage with incomplete ytInitialData
4576 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4577 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4578 retry
.error
= ExtractorError('Incomplete yt initial data received')
4581 return webpage
, data
4583 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4584 """Use if failed to extract ytcfg (and data) from initial webpage"""
4585 if not ytcfg
and self
.is_authenticated
:
4586 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4587 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4588 raise ExtractorError(
4589 f
'{msg}. If you are not downloading private content, or '
4590 'your cookies are only for the first account and channel,'
4591 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4593 self
.report_warning(msg
, only_once
=True)
4595 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4597 if not self
.skip_webpage
:
4598 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4599 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4600 # Reject webpage data if redirected to home page without explicitly requesting
4601 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4602 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4603 if (url
!= 'https://www.youtube.com/feed/recommended'
4604 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4605 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4606 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4608 raise ExtractorError(msg
, expected
=True)
4609 self
.report_warning(msg
, only_once
=True)
4611 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4612 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4615 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4616 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4617 resolve_response
= self
._extract
_response
(
4618 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4619 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4620 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4621 for ep_key
, ep
in endpoints
.items():
4622 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4624 return self
._extract
_response
(
4625 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4626 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4627 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4628 err_note
= 'Failed to resolve url (does the playlist exist?)'
4630 raise ExtractorError(err_note
, expected
=True)
4631 self
.report_warning(err_note
, item_id
)
4633 _SEARCH_PARAMS
= None
4635 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4636 data
= {'query': query}
4637 if params
is NO_DEFAULT
:
4638 params
= self
._SEARCH
_PARAMS
4640 data
['params'] = params
4643 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4644 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4646 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4647 ('continuationContents', ),
4649 display_id
= f
'query "{query}"'
4650 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4651 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4652 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4654 continuation_list
= [None]
4656 for page_num
in itertools
.count(1):
4657 data
.update(continuation_list
[0] or {})
4658 headers
= self
.generate_api_headers(
4659 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4660 search
= self
._extract
_response
(
4661 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4662 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4663 slr_contents
= traverse_obj(search
, *content_keys
)
4664 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4665 if not continuation_list
[0]:
4669 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4670 IE_DESC
= 'YouTube Tabs'
4671 _VALID_URL
= r
'''(?x:
4675 youtube(?:kids)?\.com|
4679 (?P<channel_type>channel|c|user|browse)/|
4682 (?:playlist|watch)\?.*?\blist=
4684 (?!(?:%(reserved_names)s)\b) # Direct URLs
4688 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4689 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4691 IE_NAME
= 'youtube:tab'
4694 'note': 'playlists, multipage',
4695 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4696 'playlist_mincount': 94,
4698 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4699 'title': 'Igor Kleiner - Playlists',
4700 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4701 'uploader': 'Igor Kleiner',
4702 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4703 'channel': 'Igor Kleiner',
4704 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4705 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4706 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4707 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4708 'channel_follower_count': int
4711 'note': 'playlists, multipage, different order',
4712 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4713 'playlist_mincount': 94,
4715 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4716 'title': 'Igor Kleiner - Playlists',
4717 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4718 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4719 'uploader': 'Igor Kleiner',
4720 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4721 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4722 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4723 'channel': 'Igor Kleiner',
4724 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4725 'channel_follower_count': int
4728 'note': 'playlists, series',
4729 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4730 'playlist_mincount': 5,
4732 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4733 'title': '3Blue1Brown - Playlists',
4734 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4735 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4736 'uploader': '3Blue1Brown',
4737 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4738 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4739 'channel': '3Blue1Brown',
4740 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4741 'tags': ['Mathematics'],
4742 'channel_follower_count': int
4745 'note': 'playlists, singlepage',
4746 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4747 'playlist_mincount': 4,
4749 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4750 'title': 'ThirstForScience - Playlists',
4751 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4752 'uploader': 'ThirstForScience',
4753 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4754 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4755 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4756 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4758 'channel': 'ThirstForScience',
4759 'channel_follower_count': int
4762 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4763 'only_matching': True,
4765 'note': 'basic, single video playlist',
4766 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4768 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4769 'uploader': 'Sergey M.',
4770 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4771 'title': 'youtube-dl public playlist',
4775 'modified_date': '20201130',
4776 'channel': 'Sergey M.',
4777 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4778 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4779 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4781 'playlist_count': 1,
4783 'note': 'empty playlist',
4784 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4786 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4787 'uploader': 'Sergey M.',
4788 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4789 'title': 'youtube-dl empty playlist',
4791 'channel': 'Sergey M.',
4793 'modified_date': '20160902',
4794 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4795 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4796 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4798 'playlist_count': 0,
4801 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4803 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4804 'title': 'lex will - Home',
4805 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4806 'uploader': 'lex will',
4807 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4808 'channel': 'lex will',
4809 'tags': ['bible', 'history', 'prophesy'],
4810 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4811 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4812 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4813 'channel_follower_count': int
4815 'playlist_mincount': 2,
4817 'note': 'Videos tab',
4818 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4820 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4821 'title': 'lex will - Videos',
4822 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4823 'uploader': 'lex will',
4824 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4825 'tags': ['bible', 'history', 'prophesy'],
4826 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4827 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4828 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4829 'channel': 'lex will',
4830 'channel_follower_count': int
4832 'playlist_mincount': 975,
4834 'note': 'Videos tab, sorted by popular',
4835 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4837 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4838 'title': 'lex will - Videos',
4839 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4840 'uploader': 'lex will',
4841 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4842 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4843 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4844 'channel': 'lex will',
4845 'tags': ['bible', 'history', 'prophesy'],
4846 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4847 'channel_follower_count': int
4849 'playlist_mincount': 199,
4851 'note': 'Playlists tab',
4852 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4854 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4855 'title': 'lex will - Playlists',
4856 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4857 'uploader': 'lex will',
4858 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4859 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4860 'channel': 'lex will',
4861 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4862 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4863 'tags': ['bible', 'history', 'prophesy'],
4864 'channel_follower_count': int
4866 'playlist_mincount': 17,
4868 'note': 'Community tab',
4869 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4871 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4872 'title': 'lex will - Community',
4873 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4874 'uploader': 'lex will',
4875 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4876 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4877 'channel': 'lex will',
4878 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4879 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4880 'tags': ['bible', 'history', 'prophesy'],
4881 'channel_follower_count': int
4883 'playlist_mincount': 18,
4885 'note': 'Channels tab',
4886 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4888 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4889 'title': 'lex will - Channels',
4890 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4891 'uploader': 'lex will',
4892 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4893 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4894 'channel': 'lex will',
4895 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4896 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4897 'tags': ['bible', 'history', 'prophesy'],
4898 'channel_follower_count': int
4900 'playlist_mincount': 12,
4902 'note': 'Search tab',
4903 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4904 'playlist_mincount': 40,
4906 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4907 'title': '3Blue1Brown - Search - linear algebra',
4908 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4909 'uploader': '3Blue1Brown',
4910 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4911 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4912 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4913 'tags': ['Mathematics'],
4914 'channel': '3Blue1Brown',
4915 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4916 'channel_follower_count': int
4919 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4920 'only_matching': True,
4922 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4923 'only_matching': True,
4925 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4926 'only_matching': True,
4928 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4929 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4931 'title': '29C3: Not my department',
4932 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4933 'uploader': 'Christiaan008',
4934 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4935 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4937 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4939 'modified_date': '20150605',
4940 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4941 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4942 'channel': 'Christiaan008',
4944 'playlist_count': 96,
4946 'note': 'Large playlist',
4947 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4949 'title': 'Uploads from Cauchemar',
4950 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4951 'uploader': 'Cauchemar',
4952 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4953 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4955 'modified_date': r
're:\d{8}',
4956 'channel': 'Cauchemar',
4957 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4960 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4962 'playlist_mincount': 1123,
4963 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4965 'note': 'even larger playlist, 8832 videos',
4966 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4967 'only_matching': True,
4969 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4970 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4972 'title': 'Uploads from Interstellar Movie',
4973 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4974 'uploader': 'Interstellar Movie',
4975 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4976 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4979 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4980 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4981 'channel': 'Interstellar Movie',
4983 'modified_date': r
're:\d{8}',
4985 'playlist_mincount': 21,
4987 'note': 'Playlist with "show unavailable videos" button',
4988 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
4990 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
4991 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
4992 'uploader': 'Phim Siêu Nhân Nhật Bản',
4993 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
4995 'channel': 'Phim Siêu Nhân Nhật Bản',
4997 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
4999 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5000 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5001 'modified_date': r
're:\d{8}',
5003 'playlist_mincount': 200,
5004 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5006 'note': 'Playlist with unavailable videos in page 7',
5007 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5009 'title': 'Uploads from BlankTV',
5010 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5011 'uploader': 'BlankTV',
5012 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5013 'channel': 'BlankTV',
5014 'channel_url': 'https://www.youtube.com/c/blanktv',
5015 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5018 'uploader_url': 'https://www.youtube.com/c/blanktv',
5019 'modified_date': r
're:\d{8}',
5022 'playlist_mincount': 1000,
5023 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5025 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5026 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5028 'title': 'Data Analysis with Dr Mike Pound',
5029 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5030 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5031 'uploader': 'Computerphile',
5032 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5033 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5036 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5037 'channel_url': 'https://www.youtube.com/user/Computerphile',
5038 'channel': 'Computerphile',
5040 'playlist_mincount': 11,
5042 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5043 'only_matching': True,
5045 'note': 'Playlist URL that does not actually serve a playlist',
5046 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5048 'id': 'FqZTN594JQw',
5050 'title': "Smiley's People 01 detective, Adventure Series, Action",
5051 'uploader': 'STREEM',
5052 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5053 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5054 'upload_date': '20150526',
5055 'license': 'Standard YouTube License',
5056 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5057 'categories': ['People & Blogs'],
5063 'skip_download': True,
5065 'skip': 'This video is not available.',
5066 'add_ie': [YoutubeIE
.ie_key()],
5068 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5069 'only_matching': True,
5071 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5072 'only_matching': True,
5074 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5076 'id': 'Wq15eF5vCbI', # This will keep changing
5079 'uploader': 'Sky News',
5080 'uploader_id': 'skynews',
5081 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5082 'upload_date': r
're:\d{8}',
5084 'categories': ['News & Politics'],
5087 'release_timestamp': 1642502819,
5088 'channel': 'Sky News',
5089 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5092 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5093 'playable_in_embed': True,
5094 'release_date': '20220118',
5095 'availability': 'public',
5096 'live_status': 'is_live',
5097 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5098 'channel_follower_count': int
5101 'skip_download': True,
5103 'expected_warnings': ['Ignoring subtitle tracks found in '],
5105 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5107 'id': 'a48o2S1cPoo',
5109 'title': 'The Young Turks - Live Main Show',
5110 'uploader': 'The Young Turks',
5111 'uploader_id': 'TheYoungTurks',
5112 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5113 'upload_date': '20150715',
5114 'license': 'Standard YouTube License',
5115 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5116 'categories': ['News & Politics'],
5117 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5121 'skip_download': True,
5123 'only_matching': True,
5125 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5126 'only_matching': True,
5128 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5129 'only_matching': True,
5131 'note': 'A channel that is not live. Should raise error',
5132 'url': 'https://www.youtube.com/user/numberphile/live',
5133 'only_matching': True,
5135 'url': 'https://www.youtube.com/feed/trending',
5136 'only_matching': True,
5138 'url': 'https://www.youtube.com/feed/library',
5139 'only_matching': True,
5141 'url': 'https://www.youtube.com/feed/history',
5142 'only_matching': True,
5144 'url': 'https://www.youtube.com/feed/subscriptions',
5145 'only_matching': True,
5147 'url': 'https://www.youtube.com/feed/watch_later',
5148 'only_matching': True,
5150 'note': 'Recommended - redirects to home page.',
5151 'url': 'https://www.youtube.com/feed/recommended',
5152 'only_matching': True,
5154 'note': 'inline playlist with not always working continuations',
5155 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5156 'only_matching': True,
5158 'url': 'https://www.youtube.com/course',
5159 'only_matching': True,
5161 'url': 'https://www.youtube.com/zsecurity',
5162 'only_matching': True,
5164 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5165 'only_matching': True,
5167 'url': 'https://www.youtube.com/TheYoungTurks/live',
5168 'only_matching': True,
5170 'url': 'https://www.youtube.com/hashtag/cctv9',
5176 'playlist_mincount': 350,
5178 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5179 'only_matching': True,
5181 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5182 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5183 'only_matching': True
5185 'note': '/browse/ should redirect to /channel/',
5186 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5187 'only_matching': True
5189 'note': 'VLPL, should redirect to playlist?list=PL...',
5190 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5192 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5193 'uploader': 'NoCopyrightSounds',
5194 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5195 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5196 'title': 'NCS : All Releases 💿',
5197 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5198 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5199 'modified_date': r
're:\d{8}',
5201 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5203 'channel': 'NoCopyrightSounds',
5205 'playlist_mincount': 166,
5206 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5208 'note': 'Topic, should redirect to playlist?list=UU...',
5209 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5211 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5212 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5213 'title': 'Uploads from Royalty Free Music - Topic',
5214 'uploader': 'Royalty Free Music - Topic',
5216 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5217 'channel': 'Royalty Free Music - Topic',
5219 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5220 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5221 'modified_date': r
're:\d{8}',
5222 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5225 'expected_warnings': [
5226 'The URL does not have a videos tab',
5227 r
'[Uu]navailable videos (are|will be) hidden',
5229 'playlist_mincount': 101,
5231 'note': 'Topic without a UU playlist',
5232 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5234 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5235 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5238 'expected_warnings': [
5239 'the playlist redirect gave error',
5241 'playlist_mincount': 9,
5243 'note': 'Youtube music Album',
5244 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5246 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5247 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5251 'availability': 'unlisted',
5252 'modified_date': r
're:\d{8}',
5254 'playlist_count': 50,
5256 'note': 'unlisted single video playlist',
5257 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5259 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5260 'uploader': 'colethedj',
5261 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5262 'title': 'yt-dlp unlisted playlist test',
5263 'availability': 'unlisted',
5265 'modified_date': '20220418',
5266 'channel': 'colethedj',
5269 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5270 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5271 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5273 'playlist_count': 1,
5275 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5276 'url': 'https://www.youtube.com/feed/recommended',
5278 'id': 'recommended',
5279 'title': 'recommended',
5282 'playlist_mincount': 50,
5284 'skip_download': True,
5285 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5288 'note': 'API Fallback: /videos tab, sorted by oldest first',
5289 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5291 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5292 'title': 'Cody\'sLab - Videos',
5293 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5294 'uploader': 'Cody\'sLab',
5295 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5296 'channel': 'Cody\'sLab',
5297 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5299 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5300 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5301 'channel_follower_count': int
5303 'playlist_mincount': 650,
5305 'skip_download': True,
5306 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5309 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5310 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5312 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5313 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5314 'title': 'Uploads from Royalty Free Music - Topic',
5315 'uploader': 'Royalty Free Music - Topic',
5316 'modified_date': r
're:\d{8}',
5317 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5319 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5321 'channel': 'Royalty Free Music - Topic',
5323 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5325 'expected_warnings': [
5326 'does not have a videos tab',
5327 r
'[Uu]navailable videos (are|will be) hidden',
5329 'playlist_mincount': 101,
5331 'skip_download': True,
5332 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5335 'note': 'non-standard redirect to regional channel',
5336 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5337 'only_matching': True
5339 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5340 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5342 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5343 'modified_date': '20220407',
5344 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5346 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5347 'uploader': 'pukkandan',
5348 'availability': 'unlisted',
5349 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5350 'channel': 'pukkandan',
5351 'description': 'Test for collaborative playlist',
5352 'title': 'yt-dlp test - collaborative playlist',
5354 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5356 'playlist_mincount': 2
5360 def suitable(cls
, url
):
5361 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5363 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5365 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5366 def _real_extract(self
, url
, smuggled_data
):
5367 item_id
= self
._match
_id
(url
)
5368 url
= urllib
.parse
.urlunparse(
5369 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5370 compat_opts
= self
.get_param('compat_opts', [])
5373 mobj
= self
._URL
_RE
.match(url
).groupdict()
5374 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5377 mobj
, redirect_warning
= get_mobj(url
), None
5378 # Youtube returns incomplete data if tabname is not lower case
5379 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5381 if smuggled_data
.get('is_music_url'):
5382 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5383 item_id
= item_id
[2:]
5384 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5385 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5386 mdata
= self
._extract
_tab
_endpoint
(
5387 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5388 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5389 get_all
=False, expected_type
=str)
5391 raise ExtractorError('Failed to resolve album to playlist')
5392 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5393 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5394 pre
= f
'https://www.youtube.com/channel/{item_id}'
5396 original_tab_name
= tab
5397 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5398 # Home URLs should redirect to /videos/
5399 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5400 'To download only the videos in the home page, add a "/featured" to the URL')
5403 url
= ''.join((pre
, tab
, post
))
5404 mobj
= get_mobj(url
)
5406 # Handle both video/playlist URLs
5408 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5410 if not video_id
and mobj
['not_channel'].startswith('watch'):
5412 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5413 raise ExtractorError('Unable to recognize tab page')
5414 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5415 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5416 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5417 mobj
= get_mobj(url
)
5419 if video_id
and playlist_id
:
5420 if self
.get_param('noplaylist'):
5421 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5422 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5423 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5424 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5426 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5428 # YouTube may provide a non-standard redirect to the regional channel
5429 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5430 redirect_url
= traverse_obj(
5431 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5432 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5433 redirect_url
= ''.join((
5434 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5435 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5436 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5438 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5440 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5441 selected_tab_name
= selected_tab
.get('title', '').lower()
5442 if selected_tab_name
== 'home':
5443 selected_tab_name
= 'featured'
5444 requested_tab_name
= mobj
['tab'][1:]
5445 if 'no-youtube-channel-redirect' not in compat_opts
:
5446 if requested_tab_name
== 'live': # Live tab should have redirected to the video
5447 raise UserNotLive(video_id
=mobj
['id'])
5448 if requested_tab_name
not in ('', selected_tab_name
):
5449 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5450 if not original_tab_name
:
5451 if item_id
[:2] == 'UC':
5452 # Topic channels don't have /videos. Use the equivalent playlist instead
5453 pl_id
= f
'UU{item_id[2:]}'
5454 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5456 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5457 except ExtractorError
:
5458 redirect_warning
+= ' and the playlist redirect gave error'
5460 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5461 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5462 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5463 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5465 raise ExtractorError(redirect_warning
, expected
=True)
5467 if redirect_warning
:
5468 self
.to_screen(redirect_warning
)
5469 self
.write_debug(f
'Final URL: {url}')
5471 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5472 if 'no-youtube-unavailable-videos' not in compat_opts
:
5473 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5474 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5475 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5477 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5479 playlist
= traverse_obj(
5480 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5482 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5484 video_id
= traverse_obj(
5485 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5487 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5488 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5489 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5490 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5492 raise ExtractorError('Unable to recognize tab page')
5495 class YoutubePlaylistIE(InfoExtractor
):
5496 IE_DESC
= 'YouTube playlists'
5497 _VALID_URL
= r
'''(?x)(?:
5502 youtube(?:kids)?\.com|
5507 (?P<id>%(playlist_id)s)
5509 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5510 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5512 IE_NAME
= 'youtube:playlist'
5514 'note': 'issue #673',
5515 'url': 'PLBB231211A4F62143',
5517 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5518 'id': 'PLBB231211A4F62143',
5519 'uploader': 'Wickman',
5520 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5521 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5523 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5524 'modified_date': r
're:\d{8}',
5525 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5526 'channel': 'Wickman',
5528 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5530 'playlist_mincount': 29,
5532 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5534 'title': 'YDL_safe_search',
5535 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5537 'playlist_count': 2,
5538 'skip': 'This playlist is private',
5541 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5542 'playlist_count': 4,
5545 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5546 'uploader': 'milan',
5547 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5549 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5551 'modified_date': '20140919',
5554 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5555 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5557 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5559 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5560 'playlist_mincount': 455,
5562 'title': '2018 Chinese New Singles (11/6 updated)',
5563 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5565 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5566 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5569 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5571 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5572 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5573 'modified_date': r
're:\d{8}',
5575 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5577 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5578 'only_matching': True,
5580 # music album playlist
5581 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5582 'only_matching': True,
5586 def suitable(cls
, url
):
5587 if YoutubeTabIE
.suitable(url
):
5589 from ..utils
import parse_qs
5591 if qs
.get('v', [None])[0]:
5593 return super().suitable(url
)
5595 def _real_extract(self
, url
):
5596 playlist_id
= self
._match
_id
(url
)
5597 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5598 url
= update_url_query(
5599 'https://www.youtube.com/playlist',
5600 parse_qs(url
) or {'list': playlist_id}
)
5602 url
= smuggle_url(url
, {'is_music_url': True}
)
5603 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5606 class YoutubeYtBeIE(InfoExtractor
):
5607 IE_DESC
= 'youtu.be'
5608 _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}
5610 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5612 'id': 'yeWKywCrFtk',
5614 'title': 'Small Scale Baler and Braiding Rugs',
5615 'uploader': 'Backus-Page House Museum',
5616 'uploader_id': 'backuspagemuseum',
5617 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5618 'upload_date': '20161008',
5619 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5620 'categories': ['Nonprofits & Activism'],
5624 'playable_in_embed': True,
5625 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5626 'channel': 'Backus-Page House Museum',
5627 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5628 'live_status': 'not_live',
5630 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5631 'availability': 'public',
5633 'comment_count': int,
5634 'channel_follower_count': int
5638 'skip_download': True,
5641 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5642 'only_matching': True,
5645 def _real_extract(self
, url
):
5646 mobj
= self
._match
_valid
_url
(url
)
5647 video_id
= mobj
.group('id')
5648 playlist_id
= mobj
.group('playlist_id')
5649 return self
.url_result(
5650 update_url_query('https://www.youtube.com/watch', {
5652 'list': playlist_id
,
5653 'feature': 'youtu.be',
5654 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5657 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5658 IE_DESC
= 'YouTube livestream embeds'
5659 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5661 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5662 'only_matching': True,
5665 def _real_extract(self
, url
):
5666 channel_id
= self
._match
_id
(url
)
5667 return self
.url_result(
5668 f
'https://www.youtube.com/channel/{channel_id}/live',
5669 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5672 class YoutubeYtUserIE(InfoExtractor
):
5673 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5674 IE_NAME
= 'youtube:user'
5675 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5677 'url': 'ytuser:phihag',
5678 'only_matching': True,
5681 def _real_extract(self
, url
):
5682 user_id
= self
._match
_id
(url
)
5683 return self
.url_result(
5684 'https://www.youtube.com/user/%s/videos' % user_id
,
5685 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5688 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5689 IE_NAME
= 'youtube:favorites'
5690 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5691 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5692 _LOGIN_REQUIRED
= True
5695 'only_matching': True,
5697 'url': ':ytfavorites',
5698 'only_matching': True,
5701 def _real_extract(self
, url
):
5702 return self
.url_result(
5703 'https://www.youtube.com/playlist?list=LL',
5704 ie
=YoutubeTabIE
.ie_key())
5707 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5708 IE_NAME
= 'youtube:notif'
5709 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5710 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5711 _LOGIN_REQUIRED
= True
5714 'only_matching': True,
5716 'url': ':ytnotifications',
5717 'only_matching': True,
5720 def _extract_notification_menu(self
, response
, continuation_list
):
5721 notification_list
= traverse_obj(
5723 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5724 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5725 expected_type
=list) or []
5726 continuation_list
[0] = None
5727 for item
in notification_list
:
5728 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5731 continuation
= item
.get('continuationItemRenderer')
5733 continuation_list
[0] = continuation
5735 def _extract_notification_renderer(self
, notification
):
5736 video_id
= traverse_obj(
5737 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5738 url
= f
'https://www.youtube.com/watch?v={video_id}'
5741 browse_ep
= traverse_obj(
5742 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5743 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5744 post_id
= self
._search
_regex
(
5745 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5746 'post id', default
=None)
5747 if not channel_id
or not post_id
:
5749 # The direct /post url redirects to this in the browser
5750 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5752 channel
= traverse_obj(
5753 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5755 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5756 if notification_title
:
5757 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5758 # TODO: handle recommended videos
5759 title
= self
._search
_regex
(
5760 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5761 'video title', default
=None)
5762 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5763 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5768 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5769 'video_id': video_id
,
5771 'channel_id': channel_id
,
5773 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5774 'upload_date': upload_date
,
5777 def _notification_menu_entries(self
, ytcfg
):
5778 continuation_list
= [None]
5780 for page
in itertools
.count(1):
5781 ctoken
= traverse_obj(
5782 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5783 response
= self
._extract
_response
(
5784 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5785 ep
='notification/get_notification_menu', check_get_keys
='actions',
5786 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5787 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5788 if not continuation_list
[0]:
5791 def _real_extract(self
, url
):
5792 display_id
= 'notifications'
5793 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5794 self
._report
_playlist
_authcheck
(ytcfg
)
5795 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5798 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5799 IE_DESC
= 'YouTube search'
5800 IE_NAME
= 'youtube:search'
5801 _SEARCH_KEY
= 'ytsearch'
5802 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5804 'url': 'ytsearch5:youtube-dl test video',
5805 'playlist_count': 5,
5807 'id': 'youtube-dl test video',
5808 'title': 'youtube-dl test video',
5813 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5814 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5815 _SEARCH_KEY
= 'ytsearchdate'
5816 IE_DESC
= 'YouTube search, newest videos first'
5817 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5819 'url': 'ytsearchdate5:youtube-dl test video',
5820 'playlist_count': 5,
5822 'id': 'youtube-dl test video',
5823 'title': 'youtube-dl test video',
5828 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5829 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5830 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5831 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5833 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5834 'playlist_mincount': 5,
5836 'id': 'youtube-dl test video',
5837 'title': 'youtube-dl test video',
5840 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5841 'playlist_mincount': 5,
5847 'url': 'https://www.youtube.com/results?search_query=%23cats',
5848 'playlist_mincount': 1,
5852 # The test suite does not have support for nested playlists
5854 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5859 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5860 'only_matching': True,
5863 def _real_extract(self
, url
):
5865 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5866 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5869 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5870 IE_DESC
= 'YouTube music search URLs with selectable sections, e.g. #songs'
5871 IE_NAME
= 'youtube:music:search_url'
5872 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5874 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5875 'playlist_count': 16,
5877 'id': 'royalty free music',
5878 'title': 'royalty free music',
5881 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5882 'playlist_mincount': 30,
5884 'id': 'royalty free music - songs',
5885 'title': 'royalty free music - songs',
5887 'params': {'extract_flat': 'in_playlist'}
5889 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5890 'playlist_mincount': 30,
5892 'id': 'royalty free music - community playlists',
5893 'title': 'royalty free music - community playlists',
5895 'params': {'extract_flat': 'in_playlist'}
5899 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5900 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5901 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5902 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5903 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5904 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5907 def _real_extract(self
, url
):
5909 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5910 params
= qs
.get('sp', (None,))[0]
5912 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5914 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
5915 params
= self
._SECTIONS
.get(section
)
5918 title
= join_nonempty(query
, section
, delim
=' - ')
5919 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5922 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5924 Base class for feed extractors
5925 Subclasses must re-define the _FEED_NAME property.
5927 _LOGIN_REQUIRED
= True
5928 _FEED_NAME
= 'feeds'
5930 def _real_initialize(self
):
5931 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
5935 return f
'youtube:{self._FEED_NAME}'
5937 def _real_extract(self
, url
):
5938 return self
.url_result(
5939 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
5942 class YoutubeWatchLaterIE(InfoExtractor
):
5943 IE_NAME
= 'youtube:watchlater'
5944 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5945 _VALID_URL
= r
':ytwatchlater'
5947 'url': ':ytwatchlater',
5948 'only_matching': True,
5951 def _real_extract(self
, url
):
5952 return self
.url_result(
5953 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
5956 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
5957 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
5958 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5959 _FEED_NAME
= 'recommended'
5960 _LOGIN_REQUIRED
= False
5963 'only_matching': True,
5965 'url': ':ytrecommended',
5966 'only_matching': True,
5968 'url': 'https://youtube.com',
5969 'only_matching': True,
5973 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
5974 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5975 _VALID_URL
= r
':ytsub(?:scription)?s?'
5976 _FEED_NAME
= 'subscriptions'
5979 'only_matching': True,
5981 'url': ':ytsubscriptions',
5982 'only_matching': True,
5986 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
5987 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
5988 _VALID_URL
= r
':ythis(?:tory)?'
5989 _FEED_NAME
= 'history'
5991 'url': ':ythistory',
5992 'only_matching': True,
5996 class YoutubeStoriesIE(InfoExtractor
):
5997 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
5998 IE_NAME
= 'youtube:stories'
5999 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6001 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6002 'only_matching': True,
6005 def _real_extract(self
, url
):
6006 playlist_id
= f
'RLTD{self._match_id(url)}'
6007 return self
.url_result(
6008 f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1',
6009 ie
=YoutubeTabIE
, video_id
=playlist_id
)
6012 class YoutubeTruncatedURLIE(InfoExtractor
):
6013 IE_NAME
= 'youtube:truncated_url'
6014 IE_DESC
= False # Do not list
6015 _VALID_URL
= r
'''(?x)
6017 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6020 annotation_id=annotation_[^&]+|
6026 attribution_link\?a=[^&]+
6032 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6033 'only_matching': True,
6035 'url': 'https://www.youtube.com/watch?',
6036 'only_matching': True,
6038 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6039 'only_matching': True,
6041 'url': 'https://www.youtube.com/watch?feature=foo',
6042 'only_matching': True,
6044 'url': 'https://www.youtube.com/watch?hl=en-GB',
6045 'only_matching': True,
6047 'url': 'https://www.youtube.com/watch?t=2372',
6048 'only_matching': True,
6051 def _real_extract(self
, url
):
6052 raise ExtractorError(
6053 'Did you forget to quote the URL? Remember that & is a meta '
6054 'character in most shells, so you want to put the URL in quotes, '
6056 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6057 ' or simply youtube-dl BaW_jenozKc .',
6061 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6062 IE_NAME
= 'youtube:clip'
6063 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6065 # FIXME: Other metadata should be extracted from the clip, not from the base video
6066 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6068 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6070 'section_start': 29.0,
6071 'section_end': 39.7,
6074 'availability': 'public',
6075 'categories': ['Gaming'],
6076 'channel': 'Scott The Woz',
6077 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6078 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6079 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6081 'playable_in_embed': True,
6083 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6084 'title': 'Mobile Games on Console - Scott The Woz',
6085 'upload_date': '20210920',
6086 'uploader': 'Scott The Woz',
6087 'uploader_id': 'scottthewoz',
6088 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6090 'live_status': 'not_live',
6091 'channel_follower_count': int
6095 def _real_extract(self
, url
):
6096 clip_id
= self
._match
_id
(url
)
6097 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6099 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6101 raise ExtractorError('Unable to find video ID')
6103 clip_data
= traverse_obj(data
, (
6104 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6105 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6106 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6107 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6110 '_type': 'url_transparent',
6111 'url': f
'https://www.youtube.com/watch?v={video_id}',
6112 'ie_key': YoutubeIE
.ie_key(),
6114 'section_start': int(clip_data
['startTimeMs']) / 1000,
6115 'section_end': int(clip_data
['endTimeMs']) / 1000,
6119 class YoutubeTruncatedIDIE(InfoExtractor
):
6120 IE_NAME
= 'youtube:truncated_id'
6121 IE_DESC
= False # Do not list
6122 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6125 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6126 'only_matching': True,
6129 def _real_extract(self
, url
):
6130 video_id
= self
._match
_id
(url
)
6131 raise ExtractorError(
6132 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',