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': '17.31.35',
114 'androidSdkVersion': 30,
115 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
118 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
119 'REQUIRE_JS_PLAYER': False
121 'android_embedded': {
122 'INNERTUBE_API_KEY': 'AIzaSyCjc_pVEDi4qsv5MtC2dMXzpIaDoRFLsxw',
123 'INNERTUBE_CONTEXT': {
125 'clientName': 'ANDROID_EMBEDDED_PLAYER',
126 'clientVersion': '17.31.35',
127 'androidSdkVersion': 30,
128 'userAgent': 'com.google.android.youtube/17.31.35 (Linux; U; Android 11) gzip'
131 'INNERTUBE_CONTEXT_CLIENT_NAME': 55,
132 'REQUIRE_JS_PLAYER': False
135 'INNERTUBE_API_KEY': 'AIzaSyAOghZGza2MQSZkY_zfZ370N-PUdXEo8AI',
136 'INNERTUBE_CONTEXT': {
138 'clientName': 'ANDROID_MUSIC',
139 'clientVersion': '5.16.51',
140 'androidSdkVersion': 30,
141 'userAgent': 'com.google.android.apps.youtube.music/5.16.51 (Linux; U; Android 11) gzip'
144 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
145 'REQUIRE_JS_PLAYER': False
148 'INNERTUBE_API_KEY': 'AIzaSyD_qjV8zaaUMehtLkrKFgVeSX_Iqbtyws8',
149 'INNERTUBE_CONTEXT': {
151 'clientName': 'ANDROID_CREATOR',
152 'clientVersion': '22.30.100',
153 'androidSdkVersion': 30,
154 'userAgent': 'com.google.android.apps.youtube.creator/22.30.100 (Linux; U; Android 11) gzip'
157 'INNERTUBE_CONTEXT_CLIENT_NAME': 14,
158 'REQUIRE_JS_PLAYER': False
160 # iOS clients have HLS live streams. Setting device model to get 60fps formats.
161 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/680#issuecomment-1002724558
163 'INNERTUBE_API_KEY': 'AIzaSyB-63vPrdThhKuerbB2N_l7Kwwcxj6yUAc',
164 'INNERTUBE_CONTEXT': {
167 'clientVersion': '17.30.1',
168 'deviceModel': 'iPhone14,3',
169 'userAgent': 'com.google.ios.youtube/17.30.1 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
172 'INNERTUBE_CONTEXT_CLIENT_NAME': 5,
173 'REQUIRE_JS_PLAYER': False
176 'INNERTUBE_CONTEXT': {
178 'clientName': 'IOS_MESSAGES_EXTENSION',
179 'clientVersion': '17.30.1',
180 'deviceModel': 'iPhone14,3',
181 'userAgent': 'com.google.ios.youtube/17.30.1 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
184 'INNERTUBE_CONTEXT_CLIENT_NAME': 66,
185 'REQUIRE_JS_PLAYER': False
188 'INNERTUBE_API_KEY': 'AIzaSyBAETezhkwP0ZWA02RsqT1zu78Fpt0bC_s',
189 'INNERTUBE_CONTEXT': {
191 'clientName': 'IOS_MUSIC',
192 'clientVersion': '5.18',
195 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
196 'REQUIRE_JS_PLAYER': False
199 'INNERTUBE_CONTEXT': {
201 'clientName': 'IOS_CREATOR',
202 'clientVersion': '22.29.101',
205 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
206 'REQUIRE_JS_PLAYER': False
208 # mweb has 'ultralow' formats
209 # See: https://github.com/yt-dlp/yt-dlp/pull/557
211 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
212 'INNERTUBE_CONTEXT': {
214 'clientName': 'MWEB',
215 'clientVersion': '2.20220801.00.00',
218 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
220 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
221 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
223 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
224 'INNERTUBE_CONTEXT': {
226 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
227 'clientVersion': '2.0',
230 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
235 def _split_innertube_client(client_name
):
236 variant
, *base
= client_name
.rsplit('.', 1)
238 return variant
, base
[0], variant
239 base
, *variant
= client_name
.split('_', 1)
240 return client_name
, base
, variant
[0] if variant
else None
243 def build_innertube_clients():
245 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
247 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
248 priority
= qualities(BASE_CLIENTS
[::-1])
250 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
251 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
252 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
253 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
254 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
256 _
, base_client
, variant
= _split_innertube_client(client
)
257 ytcfg
['priority'] = 10 * priority(base_client
)
260 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
261 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
262 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
263 embedscreen
['priority'] -= 3
264 elif variant
== 'embedded':
265 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
266 ytcfg
['priority'] -= 2
268 ytcfg
['priority'] -= 3
271 build_innertube_clients()
274 class YoutubeBaseInfoExtractor(InfoExtractor
):
275 """Provide base functions for Youtube extractors"""
278 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
279 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
280 r
'browse|oembed|get_video_info|iframe_api|s/player|'
281 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
283 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
285 # _NETRC_MACHINE = 'youtube'
287 # If True it will raise an error if no login info is provided
288 _LOGIN_REQUIRED
= False
291 # invidious-redirect websites
292 r
'(?:www\.)?redirect\.invidious\.io',
293 r
'(?:(?:www|dev)\.)?invidio\.us',
294 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
295 r
'(?:www\.)?invidious\.pussthecat\.org',
296 r
'(?:www\.)?invidious\.zee\.li',
297 r
'(?:www\.)?invidious\.ethibox\.fr',
298 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
299 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
300 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
301 # youtube-dl invidious instances list
302 r
'(?:(?:www|no)\.)?invidiou\.sh',
303 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
304 r
'(?:www\.)?invidious\.kabi\.tk',
305 r
'(?:www\.)?invidious\.mastodon\.host',
306 r
'(?:www\.)?invidious\.zapashcanon\.fr',
307 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
308 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
309 r
'(?:www\.)?invidious\.himiko\.cloud',
310 r
'(?:www\.)?invidious\.reallyancient\.tech',
311 r
'(?:www\.)?invidious\.tube',
312 r
'(?:www\.)?invidiou\.site',
313 r
'(?:www\.)?invidious\.site',
314 r
'(?:www\.)?invidious\.xyz',
315 r
'(?:www\.)?invidious\.nixnet\.xyz',
316 r
'(?:www\.)?invidious\.048596\.xyz',
317 r
'(?:www\.)?invidious\.drycat\.fr',
318 r
'(?:www\.)?inv\.skyn3t\.in',
319 r
'(?:www\.)?tube\.poal\.co',
320 r
'(?:www\.)?tube\.connect\.cafe',
321 r
'(?:www\.)?vid\.wxzm\.sx',
322 r
'(?:www\.)?vid\.mint\.lgbt',
323 r
'(?:www\.)?vid\.puffyan\.us',
324 r
'(?:www\.)?yewtu\.be',
325 r
'(?:www\.)?yt\.elukerio\.org',
326 r
'(?:www\.)?yt\.lelux\.fi',
327 r
'(?:www\.)?invidious\.ggc-project\.de',
328 r
'(?:www\.)?yt\.maisputain\.ovh',
329 r
'(?:www\.)?ytprivate\.com',
330 r
'(?:www\.)?invidious\.13ad\.de',
331 r
'(?:www\.)?invidious\.toot\.koeln',
332 r
'(?:www\.)?invidious\.fdn\.fr',
333 r
'(?:www\.)?watch\.nettohikari\.com',
334 r
'(?:www\.)?invidious\.namazso\.eu',
335 r
'(?:www\.)?invidious\.silkky\.cloud',
336 r
'(?:www\.)?invidious\.exonip\.de',
337 r
'(?:www\.)?invidious\.riverside\.rocks',
338 r
'(?:www\.)?invidious\.blamefran\.net',
339 r
'(?:www\.)?invidious\.moomoo\.de',
340 r
'(?:www\.)?ytb\.trom\.tf',
341 r
'(?:www\.)?yt\.cyberhost\.uk',
342 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
343 r
'(?:www\.)?qklhadlycap4cnod\.onion',
344 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
345 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
346 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
347 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
348 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
349 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
350 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
351 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
352 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
353 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
354 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
355 r
'(?:www\.)?piped\.kavin\.rocks',
356 r
'(?:www\.)?piped\.silkky\.cloud',
357 r
'(?:www\.)?piped\.tokhmi\.xyz',
358 r
'(?:www\.)?piped\.moomoo\.me',
360 r
'(?:www\.)?piped\.syncpundit\.com',
361 r
'(?:www\.)?piped\.mha\.fi',
362 r
'(?:www\.)?piped\.mint\.lgbt',
363 r
'(?:www\.)?piped\.privacy\.com\.de',
366 def _initialize_consent(self
):
367 cookies
= self
._get
_cookies
('https://www.youtube.com/')
368 if cookies
.get('__Secure-3PSID'):
371 consent
= cookies
.get('CONSENT')
373 if 'YES' in consent
.value
:
375 consent_id
= self
._search
_regex
(
376 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
378 consent_id
= random
.randint(100, 999)
379 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
381 def _initialize_pref(self
):
382 cookies
= self
._get
_cookies
('https://www.youtube.com/')
383 pref_cookie
= cookies
.get('PREF')
387 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
389 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
390 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
391 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
393 def _real_initialize(self
):
394 self
._initialize
_pref
()
395 self
._initialize
_consent
()
396 self
._check
_login
_required
()
398 def _check_login_required(self
):
399 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
400 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
402 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
403 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
405 def _get_default_ytcfg(self, client='web'):
406 return copy.deepcopy(INNERTUBE_CLIENTS[client])
408 def _get_innertube_host(self, client='web'):
409 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
411 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
412 # try_get but with fallback to default ytcfg client values when present
413 _func = lambda y: try_get(y, getter, expected_type)
414 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
416 def _extract_client_name(self, ytcfg, default_client='web'):
417 return self._ytcfg_get_safe(
418 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
419 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
421 def _extract_client_version(self, ytcfg, default_client='web'):
422 return self._ytcfg_get_safe(
423 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
424 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
426 def _select_api_hostname(self, req_api_hostname, default_client=None):
427 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
428 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
430 def _extract_api_key(self, ytcfg=None, default_client='web'):
431 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
433 def _extract_context(self, ytcfg=None, default_client='web'):
435 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
436 # Enforce language and tz for extraction
437 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
438 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
443 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
444 time_now = round(time.time())
445 if self._SAPISID is None:
446 yt_cookies = self._get_cookies('https://www.youtube.com')
447 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
448 # See: https://github.com/yt-dlp/yt-dlp/issues/393
449 sapisid_cookie = dict_get(
450 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
451 if sapisid_cookie and sapisid_cookie.value:
452 self._SAPISID = sapisid_cookie.value
453 self.write_debug('Extracted SAPISID cookie')
454 # SAPISID cookie is required if not already present
455 if not yt_cookies.get('SAPISID'):
456 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
458 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
460 self._SAPISID = False
461 if not self._SAPISID:
463 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
464 sapisidhash = hashlib.sha1(
465 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
466 return f'SAPISIDHASH {time_now}_{sapisidhash}'
468 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
469 note='Downloading API JSON', errnote='Unable to download API page',
470 context=None, api_key=None, api_hostname=None, default_client='web'):
472 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
474 real_headers = self.generate_api_headers(default_client=default_client)
475 real_headers.update({'content-type': 'application/json'})
477 real_headers.update(headers)
478 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
479 or api_key or self._extract_api_key(default_client=default_client))
480 return self._download_json(
481 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
482 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
483 data=json.dumps(data).encode('utf8'), headers=real_headers,
484 query={'key': api_key, 'prettyPrint': 'false'})
486 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
487 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
490 def _extract_session_index(*data):
492 Index of current account in account list.
493 See: https://github.com/yt-dlp/yt-dlp/pull/519
496 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
497 if session_index is not None:
501 def _extract_identity_token(self, ytcfg=None, webpage=None):
503 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
507 return self._search_regex(
508 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
509 'identity token
', default=None, fatal=False)
512 def _extract_account_syncid(*args):
514 Extract syncId required to download private playlists of secondary channels
515 @params response and/or ytcfg
518 # ytcfg includes channel_syncid if on secondary channel
519 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
523 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
524 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
525 if len(sync_ids) >= 2 and sync_ids[1]:
526 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
527 # and just "user_syncid||" for primary channel. We only want the channel_syncid
531 def _extract_visitor_data(*args):
533 Extracts visitorData from an API response or ytcfg
534 Appears to be used to track session state
537 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
540 @functools.cached_property
541 def is_authenticated(self):
542 return bool(self._generate_sapisidhash_header())
544 def extract_ytcfg(self, video_id, webpage):
547 return self._parse_json(
549 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
550 default='{}'), video_id, fatal=False) or {}
552 def generate_api_headers(
553 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
554 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
556 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
558 'X-YouTube-Client-Name': str(
559 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
560 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
562 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
563 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
564 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
),
565 'User-Agent': self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT']['client']['userAgent'], default_client
=default_client
)
567 if session_index
is None:
568 session_index
= self
._extract
_session
_index
(ytcfg
)
569 if account_syncid
or session_index
is not None:
570 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
572 auth
= self
._generate
_sapisidhash
_header
(origin
)
574 headers
['Authorization'] = auth
575 headers
['X-Origin'] = origin
576 return {h: v for h, v in headers.items() if v is not None}
578 def _download_ytcfg(self
, client
, video_id
):
580 'web': 'https://www.youtube.com',
581 'web_music': 'https://music.youtube.com',
582 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
586 webpage
= self
._download
_webpage
(
587 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
588 return self
.extract_ytcfg(video_id
, webpage
) or {}
591 def _build_api_continuation_query(continuation
, ctp
=None):
593 'continuation': continuation
595 # TODO: Inconsistency with clickTrackingParams.
596 # Currently we have a fixed ctp contained within context (from ytcfg)
597 # and a ctp in root query for continuation.
599 query
['clickTracking'] = {'clickTrackingParams': ctp}
603 def _extract_next_continuation_data(cls
, renderer
):
604 next_continuation
= try_get(
605 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
606 lambda x
: x
['continuation']['reloadContinuationData']), dict)
607 if not next_continuation
:
609 continuation
= next_continuation
.get('continuation')
612 ctp
= next_continuation
.get('clickTrackingParams')
613 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
616 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
617 if isinstance(continuation_ep
, dict):
618 continuation
= try_get(
619 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
622 ctp
= continuation_ep
.get('clickTrackingParams')
623 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
626 def _extract_continuation(cls
, renderer
):
627 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
628 if next_continuation
:
629 return next_continuation
632 for key
in ('contents', 'items'):
633 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
635 for content
in contents
:
636 if not isinstance(content
, dict):
638 continuation_ep
= try_get(
639 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
640 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
642 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
647 def _extract_alerts(cls
, data
):
648 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
649 if not isinstance(alert_dict
, dict):
651 for alert
in alert_dict
.values():
652 alert_type
= alert
.get('type')
655 message
= cls
._get
_text
(alert
, 'text')
657 yield alert_type
, message
659 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
662 for alert_type
, alert_message
in alerts
:
663 if alert_type
.lower() == 'error' and fatal
:
664 errors
.append([alert_type
, alert_message
])
666 warnings
.append([alert_type
, alert_message
])
668 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
669 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
671 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
673 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
674 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
676 def _extract_badges(self
, renderer
: dict):
678 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
679 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], str)
681 badges
.add(label
.lower())
685 def _get_text(data
, *path_list
, max_runs
=None):
686 for path
in path_list
or [None]:
690 obj
= traverse_obj(data
, path
, default
=[])
691 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
694 text
= try_get(item
, lambda x
: x
['simpleText'], str)
697 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
698 if not runs
and isinstance(item
, list):
701 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
702 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
706 def _get_count(self
, data
, *path_list
):
707 count_text
= self
._get
_text
(data
, *path_list
) or ''
708 count
= parse_count(count_text
)
711 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
715 def _extract_thumbnails(data
, *path_list
):
717 Extract thumbnails from thumbnails dict
718 @param path_list: path list to level that contains 'thumbnails' key
721 for path
in path_list
or [()]:
722 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
723 thumbnail_url
= url_or_none(thumbnail
.get('url'))
724 if not thumbnail_url
:
726 # Sometimes youtube gives a wrong thumbnail URL. See:
727 # https://github.com/yt-dlp/yt-dlp/issues/233
728 # https://github.com/ytdl-org/youtube-dl/issues/28023
729 if 'maxresdefault' in thumbnail_url
:
730 thumbnail_url
= thumbnail_url
.split('?')[0]
732 'url': thumbnail_url
,
733 'height': int_or_none(thumbnail
.get('height')),
734 'width': int_or_none(thumbnail
.get('width')),
739 def extract_relative_time(relative_time_text
):
741 Extracts a relative time from string and converts to dt object
742 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
744 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
)
746 start
= mobj
.group('start')
748 return datetime_from_str(start
)
750 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
754 def _extract_time_text(self
, renderer
, *path_list
):
755 """@returns (timestamp, time_text)"""
756 text
= self
._get
_text
(renderer
, *path_list
) or ''
757 dt
= self
.extract_relative_time(text
)
759 if isinstance(dt
, datetime
.datetime
):
760 timestamp
= calendar
.timegm(dt
.timetuple())
762 if timestamp
is None:
764 unified_timestamp(text
) or unified_timestamp(
766 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
767 text
.lower(), 'time text', default
=None)))
769 if text
and timestamp
is None:
770 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
771 return timestamp
, text
773 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
774 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
775 default_client
='web'):
776 for retry
in self
.RetryManager():
778 response
= self
._call
_api
(
779 ep
=ep
, fatal
=True, headers
=headers
,
780 video_id
=item_id
, query
=query
, note
=note
,
781 context
=self
._extract
_context
(ytcfg
, default_client
),
782 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
783 api_hostname
=api_hostname
, default_client
=default_client
)
784 except ExtractorError
as e
:
785 if not isinstance(e
.cause
, network_exceptions
):
786 return self
._error
_or
_warning
(e
, fatal
=fatal
)
787 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
791 first_bytes
= e
.cause
.read(512)
792 if not is_html(first_bytes
):
795 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
796 lambda x
: x
['error']['message'], str)
798 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
799 # Downloading page may result in intermittent 5xx HTTP error
800 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
801 # We also want to catch all other network exceptions since errors in later pages can be troublesome
802 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
803 if e
.cause
.code
not in (403, 429):
806 return self
._error
_or
_warning
(e
, fatal
=fatal
)
809 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
810 except ExtractorError
as e
:
811 # YouTube servers may return errors we want to retry on in a 200 OK response
812 # See: https://github.com/yt-dlp/yt-dlp/issues/839
813 if 'unknown error' in e
.msg
.lower():
816 return self
._error
_or
_warning
(e
, fatal
=fatal
)
817 # Youtube sometimes sends incomplete data
818 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
819 if not traverse_obj(response
, *variadic(check_get_keys
)):
820 retry
.error
= ExtractorError('Incomplete data received', expected
=True)
826 def is_music_url(url
):
827 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
829 def _extract_video(self
, renderer
):
830 video_id
= renderer
.get('videoId')
831 title
= self
._get
_text
(renderer
, 'title')
832 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
833 duration
= parse_duration(self
._get
_text
(
834 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
836 duration
= parse_duration(self
._search
_regex
(
837 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
838 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
839 video_id
, default
=None, group
='duration'))
841 view_count
= self
._get
_count
(renderer
, 'viewCountText')
843 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
844 channel_id
= traverse_obj(
845 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
846 expected_type
=str, get_all
=False)
847 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
848 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
849 overlay_style
= traverse_obj(
850 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
851 get_all
=False, expected_type
=str)
852 badges
= self
._extract
_badges
(renderer
)
853 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
854 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
855 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
856 expected_type
=str)) or ''
857 url
= f
'https://www.youtube.com/watch?v={video_id}'
858 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
859 url
= f
'https://www.youtube.com/shorts/{video_id}'
863 'ie_key': YoutubeIE
.ie_key(),
867 'description': description
,
868 'duration': duration
,
869 'view_count': view_count
,
870 'uploader': uploader
,
871 'channel_id': channel_id
,
872 'thumbnails': thumbnails
,
873 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
874 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
876 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
877 else 'was_live' if 'streamed' in time_text
.lower()
878 else 'is_live' if overlay_style
== 'LIVE' or 'live now' in badges
880 'release_timestamp': scheduled_timestamp
,
881 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
885 class YoutubeIE(YoutubeBaseInfoExtractor
):
887 _VALID_URL
= r
"""(?x)^
889 (?:https?://|//) # http(s):// or protocol-independent URL
890 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
891 (?:www\.)?deturl\.com/www\.youtube\.com|
892 (?:www\.)?pwnyoutube\.com|
893 (?:www\.)?hooktube\.com|
894 (?:www\.)?yourepeat\.com|
897 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
898 (?:.*?\#/)? # handle anchor (#/) redirect urls
899 (?: # the various things that can precede the ID:
900 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
901 |(?: # or the v= param in all its forms
902 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
903 (?:\?|\#!?) # the params delimiter ? or # or #!
904 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
909 youtu\.be| # just youtu.be/xxxx
910 vid\.plus| # or vid.plus/xxxx
911 zwearz\.com/watch| # or zwearz.com/watch/xxxx
914 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
916 )? # all until now is optional -> you can pass the naked ID
917 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
918 (?(1).+)? # if we found the ID, everything can follow
920 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
922 _EMBED_REGEX
= [r
'''(?x)
932 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
933 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
936 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
937 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$',
938 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
941 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
942 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
943 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
944 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
945 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
946 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
947 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
948 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
949 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
950 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
951 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
952 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
953 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
954 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
955 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
956 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
957 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
958 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
962 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
963 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
964 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
965 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
966 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
967 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
968 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
970 # Apple HTTP Live Streaming
971 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
972 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
973 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
974 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
975 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
976 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
977 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
978 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
981 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
982 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
983 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
984 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
985 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
987 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
990 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
991 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
992 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
995 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
996 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
997 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
998 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
999 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1000 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1001 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1004 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1005 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1006 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1007 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1008 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1011 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1012 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1013 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1014 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1015 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1020 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1022 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1023 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1024 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1025 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1028 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1029 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1031 # Dash webm audio with opus inside
1032 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1033 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1034 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1037 '_rtmp': {'protocol': 'rtmp'},
1039 # av01 video only formats sometimes served with "unknown" codecs
1040 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1041 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1042 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1043 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1044 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1045 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1046 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1047 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1049 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1056 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1058 'id': 'BaW_jenozKc',
1060 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1061 'uploader': 'Philipp Hagemeister',
1062 'uploader_id': 'phihag',
1063 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1064 'channel': 'Philipp Hagemeister',
1065 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1066 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1067 'upload_date': '20121002',
1068 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1069 'categories': ['Science & Technology'],
1070 'tags': ['youtube-dl'],
1074 'availability': 'public',
1075 'playable_in_embed': True,
1076 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1077 'live_status': 'not_live',
1081 'comment_count': int,
1082 'channel_follower_count': int
1086 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1087 'note': 'Embed-only video (#1746)',
1089 'id': 'yZIXLfi8CZQ',
1091 'upload_date': '20120608',
1092 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1093 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1094 'uploader': 'SET India',
1095 'uploader_id': 'setindia',
1096 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1099 'skip': 'Private video',
1102 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1103 'note': 'Use the first video ID in the URL',
1105 'id': 'BaW_jenozKc',
1107 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1108 'uploader': 'Philipp Hagemeister',
1109 'uploader_id': 'phihag',
1110 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1111 'channel': 'Philipp Hagemeister',
1112 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1113 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1114 'upload_date': '20121002',
1115 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1116 'categories': ['Science & Technology'],
1117 'tags': ['youtube-dl'],
1121 'availability': 'public',
1122 'playable_in_embed': True,
1123 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1124 'live_status': 'not_live',
1126 'comment_count': int,
1127 'channel_follower_count': int
1130 'skip_download': True,
1134 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1135 'note': '256k DASH audio (format 141) via DASH manifest',
1137 'id': 'a9LDPn-MO4I',
1139 'upload_date': '20121002',
1140 'uploader_id': '8KVIDEO',
1141 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1143 'uploader': '8KVIDEO',
1144 'title': 'UHDTV TEST 8K VIDEO.mp4'
1147 'youtube_include_dash_manifest': True,
1150 'skip': 'format 141 not served anymore',
1152 # DASH manifest with encrypted signature
1154 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1156 'id': 'IB3lcPjvWLA',
1158 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1159 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1161 'uploader': 'AfrojackVEVO',
1162 'uploader_id': 'AfrojackVEVO',
1163 'upload_date': '20131011',
1166 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1167 'playable_in_embed': True,
1168 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1170 'track': 'The Spark',
1171 'live_status': 'not_live',
1172 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1173 'channel': 'Afrojack',
1174 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1176 'availability': 'public',
1177 'categories': ['Music'],
1179 'alt_title': 'The Spark',
1180 'channel_follower_count': int
1183 'youtube_include_dash_manifest': True,
1184 'format': '141/bestaudio[ext=m4a]',
1187 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1189 'note': 'Embed allowed age-gate video',
1190 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1192 'id': 'HtVdAasjOgU',
1194 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1195 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1197 'uploader': 'The Witcher',
1198 'uploader_id': 'WitcherGame',
1199 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1200 'upload_date': '20140605',
1202 'categories': ['Gaming'],
1203 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1204 'availability': 'needs_auth',
1205 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1207 'channel': 'The Witcher',
1208 'live_status': 'not_live',
1210 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1211 'playable_in_embed': True,
1213 'channel_follower_count': int
1217 'note': 'Age-gate video with embed allowed in public site',
1218 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1220 'id': 'HsUATh_Nc2U',
1222 'title': 'Godzilla 2 (Official Video)',
1223 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1224 'upload_date': '20200408',
1225 'uploader_id': 'FlyingKitty900',
1226 'uploader': 'FlyingKitty',
1228 'availability': 'needs_auth',
1229 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1230 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1231 'channel': 'FlyingKitty',
1232 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1234 'categories': ['Entertainment'],
1235 'live_status': 'not_live',
1236 'tags': ['Flyingkitty', 'godzilla 2'],
1237 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1240 'playable_in_embed': True,
1241 'channel_follower_count': int
1245 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1246 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1248 'id': 'Tq92D6wQ1mg',
1249 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1251 'upload_date': '20191228',
1252 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1253 'uploader': 'Projekt Melody',
1254 'description': 'md5:17eccca93a786d51bc67646756894066',
1257 'availability': 'needs_auth',
1258 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1259 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1261 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1262 'channel': 'Projekt Melody',
1263 'live_status': 'not_live',
1264 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1265 'playable_in_embed': True,
1266 'categories': ['Entertainment'],
1268 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1269 'comment_count': int,
1270 'channel_follower_count': int
1274 'note': 'Non-Agegated non-embeddable video',
1275 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1277 'id': 'MeJVWBSsPAY',
1279 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1280 'uploader': 'Herr Lurik',
1281 'uploader_id': 'st3in234',
1282 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1283 'upload_date': '20130730',
1284 'track': 'Such mich find mich',
1286 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1288 'playable_in_embed': False,
1289 'creator': 'OOMPH!',
1290 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1292 'alt_title': 'Such mich find mich',
1294 'channel': 'Herr Lurik',
1295 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1296 'categories': ['Music'],
1297 'availability': 'public',
1298 'uploader_url': 'http://www.youtube.com/user/st3in234',
1299 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1300 'live_status': 'not_live',
1302 'channel_follower_count': int
1306 'note': 'Non-bypassable age-gated video',
1307 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1308 'only_matching': True,
1310 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1311 # YouTube Red ad is not captured for creator
1313 'url': '__2ABJjxzNo',
1315 'id': '__2ABJjxzNo',
1318 'upload_date': '20100430',
1319 'uploader_id': 'deadmau5',
1320 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1321 'creator': 'deadmau5',
1322 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1323 'uploader': 'deadmau5',
1324 'title': 'Deadmau5 - Some Chords (HD)',
1325 'alt_title': 'Some Chords',
1326 'availability': 'public',
1328 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1330 'live_status': 'not_live',
1331 'channel': 'deadmau5',
1332 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1334 'track': 'Some Chords',
1335 'artist': 'deadmau5',
1336 'playable_in_embed': True,
1338 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1339 'categories': ['Music'],
1340 'album': 'Some Chords',
1341 'channel_follower_count': int
1343 'expected_warnings': [
1344 'DASH manifest missing',
1347 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1349 'url': 'lqQg6PlCWgI',
1351 'id': 'lqQg6PlCWgI',
1354 'upload_date': '20150827',
1355 'uploader_id': 'olympic',
1356 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1357 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1358 'uploader': 'Olympics',
1359 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1361 'release_timestamp': 1343767800,
1362 'playable_in_embed': True,
1363 'categories': ['Sports'],
1364 'release_date': '20120731',
1365 'channel': 'Olympics',
1366 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1367 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1368 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1370 'availability': 'public',
1371 'live_status': 'was_live',
1373 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1374 'channel_follower_count': int
1377 'skip_download': 'requires avconv',
1382 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1384 'id': '_b-2C3KPAM0',
1386 'stretched_ratio': 16 / 9.,
1388 'upload_date': '20110310',
1389 'uploader_id': 'AllenMeow',
1390 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1391 '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',
1393 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1394 'playable_in_embed': True,
1398 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1399 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1400 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1402 'categories': ['People & Blogs'],
1404 'live_status': 'not_live',
1405 'availability': 'unlisted',
1406 'comment_count': int,
1407 'channel_follower_count': int
1410 # url_encoded_fmt_stream_map is empty string
1412 'url': 'qEJwOuvDf7I',
1414 'id': 'qEJwOuvDf7I',
1416 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1418 'upload_date': '20150404',
1419 'uploader_id': 'spbelect',
1420 'uploader': 'Наблюдатели Петербурга',
1423 'skip_download': 'requires avconv',
1425 'skip': 'This live event has ended.',
1427 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1429 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1431 'id': 'FIl7x6_3R5Y',
1433 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1434 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1436 'upload_date': '20150625',
1437 'uploader_id': 'dorappi2000',
1438 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1439 'uploader': 'dorappi2000',
1440 'formats': 'mincount:31',
1442 'skip': 'not actual anymore',
1444 # DASH manifest with segment_list
1446 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1447 'md5': '8ce563a1d667b599d21064e982ab9e31',
1449 'id': 'CsmdDsKjzN8',
1451 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1452 'uploader': 'Airtek',
1453 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1454 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1455 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1458 'youtube_include_dash_manifest': True,
1459 'format': '135', # bestvideo
1461 'skip': 'This live event has ended.',
1464 # Multifeed videos (multiple cameras), URL is for Main Camera
1465 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1467 'id': 'jvGDaLqkpTg',
1468 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1469 'description': 'md5:e03b909557865076822aa169218d6a5d',
1473 'id': 'jvGDaLqkpTg',
1475 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1476 'description': 'md5:e03b909557865076822aa169218d6a5d',
1478 'upload_date': '20161111',
1479 'uploader': 'Team PGP',
1480 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1481 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1485 'id': '3AKt1R1aDnw',
1487 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1488 'description': 'md5:e03b909557865076822aa169218d6a5d',
1490 'upload_date': '20161111',
1491 'uploader': 'Team PGP',
1492 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1493 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1497 'id': 'RtAMM00gpVc',
1499 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1500 'description': 'md5:e03b909557865076822aa169218d6a5d',
1502 'upload_date': '20161111',
1503 'uploader': 'Team PGP',
1504 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1505 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1509 'id': '6N2fdlP3C5U',
1511 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1512 'description': 'md5:e03b909557865076822aa169218d6a5d',
1514 'upload_date': '20161111',
1515 'uploader': 'Team PGP',
1516 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1517 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1521 'skip_download': True,
1523 'skip': 'Not multifeed anymore',
1526 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1527 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1529 'id': 'gVfLd0zydlo',
1530 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1532 'playlist_count': 2,
1533 'skip': 'Not multifeed anymore',
1536 'url': 'https://vid.plus/FlRa-iH7PGw',
1537 'only_matching': True,
1540 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1541 'only_matching': True,
1544 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1545 # Also tests cut-off URL expansion in video description (see
1546 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1547 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1548 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1550 'id': 'lsguqyKfVQg',
1552 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1553 'alt_title': 'Dark Walk',
1554 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1556 'upload_date': '20151119',
1557 'uploader_id': 'IronSoulElf',
1558 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1559 'uploader': 'IronSoulElf',
1560 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1561 'track': 'Dark Walk',
1562 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1563 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1564 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1565 'categories': ['Film & Animation'],
1567 'live_status': 'not_live',
1568 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1569 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1571 'availability': 'public',
1572 'channel': 'IronSoulElf',
1573 'playable_in_embed': True,
1576 'channel_follower_count': int
1579 'skip_download': True,
1583 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1584 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1585 'only_matching': True,
1588 # Video with yt:stretch=17:0
1589 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1591 'id': 'Q39EVAstoRM',
1593 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1594 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1595 'upload_date': '20151107',
1596 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1597 'uploader': 'CH GAMER DROID',
1600 'skip_download': True,
1602 'skip': 'This video does not exist.',
1605 # Video with incomplete 'yt:stretch=16:'
1606 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1607 'only_matching': True,
1610 # Video licensed under Creative Commons
1611 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1613 'id': 'M4gD1WSo5mA',
1615 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1616 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1618 'upload_date': '20150128',
1619 'uploader_id': 'BerkmanCenter',
1620 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1621 'uploader': 'The Berkman Klein Center for Internet & Society',
1622 'license': 'Creative Commons Attribution license (reuse allowed)',
1623 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1624 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1627 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1628 'channel': 'The Berkman Klein Center for Internet & Society',
1629 'availability': 'public',
1631 'categories': ['Education'],
1632 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1633 'live_status': 'not_live',
1634 'playable_in_embed': True,
1635 'comment_count': int,
1636 'channel_follower_count': int
1639 'skip_download': True,
1643 # Channel-like uploader_url
1644 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1646 'id': 'eQcmzGIKrzg',
1648 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1649 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1651 'upload_date': '20151120',
1652 'uploader': 'Bernie Sanders',
1653 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1654 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1655 'license': 'Creative Commons Attribution license (reuse allowed)',
1656 'playable_in_embed': True,
1659 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1661 'availability': 'public',
1662 'categories': ['News & Politics'],
1663 'channel': 'Bernie Sanders',
1664 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1666 'live_status': 'not_live',
1667 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1668 'comment_count': int,
1669 'channel_follower_count': int
1672 'skip_download': True,
1676 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1677 'only_matching': True,
1680 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1681 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1682 'only_matching': True,
1685 # Rental video preview
1686 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1688 'id': 'uGpuVWrhIzE',
1690 'title': 'Piku - Trailer',
1691 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1692 'upload_date': '20150811',
1693 'uploader': 'FlixMatrix',
1694 'uploader_id': 'FlixMatrixKaravan',
1695 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1696 'license': 'Standard YouTube License',
1699 'skip_download': True,
1701 'skip': 'This video is not available.',
1704 # YouTube Red video with episode data
1705 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1707 'id': 'iqKdEhx-dD4',
1709 'title': 'Isolation - Mind Field (Ep 1)',
1710 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1712 'upload_date': '20170118',
1713 'uploader': 'Vsauce',
1714 'uploader_id': 'Vsauce',
1715 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1716 'series': 'Mind Field',
1718 'episode_number': 1,
1719 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1722 'availability': 'public',
1724 'channel': 'Vsauce',
1725 'episode': 'Episode 1',
1726 'categories': ['Entertainment'],
1727 'season': 'Season 1',
1728 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1729 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1731 'playable_in_embed': True,
1732 'live_status': 'not_live',
1733 'channel_follower_count': int
1736 'skip_download': True,
1738 'expected_warnings': [
1739 'Skipping DASH manifest',
1743 # The following content has been identified by the YouTube community
1744 # as inappropriate or offensive to some audiences.
1745 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1747 'id': '6SJNVb0GnPI',
1749 'title': 'Race Differences in Intelligence',
1750 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1752 'upload_date': '20140124',
1753 'uploader': 'New Century Foundation',
1754 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1758 'skip_download': True,
1760 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1764 'url': '1t24XAntNCY',
1765 'only_matching': True,
1768 # geo restricted to JP
1769 'url': 'sJL6WA-aGkQ',
1770 'only_matching': True,
1773 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1774 'only_matching': True,
1777 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1778 'only_matching': True,
1781 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1782 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1783 'only_matching': True,
1787 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1788 'only_matching': True,
1791 # Video with unsupported adaptive stream type formats
1792 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1794 'id': 'Z4Vy8R84T1U',
1796 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1797 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1799 'upload_date': '20130923',
1800 'uploader': 'Amelia Putri Harwita',
1801 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1802 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1803 'formats': 'maxcount:10',
1806 'skip_download': True,
1807 'youtube_include_dash_manifest': False,
1809 'skip': 'not actual anymore',
1812 # Youtube Music Auto-generated description
1813 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1815 'id': 'MgNrAu2pzNs',
1817 'title': 'Voyeur Girl',
1818 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1819 'upload_date': '20190312',
1820 'uploader': 'Stephen - Topic',
1821 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1822 'artist': 'Stephen',
1823 'track': 'Voyeur Girl',
1824 'album': 'it\'s too much love to know my dear',
1825 'release_date': '20190313',
1826 'release_year': 2019,
1827 'alt_title': 'Voyeur Girl',
1829 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1830 'playable_in_embed': True,
1832 'categories': ['Music'],
1833 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1834 'channel': 'Stephen',
1835 'availability': 'public',
1836 'creator': 'Stephen',
1838 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1840 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1842 'live_status': 'not_live',
1843 'channel_follower_count': int
1846 'skip_download': True,
1850 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1851 'only_matching': True,
1854 # invalid -> valid video id redirection
1855 'url': 'DJztXj2GPfl',
1857 'id': 'DJztXj2GPfk',
1859 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1860 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1861 'upload_date': '20090125',
1862 'uploader': 'Prochorowka',
1863 'uploader_id': 'Prochorowka',
1864 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1865 'artist': 'Panjabi MC',
1866 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1867 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1870 'skip_download': True,
1872 'skip': 'Video unavailable',
1875 # empty description results in an empty string
1876 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1878 'id': 'x41yOUIvK2k',
1880 'title': 'IMG 3456',
1882 'upload_date': '20170613',
1883 'uploader_id': 'ElevageOrVert',
1884 'uploader': 'ElevageOrVert',
1886 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1887 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1889 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1891 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1892 'availability': 'public',
1894 'categories': ['Pets & Animals'],
1896 'playable_in_embed': True,
1897 'live_status': 'not_live',
1898 'channel': 'ElevageOrVert',
1899 'channel_follower_count': int
1902 'skip_download': True,
1906 # with '};' inside yt initial data (see [1])
1907 # see [2] for an example with '};' inside ytInitialPlayerResponse
1908 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1909 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1910 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1912 'id': 'CHqg6qOn4no',
1914 'title': 'Part 77 Sort a list of simple types in c#',
1915 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1916 'upload_date': '20130831',
1917 'uploader_id': 'kudvenkat',
1918 'uploader': 'kudvenkat',
1919 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1921 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1922 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1923 'live_status': 'not_live',
1924 'categories': ['Education'],
1925 'availability': 'public',
1926 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1928 'playable_in_embed': True,
1932 'channel': 'kudvenkat',
1933 'comment_count': int,
1934 'channel_follower_count': int
1937 'skip_download': True,
1941 # another example of '};' in ytInitialData
1942 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1943 'only_matching': True,
1946 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1947 'only_matching': True,
1950 # https://github.com/ytdl-org/youtube-dl/pull/28094
1951 'url': 'OtqTfy26tG0',
1953 'id': 'OtqTfy26tG0',
1955 'title': 'Burn Out',
1956 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1957 'upload_date': '20141120',
1958 'uploader': 'The Cinematic Orchestra - Topic',
1959 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1960 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1961 'artist': 'The Cinematic Orchestra',
1962 'track': 'Burn Out',
1963 'album': 'Every Day',
1965 'live_status': 'not_live',
1966 'alt_title': 'Burn Out',
1970 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1971 'creator': 'The Cinematic Orchestra',
1972 'channel': 'The Cinematic Orchestra',
1973 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1974 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1975 'availability': 'public',
1976 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1977 'categories': ['Music'],
1978 'playable_in_embed': True,
1979 'channel_follower_count': int
1982 'skip_download': True,
1986 # controversial video, only works with bpctr when authenticated with cookies
1987 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1988 'only_matching': True,
1991 # controversial video, requires bpctr/contentCheckOk
1992 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1994 'id': 'SZJvDhaSDnc',
1996 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1997 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1998 'uploader': 'CBS Mornings',
1999 'uploader_id': 'CBSThisMorning',
2000 'upload_date': '20140716',
2001 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2003 'categories': ['News & Politics'],
2004 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2006 'channel': 'CBS Mornings',
2007 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2008 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2010 'availability': 'needs_auth',
2011 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2013 'live_status': 'not_live',
2014 'playable_in_embed': True,
2015 'channel_follower_count': int
2019 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2020 'url': 'cBvYw8_A0vQ',
2022 'id': 'cBvYw8_A0vQ',
2024 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2025 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2026 'upload_date': '20201120',
2027 'uploader': 'Walk around Japan',
2028 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2029 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2031 'categories': ['Travel & Events'],
2032 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2034 'channel': 'Walk around Japan',
2035 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2036 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2038 'availability': 'public',
2039 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2040 'live_status': 'not_live',
2041 'playable_in_embed': True,
2042 'channel_follower_count': int
2045 'skip_download': True,
2048 # Has multiple audio streams
2049 'url': 'WaOKSUlf4TM',
2050 'only_matching': True
2052 # Requires Premium: has format 141 when requested using YTM url
2053 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2054 'only_matching': True
2056 # multiple subtitles with same lang_code
2057 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2058 'only_matching': True,
2060 # Force use android client fallback
2061 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2063 'id': 'YOelRv7fMxY',
2064 'title': 'DIGGING A SECRET TUNNEL Part 1',
2066 'upload_date': '20210624',
2067 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2068 'uploader': 'colinfurze',
2069 'uploader_id': 'colinfurze',
2070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2071 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2073 'categories': ['Entertainment'],
2074 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2076 'channel': 'colinfurze',
2077 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2078 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2080 'availability': 'public',
2082 'live_status': 'not_live',
2083 'playable_in_embed': True,
2084 'channel_follower_count': int
2087 'format': '17', # 3gp format available on android
2088 'extractor_args': {'youtube': {'player_client': ['android']}},
2092 # Skip download of additional client configs (remix client config in this case)
2093 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2094 'only_matching': True,
2096 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2100 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2101 'only_matching': True,
2103 'note': 'Storyboards',
2104 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2106 'id': '5KLPxDtMqe8',
2109 'title': 'Your Brain is Plastic',
2110 'uploader_id': 'scishow',
2111 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2112 'upload_date': '20140324',
2113 'uploader': 'SciShow',
2115 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2116 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2118 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2119 'playable_in_embed': True,
2121 'uploader_url': 'http://www.youtube.com/user/scishow',
2122 'availability': 'public',
2123 'channel': 'SciShow',
2124 'live_status': 'not_live',
2126 'categories': ['Education'],
2128 'channel_follower_count': int
2129 }, 'params': {'format': 'mhtml', 'skip_download': True}
2131 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2132 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2134 'id': '2NUZ8W2llS4',
2136 'title': 'The NP that test your phone performance 🙂',
2137 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2138 'uploader': 'Leon Nguyen',
2139 'uploader_id': 'VNSXIII',
2140 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2141 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2142 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2146 'categories': ['Gaming'],
2148 'playable_in_embed': True,
2149 'live_status': 'not_live',
2150 'upload_date': '20220103',
2152 'availability': 'public',
2153 'channel': 'Leon Nguyen',
2154 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2155 'comment_count': int,
2156 'channel_follower_count': int
2159 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2160 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2162 'id': 'mzZzzBU6lrM',
2164 'title': 'I Met GeorgeNotFound In Real Life...',
2165 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2166 'uploader': 'Quackity',
2167 'uploader_id': 'QuackityHQ',
2168 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2169 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2170 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2174 'categories': ['Entertainment'],
2176 'playable_in_embed': True,
2177 'live_status': 'not_live',
2178 'release_timestamp': 1641172509,
2179 'release_date': '20220103',
2180 'upload_date': '20220103',
2182 'availability': 'public',
2183 'channel': 'Quackity',
2184 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2185 'channel_follower_count': int
2188 { # continuous livestream. Microformat upload date should be preferred.
2189 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2190 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2192 'id': 'kgx4WGK0oNU',
2193 '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}',
2195 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2196 'availability': 'public',
2198 'release_timestamp': 1637975704,
2199 'upload_date': '20210619',
2200 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2201 'live_status': 'is_live',
2202 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2203 'uploader': '阿鲍Abao',
2204 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2205 'channel': 'Abao in Tokyo',
2206 'channel_follower_count': int,
2207 'release_date': '20211127',
2209 'categories': ['People & Blogs'],
2211 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2213 'playable_in_embed': True,
2214 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2216 'params': {'skip_download': True}
2218 # Story. Requires specific player params to work.
2219 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2221 'id': 'vv8qTUWmulI',
2223 'availability': 'unlisted',
2225 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2226 'upload_date': '20220526',
2227 'categories': ['Education'],
2229 'channel': 'IT\'S HISTORY',
2231 'uploader_id': 'BlastfromthePast',
2233 'uploader': 'IT\'S HISTORY',
2234 'playable_in_embed': True,
2236 'live_status': 'not_live',
2238 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2239 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2240 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2242 'skip': 'stories get removed after some period of time',
2244 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2246 'id': 'tjjjtzRLHvA',
2248 'title': 'ハッシュタグ無し };if window.ytcsi',
2249 'upload_date': '20220323',
2251 'availability': 'unlisted',
2252 'channel': 'nao20010128nao',
2253 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2255 'uploader': 'nao20010128nao',
2256 'uploader_id': 'nao20010128nao',
2257 'categories': ['Music'],
2260 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2261 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2262 'live_status': 'not_live',
2263 'playable_in_embed': True,
2264 'channel_follower_count': int,
2267 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2270 'note': '6 channel audio',
2271 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2272 'only_matching': True,
2277 # YouTube <object> embed
2279 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2280 'md5': '873c81d308b979f0e23ee7e620b312a3',
2282 'id': 'msN87y-iEx0',
2284 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2285 'upload_date': '20080526',
2286 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2287 'uploader': 'Christopher Sykes',
2288 'uploader_id': 'ChristopherJSykes',
2290 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2291 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2292 'playable_in_embed': True,
2293 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2295 'comment_count': int,
2296 'channel': 'Christopher Sykes',
2297 'live_status': 'not_live',
2298 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2299 'availability': 'public',
2302 'categories': ['Science & Technology'],
2303 'channel_follower_count': int,
2304 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2307 'skip_download': True,
2313 def suitable(cls, url):
2314 from ..utils import parse_qs
2317 if qs.get('list', [None])[0]:
2319 return super().suitable(url)
2321 def __init__(self, *args, **kwargs):
2322 super().__init__(*args, **kwargs)
2323 self._code_cache = {}
2324 self._player_cache = {}
2326 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2327 lock = threading.Lock()
2330 start_time = time.time()
2331 formats = [f for f in formats if f.get('is_from_start')]
2333 def refetch_manifest(format_id, delay):
2334 nonlocal formats, start_time, is_live
2335 if time.time() <= start_time + delay:
2338 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2339 video_details = traverse_obj(
2340 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2341 microformats = traverse_obj(
2342 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2343 expected_type=dict, default=[])
2344 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2345 start_time = time.time()
2347 def mpd_feed(format_id, delay):
2349 @returns (manifest_url, manifest_stream_number, is_live) or None
2352 refetch_manifest(format_id, delay)
2354 f = next((f for f in formats if f['format_id'] == format_id), None)
2357 self.to_screen(f'{video_id}: Video is no longer live')
2359 self.report_warning(
2360 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2362 return f['manifest_url'], f['manifest_stream_number'], is_live
2366 f['protocol'] = 'http_dash_segments_generator'
2367 f['fragments'] = functools.partial(
2368 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2370 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2371 FETCH_SPAN, MAX_DURATION = 5, 432000
2373 mpd_url, stream_number, is_live = None, None, True
2376 download_start_time = ctx.get('start') or time.time()
2378 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2379 if lack_early_segments:
2380 self.report_warning(bug_reports_message(
2381 'Starting download from the last 120 hours of the live stream since '
2382 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2383 lack_early_segments = True
2385 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2386 fragments, fragment_base_url = None, None
2388 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2389 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2390 # Obtain from MPD's maximum seq value
2391 old_mpd_url = mpd_url
2392 last_error = ctx.pop('last_error', None)
2393 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2394 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2395 or (mpd_url, stream_number, False))
2396 if not refresh_sequence:
2397 if expire_fast and not is_live:
2398 return False, last_seq
2399 elif old_mpd_url == mpd_url:
2400 return True, last_seq
2402 fmts, _ = self._extract_mpd_formats_and_subtitles(
2403 mpd_url, None, note=False, errnote=False, fatal=False)
2404 except ExtractorError:
2407 no_fragment_score += 2
2408 return False, last_seq
2409 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2410 fragments = fmt_info['fragments']
2411 fragment_base_url = fmt_info['fragment_base_url']
2412 assert fragment_base_url
2414 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2415 return True, _last_seq
2418 fetch_time = time.time()
2419 if no_fragment_score > 30:
2421 if last_segment_url:
2422 # Obtain from "X-Head-Seqnum" header value from each segment
2424 urlh = self._request_webpage(
2425 last_segment_url, None, note=False, errnote=False, fatal=False)
2426 except ExtractorError:
2428 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2429 if last_seq is None:
2430 no_fragment_score += 2
2431 last_segment_url = None
2434 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2435 no_fragment_score += 2
2436 if not should_continue:
2439 if known_idx > last_seq:
2440 last_segment_url = None
2445 if begin_index < 0 and known_idx < 0:
2446 # skip from the start when it's negative value
2447 known_idx = last_seq + begin_index
2448 if lack_early_segments:
2449 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2451 for idx in range(known_idx, last_seq):
2452 # do not update sequence here or you'll get skipped some part of it
2453 should_continue, _ = _extract_sequence_from_mpd(False, False)
2454 if not should_continue:
2456 raise ExtractorError('breaking out of outer loop')
2457 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2459 'url': last_segment_url,
2460 'fragment_count': last_seq,
2462 if known_idx == last_seq:
2463 no_fragment_score += 5
2465 no_fragment_score = 0
2466 known_idx = last_seq
2467 except ExtractorError:
2470 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2472 def _extract_player_url(self, *ytcfgs, webpage=None):
2473 player_url = traverse_obj(
2474 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2475 get_all=False, expected_type=str)
2478 return urljoin('https://www.youtube.com', player_url)
2480 def _download_player_url(self, video_id, fatal=False):
2481 res = self._download_webpage(
2482 'https://www.youtube.com/iframe_api',
2483 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2485 player_version = self._search_regex(
2486 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2488 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2490 def _signature_cache_id(self, example_sig):
2491 """ Return a string representation of a signature """
2492 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2495 def _extract_player_info(cls, player_url):
2496 for player_re in cls._PLAYER_INFO_RE:
2497 id_m = re.search(player_re, player_url)
2501 raise ExtractorError('Cannot identify player %r' % player_url)
2502 return id_m.group('id')
2504 def _load_player(self, video_id, player_url, fatal=True):
2505 player_id = self._extract_player_info(player_url)
2506 if player_id not in self._code_cache:
2507 code = self._download_webpage(
2508 player_url, video_id, fatal=fatal,
2509 note='Downloading player ' + player_id,
2510 errnote='Download of %s failed' % player_url)
2512 self._code_cache[player_id] = code
2513 return self._code_cache.get(player_id)
2515 def _extract_signature_function(self, video_id, player_url, example_sig):
2516 player_id = self._extract_player_info(player_url)
2518 # Read from filesystem cache
2519 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2520 assert os.path.basename(func_id) == func_id
2522 self.write_debug(f'Extracting signature function {func_id}')
2523 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2526 code = self._load_player(video_id, player_url)
2528 res = self._parse_sig_js(code)
2529 test_string = ''.join(map(chr, range(len(example_sig))))
2530 cache_spec = [ord(c) for c in res(test_string)]
2531 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2533 return lambda s: ''.join(s[i] for i in cache_spec)
2535 def _print_sig_code(self, func, example_sig):
2536 if not self.get_param('youtube_print_sig_code'):
2539 def gen_sig_code(idxs):
2540 def _genslice(start, end, step):
2541 starts = '' if start == 0 else str(start)
2542 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2543 steps = '' if step == 1 else (':%d' % step)
2544 return f's[{starts}{ends}{steps}]'
2547 # Quelch pyflakes warnings - start will be set when step is set
2548 start = '(Never used)'
2549 for i, prev in zip(idxs[1:], idxs[:-1]):
2550 if step is not None:
2551 if i - prev == step:
2553 yield _genslice(start, prev, step)
2556 if i - prev in [-1, 1]:
2561 yield 's[%d]' % prev
2565 yield _genslice(start, i, step)
2567 test_string = ''.join(map(chr, range(len(example_sig))))
2568 cache_res = func(test_string)
2569 cache_spec = [ord(c) for c in cache_res]
2570 expr_code = ' + '.join(gen_sig_code(cache_spec))
2571 signature_id_tuple = '(%s)' % (
2572 ', '.join(str(len(p)) for p in example_sig.split('.')))
2573 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2574 ' return %s\n') % (signature_id_tuple, expr_code)
2575 self.to_screen('Extracted signature function:\n' + code)
2577 def _parse_sig_js(self, jscode):
2578 funcname = self._search_regex(
2579 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2580 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2581 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2582 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2583 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}\(a,\d+\)',
2584 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\(\s*""\s*\)',
2585 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2587 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2588 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2589 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2590 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2591 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2592 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2593 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2594 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2595 jscode, 'Initial JS player signature function name', group='sig')
2597 jsi = JSInterpreter(jscode)
2598 initial_function = jsi.extract_function(funcname)
2599 return lambda s: initial_function([s])
2601 def _cached(self, func, *cache_id):
2602 def inner(*args, **kwargs):
2603 if cache_id not in self._player_cache:
2605 self._player_cache[cache_id] = func(*args, **kwargs)
2606 except ExtractorError as e:
2607 self._player_cache[cache_id] = e
2608 except Exception as e:
2609 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2611 ret = self._player_cache[cache_id]
2612 if isinstance(ret, Exception):
2617 def _decrypt_signature(self, s, video_id, player_url):
2618 """Turn the encrypted s field into a working signature"""
2619 extract_sig = self._cached(
2620 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2621 func = extract_sig(video_id, player_url, s)
2622 self._print_sig_code(func, s)
2625 def _decrypt_nsig(self, s, video_id, player_url):
2626 """Turn the encrypted n field into a working signature"""
2627 if player_url is None:
2628 raise ExtractorError('Cannot decrypt nsig without player_url')
2629 player_url = urljoin('https://www.youtube.com', player_url)
2631 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2632 if self.get_param('youtube_print_sig_code'):
2633 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2636 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2637 ret = extract_nsig(jsi, func_code)(s)
2638 except JSInterpreter.Exception as e:
2640 jsi = PhantomJSwrapper(self, timeout=5000)
2641 except ExtractorError:
2643 self.report_warning(
2644 f'Native nsig extraction failed: Trying with PhantomJS\n'
2645 f' n = {s} ; player = {player_url}', video_id)
2648 args, func_body = func_code
2650 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2651 video_id=video_id, note='Executing signature code').strip()
2653 self.write_debug(f'Decrypted nsig {s} => {ret}')
2656 def _extract_n_function_name(self, jscode):
2657 funcname, idx = self._search_regex(
2658 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2659 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2663 return json.loads(js_to_json(self._search_regex(
2664 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2665 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2667 def _extract_n_function_code(self, video_id, player_url):
2668 player_id = self._extract_player_info(player_url)
2669 func_code = self.cache.load('youtube-nsig', player_id, after='2022.08.19')
2670 jscode = func_code or self._load_player(video_id, player_url)
2671 jsi = JSInterpreter(jscode)
2674 return jsi, player_id, func_code
2676 func_code = jsi.extract_function_code(self._extract_n_function_name(jscode))
2677 self.cache.store('youtube-nsig', player_id, func_code)
2678 return jsi, player_id, func_code
2680 def _extract_n_function_from_code(self, jsi, func_code):
2681 func = jsi.extract_function_from_code(*func_code)
2683 def extract_nsig(s):
2686 except JSInterpreter.Exception:
2688 except Exception as e:
2689 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2691 if ret.startswith('enhanced_except_'):
2692 raise JSInterpreter.Exception('Signature function returned an exception')
2697 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2699 Extract signatureTimestamp (sts)
2700 Required to tell API what sig/player version is in use.
2703 if isinstance(ytcfg, dict):
2704 sts = int_or_none(ytcfg.get('STS'))
2707 # Attempt to extract from player
2708 if player_url is None:
2709 error_msg = 'Cannot extract signature timestamp without player_url.'
2711 raise ExtractorError(error_msg)
2712 self.report_warning(error_msg)
2714 code = self._load_player(video_id, player_url, fatal=fatal)
2716 sts = int_or_none(self._search_regex(
2717 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2718 'JS player signature timestamp', group='sts', fatal=fatal))
2721 def _mark_watched(self, video_id, player_responses):
2722 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2723 label = 'fully ' if is_full else ''
2724 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2725 expected_type=url_or_none)
2727 self.report_warning(f'Unable to mark {label}watched')
2729 parsed_url = urllib.parse.urlparse(url)
2730 qs = urllib.parse.parse_qs(parsed_url.query)
2732 # cpn generation algorithm is reverse engineered from base.js.
2733 # In fact it works even with dummy cpn.
2734 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2735 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2737 # # more consistent results setting it to right before the end
2738 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2743 'cmt': video_length,
2744 'el': 'detailpage', # otherwise defaults to "shorts"
2748 # these seem to mark watchtime "history" in the real world
2749 # they're required, so send in a single value
2755 url = urllib.parse.urlunparse(
2756 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2758 self._download_webpage(
2759 url, video_id, f'Marking {label}watched',
2760 'Unable to mark watched', fatal=False)
2763 def _extract_from_webpage(cls, url, webpage):
2764 # Invidious Instances
2765 # https://github.com/yt-dlp/yt-dlp/issues/195
2766 # https://github.com/iv-org/invidious/pull/1730
2768 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2771 yield cls.url_result(mobj.group('url'), cls)
2772 raise cls.StopExtraction()
2774 yield from super()._extract_from_webpage(url, webpage)
2776 # lazyYT YouTube embed
2777 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2778 yield cls.url_result(unescapeHTML(id_), cls, id_)
2780 # Wordpress "YouTube Video Importer" plugin
2781 for m in re.findall(r'''(?x
)<div
[^
>]+
2782 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2783 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
2784 yield cls.url_result(m[-1], cls, m[-1])
2787 def extract_id(cls, url):
2788 video_id = cls.get_temp_id(url)
2790 raise ExtractorError(f'Invalid URL: {url}')
2793 def _extract_chapters_from_json(self, data, duration):
2794 chapter_list = traverse_obj(
2796 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2797 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2798 ), expected_type=list)
2800 return self._extract_chapters(
2802 chapter_time=lambda chapter: float_or_none(
2803 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2804 chapter_title=lambda chapter: traverse_obj(
2805 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2808 def _extract_chapters_from_engagement_panel(self, data, duration):
2809 content_list = traverse_obj(
2811 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2812 expected_type=list, default=[])
2813 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2814 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2816 return next(filter(None, (
2817 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2818 chapter_time, chapter_title, duration)
2819 for contents in content_list)), [])
2821 def _extract_chapters_from_description(self, description, duration):
2822 return self._extract_chapters(
2823 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2824 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2825 duration=duration, strict=False)
2827 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2831 'start_time': chapter_time(chapter),
2832 'title': chapter_title(chapter),
2833 } for chapter in chapter_list or []]
2835 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2837 chapters = [{'start_time': 0}]
2838 for idx, chapter in enumerate(chapter_list):
2839 if chapter['start_time'] is None:
2840 self.report_warning(f'Incomplete chapter {idx}')
2841 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2842 chapters.append(chapter)
2844 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2847 def _extract_comment(self, comment_renderer, parent=None):
2848 comment_id = comment_renderer.get('commentId')
2852 text = self._get_text(comment_renderer, 'contentText')
2854 # note: timestamp is an estimate calculated from the current time and time_text
2855 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2856 author = self._get_text(comment_renderer, 'authorText')
2857 author_id = try_get(comment_renderer,
2858 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2860 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2861 lambda x: x['likeCount']), str)) or 0
2862 author_thumbnail = try_get(comment_renderer,
2863 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2865 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2866 is_favorited = 'creatorHeart' in (try_get(
2867 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2871 'timestamp': timestamp,
2872 'time_text': time_text,
2873 'like_count': votes,
2874 'is_favorited': is_favorited,
2876 'author_id': author_id,
2877 'author_thumbnail': author_thumbnail,
2878 'author_is_uploader': author_is_uploader,
2879 'parent': parent or 'root'
2882 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2884 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2886 def extract_header(contents):
2887 _continuation = None
2888 for content in contents:
2889 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2890 expected_comment_count = self._get_count(
2891 comments_header_renderer, 'countText', 'commentsCount')
2893 if expected_comment_count:
2894 tracker['est_total'] = expected_comment_count
2895 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2896 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2898 sort_menu_item = try_get(
2899 comments_header_renderer,
2900 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2901 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2903 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2904 if not _continuation:
2907 sort_text = str_or_none(sort_menu_item.get('title'))
2909 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2910 self.to_screen('Sorting comments by %s' % sort_text.lower())
2912 return _continuation
2914 def extract_thread(contents):
2916 tracker['current_page_thread'] = 0
2917 for content in contents:
2918 if not parent and tracker['total_parent_comments'] >= max_parents:
2920 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2921 comment_renderer = get_first(
2922 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2923 expected_type=dict, default={})
2925 comment = self._extract_comment(comment_renderer, parent)
2929 tracker['running_total'] += 1
2930 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2933 # Attempt to get the replies
2934 comment_replies_renderer = try_get(
2935 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2937 if comment_replies_renderer:
2938 tracker['current_page_thread'] += 1
2939 comment_entries_iter = self._comment_entries(
2940 comment_replies_renderer, ytcfg, video_id,
2941 parent=comment.get('id'), tracker=tracker)
2942 yield from itertools.islice(comment_entries_iter, min(
2943 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2945 # Keeps track of counts across recursive calls
2950 current_page_thread=0,
2951 total_parent_comments=0,
2952 total_reply_comments=0)
2955 # YouTube comments have a max depth of 2
2956 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
2958 self._downloader.deprecation_warning(
2959 '[youtube] max_comment_depth extractor argument is deprecated. Set max replies in the max-comments extractor argument instead.')
2960 if max_depth == 1 and parent:
2963 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
2964 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
2966 continuation = self._extract_continuation(root_continuation_data)
2969 is_forced_continuation = False
2970 is_first_continuation = parent is None
2971 if is_first_continuation and not continuation:
2972 # Sometimes you can get comments by generating the continuation yourself,
2973 # even if YouTube initially reports them being disabled - e.g. stories comments.
2974 # Note: if the comment section is actually disabled, YouTube may return a response with
2975 # required check_get_keys missing. So we will disable that check initially in this case.
2976 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
2977 is_forced_continuation = True
2979 for page_num in itertools.count(0):
2980 if not continuation:
2982 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
2983 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
2985 if is_first_continuation:
2986 note_prefix = 'Downloading comment section API JSON'
2988 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2989 tracker['current_page_thread'], comment_prog_str)
2991 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2992 ' ' if parent else '', ' replies' if parent else '',
2993 page_num, comment_prog_str)
2995 response = self._extract_response(
2996 item_id=None, query=continuation,
2997 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2998 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
2999 is_forced_continuation = False
3000 continuation_contents = traverse_obj(
3001 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3004 for continuation_section in continuation_contents:
3005 continuation_items = traverse_obj(
3006 continuation_section,
3007 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3008 get_all=False, expected_type=list) or []
3009 if is_first_continuation:
3010 continuation = extract_header(continuation_items)
3011 is_first_continuation = False
3016 for entry in extract_thread(continuation_items):
3020 continuation = self._extract_continuation({'contents': continuation_items})
3024 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3025 if message and not parent and tracker['running_total'] == 0:
3026 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3029 def _generate_comment_continuation(video_id):
3031 Generates initial comment section continuation token from given video id
3033 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3034 return base64.b64encode(token.encode()).decode()
3036 def _get_comments(self, ytcfg, video_id, contents, webpage):
3037 """Entry for comment extraction"""
3038 def _real_comment_extract(contents):
3040 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3041 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3042 yield from self._comment_entries(renderer, ytcfg, video_id)
3044 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3045 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3048 def _get_checkok_params():
3049 return {'contentCheckOk': True, 'racyCheckOk': True}
3052 def _generate_player_context(cls, sts=None):
3054 'html5Preference': 'HTML5_PREF_WANTS',
3057 context['signatureTimestamp'] = sts
3059 'playbackContext': {
3060 'contentPlaybackContext': context
3062 **cls._get_checkok_params()
3066 def _is_agegated(player_response):
3067 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3070 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3071 AGE_GATE_REASONS = (
3072 'confirm your age', 'age-restricted', 'inappropriate', # reason
3073 'age_verification_required', 'age_check_required', # status
3075 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3078 def _is_unplayable(player_response):
3079 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3081 _STORY_PLAYER_PARAMS = '8AEB'
3083 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3085 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3086 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3087 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3088 headers = self.generate_api_headers(
3089 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3092 'videoId': video_id,
3094 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3095 yt_query['params'] = self._STORY_PLAYER_PARAMS
3097 yt_query.update(self._generate_player_context(sts))
3098 return self._extract_response(
3099 item_id=video_id, ep='player', query=yt_query,
3100 ytcfg=player_ytcfg, headers=headers, fatal=True,
3101 default_client=client,
3102 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3105 def _get_requested_clients(self, url, smuggled_data):
3106 requested_clients = []
3107 default = ['android', 'web']
3108 allowed_clients = sorted(
3109 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3110 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3111 for client in self._configuration_arg('player_client'):
3112 if client in allowed_clients:
3113 requested_clients.append(client)
3114 elif client == 'default':
3115 requested_clients.extend(default)
3116 elif client == 'all':
3117 requested_clients.extend(allowed_clients)
3119 self.report_warning(f'Skipping unsupported client {client}')
3120 if not requested_clients:
3121 requested_clients = default
3123 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3124 requested_clients.extend(
3125 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3127 return orderedSet(requested_clients)
3129 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3132 initial_pr = self._search_json(
3133 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3135 all_clients = set(clients)
3136 clients = clients[::-1]
3139 def append_client(*client_names):
3140 """ Append the first client name that exists but not already used """
3141 for client_name in client_names:
3142 actual_client = _split_innertube_client(client_name)[0]
3143 if actual_client in INNERTUBE_CLIENTS:
3144 if actual_client not in all_clients:
3145 clients.append(client_name)
3146 all_clients.add(actual_client)
3149 # Android player_response does not have microFormats which are needed for
3150 # extraction of some data. So we return the initial_pr with formats
3151 # stripped out even if not requested by the user
3152 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3154 pr = dict(initial_pr)
3155 pr['streamingData'] = None
3159 tried_iframe_fallback = False
3162 client, base_client, variant = _split_innertube_client(clients.pop())
3163 player_ytcfg = master_ytcfg if client == 'web' else {}
3164 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3165 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3167 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3168 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3169 if 'js' in self._configuration_arg('player_skip'):
3170 require_js_player = False
3173 if not player_url and not tried_iframe_fallback and require_js_player:
3174 player_url = self._download_player_url(video_id)
3175 tried_iframe_fallback = True
3178 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3179 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3180 except ExtractorError as e:
3182 self.report_warning(last_error)
3187 # YouTube may return a different video player response than expected.
3188 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3189 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3190 if pr_video_id and pr_video_id != video_id:
3191 self.report_warning(
3192 f'Skipping player response from {client} client (got player response for video "{pr_video_id}
" instead of "{video_id}
")' + bug_reports_message())
3196 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3197 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3198 append_client(f'{base_client}_creator')
3199 elif self._is_agegated(pr):
3200 if variant == 'tv_embedded':
3201 append_client(f'{base_client}_embedded')
3203 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3208 self.report_warning(last_error)
3209 return prs, player_url
3211 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
3212 itags, stream_ids = {}, []
3213 itag_qualities, res_qualities = {}, {0: None}
3215 # Normally tiny is the smallest video-only formats. But
3216 # audio-only formats with unknown quality may get tagged as tiny
3218 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3219 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3221 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3223 for fmt in streaming_formats:
3224 if fmt.get('targetDurationSec'):
3227 itag = str_or_none(fmt.get('itag'))
3228 audio_track = fmt.get('audioTrack') or {}
3229 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3230 if stream_id in stream_ids:
3233 quality = fmt.get('quality')
3234 height = int_or_none(fmt.get('height'))
3235 if quality == 'tiny' or not quality:
3236 quality = fmt.get('audioQuality', '').lower() or quality
3237 # The 3gp format (17) in android client has a quality of "small
",
3238 # but is actually worse than other formats
3243 itag_qualities[itag] = quality
3245 res_qualities[height] = quality
3246 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3247 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3248 # number of fragment that would subsequently requested with (`&sq=N`)
3249 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3252 fmt_url = fmt.get('url')
3254 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3255 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3256 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3257 if not all((sc, fmt_url, player_url, encrypted_sig)):
3260 fmt_url += '&%s=%s' % (
3261 traverse_obj(sc, ('sp', -1)) or 'signature',
3262 self._decrypt_signature(encrypted_sig, video_id, player_url)
3264 except ExtractorError as e:
3265 self.report_warning('Signature extraction failed: Some formats may be missing',
3266 video_id=video_id, only_once=True)
3267 self.write_debug(e, only_once=True)
3270 query = parse_qs(fmt_url)
3274 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3275 fmt_url = update_url_query(fmt_url, {
3276 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3278 except ExtractorError as e:
3280 if isinstance(e, JSInterpreter.Exception):
3281 phantomjs_hint = f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} to workaround the issue\n'
3282 self.report_warning(
3283 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3284 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3285 self.write_debug(e, only_once=True)
3289 itags[itag] = 'https'
3290 stream_ids.append(stream_id)
3292 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3293 language_preference = (
3294 10 if audio_track.get('audioIsDefault') and 10
3295 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3297 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3298 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3299 # Make sure to avoid false positives with small duration differences.
3300 # E.g. __2ABJjxzNo, ySuUZEjARPY
3301 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3303 self.report_warning(
3304 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3306 'asr': int_or_none(fmt.get('audioSampleRate')),
3307 'filesize': int_or_none(fmt.get('contentLength')),
3309 'format_note': join_nonempty(
3310 '%s%s' % (audio_track.get('displayName') or '',
3311 ' (default)' if language_preference > 0 else ''),
3312 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3313 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3314 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3315 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3316 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3317 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3318 'fps': int_or_none(fmt.get('fps')) or None,
3319 'audio_channels': fmt.get('audioChannels'),
3321 'quality': q(quality),
3322 'has_drm': bool(fmt.get('drmFamilies')),
3325 'width': int_or_none(fmt.get('width')),
3326 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3327 'desc' if language_preference < -1 else ''),
3328 'language_preference': language_preference,
3329 # Strictly de-prioritize damaged and 3gp formats
3330 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3332 mime_mobj = re.match(
3333 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3335 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3336 dct.update(parse_codecs(mime_mobj.group(2)))
3337 no_audio = dct.get('acodec
') == 'none
'
3338 no_video = dct.get('vcodec
') == 'none
'
3343 if no_audio or no_video:
3344 dct['downloader_options
'] = {
3345 # Youtube throttles chunks >~10M
3346 'http_chunk_size
': 10485760,
3349 dct['container
'] = dct['ext
'] + '_dash
'
3352 live_from_start = is_live and self.get_param('live_from_start
')
3353 skip_manifests = self._configuration_arg('skip
')
3354 if not self.get_param('youtube_include_hls_manifest
', True):
3355 skip_manifests.append('hls
')
3356 if not self.get_param('youtube_include_dash_manifest
', True):
3357 skip_manifests.append('dash
')
3358 get_dash = 'dash
' not in skip_manifests and (
3359 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3360 get_hls = not live_from_start and 'hls
' not in skip_manifests
3362 def process_manifest_format(f, proto, itag):
3364 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3366 itag = f'{itag}
-{proto}
'
3368 f['format_id
'] = itag
3371 f['quality
'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id
'].split('-')[0]), -1))
3372 if f['quality
'] == -1 and f.get('height
'):
3373 f['quality
'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height
']))])
3377 for sd in streaming_data:
3378 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3379 if hls_manifest_url:
3380 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4
', fatal=False, live=is_live)
3381 subtitles = self._merge_subtitles(subs, subtitles)
3383 if process_manifest_format(f, 'hls
', self._search_regex(
3384 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3387 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3388 if dash_manifest_url:
3389 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3390 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3392 if process_manifest_format(f, 'dash
', f['format_id
']):
3393 f['filesize
'] = int_or_none(self._search_regex(
3394 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3396 f['is_from_start
'] = True
3401 def _extract_storyboard(self, player_responses, duration):
3403 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3404 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3408 for i, args in enumerate(spec):
3409 args = args.split('#')
3410 counts
= list(map(int_or_none
, args
[:5]))
3411 if len(args
) != 8 or not all(counts
):
3412 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3414 width
, height
, frame_count
, cols
, rows
= counts
3417 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3418 fragment_count
= frame_count
/ (cols
* rows
)
3419 fragment_duration
= duration
/ fragment_count
3421 'format_id': f
'sb{i}',
3422 'format_note': 'storyboard',
3424 'protocol': 'mhtml',
3430 'fps': frame_count
/ duration
,
3434 'url': url
.replace('$M', str(j
)),
3435 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3436 } for j
in range(math
.ceil(fragment_count
))],
3439 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3441 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3442 query
= {'bpctr': '9999999999', 'has_verified': '1'}
3443 if smuggled_data
.get('is_story'):
3444 query
['pp'] = self
._STORY
_PLAYER
_PARAMS
3445 webpage
= self
._download
_webpage
(
3446 webpage_url
, video_id
, fatal
=False, query
=query
)
3448 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3450 player_responses
, player_url
= self
._extract
_player
_responses
(
3451 self
._get
_requested
_clients
(url
, smuggled_data
),
3452 video_id
, webpage
, master_ytcfg
, smuggled_data
)
3454 return webpage
, master_ytcfg
, player_responses
, player_url
3456 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3457 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3458 is_live
= get_first(video_details
, 'isLive')
3460 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3462 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3463 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, is_live
, duration
)
3465 return live_broadcast_details
, is_live
, streaming_data
, formats
, subtitles
3467 def _real_extract(self
, url
):
3468 url
, smuggled_data
= unsmuggle_url(url
, {})
3469 video_id
= self
._match
_id
(url
)
3471 base_url
= self
.http_scheme() + '//www.youtube.com/'
3472 webpage_url
= base_url
+ 'watch?v=' + video_id
3474 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3476 playability_statuses
= traverse_obj(
3477 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3479 trailer_video_id
= get_first(
3480 playability_statuses
,
3481 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3483 if trailer_video_id
:
3484 return self
.url_result(
3485 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3487 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3488 if webpage
else (lambda x
: None))
3490 video_details
= traverse_obj(
3491 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3492 microformats
= traverse_obj(
3493 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3494 expected_type
=dict, default
=[])
3496 get_first(video_details
, 'title')
3497 or self
._get
_text
(microformats
, (..., 'title'))
3498 or search_meta(['og:title', 'twitter:title', 'title']))
3499 video_description
= get_first(video_details
, 'shortDescription')
3501 multifeed_metadata_list
= get_first(
3503 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3505 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3506 if self
.get_param('noplaylist'):
3507 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3511 for feed
in multifeed_metadata_list
.split(','):
3512 # Unquote should take place before split on comma (,) since textual
3513 # fields may contain comma as well (see
3514 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3515 feed_data
= urllib
.parse
.parse_qs(
3516 urllib
.parse
.unquote_plus(feed
))
3518 def feed_entry(name
):
3520 feed_data
, lambda x
: x
[name
][0], str)
3522 feed_id
= feed_entry('id')
3525 feed_title
= feed_entry('title')
3528 title
+= ' (%s)' % feed_title
3530 '_type': 'url_transparent',
3531 'ie_key': 'Youtube',
3533 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3534 {'force_singlefeed': True}
),
3537 feed_ids
.append(feed_id
)
3539 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3540 % (', '.join(feed_ids
), video_id
))
3541 return self
.playlist_result(
3542 entries
, video_id
, video_title
, video_description
)
3544 duration
= int_or_none(
3545 get_first(video_details
, 'lengthSeconds')
3546 or get_first(microformats
, 'lengthSeconds')
3547 or parse_duration(search_meta('duration'))) or None
3549 live_broadcast_details
, is_live
, streaming_data
, formats
, automatic_captions
= \
3550 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
)
3553 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3554 self
.report_drm(video_id
)
3556 playability_statuses
,
3557 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3558 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3559 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3561 if subreason
== 'The uploader has not made this video available in your country.':
3562 countries
= get_first(microformats
, 'availableCountries')
3564 regions_allowed
= search_meta('regionsAllowed')
3565 countries
= regions_allowed
.split(',') if regions_allowed
else None
3566 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3567 reason
+= f
'. {subreason}'
3569 self
.raise_no_formats(reason
, expected
=True)
3571 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3572 if not keywords
and webpage
:
3574 unescapeHTML(m
.group('content'))
3575 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3576 for keyword
in keywords
:
3577 if keyword
.startswith('yt:stretch='):
3578 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3580 # NB: float is intentional for forcing float division
3581 w
, h
= (float(v
) for v
in mobj
.groups())
3585 if f
.get('vcodec') != 'none':
3586 f
['stretched_ratio'] = ratio
3588 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3589 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3592 'url': thumbnail_url
,
3594 original_thumbnails
= thumbnails
.copy()
3596 # The best resolution thumbnails sometimes does not appear in the webpage
3597 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3598 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3600 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3601 # in resolution, these are not the custom thumbnail. So de-prioritize them
3602 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3603 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3605 n_thumbnail_names
= len(thumbnail_names
)
3607 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3608 video_id
=video_id
, name
=name
, ext
=ext
,
3609 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3610 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3611 for thumb
in thumbnails
:
3612 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3613 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3614 self
._remove
_duplicate
_formats
(thumbnails
)
3615 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3617 category
= get_first(microformats
, 'category') or search_meta('genre')
3618 channel_id
= str_or_none(
3619 get_first(video_details
, 'channelId')
3620 or get_first(microformats
, 'externalChannelId')
3621 or search_meta('channelId'))
3622 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3624 live_content
= get_first(video_details
, 'isLiveContent')
3625 is_upcoming
= get_first(video_details
, 'isUpcoming')
3627 if is_upcoming
or live_content
is False:
3629 if is_upcoming
is None and (live_content
or is_live
):
3631 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3632 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3633 if not duration
and live_end_time
and live_start_time
:
3634 duration
= live_end_time
- live_start_time
3636 if is_live
and self
.get_param('live_from_start'):
3637 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3639 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3641 # source_preference is lower for throttled/potentially damaged formats
3642 self
._sort
_formats
(formats
, (
3643 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
3647 'title': video_title
,
3649 'thumbnails': thumbnails
,
3650 # The best thumbnail that we are sure exists. Prevents unnecessary
3651 # URL checking if user don't care about getting the best possible thumbnail
3652 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3653 'description': video_description
,
3654 'uploader': get_first(video_details
, 'author'),
3655 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3656 'uploader_url': owner_profile_url
,
3657 'channel_id': channel_id
,
3658 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3659 'duration': duration
,
3660 'view_count': int_or_none(
3661 get_first((video_details
, microformats
), (..., 'viewCount'))
3662 or search_meta('interactionCount')),
3663 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3664 'age_limit': 18 if (
3665 get_first(microformats
, 'isFamilySafe') is False
3666 or search_meta('isFamilyFriendly') == 'false'
3667 or search_meta('og:restrictions:age') == '18+') else 0,
3668 'webpage_url': webpage_url
,
3669 'categories': [category
] if category
else None,
3671 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3673 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3674 else None if is_live
is None or is_upcoming
is None
3676 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3677 'release_timestamp': live_start_time
,
3680 if get_first(video_details
, 'isPostLiveDvr'):
3681 self
.write_debug('Video is in Post-Live Manifestless mode')
3682 info
['live_status'] = 'post_live'
3683 if (duration
or 0) > 4 * 3600:
3684 self
.report_warning(
3685 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3686 'This is a known issue and patches are welcome')
3689 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3691 def get_lang_code(track
):
3692 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3693 or track
.get('languageCode'))
3695 # Converted into dicts to remove duplicates
3697 get_lang_code(sub
): sub
3698 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3699 translation_languages
= {
3700 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3701 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3703 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3704 lang_subs
= container
.setdefault(lang_code
, [])
3705 for fmt
in self
._SUBTITLE
_FORMATS
:
3711 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3715 # NB: Constructing the full subtitle dictionary is slow
3716 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3717 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3718 for lang_code
, caption_track
in captions
.items():
3719 base_url
= caption_track
.get('baseUrl')
3720 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3723 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3724 if caption_track
.get('kind') != 'asr':
3728 subtitles
, base_url
, lang_code
, lang_name
, {})
3729 if not caption_track
.get('isTranslatable'):
3731 for trans_code
, trans_name
in translation_languages
.items():
3734 orig_trans_code
= trans_code
3735 if caption_track
.get('kind') != 'asr':
3736 if not get_translated_subs
:
3738 trans_code
+= f
'-{lang_code}'
3739 trans_name
+= format_field(lang_name
, None, ' from %s')
3740 # Add an "-orig" label to the original language so that it can be distinguished.
3741 # The subs are returned without "-orig" as well for compatibility
3742 if lang_code
== f
'a-{orig_trans_code}':
3744 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3745 # Setting tlang=lang returns damaged subtitles.
3746 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3747 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3749 info
['automatic_captions'] = automatic_captions
3750 info
['subtitles'] = subtitles
3752 parsed_url
= urllib
.parse
.urlparse(url
)
3753 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3754 query
= urllib
.parse
.parse_qs(component
)
3755 for k
, v
in query
.items():
3756 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3758 if d_k
not in info
and k
in s_ks
:
3759 info
[d_k
] = parse_duration(query
[k
][0])
3761 # Youtube Music Auto-generated description
3762 if video_description
:
3765 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3767 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3768 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3769 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3770 .+\nAuto-generated\ by\ YouTube\.\s*$
3771 ''', video_description
)
3773 release_year
= mobj
.group('release_year')
3774 release_date
= mobj
.group('release_date')
3776 release_date
= release_date
.replace('-', '')
3777 if not release_year
:
3778 release_year
= release_date
[:4]
3780 'album': mobj
.group('album'.strip()),
3781 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3782 'track': mobj
.group('track').strip(),
3783 'release_date': release_date
,
3784 'release_year': int_or_none(release_year
),
3789 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3790 if not initial_data
:
3791 query
= {'videoId': video_id}
3792 query
.update(self
._get
_checkok
_params
())
3793 initial_data
= self
._extract
_response
(
3794 item_id
=video_id
, ep
='next', fatal
=False,
3795 ytcfg
=master_ytcfg
, query
=query
,
3796 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3797 note
='Downloading initial data API JSON')
3799 info
['comment_count'] = traverse_obj(initial_data
, (
3800 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3801 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3803 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3804 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3805 ), expected_type
=int_or_none
, get_all
=False)
3807 try: # This will error if there is no livechat
3808 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3809 except (KeyError, IndexError, TypeError):
3812 info
.setdefault('subtitles', {})['live_chat'] = [{
3813 # url is needed to set cookies
3814 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3815 'video_id': video_id
,
3817 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3821 info
['chapters'] = (
3822 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3823 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3824 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3827 contents
= traverse_obj(
3828 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3829 expected_type
=list, default
=[])
3831 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3833 stl
= vpir
.get('superTitleLink')
3835 stl
= self
._get
_text
(stl
)
3838 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3839 info
['location'] = stl
3841 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3844 'series': mobj
.group(1),
3845 'season_number': int(mobj
.group(2)),
3846 'episode_number': int(mobj
.group(3)),
3848 for tlb
in (try_get(
3850 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3852 tbr
= tlb
.get('toggleButtonRenderer') or {}
3853 for getter
, regex
in [(
3854 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3855 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3856 lambda x
: x
['accessibility'],
3857 lambda x
: x
['accessibilityData']['accessibilityData'],
3858 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3859 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3861 mobj
= re
.match(regex
, label
)
3863 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3865 sbr_tooltip
= try_get(
3866 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3868 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3870 'like_count': str_to_int(like_count
),
3871 'dislike_count': str_to_int(dislike_count
),
3873 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3875 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3877 'channel': self
._get
_text
(vor
, 'title'),
3878 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3882 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3884 multiple_songs
= False
3886 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3887 multiple_songs
= True
3890 mrr
= row
.get('metadataRowRenderer') or {}
3891 mrr_title
= mrr
.get('title')
3894 mrr_title
= self
._get
_text
(mrr
, 'title')
3895 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3896 if mrr_title
== 'License':
3897 info
['license'] = mrr_contents_text
3898 elif not multiple_songs
:
3899 if mrr_title
== 'Album':
3900 info
['album'] = mrr_contents_text
3901 elif mrr_title
== 'Artist':
3902 info
['artist'] = mrr_contents_text
3903 elif mrr_title
== 'Song':
3904 info
['track'] = mrr_contents_text
3907 'channel': 'uploader',
3908 'channel_id': 'uploader_id',
3909 'channel_url': 'uploader_url',
3912 # The upload date for scheduled, live and past live streams / premieres in microformats
3913 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3914 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3916 unified_strdate(get_first(microformats
, 'uploadDate'))
3917 or unified_strdate(search_meta('uploadDate')))
3918 if not upload_date
or (not info
.get('is_live') and not info
.get('was_live') and info
.get('live_status') != 'is_upcoming'):
3919 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3920 info
['upload_date'] = upload_date
3922 for to
, frm
in fallbacks
.items():
3923 if not info
.get(to
):
3924 info
[to
] = info
.get(frm
)
3926 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3931 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3932 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3933 is_membersonly
= None
3935 if initial_data
and is_private
is not None:
3936 is_membersonly
= False
3938 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3939 badge_labels
= set()
3940 for content
in contents
:
3941 if not isinstance(content
, dict):
3943 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3944 for badge_label
in badge_labels
:
3945 if badge_label
.lower() == 'members only':
3946 is_membersonly
= True
3947 elif badge_label
.lower() == 'premium':
3949 elif badge_label
.lower() == 'unlisted':
3952 info
['availability'] = self
._availability
(
3953 is_private
=is_private
,
3954 needs_premium
=is_premium
,
3955 needs_subscription
=is_membersonly
,
3956 needs_auth
=info
['age_limit'] >= 18,
3957 is_unlisted
=None if is_private
is None else is_unlisted
)
3959 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
3961 self
.mark_watched(video_id
, player_responses
)
3966 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
3969 def passthrough_smuggled_data(func
):
3970 def _smuggle(entries
, smuggled_data
):
3971 for entry
in entries
:
3972 # TODO: Convert URL to music.youtube instead.
3973 # Do we need to passthrough any other smuggled_data?
3974 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
3977 @functools.wraps(func
)
3978 def wrapper(self
, url
):
3979 url
, smuggled_data
= unsmuggle_url(url
, {})
3980 if self
.is_music_url(url
):
3981 smuggled_data
['is_music_url'] = True
3982 info_dict
= func(self
, url
, smuggled_data
)
3983 if smuggled_data
and info_dict
.get('entries'):
3984 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
3988 def _extract_channel_id(self
, webpage
):
3989 channel_id
= self
._html
_search
_meta
(
3990 'channelId', webpage
, 'channel id', default
=None)
3993 channel_url
= self
._html
_search
_meta
(
3994 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3995 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3996 'twitter:app:url:googleplay'), webpage
, 'channel url')
3997 return self
._search
_regex
(
3998 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3999 channel_url
, 'channel id')
4002 def _extract_basic_item_renderer(item
):
4003 # Modified from _extract_grid_item_renderer
4004 known_basic_renderers
= (
4005 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4007 for key
, renderer
in item
.items():
4008 if not isinstance(renderer
, dict):
4010 elif key
in known_basic_renderers
:
4012 elif key
.startswith('grid') and key
.endswith('Renderer'):
4015 def _grid_entries(self
, grid_renderer
):
4016 for item
in grid_renderer
['items']:
4017 if not isinstance(item
, dict):
4019 renderer
= self
._extract
_basic
_item
_renderer
(item
)
4020 if not isinstance(renderer
, dict):
4022 title
= self
._get
_text
(renderer
, 'title')
4025 playlist_id
= renderer
.get('playlistId')
4027 yield self
.url_result(
4028 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4029 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4033 video_id
= renderer
.get('videoId')
4035 yield self
._extract
_video
(renderer
)
4038 channel_id
= renderer
.get('channelId')
4040 yield self
.url_result(
4041 'https://www.youtube.com/channel/%s' % channel_id
,
4042 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
4044 # generic endpoint URL support
4045 ep_url
= urljoin('https://www.youtube.com/', try_get(
4046 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4049 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4050 if ie
.suitable(ep_url
):
4051 yield self
.url_result(
4052 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4055 def _music_reponsive_list_entry(self
, renderer
):
4056 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4058 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4059 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4060 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4062 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4064 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4065 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4066 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4067 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4068 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4070 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4071 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4073 def _shelf_entries_from_content(self
, shelf_renderer
):
4074 content
= shelf_renderer
.get('content')
4075 if not isinstance(content
, dict):
4077 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4079 # TODO: add support for nested playlists so each shelf is processed
4080 # as separate playlist
4081 # TODO: this includes only first N items
4082 yield from self
._grid
_entries
(renderer
)
4083 renderer
= content
.get('horizontalListRenderer')
4088 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4090 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4092 shelf_url
= urljoin('https://www.youtube.com', ep
)
4094 # Skipping links to another channels, note that checking for
4095 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4097 if skip_channels
and '/channels?' in shelf_url
:
4099 title
= self
._get
_text
(shelf_renderer
, 'title')
4100 yield self
.url_result(shelf_url
, video_title
=title
)
4101 # Shelf may not contain shelf URL, fallback to extraction from content
4102 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4104 def _playlist_entries(self
, video_list_renderer
):
4105 for content
in video_list_renderer
['contents']:
4106 if not isinstance(content
, dict):
4108 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4109 if not isinstance(renderer
, dict):
4111 video_id
= renderer
.get('videoId')
4114 yield self
._extract
_video
(renderer
)
4116 def _rich_entries(self
, rich_grid_renderer
):
4118 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4119 video_id
= renderer
.get('videoId')
4122 yield self
._extract
_video
(renderer
)
4124 def _video_entry(self
, video_renderer
):
4125 video_id
= video_renderer
.get('videoId')
4127 return self
._extract
_video
(video_renderer
)
4129 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4130 url
= urljoin('https://youtube.com', traverse_obj(
4131 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4133 return self
.url_result(
4134 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4136 def _post_thread_entries(self
, post_thread_renderer
):
4137 post_renderer
= try_get(
4138 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4139 if not post_renderer
:
4142 video_renderer
= try_get(
4143 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4144 video_id
= video_renderer
.get('videoId')
4146 entry
= self
._extract
_video
(video_renderer
)
4149 # playlist attachment
4150 playlist_id
= try_get(
4151 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4153 yield self
.url_result(
4154 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4155 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4156 # inline video links
4157 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4159 if not isinstance(run
, dict):
4162 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4165 if not YoutubeIE
.suitable(ep_url
):
4167 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4168 if video_id
== ep_video_id
:
4170 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4172 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4173 contents
= post_thread_continuation
.get('contents')
4174 if not isinstance(contents
, list):
4176 for content
in contents
:
4177 renderer
= content
.get('backstagePostThreadRenderer')
4178 if isinstance(renderer
, dict):
4179 yield from self
._post
_thread
_entries
(renderer
)
4181 renderer
= content
.get('videoRenderer')
4182 if isinstance(renderer
, dict):
4183 yield self
._video
_entry
(renderer
)
4186 def _rich_grid_entries(self, contents):
4187 for content in contents:
4188 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4190 entry = self._video_entry(video_renderer)
4195 def _extract_entries(self
, parent_renderer
, continuation_list
):
4196 # continuation_list is modified in-place with continuation_list = [continuation_token]
4197 continuation_list
[:] = [None]
4198 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4199 for content
in contents
:
4200 if not isinstance(content
, dict):
4202 is_renderer
= traverse_obj(
4203 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4206 renderer
= content
.get('richItemRenderer')
4208 for entry
in self
._rich
_entries
(renderer
):
4210 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4212 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4213 for isr_content
in isr_contents
:
4214 if not isinstance(isr_content
, dict):
4218 'playlistVideoListRenderer': self
._playlist
_entries
,
4219 'gridRenderer': self
._grid
_entries
,
4220 'reelShelfRenderer': self
._grid
_entries
,
4221 'shelfRenderer': self
._shelf
_entries
,
4222 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4223 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4224 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4225 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4226 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4227 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4229 for key
, renderer
in isr_content
.items():
4230 if key
not in known_renderers
:
4232 for entry
in known_renderers
[key
](renderer
):
4235 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4238 if not continuation_list
[0]:
4239 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4241 if not continuation_list
[0]:
4242 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4244 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4245 continuation_list
= [None]
4246 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4247 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4251 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4252 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4253 yield from extract_entries(parent_renderer
)
4254 continuation
= continuation_list
[0]
4256 for page_num
in itertools
.count(1):
4257 if not continuation
:
4259 headers
= self
.generate_api_headers(
4260 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4261 response
= self
._extract
_response
(
4262 item_id
=f
'{item_id} page {page_num}',
4263 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4264 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4268 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4269 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4270 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4272 known_continuation_renderers
= {
4273 'playlistVideoListContinuation': self
._playlist
_entries
,
4274 'gridContinuation': self
._grid
_entries
,
4275 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4276 'sectionListContinuation': extract_entries
, # for feeds
4278 continuation_contents
= try_get(
4279 response
, lambda x
: x
['continuationContents'], dict) or {}
4280 continuation_renderer
= None
4281 for key
, value
in continuation_contents
.items():
4282 if key
not in known_continuation_renderers
:
4284 continuation_renderer
= value
4285 continuation_list
= [None]
4286 yield from known_continuation_renderers
[key
](continuation_renderer
)
4287 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4289 if continuation_renderer
:
4293 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4294 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4295 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4296 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4297 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4298 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4299 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4300 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4302 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4303 continuation_items
= try_get(
4304 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4305 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4306 video_items_renderer
= None
4307 for key
, value
in continuation_item
.items():
4308 if key
not in known_renderers
:
4310 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4311 continuation_list
= [None]
4312 yield from known_renderers
[key
][0](video_items_renderer
)
4313 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4315 if video_items_renderer
:
4320 def _extract_selected_tab(tabs
, fatal
=True):
4322 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4323 if renderer
.get('selected') is True:
4327 raise ExtractorError('Unable to find selected tab')
4329 def _extract_uploader(self
, data
):
4331 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4333 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4335 owner_text
= owner
.get('text')
4336 uploader
['uploader'] = self
._search
_regex
(
4337 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4338 uploader
['uploader_id'] = try_get(
4339 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], str)
4340 uploader
['uploader_url'] = urljoin(
4341 'https://www.youtube.com/',
4342 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4343 return {k: v for k, v in uploader.items() if v is not None}
4345 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4346 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4349 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4350 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4352 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4354 channel_name
= renderer
.get('title')
4355 channel_url
= renderer
.get('channelUrl')
4356 channel_id
= renderer
.get('externalId')
4359 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4362 title
= renderer
.get('title')
4363 description
= renderer
.get('description', '')
4364 playlist_id
= channel_id
4365 tags
= renderer
.get('keywords', '').split()
4367 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4368 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4369 def _get_uncropped(url
):
4370 return url_or_none((url
or '').split('=')[0] + '=s0')
4372 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4373 if avatar_thumbnails
:
4374 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4375 if uncropped_avatar
:
4376 avatar_thumbnails
.append({
4377 'url': uncropped_avatar
,
4378 'id': 'avatar_uncropped',
4382 channel_banners
= self
._extract
_thumbnails
(
4383 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4384 for banner
in channel_banners
:
4385 banner
['preference'] = -10
4388 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4389 if uncropped_banner
:
4390 channel_banners
.append({
4391 'url': uncropped_banner
,
4392 'id': 'banner_uncropped',
4396 primary_thumbnails
= self
._extract
_thumbnails
(
4397 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4399 if playlist_id
is None:
4400 playlist_id
= item_id
4402 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4403 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4405 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4406 title
+= format_field(selected_tab
, 'title', ' - %s')
4407 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4410 'playlist_id': playlist_id
,
4411 'playlist_title': title
,
4412 'playlist_description': description
,
4413 'uploader': channel_name
,
4414 'uploader_id': channel_id
,
4415 'uploader_url': channel_url
,
4416 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4418 'view_count': self
._get
_count
(playlist_stats
, 1),
4419 'availability': self
._extract
_availability
(data
),
4420 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4421 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4422 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4425 metadata
.update(self
._extract
_uploader
(data
))
4427 'channel': metadata
['uploader'],
4428 'channel_id': metadata
['uploader_id'],
4429 'channel_url': metadata
['uploader_url']})
4430 return self
.playlist_result(
4432 selected_tab
, playlist_id
, ytcfg
,
4433 self
._extract
_account
_syncid
(ytcfg
, data
),
4434 self
._extract
_visitor
_data
(data
, ytcfg
)),
4437 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4438 first_id
= last_id
= response
= None
4439 for page_num
in itertools
.count(1):
4440 videos
= list(self
._playlist
_entries
(playlist
))
4443 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4444 if start
>= len(videos
):
4446 yield from videos
[start
:]
4447 first_id
= first_id
or videos
[0]['id']
4448 last_id
= videos
[-1]['id']
4449 watch_endpoint
= try_get(
4450 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4451 headers
= self
.generate_api_headers(
4452 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4453 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4455 'playlistId': playlist_id
,
4456 'videoId': watch_endpoint
.get('videoId') or last_id
,
4457 'index': watch_endpoint
.get('index') or len(videos
),
4458 'params': watch_endpoint
.get('params') or 'OAE%3D'
4460 response
= self
._extract
_response
(
4461 item_id
='%s page %d' % (playlist_id
, page_num
),
4462 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4463 check_get_keys
='contents'
4466 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4468 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4469 title
= playlist
.get('title') or try_get(
4470 data
, lambda x
: x
['titleText']['simpleText'], str)
4471 playlist_id
= playlist
.get('playlistId') or item_id
4473 # Delegating everything except mix playlists to regular tab-based playlist URL
4474 playlist_url
= urljoin(url
, try_get(
4475 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4478 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4479 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4480 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4482 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4483 return self
.url_result(
4484 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4487 return self
.playlist_result(
4488 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4489 playlist_id
=playlist_id
, playlist_title
=title
)
4491 def _extract_availability(self
, data
):
4493 Gets the availability of a given playlist/tab.
4494 Note: Unless YouTube tells us explicitly, we do not assume it is public
4495 @param data: response
4497 is_private
= is_unlisted
= None
4498 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4499 badge_labels
= self
._extract
_badges
(renderer
)
4501 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4502 privacy_dropdown_entries
= try_get(
4503 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4504 for renderer_dict
in privacy_dropdown_entries
:
4505 is_selected
= try_get(
4506 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4509 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4511 badge_labels
.add(label
.lower())
4514 for badge_label
in badge_labels
:
4515 if badge_label
== 'unlisted':
4517 elif badge_label
== 'private':
4519 elif badge_label
== 'public':
4520 is_unlisted
= is_private
= False
4521 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4524 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4525 sidebar_renderer
= try_get(
4526 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4527 for item
in sidebar_renderer
:
4528 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4532 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4534 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4536 browse_id
= params
= None
4537 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4540 menu_renderer
= try_get(
4541 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4542 for menu_item
in menu_renderer
:
4543 if not isinstance(menu_item
, dict):
4545 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4547 nav_item_renderer
, lambda x
: x
['text']['simpleText'], str)
4548 if not text
or text
.lower() != 'show unavailable videos':
4550 browse_endpoint
= try_get(
4551 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4552 browse_id
= browse_endpoint
.get('browseId')
4553 params
= browse_endpoint
.get('params')
4556 headers
= self
.generate_api_headers(
4557 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4558 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4560 'params': params
or 'wgYCCAA=',
4561 'browseId': browse_id
or 'VL%s' % item_id
4563 return self
._extract
_response
(
4564 item_id
=item_id
, headers
=headers
, query
=query
,
4565 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4566 note
='Downloading API JSON with unavailable videos')
4568 @functools.cached_property
4569 def skip_webpage(self
):
4570 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4572 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4573 webpage
, data
= None, None
4574 for retry
in self
.RetryManager(fatal
=fatal
):
4576 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
4577 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4578 except ExtractorError
as e
:
4579 if isinstance(e
.cause
, network_exceptions
):
4580 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4583 self
._error
_or
_warning
(e
, fatal
=fatal
)
4587 self
._extract
_and
_report
_alerts
(data
)
4588 except ExtractorError
as e
:
4589 self
._error
_or
_warning
(e
, fatal
=fatal
)
4592 # Sometimes youtube returns a webpage with incomplete ytInitialData
4593 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4594 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4595 retry
.error
= ExtractorError('Incomplete yt initial data received')
4598 return webpage
, data
4600 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4601 """Use if failed to extract ytcfg (and data) from initial webpage"""
4602 if not ytcfg
and self
.is_authenticated
:
4603 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4604 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4605 raise ExtractorError(
4606 f
'{msg}. If you are not downloading private content, or '
4607 'your cookies are only for the first account and channel,'
4608 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4610 self
.report_warning(msg
, only_once
=True)
4612 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4614 if not self
.skip_webpage
:
4615 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4616 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4617 # Reject webpage data if redirected to home page without explicitly requesting
4618 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4619 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4620 if (url
!= 'https://www.youtube.com/feed/recommended'
4621 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4622 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4623 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4625 raise ExtractorError(msg
, expected
=True)
4626 self
.report_warning(msg
, only_once
=True)
4628 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4629 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4632 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4633 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4634 resolve_response
= self
._extract
_response
(
4635 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4636 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4637 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4638 for ep_key
, ep
in endpoints
.items():
4639 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4641 return self
._extract
_response
(
4642 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4643 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4644 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4645 err_note
= 'Failed to resolve url (does the playlist exist?)'
4647 raise ExtractorError(err_note
, expected
=True)
4648 self
.report_warning(err_note
, item_id
)
4650 _SEARCH_PARAMS
= None
4652 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4653 data
= {'query': query}
4654 if params
is NO_DEFAULT
:
4655 params
= self
._SEARCH
_PARAMS
4657 data
['params'] = params
4660 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4661 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4663 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4664 ('continuationContents', ),
4666 display_id
= f
'query "{query}"'
4667 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4668 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4669 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4671 continuation_list
= [None]
4673 for page_num
in itertools
.count(1):
4674 data
.update(continuation_list
[0] or {})
4675 headers
= self
.generate_api_headers(
4676 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4677 search
= self
._extract
_response
(
4678 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4679 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4680 slr_contents
= traverse_obj(search
, *content_keys
)
4681 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4682 if not continuation_list
[0]:
4686 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4687 IE_DESC
= 'YouTube Tabs'
4688 _VALID_URL
= r
'''(?x:
4692 youtube(?:kids)?\.com|
4696 (?P<channel_type>channel|c|user|browse)/|
4699 (?:playlist|watch)\?.*?\blist=
4701 (?!(?:%(reserved_names)s)\b) # Direct URLs
4705 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4706 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4708 IE_NAME
= 'youtube:tab'
4711 'note': 'playlists, multipage',
4712 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4713 'playlist_mincount': 94,
4715 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4716 'title': 'Igor Kleiner - Playlists',
4717 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4718 'uploader': 'Igor Kleiner',
4719 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4720 'channel': 'Igor Kleiner',
4721 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4722 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4723 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4724 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4725 'channel_follower_count': int
4728 'note': 'playlists, multipage, different order',
4729 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4730 'playlist_mincount': 94,
4732 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4733 'title': 'Igor Kleiner - Playlists',
4734 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4735 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4736 'uploader': 'Igor Kleiner',
4737 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4738 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4739 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4740 'channel': 'Igor Kleiner',
4741 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4742 'channel_follower_count': int
4745 'note': 'playlists, series',
4746 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4747 'playlist_mincount': 5,
4749 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4750 'title': '3Blue1Brown - Playlists',
4751 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4752 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4753 'uploader': '3Blue1Brown',
4754 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4755 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4756 'channel': '3Blue1Brown',
4757 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4758 'tags': ['Mathematics'],
4759 'channel_follower_count': int
4762 'note': 'playlists, singlepage',
4763 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4764 'playlist_mincount': 4,
4766 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4767 'title': 'ThirstForScience - Playlists',
4768 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4769 'uploader': 'ThirstForScience',
4770 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4771 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4772 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4773 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4775 'channel': 'ThirstForScience',
4776 'channel_follower_count': int
4779 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4780 'only_matching': True,
4782 'note': 'basic, single video playlist',
4783 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4785 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4786 'uploader': 'Sergey M.',
4787 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4788 'title': 'youtube-dl public playlist',
4792 'modified_date': '20201130',
4793 'channel': 'Sergey M.',
4794 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4795 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4796 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4798 'playlist_count': 1,
4800 'note': 'empty playlist',
4801 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4803 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4804 'uploader': 'Sergey M.',
4805 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4806 'title': 'youtube-dl empty playlist',
4808 'channel': 'Sergey M.',
4810 'modified_date': '20160902',
4811 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4812 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4813 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4815 'playlist_count': 0,
4818 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4820 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4821 'title': 'lex will - Home',
4822 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4823 'uploader': 'lex will',
4824 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4825 'channel': 'lex will',
4826 'tags': ['bible', 'history', 'prophesy'],
4827 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4828 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4829 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4830 'channel_follower_count': int
4832 'playlist_mincount': 2,
4834 'note': 'Videos tab',
4835 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4837 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4838 'title': 'lex will - Videos',
4839 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4840 'uploader': 'lex will',
4841 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4842 'tags': ['bible', 'history', 'prophesy'],
4843 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4844 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4845 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4846 'channel': 'lex will',
4847 'channel_follower_count': int
4849 'playlist_mincount': 975,
4851 'note': 'Videos tab, sorted by popular',
4852 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4854 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4855 'title': 'lex will - Videos',
4856 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4857 'uploader': 'lex will',
4858 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4859 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4860 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4861 'channel': 'lex will',
4862 'tags': ['bible', 'history', 'prophesy'],
4863 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4864 'channel_follower_count': int
4866 'playlist_mincount': 199,
4868 'note': 'Playlists tab',
4869 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4871 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4872 'title': 'lex will - Playlists',
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': 17,
4885 'note': 'Community tab',
4886 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4888 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4889 'title': 'lex will - Community',
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': 18,
4902 'note': 'Channels tab',
4903 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4905 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4906 'title': 'lex will - Channels',
4907 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4908 'uploader': 'lex will',
4909 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4910 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4911 'channel': 'lex will',
4912 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4913 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4914 'tags': ['bible', 'history', 'prophesy'],
4915 'channel_follower_count': int
4917 'playlist_mincount': 12,
4919 'note': 'Search tab',
4920 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4921 'playlist_mincount': 40,
4923 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4924 'title': '3Blue1Brown - Search - linear algebra',
4925 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4926 'uploader': '3Blue1Brown',
4927 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4928 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4929 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4930 'tags': ['Mathematics'],
4931 'channel': '3Blue1Brown',
4932 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4933 'channel_follower_count': int
4936 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4937 'only_matching': True,
4939 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4940 'only_matching': True,
4942 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4943 'only_matching': True,
4945 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
4946 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4948 'title': '29C3: Not my department',
4949 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
4950 'uploader': 'Christiaan008',
4951 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4952 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
4954 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4956 'modified_date': '20150605',
4957 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
4958 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
4959 'channel': 'Christiaan008',
4961 'playlist_count': 96,
4963 'note': 'Large playlist',
4964 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
4966 'title': 'Uploads from Cauchemar',
4967 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
4968 'uploader': 'Cauchemar',
4969 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4970 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
4972 'modified_date': r
're:\d{8}',
4973 'channel': 'Cauchemar',
4974 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
4977 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
4979 'playlist_mincount': 1123,
4980 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
4982 'note': 'even larger playlist, 8832 videos',
4983 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
4984 'only_matching': True,
4986 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
4987 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
4989 'title': 'Uploads from Interstellar Movie',
4990 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
4991 'uploader': 'Interstellar Movie',
4992 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4993 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
4996 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
4997 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
4998 'channel': 'Interstellar Movie',
5000 'modified_date': r
're:\d{8}',
5002 'playlist_mincount': 21,
5004 'note': 'Playlist with "show unavailable videos" button',
5005 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5007 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5008 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5009 'uploader': 'Phim Siêu Nhân Nhật Bản',
5010 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5012 'channel': 'Phim Siêu Nhân Nhật Bản',
5014 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5016 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5017 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5018 'modified_date': r
're:\d{8}',
5020 'playlist_mincount': 200,
5021 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5023 'note': 'Playlist with unavailable videos in page 7',
5024 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5026 'title': 'Uploads from BlankTV',
5027 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5028 'uploader': 'BlankTV',
5029 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5030 'channel': 'BlankTV',
5031 'channel_url': 'https://www.youtube.com/c/blanktv',
5032 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5035 'uploader_url': 'https://www.youtube.com/c/blanktv',
5036 'modified_date': r
're:\d{8}',
5039 'playlist_mincount': 1000,
5040 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5042 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5043 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5045 'title': 'Data Analysis with Dr Mike Pound',
5046 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5047 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5048 'uploader': 'Computerphile',
5049 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5050 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5053 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5054 'channel_url': 'https://www.youtube.com/user/Computerphile',
5055 'channel': 'Computerphile',
5057 'playlist_mincount': 11,
5059 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5060 'only_matching': True,
5062 'note': 'Playlist URL that does not actually serve a playlist',
5063 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5065 'id': 'FqZTN594JQw',
5067 'title': "Smiley's People 01 detective, Adventure Series, Action",
5068 'uploader': 'STREEM',
5069 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5070 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5071 'upload_date': '20150526',
5072 'license': 'Standard YouTube License',
5073 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5074 'categories': ['People & Blogs'],
5080 'skip_download': True,
5082 'skip': 'This video is not available.',
5083 'add_ie': [YoutubeIE
.ie_key()],
5085 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5086 'only_matching': True,
5088 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5089 'only_matching': True,
5091 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5093 'id': 'Wq15eF5vCbI', # This will keep changing
5096 'uploader': 'Sky News',
5097 'uploader_id': 'skynews',
5098 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5099 'upload_date': r
're:\d{8}',
5101 'categories': ['News & Politics'],
5104 'release_timestamp': 1642502819,
5105 'channel': 'Sky News',
5106 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5109 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5110 'playable_in_embed': True,
5111 'release_date': '20220118',
5112 'availability': 'public',
5113 'live_status': 'is_live',
5114 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5115 'channel_follower_count': int
5118 'skip_download': True,
5120 'expected_warnings': ['Ignoring subtitle tracks found in '],
5122 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5124 'id': 'a48o2S1cPoo',
5126 'title': 'The Young Turks - Live Main Show',
5127 'uploader': 'The Young Turks',
5128 'uploader_id': 'TheYoungTurks',
5129 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5130 'upload_date': '20150715',
5131 'license': 'Standard YouTube License',
5132 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5133 'categories': ['News & Politics'],
5134 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5138 'skip_download': True,
5140 'only_matching': True,
5142 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5143 'only_matching': True,
5145 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5146 'only_matching': True,
5148 'note': 'A channel that is not live. Should raise error',
5149 'url': 'https://www.youtube.com/user/numberphile/live',
5150 'only_matching': True,
5152 'url': 'https://www.youtube.com/feed/trending',
5153 'only_matching': True,
5155 'url': 'https://www.youtube.com/feed/library',
5156 'only_matching': True,
5158 'url': 'https://www.youtube.com/feed/history',
5159 'only_matching': True,
5161 'url': 'https://www.youtube.com/feed/subscriptions',
5162 'only_matching': True,
5164 'url': 'https://www.youtube.com/feed/watch_later',
5165 'only_matching': True,
5167 'note': 'Recommended - redirects to home page.',
5168 'url': 'https://www.youtube.com/feed/recommended',
5169 'only_matching': True,
5171 'note': 'inline playlist with not always working continuations',
5172 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5173 'only_matching': True,
5175 'url': 'https://www.youtube.com/course',
5176 'only_matching': True,
5178 'url': 'https://www.youtube.com/zsecurity',
5179 'only_matching': True,
5181 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5182 'only_matching': True,
5184 'url': 'https://www.youtube.com/TheYoungTurks/live',
5185 'only_matching': True,
5187 'url': 'https://www.youtube.com/hashtag/cctv9',
5193 'playlist_mincount': 350,
5195 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5196 'only_matching': True,
5198 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5199 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5200 'only_matching': True
5202 'note': '/browse/ should redirect to /channel/',
5203 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5204 'only_matching': True
5206 'note': 'VLPL, should redirect to playlist?list=PL...',
5207 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5209 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5210 'uploader': 'NoCopyrightSounds',
5211 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5212 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5213 'title': 'NCS : All Releases 💿',
5214 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5215 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5216 'modified_date': r
're:\d{8}',
5218 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5220 'channel': 'NoCopyrightSounds',
5222 'playlist_mincount': 166,
5223 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5225 'note': 'Topic, should redirect to playlist?list=UU...',
5226 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5228 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5229 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5230 'title': 'Uploads from Royalty Free Music - Topic',
5231 'uploader': 'Royalty Free Music - Topic',
5233 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5234 'channel': 'Royalty Free Music - Topic',
5236 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5237 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5238 'modified_date': r
're:\d{8}',
5239 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5242 'expected_warnings': [
5243 'The URL does not have a videos tab',
5244 r
'[Uu]navailable videos (are|will be) hidden',
5246 'playlist_mincount': 101,
5248 'note': 'Topic without a UU playlist',
5249 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5251 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5252 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5255 'expected_warnings': [
5256 'the playlist redirect gave error',
5258 'playlist_mincount': 9,
5260 'note': 'Youtube music Album',
5261 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5263 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5264 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5268 'availability': 'unlisted',
5269 'modified_date': r
're:\d{8}',
5271 'playlist_count': 50,
5273 'note': 'unlisted single video playlist',
5274 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5276 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5277 'uploader': 'colethedj',
5278 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5279 'title': 'yt-dlp unlisted playlist test',
5280 'availability': 'unlisted',
5282 'modified_date': '20220418',
5283 'channel': 'colethedj',
5286 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5287 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5288 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5290 'playlist_count': 1,
5292 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5293 'url': 'https://www.youtube.com/feed/recommended',
5295 'id': 'recommended',
5296 'title': 'recommended',
5299 'playlist_mincount': 50,
5301 'skip_download': True,
5302 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5305 'note': 'API Fallback: /videos tab, sorted by oldest first',
5306 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5308 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5309 'title': 'Cody\'sLab - Videos',
5310 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5311 'uploader': 'Cody\'sLab',
5312 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5313 'channel': 'Cody\'sLab',
5314 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5316 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5317 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5318 'channel_follower_count': int
5320 'playlist_mincount': 650,
5322 'skip_download': True,
5323 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5326 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5327 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5329 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5330 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5331 'title': 'Uploads from Royalty Free Music - Topic',
5332 'uploader': 'Royalty Free Music - Topic',
5333 'modified_date': r
're:\d{8}',
5334 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5336 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5338 'channel': 'Royalty Free Music - Topic',
5340 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5342 'expected_warnings': [
5343 'does not have a videos tab',
5344 r
'[Uu]navailable videos (are|will be) hidden',
5346 'playlist_mincount': 101,
5348 'skip_download': True,
5349 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5352 'note': 'non-standard redirect to regional channel',
5353 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5354 'only_matching': True
5356 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5357 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5359 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5360 'modified_date': '20220407',
5361 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5363 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5364 'uploader': 'pukkandan',
5365 'availability': 'unlisted',
5366 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5367 'channel': 'pukkandan',
5368 'description': 'Test for collaborative playlist',
5369 'title': 'yt-dlp test - collaborative playlist',
5371 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5373 'playlist_mincount': 2
5377 def suitable(cls
, url
):
5378 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5380 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5382 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5383 def _real_extract(self
, url
, smuggled_data
):
5384 item_id
= self
._match
_id
(url
)
5385 url
= urllib
.parse
.urlunparse(
5386 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5387 compat_opts
= self
.get_param('compat_opts', [])
5390 mobj
= self
._URL
_RE
.match(url
).groupdict()
5391 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5394 mobj
, redirect_warning
= get_mobj(url
), None
5395 # Youtube returns incomplete data if tabname is not lower case
5396 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5398 if smuggled_data
.get('is_music_url'):
5399 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5400 item_id
= item_id
[2:]
5401 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5402 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5403 mdata
= self
._extract
_tab
_endpoint
(
5404 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5405 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5406 get_all
=False, expected_type
=str)
5408 raise ExtractorError('Failed to resolve album to playlist')
5409 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5410 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5411 pre
= f
'https://www.youtube.com/channel/{item_id}'
5413 original_tab_name
= tab
5414 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5415 # Home URLs should redirect to /videos/
5416 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5417 'To download only the videos in the home page, add a "/featured" to the URL')
5420 url
= ''.join((pre
, tab
, post
))
5421 mobj
= get_mobj(url
)
5423 # Handle both video/playlist URLs
5425 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5427 if not video_id
and mobj
['not_channel'].startswith('watch'):
5429 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5430 raise ExtractorError('Unable to recognize tab page')
5431 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5432 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5433 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5434 mobj
= get_mobj(url
)
5436 if video_id
and playlist_id
:
5437 if self
.get_param('noplaylist'):
5438 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5439 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5440 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5441 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5443 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5445 # YouTube may provide a non-standard redirect to the regional channel
5446 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5447 redirect_url
= traverse_obj(
5448 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5449 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5450 redirect_url
= ''.join((
5451 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5452 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5453 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5455 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5457 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5458 selected_tab_name
= selected_tab
.get('title', '').lower()
5459 if selected_tab_name
== 'home':
5460 selected_tab_name
= 'featured'
5461 requested_tab_name
= mobj
['tab'][1:]
5462 if 'no-youtube-channel-redirect' not in compat_opts
:
5463 if requested_tab_name
== 'live': # Live tab should have redirected to the video
5464 raise UserNotLive(video_id
=mobj
['id'])
5465 if requested_tab_name
not in ('', selected_tab_name
):
5466 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5467 if not original_tab_name
:
5468 if item_id
[:2] == 'UC':
5469 # Topic channels don't have /videos. Use the equivalent playlist instead
5470 pl_id
= f
'UU{item_id[2:]}'
5471 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5473 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5474 except ExtractorError
:
5475 redirect_warning
+= ' and the playlist redirect gave error'
5477 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5478 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5479 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5480 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5482 raise ExtractorError(redirect_warning
, expected
=True)
5484 if redirect_warning
:
5485 self
.to_screen(redirect_warning
)
5486 self
.write_debug(f
'Final URL: {url}')
5488 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5489 if 'no-youtube-unavailable-videos' not in compat_opts
:
5490 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5491 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5492 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5494 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5496 playlist
= traverse_obj(
5497 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5499 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5501 video_id
= traverse_obj(
5502 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5504 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5505 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5506 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5507 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5509 raise ExtractorError('Unable to recognize tab page')
5512 class YoutubePlaylistIE(InfoExtractor
):
5513 IE_DESC
= 'YouTube playlists'
5514 _VALID_URL
= r
'''(?x)(?:
5519 youtube(?:kids)?\.com|
5524 (?P<id>%(playlist_id)s)
5526 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5527 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5529 IE_NAME
= 'youtube:playlist'
5531 'note': 'issue #673',
5532 'url': 'PLBB231211A4F62143',
5534 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5535 'id': 'PLBB231211A4F62143',
5536 'uploader': 'Wickman',
5537 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5538 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5540 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5541 'modified_date': r
're:\d{8}',
5542 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5543 'channel': 'Wickman',
5545 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5547 'playlist_mincount': 29,
5549 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5551 'title': 'YDL_safe_search',
5552 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5554 'playlist_count': 2,
5555 'skip': 'This playlist is private',
5558 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5559 'playlist_count': 4,
5562 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5563 'uploader': 'milan',
5564 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5566 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5568 'modified_date': '20140919',
5571 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5572 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5574 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5576 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5577 'playlist_mincount': 455,
5579 'title': '2018 Chinese New Singles (11/6 updated)',
5580 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5582 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5583 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5586 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5588 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5589 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5590 'modified_date': r
're:\d{8}',
5592 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5594 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5595 'only_matching': True,
5597 # music album playlist
5598 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5599 'only_matching': True,
5603 def suitable(cls
, url
):
5604 if YoutubeTabIE
.suitable(url
):
5606 from ..utils
import parse_qs
5608 if qs
.get('v', [None])[0]:
5610 return super().suitable(url
)
5612 def _real_extract(self
, url
):
5613 playlist_id
= self
._match
_id
(url
)
5614 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5615 url
= update_url_query(
5616 'https://www.youtube.com/playlist',
5617 parse_qs(url
) or {'list': playlist_id}
)
5619 url
= smuggle_url(url
, {'is_music_url': True}
)
5620 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5623 class YoutubeYtBeIE(InfoExtractor
):
5624 IE_DESC
= 'youtu.be'
5625 _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}
5627 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5629 'id': 'yeWKywCrFtk',
5631 'title': 'Small Scale Baler and Braiding Rugs',
5632 'uploader': 'Backus-Page House Museum',
5633 'uploader_id': 'backuspagemuseum',
5634 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5635 'upload_date': '20161008',
5636 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5637 'categories': ['Nonprofits & Activism'],
5641 'playable_in_embed': True,
5642 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5643 'channel': 'Backus-Page House Museum',
5644 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5645 'live_status': 'not_live',
5647 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5648 'availability': 'public',
5650 'comment_count': int,
5651 'channel_follower_count': int
5655 'skip_download': True,
5658 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5659 'only_matching': True,
5662 def _real_extract(self
, url
):
5663 mobj
= self
._match
_valid
_url
(url
)
5664 video_id
= mobj
.group('id')
5665 playlist_id
= mobj
.group('playlist_id')
5666 return self
.url_result(
5667 update_url_query('https://www.youtube.com/watch', {
5669 'list': playlist_id
,
5670 'feature': 'youtu.be',
5671 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5674 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5675 IE_DESC
= 'YouTube livestream embeds'
5676 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5678 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5679 'only_matching': True,
5682 def _real_extract(self
, url
):
5683 channel_id
= self
._match
_id
(url
)
5684 return self
.url_result(
5685 f
'https://www.youtube.com/channel/{channel_id}/live',
5686 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5689 class YoutubeYtUserIE(InfoExtractor
):
5690 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5691 IE_NAME
= 'youtube:user'
5692 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5694 'url': 'ytuser:phihag',
5695 'only_matching': True,
5698 def _real_extract(self
, url
):
5699 user_id
= self
._match
_id
(url
)
5700 return self
.url_result(
5701 'https://www.youtube.com/user/%s/videos' % user_id
,
5702 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5705 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5706 IE_NAME
= 'youtube:favorites'
5707 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5708 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5709 _LOGIN_REQUIRED
= True
5712 'only_matching': True,
5714 'url': ':ytfavorites',
5715 'only_matching': True,
5718 def _real_extract(self
, url
):
5719 return self
.url_result(
5720 'https://www.youtube.com/playlist?list=LL',
5721 ie
=YoutubeTabIE
.ie_key())
5724 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5725 IE_NAME
= 'youtube:notif'
5726 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5727 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5728 _LOGIN_REQUIRED
= True
5731 'only_matching': True,
5733 'url': ':ytnotifications',
5734 'only_matching': True,
5737 def _extract_notification_menu(self
, response
, continuation_list
):
5738 notification_list
= traverse_obj(
5740 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5741 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5742 expected_type
=list) or []
5743 continuation_list
[0] = None
5744 for item
in notification_list
:
5745 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5748 continuation
= item
.get('continuationItemRenderer')
5750 continuation_list
[0] = continuation
5752 def _extract_notification_renderer(self
, notification
):
5753 video_id
= traverse_obj(
5754 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5755 url
= f
'https://www.youtube.com/watch?v={video_id}'
5758 browse_ep
= traverse_obj(
5759 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5760 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5761 post_id
= self
._search
_regex
(
5762 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5763 'post id', default
=None)
5764 if not channel_id
or not post_id
:
5766 # The direct /post url redirects to this in the browser
5767 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5769 channel
= traverse_obj(
5770 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5772 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5773 if notification_title
:
5774 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5775 # TODO: handle recommended videos
5776 title
= self
._search
_regex
(
5777 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5778 'video title', default
=None)
5779 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5780 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5785 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5786 'video_id': video_id
,
5788 'channel_id': channel_id
,
5790 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5791 'upload_date': upload_date
,
5794 def _notification_menu_entries(self
, ytcfg
):
5795 continuation_list
= [None]
5797 for page
in itertools
.count(1):
5798 ctoken
= traverse_obj(
5799 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5800 response
= self
._extract
_response
(
5801 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5802 ep
='notification/get_notification_menu', check_get_keys
='actions',
5803 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5804 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5805 if not continuation_list
[0]:
5808 def _real_extract(self
, url
):
5809 display_id
= 'notifications'
5810 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5811 self
._report
_playlist
_authcheck
(ytcfg
)
5812 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5815 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5816 IE_DESC
= 'YouTube search'
5817 IE_NAME
= 'youtube:search'
5818 _SEARCH_KEY
= 'ytsearch'
5819 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5821 'url': 'ytsearch5:youtube-dl test video',
5822 'playlist_count': 5,
5824 'id': 'youtube-dl test video',
5825 'title': 'youtube-dl test video',
5830 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5831 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5832 _SEARCH_KEY
= 'ytsearchdate'
5833 IE_DESC
= 'YouTube search, newest videos first'
5834 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5836 'url': 'ytsearchdate5:youtube-dl test video',
5837 'playlist_count': 5,
5839 'id': 'youtube-dl test video',
5840 'title': 'youtube-dl test video',
5845 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5846 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5847 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5848 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5850 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5851 'playlist_mincount': 5,
5853 'id': 'youtube-dl test video',
5854 'title': 'youtube-dl test video',
5857 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5858 'playlist_mincount': 5,
5864 'url': 'https://www.youtube.com/results?search_query=%23cats',
5865 'playlist_mincount': 1,
5869 # The test suite does not have support for nested playlists
5871 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5876 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5877 'only_matching': True,
5880 def _real_extract(self
, url
):
5882 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5883 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5886 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5887 IE_DESC
= 'YouTube music search URLs with selectable sections, e.g. #songs'
5888 IE_NAME
= 'youtube:music:search_url'
5889 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5891 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5892 'playlist_count': 16,
5894 'id': 'royalty free music',
5895 'title': 'royalty free music',
5898 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5899 'playlist_mincount': 30,
5901 'id': 'royalty free music - songs',
5902 'title': 'royalty free music - songs',
5904 'params': {'extract_flat': 'in_playlist'}
5906 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5907 'playlist_mincount': 30,
5909 'id': 'royalty free music - community playlists',
5910 'title': 'royalty free music - community playlists',
5912 'params': {'extract_flat': 'in_playlist'}
5916 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5917 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5918 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5919 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5920 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5921 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5924 def _real_extract(self
, url
):
5926 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5927 params
= qs
.get('sp', (None,))[0]
5929 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5931 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
5932 params
= self
._SECTIONS
.get(section
)
5935 title
= join_nonempty(query
, section
, delim
=' - ')
5936 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5939 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5941 Base class for feed extractors
5942 Subclasses must re-define the _FEED_NAME property.
5944 _LOGIN_REQUIRED
= True
5945 _FEED_NAME
= 'feeds'
5947 def _real_initialize(self
):
5948 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
5952 return f
'youtube:{self._FEED_NAME}'
5954 def _real_extract(self
, url
):
5955 return self
.url_result(
5956 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
5959 class YoutubeWatchLaterIE(InfoExtractor
):
5960 IE_NAME
= 'youtube:watchlater'
5961 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
5962 _VALID_URL
= r
':ytwatchlater'
5964 'url': ':ytwatchlater',
5965 'only_matching': True,
5968 def _real_extract(self
, url
):
5969 return self
.url_result(
5970 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
5973 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
5974 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
5975 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
5976 _FEED_NAME
= 'recommended'
5977 _LOGIN_REQUIRED
= False
5980 'only_matching': True,
5982 'url': ':ytrecommended',
5983 'only_matching': True,
5985 'url': 'https://youtube.com',
5986 'only_matching': True,
5990 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
5991 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
5992 _VALID_URL
= r
':ytsub(?:scription)?s?'
5993 _FEED_NAME
= 'subscriptions'
5996 'only_matching': True,
5998 'url': ':ytsubscriptions',
5999 'only_matching': True,
6003 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
6004 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
6005 _VALID_URL
= r
':ythis(?:tory)?'
6006 _FEED_NAME
= 'history'
6008 'url': ':ythistory',
6009 'only_matching': True,
6013 class YoutubeStoriesIE(InfoExtractor
):
6014 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
6015 IE_NAME
= 'youtube:stories'
6016 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6018 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6019 'only_matching': True,
6022 def _real_extract(self
, url
):
6023 playlist_id
= f
'RLTD{self._match_id(url)}'
6024 return self
.url_result(
6025 smuggle_url(f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}
),
6026 ie
=YoutubeTabIE
, video_id
=playlist_id
)
6029 class YoutubeTruncatedURLIE(InfoExtractor
):
6030 IE_NAME
= 'youtube:truncated_url'
6031 IE_DESC
= False # Do not list
6032 _VALID_URL
= r
'''(?x)
6034 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6037 annotation_id=annotation_[^&]+|
6043 attribution_link\?a=[^&]+
6049 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6050 'only_matching': True,
6052 'url': 'https://www.youtube.com/watch?',
6053 'only_matching': True,
6055 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6056 'only_matching': True,
6058 'url': 'https://www.youtube.com/watch?feature=foo',
6059 'only_matching': True,
6061 'url': 'https://www.youtube.com/watch?hl=en-GB',
6062 'only_matching': True,
6064 'url': 'https://www.youtube.com/watch?t=2372',
6065 'only_matching': True,
6068 def _real_extract(self
, url
):
6069 raise ExtractorError(
6070 'Did you forget to quote the URL? Remember that & is a meta '
6071 'character in most shells, so you want to put the URL in quotes, '
6073 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6074 ' or simply youtube-dl BaW_jenozKc .',
6078 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6079 IE_NAME
= 'youtube:clip'
6080 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6082 # FIXME: Other metadata should be extracted from the clip, not from the base video
6083 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6085 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6087 'section_start': 29.0,
6088 'section_end': 39.7,
6091 'availability': 'public',
6092 'categories': ['Gaming'],
6093 'channel': 'Scott The Woz',
6094 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6095 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6096 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6098 'playable_in_embed': True,
6100 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6101 'title': 'Mobile Games on Console - Scott The Woz',
6102 'upload_date': '20210920',
6103 'uploader': 'Scott The Woz',
6104 'uploader_id': 'scottthewoz',
6105 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6107 'live_status': 'not_live',
6108 'channel_follower_count': int
6112 def _real_extract(self
, url
):
6113 clip_id
= self
._match
_id
(url
)
6114 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6116 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6118 raise ExtractorError('Unable to find video ID')
6120 clip_data
= traverse_obj(data
, (
6121 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6122 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6123 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6124 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6127 '_type': 'url_transparent',
6128 'url': f
'https://www.youtube.com/watch?v={video_id}',
6129 'ie_key': YoutubeIE
.ie_key(),
6131 'section_start': int(clip_data
['startTimeMs']) / 1000,
6132 'section_end': int(clip_data
['endTimeMs']) / 1000,
6136 class YoutubeTruncatedIDIE(InfoExtractor
):
6137 IE_NAME
= 'youtube:truncated_id'
6138 IE_DESC
= False # Do not list
6139 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6142 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6143 'only_matching': True,
6146 def _real_extract(self
, url
):
6147 video_id
= self
._match
_id
(url
)
6148 raise ExtractorError(
6149 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',