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': '17.33.2',
168 'deviceModel': 'iPhone14,3',
169 'userAgent': 'com.google.ios.youtube/17.33.2 (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': '17.33.2',
180 'deviceModel': 'iPhone14,3',
181 'userAgent': 'com.google.ios.youtube/17.33.2 (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': '5.21',
193 'deviceModel': 'iPhone14,3',
194 'userAgent': 'com.google.ios.youtubemusic/5.21 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
197 'INNERTUBE_CONTEXT_CLIENT_NAME': 26,
198 'REQUIRE_JS_PLAYER': False
201 'INNERTUBE_CONTEXT': {
203 'clientName': 'IOS_CREATOR',
204 'clientVersion': '22.33.101',
205 'deviceModel': 'iPhone14,3',
206 'userAgent': 'com.google.ios.ytcreator/22.33.101 (iPhone14,3; U; CPU iOS 15_6 like Mac OS X)'
209 'INNERTUBE_CONTEXT_CLIENT_NAME': 15,
210 'REQUIRE_JS_PLAYER': False
212 # mweb has 'ultralow' formats
213 # See: https://github.com/yt-dlp/yt-dlp/pull/557
215 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
216 'INNERTUBE_CONTEXT': {
218 'clientName': 'MWEB',
219 'clientVersion': '2.20220801.00.00',
222 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
224 # This client can access age restricted videos (unless the uploader has disabled the 'allow embedding' option)
225 # See: https://github.com/zerodytrash/YouTube-Internal-Clients
227 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
228 'INNERTUBE_CONTEXT': {
230 'clientName': 'TVHTML5_SIMPLY_EMBEDDED_PLAYER',
231 'clientVersion': '2.0',
234 'INNERTUBE_CONTEXT_CLIENT_NAME': 85
239 def _split_innertube_client(client_name
):
240 variant
, *base
= client_name
.rsplit('.', 1)
242 return variant
, base
[0], variant
243 base
, *variant
= client_name
.split('_', 1)
244 return client_name
, base
, variant
[0] if variant
else None
247 def build_innertube_clients():
249 'embedUrl': 'https://www.youtube.com/', # Can be any valid URL
251 BASE_CLIENTS
= ('android', 'web', 'tv', 'ios', 'mweb')
252 priority
= qualities(BASE_CLIENTS
[::-1])
254 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
255 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8')
256 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
257 ytcfg
.setdefault('REQUIRE_JS_PLAYER', True)
258 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
260 _
, base_client
, variant
= _split_innertube_client(client
)
261 ytcfg
['priority'] = 10 * priority(base_client
)
264 INNERTUBE_CLIENTS
[f
'{client}_embedscreen'] = embedscreen
= copy
.deepcopy(ytcfg
)
265 embedscreen
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
266 embedscreen
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
267 embedscreen
['priority'] -= 3
268 elif variant
== 'embedded':
269 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = THIRD_PARTY
270 ytcfg
['priority'] -= 2
272 ytcfg
['priority'] -= 3
275 build_innertube_clients()
278 class YoutubeBaseInfoExtractor(InfoExtractor
):
279 """Provide base functions for Youtube extractors"""
282 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|clip|'
283 r
'shorts|movies|results|search|shared|hashtag|trending|explore|feed|feeds|'
284 r
'browse|oembed|get_video_info|iframe_api|s/player|'
285 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
287 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
289 # _NETRC_MACHINE = 'youtube'
291 # If True it will raise an error if no login info is provided
292 _LOGIN_REQUIRED
= False
295 # invidious-redirect websites
296 r
'(?:www\.)?redirect\.invidious\.io',
297 r
'(?:(?:www|dev)\.)?invidio\.us',
298 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/docs/instances.md
299 r
'(?:www\.)?invidious\.pussthecat\.org',
300 r
'(?:www\.)?invidious\.zee\.li',
301 r
'(?:www\.)?invidious\.ethibox\.fr',
302 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
303 r
'(?:www\.)?osbivz6guyeahrwp2lnwyjk2xos342h4ocsxyqrlaopqjuhwn2djiiyd\.onion',
304 r
'(?:www\.)?u2cvlit75owumwpy4dj2hsmvkq7nvrclkpht7xgyye2pyoxhpmclkrad\.onion',
305 # youtube-dl invidious instances list
306 r
'(?:(?:www|no)\.)?invidiou\.sh',
307 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
308 r
'(?:www\.)?invidious\.kabi\.tk',
309 r
'(?:www\.)?invidious\.mastodon\.host',
310 r
'(?:www\.)?invidious\.zapashcanon\.fr',
311 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
312 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
313 r
'(?:www\.)?invidious\.himiko\.cloud',
314 r
'(?:www\.)?invidious\.reallyancient\.tech',
315 r
'(?:www\.)?invidious\.tube',
316 r
'(?:www\.)?invidiou\.site',
317 r
'(?:www\.)?invidious\.site',
318 r
'(?:www\.)?invidious\.xyz',
319 r
'(?:www\.)?invidious\.nixnet\.xyz',
320 r
'(?:www\.)?invidious\.048596\.xyz',
321 r
'(?:www\.)?invidious\.drycat\.fr',
322 r
'(?:www\.)?inv\.skyn3t\.in',
323 r
'(?:www\.)?tube\.poal\.co',
324 r
'(?:www\.)?tube\.connect\.cafe',
325 r
'(?:www\.)?vid\.wxzm\.sx',
326 r
'(?:www\.)?vid\.mint\.lgbt',
327 r
'(?:www\.)?vid\.puffyan\.us',
328 r
'(?:www\.)?yewtu\.be',
329 r
'(?:www\.)?yt\.elukerio\.org',
330 r
'(?:www\.)?yt\.lelux\.fi',
331 r
'(?:www\.)?invidious\.ggc-project\.de',
332 r
'(?:www\.)?yt\.maisputain\.ovh',
333 r
'(?:www\.)?ytprivate\.com',
334 r
'(?:www\.)?invidious\.13ad\.de',
335 r
'(?:www\.)?invidious\.toot\.koeln',
336 r
'(?:www\.)?invidious\.fdn\.fr',
337 r
'(?:www\.)?watch\.nettohikari\.com',
338 r
'(?:www\.)?invidious\.namazso\.eu',
339 r
'(?:www\.)?invidious\.silkky\.cloud',
340 r
'(?:www\.)?invidious\.exonip\.de',
341 r
'(?:www\.)?invidious\.riverside\.rocks',
342 r
'(?:www\.)?invidious\.blamefran\.net',
343 r
'(?:www\.)?invidious\.moomoo\.de',
344 r
'(?:www\.)?ytb\.trom\.tf',
345 r
'(?:www\.)?yt\.cyberhost\.uk',
346 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
347 r
'(?:www\.)?qklhadlycap4cnod\.onion',
348 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
349 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
350 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
351 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
352 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
353 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
354 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
355 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
356 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
357 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
358 # piped instances from https://github.com/TeamPiped/Piped/wiki/Instances
359 r
'(?:www\.)?piped\.kavin\.rocks',
360 r
'(?:www\.)?piped\.silkky\.cloud',
361 r
'(?:www\.)?piped\.tokhmi\.xyz',
362 r
'(?:www\.)?piped\.moomoo\.me',
364 r
'(?:www\.)?piped\.syncpundit\.com',
365 r
'(?:www\.)?piped\.mha\.fi',
366 r
'(?:www\.)?piped\.mint\.lgbt',
367 r
'(?:www\.)?piped\.privacy\.com\.de',
370 def _initialize_consent(self
):
371 cookies
= self
._get
_cookies
('https://www.youtube.com/')
372 if cookies
.get('__Secure-3PSID'):
375 consent
= cookies
.get('CONSENT')
377 if 'YES' in consent
.value
:
379 consent_id
= self
._search
_regex
(
380 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
382 consent_id
= random
.randint(100, 999)
383 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
385 def _initialize_pref(self
):
386 cookies
= self
._get
_cookies
('https://www.youtube.com/')
387 pref_cookie
= cookies
.get('PREF')
391 pref
= dict(urllib
.parse
.parse_qsl(pref_cookie
.value
))
393 self
.report_warning('Failed to parse user PREF cookie' + bug_reports_message())
394 pref
.update({'hl': 'en', 'tz': 'UTC'}
)
395 self
._set
_cookie
('.youtube.com', name
='PREF', value
=urllib
.parse
.urlencode(pref
))
397 def _real_initialize(self
):
398 self
._initialize
_pref
()
399 self
._initialize
_consent
()
400 self
._check
_login
_required
()
402 def _check_login_required(self
):
403 if self
._LOGIN
_REQUIRED
and not self
._cookies
_passed
:
404 self
.raise_login_required('Login details are needed to download this content', method
='cookies')
406 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*='
407 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*='
409 def _get_default_ytcfg(self, client='web'):
410 return copy.deepcopy(INNERTUBE_CLIENTS[client])
412 def _get_innertube_host(self, client='web'):
413 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
415 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
416 # try_get but with fallback to default ytcfg client values when present
417 _func = lambda y: try_get(y, getter, expected_type)
418 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
420 def _extract_client_name(self, ytcfg, default_client='web'):
421 return self._ytcfg_get_safe(
422 ytcfg, (lambda x: x['INNERTUBE_CLIENT_NAME'],
423 lambda x: x['INNERTUBE_CONTEXT']['client']['clientName']), str, default_client)
425 def _extract_client_version(self, ytcfg, default_client='web'):
426 return self._ytcfg_get_safe(
427 ytcfg, (lambda x: x['INNERTUBE_CLIENT_VERSION'],
428 lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion']), str, default_client)
430 def _select_api_hostname(self, req_api_hostname, default_client=None):
431 return (self._configuration_arg('innertube_host', [''], ie_key=YoutubeIE.ie_key())[0]
432 or req_api_hostname or self._get_innertube_host(default_client or 'web'))
434 def _extract_api_key(self, ytcfg=None, default_client='web'):
435 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], str, default_client)
437 def _extract_context(self, ytcfg=None, default_client='web'):
439 (ytcfg, self._get_default_ytcfg(default_client)), 'INNERTUBE_CONTEXT', expected_type=dict)
440 # Enforce language and tz for extraction
441 client_context = traverse_obj(context, 'client', expected_type=dict, default={})
442 client_context.update({'hl': 'en', 'timeZone': 'UTC', 'utcOffsetMinutes': 0})
447 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
448 time_now = round(time.time())
449 if self._SAPISID is None:
450 yt_cookies = self._get_cookies('https://www.youtube.com')
451 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
452 # See: https://github.com/yt-dlp/yt-dlp/issues/393
453 sapisid_cookie = dict_get(
454 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
455 if sapisid_cookie and sapisid_cookie.value:
456 self._SAPISID = sapisid_cookie.value
457 self.write_debug('Extracted SAPISID cookie')
458 # SAPISID cookie is required if not already present
459 if not yt_cookies.get('SAPISID'):
460 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie')
462 '.youtube.com', 'SAPISID', self._SAPISID, secure=True, expire_time=time_now + 3600)
464 self._SAPISID = False
465 if not self._SAPISID:
467 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
468 sapisidhash = hashlib.sha1(
469 f'{time_now} {self._SAPISID} {origin}'.encode()).hexdigest()
470 return f'SAPISIDHASH {time_now}_{sapisidhash}'
472 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
473 note='Downloading API JSON', errnote='Unable to download API page',
474 context=None, api_key=None, api_hostname=None, default_client='web'):
476 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
478 real_headers = self.generate_api_headers(default_client=default_client)
479 real_headers.update({'content-type': 'application/json'})
481 real_headers.update(headers)
482 api_key = (self._configuration_arg('innertube_key', [''], ie_key=YoutubeIE.ie_key(), casesense=True)[0]
483 or api_key or self._extract_api_key(default_client=default_client))
484 return self._download_json(
485 f'https://{self._select_api_hostname(api_hostname, default_client)}/youtubei/v1/{ep}',
486 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
487 data=json.dumps(data).encode('utf8'), headers=real_headers,
488 query={'key': api_key, 'prettyPrint': 'false'})
490 def extract_yt_initial_data(self, item_id, webpage, fatal=True):
491 return self._search_json(self._YT_INITIAL_DATA_RE, webpage, 'yt initial data', item_id, fatal=fatal)
494 def _extract_session_index(*data):
496 Index of current account in account list.
497 See: https://github.com/yt-dlp/yt-dlp/pull/519
500 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
501 if session_index is not None:
505 def _extract_identity_token(self, ytcfg=None, webpage=None):
507 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], str)
511 return self._search_regex(
512 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
513 'identity token
', default=None, fatal=False)
516 def _extract_account_syncid(*args):
518 Extract syncId required to download private playlists of secondary channels
519 @params response and/or ytcfg
522 # ytcfg includes channel_syncid if on secondary channel
523 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], str)
527 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
528 lambda x: x['DATASYNC_ID
']), str) or '').split('||
')
529 if len(sync_ids) >= 2 and sync_ids[1]:
530 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
531 # and just "user_syncid||" for primary channel. We only want the channel_syncid
535 def _extract_visitor_data(*args):
537 Extracts visitorData from an API response or ytcfg
538 Appears to be used to track session state
541 args, [('VISITOR_DATA
', ('INNERTUBE_CONTEXT
', 'client
', 'visitorData
'), ('responseContext
', 'visitorData
'))],
544 @functools.cached_property
545 def is_authenticated(self):
546 return bool(self._generate_sapisidhash_header())
548 def extract_ytcfg(self, video_id, webpage):
551 return self._parse_json(
553 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
554 default='{}'), video_id, fatal=False) or {}
556 def generate_api_headers(
557 self
, *, ytcfg
=None, account_syncid
=None, session_index
=None,
558 visitor_data
=None, identity_token
=None, api_hostname
=None, default_client
='web'):
560 origin
= 'https://' + (self
._select
_api
_hostname
(api_hostname
, default_client
))
562 'X-YouTube-Client-Name': str(
563 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
564 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
566 'X-Youtube-Identity-Token': identity_token
or self
._extract
_identity
_token
(ytcfg
),
567 'X-Goog-PageId': account_syncid
or self
._extract
_account
_syncid
(ytcfg
),
568 'X-Goog-Visitor-Id': visitor_data
or self
._extract
_visitor
_data
(ytcfg
),
569 'User-Agent': self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT']['client']['userAgent'], default_client
=default_client
)
571 if session_index
is None:
572 session_index
= self
._extract
_session
_index
(ytcfg
)
573 if account_syncid
or session_index
is not None:
574 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
576 auth
= self
._generate
_sapisidhash
_header
(origin
)
578 headers
['Authorization'] = auth
579 headers
['X-Origin'] = origin
580 return {h: v for h, v in headers.items() if v is not None}
582 def _download_ytcfg(self
, client
, video_id
):
584 'web': 'https://www.youtube.com',
585 'web_music': 'https://music.youtube.com',
586 'web_embedded': f
'https://www.youtube.com/embed/{video_id}?html5=1'
590 webpage
= self
._download
_webpage
(
591 url
, video_id
, fatal
=False, note
=f
'Downloading {client.replace("_", " ").strip()} client config')
592 return self
.extract_ytcfg(video_id
, webpage
) or {}
595 def _build_api_continuation_query(continuation
, ctp
=None):
597 'continuation': continuation
599 # TODO: Inconsistency with clickTrackingParams.
600 # Currently we have a fixed ctp contained within context (from ytcfg)
601 # and a ctp in root query for continuation.
603 query
['clickTracking'] = {'clickTrackingParams': ctp}
607 def _extract_next_continuation_data(cls
, renderer
):
608 next_continuation
= try_get(
609 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
610 lambda x
: x
['continuation']['reloadContinuationData']), dict)
611 if not next_continuation
:
613 continuation
= next_continuation
.get('continuation')
616 ctp
= next_continuation
.get('clickTrackingParams')
617 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
620 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
621 if isinstance(continuation_ep
, dict):
622 continuation
= try_get(
623 continuation_ep
, lambda x
: x
['continuationCommand']['token'], str)
626 ctp
= continuation_ep
.get('clickTrackingParams')
627 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
630 def _extract_continuation(cls
, renderer
):
631 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
632 if next_continuation
:
633 return next_continuation
636 for key
in ('contents', 'items'):
637 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
639 for content
in contents
:
640 if not isinstance(content
, dict):
642 continuation_ep
= try_get(
643 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
644 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
646 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
651 def _extract_alerts(cls
, data
):
652 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
653 if not isinstance(alert_dict
, dict):
655 for alert
in alert_dict
.values():
656 alert_type
= alert
.get('type')
659 message
= cls
._get
_text
(alert
, 'text')
661 yield alert_type
, message
663 def _report_alerts(self
, alerts
, expected
=True, fatal
=True, only_once
=False):
666 for alert_type
, alert_message
in alerts
:
667 if alert_type
.lower() == 'error' and fatal
:
668 errors
.append([alert_type
, alert_message
])
670 warnings
.append([alert_type
, alert_message
])
672 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
673 self
.report_warning(f
'YouTube said: {alert_type} - {alert_message}', only_once
=only_once
)
675 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
677 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
678 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
680 def _extract_badges(self
, renderer
: dict):
682 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
683 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], str)
685 badges
.add(label
.lower())
689 def _get_text(data
, *path_list
, max_runs
=None):
690 for path
in path_list
or [None]:
694 obj
= traverse_obj(data
, path
, default
=[])
695 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
698 text
= try_get(item
, lambda x
: x
['simpleText'], str)
701 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
702 if not runs
and isinstance(item
, list):
705 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
706 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
710 def _get_count(self
, data
, *path_list
):
711 count_text
= self
._get
_text
(data
, *path_list
) or ''
712 count
= parse_count(count_text
)
715 self
._search
_regex
(r
'^([\d,]+)', re
.sub(r
'\s', '', count_text
), 'count', default
=None))
719 def _extract_thumbnails(data
, *path_list
):
721 Extract thumbnails from thumbnails dict
722 @param path_list: path list to level that contains 'thumbnails' key
725 for path
in path_list
or [()]:
726 for thumbnail
in traverse_obj(data
, (*variadic(path
), 'thumbnails', ...), default
=[]):
727 thumbnail_url
= url_or_none(thumbnail
.get('url'))
728 if not thumbnail_url
:
730 # Sometimes youtube gives a wrong thumbnail URL. See:
731 # https://github.com/yt-dlp/yt-dlp/issues/233
732 # https://github.com/ytdl-org/youtube-dl/issues/28023
733 if 'maxresdefault' in thumbnail_url
:
734 thumbnail_url
= thumbnail_url
.split('?')[0]
736 'url': thumbnail_url
,
737 'height': int_or_none(thumbnail
.get('height')),
738 'width': int_or_none(thumbnail
.get('width')),
743 def extract_relative_time(relative_time_text
):
745 Extracts a relative time from string and converts to dt object
746 e.g. 'streamed 6 days ago', '5 seconds ago (edited)', 'updated today'
748 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
)
750 start
= mobj
.group('start')
752 return datetime_from_str(start
)
754 return datetime_from_str('now-%s%s' % (mobj
.group('time'), mobj
.group('unit')))
758 def _extract_time_text(self
, renderer
, *path_list
):
759 """@returns (timestamp, time_text)"""
760 text
= self
._get
_text
(renderer
, *path_list
) or ''
761 dt
= self
.extract_relative_time(text
)
763 if isinstance(dt
, datetime
.datetime
):
764 timestamp
= calendar
.timegm(dt
.timetuple())
766 if timestamp
is None:
768 unified_timestamp(text
) or unified_timestamp(
770 (r
'([a-z]+\s*\d{1,2},?\s*20\d{2})', r
'(?:.+|^)(?:live|premieres|ed|ing)(?:\s*(?:on|for))?\s*(.+\d)'),
771 text
.lower(), 'time text', default
=None)))
773 if text
and timestamp
is None:
774 self
.report_warning(f
"Cannot parse localized time text '{text}'" + bug_reports_message(), only_once
=True)
775 return timestamp
, text
777 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
778 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
779 default_client
='web'):
780 for retry
in self
.RetryManager():
782 response
= self
._call
_api
(
783 ep
=ep
, fatal
=True, headers
=headers
,
784 video_id
=item_id
, query
=query
, note
=note
,
785 context
=self
._extract
_context
(ytcfg
, default_client
),
786 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
787 api_hostname
=api_hostname
, default_client
=default_client
)
788 except ExtractorError
as e
:
789 if not isinstance(e
.cause
, network_exceptions
):
790 return self
._error
_or
_warning
(e
, fatal
=fatal
)
791 elif not isinstance(e
.cause
, urllib
.error
.HTTPError
):
795 first_bytes
= e
.cause
.read(512)
796 if not is_html(first_bytes
):
799 self
._webpage
_read
_content
(e
.cause
, None, item_id
, prefix
=first_bytes
) or '{}', item_id
, fatal
=False),
800 lambda x
: x
['error']['message'], str)
802 self
._report
_alerts
([('ERROR', yt_error
)], fatal
=False)
803 # Downloading page may result in intermittent 5xx HTTP error
804 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
805 # We also want to catch all other network exceptions since errors in later pages can be troublesome
806 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
807 if e
.cause
.code
not in (403, 429):
810 return self
._error
_or
_warning
(e
, fatal
=fatal
)
813 self
._extract
_and
_report
_alerts
(response
, only_once
=True)
814 except ExtractorError
as e
:
815 # YouTube servers may return errors we want to retry on in a 200 OK response
816 # See: https://github.com/yt-dlp/yt-dlp/issues/839
817 if 'unknown error' in e
.msg
.lower():
820 return self
._error
_or
_warning
(e
, fatal
=fatal
)
821 # Youtube sometimes sends incomplete data
822 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
823 if not traverse_obj(response
, *variadic(check_get_keys
)):
824 retry
.error
= ExtractorError('Incomplete data received', expected
=True)
830 def is_music_url(url
):
831 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
833 def _extract_video(self
, renderer
):
834 video_id
= renderer
.get('videoId')
835 title
= self
._get
_text
(renderer
, 'title')
836 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
837 duration
= parse_duration(self
._get
_text
(
838 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
840 duration
= parse_duration(self
._search
_regex
(
841 r
'(?i)(ago)(?!.*\1)\s+(?P<duration>[a-z0-9 ,]+?)(?:\s+[\d,]+\s+views)?(?:\s+-\s+play\s+short)?$',
842 traverse_obj(renderer
, ('title', 'accessibility', 'accessibilityData', 'label'), default
='', expected_type
=str),
843 video_id
, default
=None, group
='duration'))
845 view_count
= self
._get
_count
(renderer
, 'viewCountText')
847 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
848 channel_id
= traverse_obj(
849 renderer
, ('shortBylineText', 'runs', ..., 'navigationEndpoint', 'browseEndpoint', 'browseId'),
850 expected_type
=str, get_all
=False)
851 timestamp
, time_text
= self
._extract
_time
_text
(renderer
, 'publishedTimeText')
852 scheduled_timestamp
= str_to_int(traverse_obj(renderer
, ('upcomingEventData', 'startTime'), get_all
=False))
853 overlay_style
= traverse_obj(
854 renderer
, ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'style'),
855 get_all
=False, expected_type
=str)
856 badges
= self
._extract
_badges
(renderer
)
857 thumbnails
= self
._extract
_thumbnails
(renderer
, 'thumbnail')
858 navigation_url
= urljoin('https://www.youtube.com/', traverse_obj(
859 renderer
, ('navigationEndpoint', 'commandMetadata', 'webCommandMetadata', 'url'),
860 expected_type
=str)) or ''
861 url
= f
'https://www.youtube.com/watch?v={video_id}'
862 if overlay_style
== 'SHORTS' or '/shorts/' in navigation_url
:
863 url
= f
'https://www.youtube.com/shorts/{video_id}'
867 'ie_key': YoutubeIE
.ie_key(),
871 'description': description
,
872 'duration': duration
,
873 'view_count': view_count
,
874 'uploader': uploader
,
875 'channel_id': channel_id
,
876 'thumbnails': thumbnails
,
877 'upload_date': (strftime_or_none(timestamp
, '%Y%m%d')
878 if self
._configuration
_arg
('approximate_date', ie_key
='youtubetab')
880 'live_status': ('is_upcoming' if scheduled_timestamp
is not None
881 else 'was_live' if 'streamed' in time_text
.lower()
882 else 'is_live' if overlay_style
== 'LIVE' or 'live now' in badges
884 'release_timestamp': scheduled_timestamp
,
885 'availability': self
._availability
(needs_premium
='premium' in badges
, needs_subscription
='members only' in badges
)
889 class YoutubeIE(YoutubeBaseInfoExtractor
):
891 _VALID_URL
= r
"""(?x)^
893 (?:https?://|//) # http(s):// or protocol-independent URL
894 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
895 (?:www\.)?deturl\.com/www\.youtube\.com|
896 (?:www\.)?pwnyoutube\.com|
897 (?:www\.)?hooktube\.com|
898 (?:www\.)?yourepeat\.com|
901 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
902 (?:.*?\#/)? # handle anchor (#/) redirect urls
903 (?: # the various things that can precede the ID:
904 (?:(?:v|embed|e|shorts)/(?!videoseries|live_stream)) # v/ or embed/ or e/ or shorts/
905 |(?: # or the v= param in all its forms
906 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
907 (?:\?|\#!?) # the params delimiter ? or # or #!
908 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
913 youtu\.be| # just youtu.be/xxxx
914 vid\.plus| # or vid.plus/xxxx
915 zwearz\.com/watch| # or zwearz.com/watch/xxxx
918 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
920 )? # all until now is optional -> you can pass the naked ID
921 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
922 (?(1).+)? # if we found the ID, everything can follow
924 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
926 _EMBED_REGEX
= [r
'''(?x)
936 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
937 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
940 r'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
941 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player(?:_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?|-plasma-ias-(?:phone|tablet)-[a-z]{2}_[A-Z]{2}\.vflset)/base\.js$',
942 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
945 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
946 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
947 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
948 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
949 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
950 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
951 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
952 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
953 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
954 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
955 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
956 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
957 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
958 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
959 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
960 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
961 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
962 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
966 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
967 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
968 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
969 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
970 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
971 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
972 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
974 # Apple HTTP Live Streaming
975 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
976 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
977 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
978 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
979 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
980 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
981 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
982 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
985 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
986 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
987 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
988 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
989 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
990 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
991 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
992 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
993 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
994 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
995 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
996 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
999 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
1000 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
1001 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
1002 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1003 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
1004 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
1005 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
1008 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1009 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1010 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1011 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1012 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1013 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
1014 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
1015 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1016 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1017 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1018 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1019 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1020 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1021 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1022 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1023 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1024 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1025 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1026 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1027 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1028 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
1029 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
1032 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
1033 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
1035 # Dash webm audio with opus inside
1036 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
1037 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
1038 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
1041 '_rtmp': {'protocol': 'rtmp'},
1043 # av01 video only formats sometimes served with "unknown" codecs
1044 '394': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1045 '395': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'av01.0.00M.08'},
1046 '396': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'av01.0.01M.08'},
1047 '397': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'av01.0.04M.08'},
1048 '398': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'av01.0.05M.08'},
1049 '399': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'av01.0.08M.08'},
1050 '400': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1051 '401': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'av01.0.12M.08'},
1053 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1060 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1062 'id': 'BaW_jenozKc',
1064 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1065 'uploader': 'Philipp Hagemeister',
1066 'uploader_id': 'phihag',
1067 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1068 'channel': 'Philipp Hagemeister',
1069 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1070 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1071 'upload_date': '20121002',
1072 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1073 'categories': ['Science & Technology'],
1074 'tags': ['youtube-dl'],
1078 'availability': 'public',
1079 'playable_in_embed': True,
1080 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1081 'live_status': 'not_live',
1085 'comment_count': int,
1086 'channel_follower_count': int
1090 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1091 'note': 'Embed-only video (#1746)',
1093 'id': 'yZIXLfi8CZQ',
1095 'upload_date': '20120608',
1096 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1097 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1098 'uploader': 'SET India',
1099 'uploader_id': 'setindia',
1100 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
1103 'skip': 'Private video',
1106 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1107 'note': 'Use the first video ID in the URL',
1109 'id': 'BaW_jenozKc',
1111 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1112 'uploader': 'Philipp Hagemeister',
1113 'uploader_id': 'phihag',
1114 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
1115 'channel': 'Philipp Hagemeister',
1116 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1117 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1118 'upload_date': '20121002',
1119 'description': 'md5:8fb536f4877b8a7455c2ec23794dbc22',
1120 'categories': ['Science & Technology'],
1121 'tags': ['youtube-dl'],
1125 'availability': 'public',
1126 'playable_in_embed': True,
1127 'thumbnail': 'https://i.ytimg.com/vi/BaW_jenozKc/maxresdefault.jpg',
1128 'live_status': 'not_live',
1130 'comment_count': int,
1131 'channel_follower_count': int
1134 'skip_download': True,
1138 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1139 'note': '256k DASH audio (format 141) via DASH manifest',
1141 'id': 'a9LDPn-MO4I',
1143 'upload_date': '20121002',
1144 'uploader_id': '8KVIDEO',
1145 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1147 'uploader': '8KVIDEO',
1148 'title': 'UHDTV TEST 8K VIDEO.mp4'
1151 'youtube_include_dash_manifest': True,
1154 'skip': 'format 141 not served anymore',
1156 # DASH manifest with encrypted signature
1158 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1160 'id': 'IB3lcPjvWLA',
1162 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1163 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1165 'uploader': 'AfrojackVEVO',
1166 'uploader_id': 'AfrojackVEVO',
1167 'upload_date': '20131011',
1170 'channel_id': 'UChuZAo1RKL85gev3Eal9_zg',
1171 'playable_in_embed': True,
1172 'channel_url': 'https://www.youtube.com/channel/UChuZAo1RKL85gev3Eal9_zg',
1174 'track': 'The Spark',
1175 'live_status': 'not_live',
1176 'thumbnail': 'https://i.ytimg.com/vi_webp/IB3lcPjvWLA/maxresdefault.webp',
1177 'channel': 'Afrojack',
1178 'uploader_url': 'http://www.youtube.com/user/AfrojackVEVO',
1180 'availability': 'public',
1181 'categories': ['Music'],
1183 'alt_title': 'The Spark',
1184 'channel_follower_count': int
1187 'youtube_include_dash_manifest': True,
1188 'format': '141/bestaudio[ext=m4a]',
1191 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1193 'note': 'Embed allowed age-gate video',
1194 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1196 'id': 'HtVdAasjOgU',
1198 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1199 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1201 'uploader': 'The Witcher',
1202 'uploader_id': 'WitcherGame',
1203 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1204 'upload_date': '20140605',
1206 'categories': ['Gaming'],
1207 'thumbnail': 'https://i.ytimg.com/vi_webp/HtVdAasjOgU/maxresdefault.webp',
1208 'availability': 'needs_auth',
1209 'channel_url': 'https://www.youtube.com/channel/UCzybXLxv08IApdjdN0mJhEg',
1211 'channel': 'The Witcher',
1212 'live_status': 'not_live',
1214 'channel_id': 'UCzybXLxv08IApdjdN0mJhEg',
1215 'playable_in_embed': True,
1217 'channel_follower_count': int
1221 'note': 'Age-gate video with embed allowed in public site',
1222 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1224 'id': 'HsUATh_Nc2U',
1226 'title': 'Godzilla 2 (Official Video)',
1227 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1228 'upload_date': '20200408',
1229 'uploader_id': 'FlyingKitty900',
1230 'uploader': 'FlyingKitty',
1232 'availability': 'needs_auth',
1233 'channel_id': 'UCYQT13AtrJC0gsM1far_zJg',
1234 'uploader_url': 'http://www.youtube.com/user/FlyingKitty900',
1235 'channel': 'FlyingKitty',
1236 'channel_url': 'https://www.youtube.com/channel/UCYQT13AtrJC0gsM1far_zJg',
1238 'categories': ['Entertainment'],
1239 'live_status': 'not_live',
1240 'tags': ['Flyingkitty', 'godzilla 2'],
1241 'thumbnail': 'https://i.ytimg.com/vi/HsUATh_Nc2U/maxresdefault.jpg',
1244 'playable_in_embed': True,
1245 'channel_follower_count': int
1249 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1250 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1252 'id': 'Tq92D6wQ1mg',
1253 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1255 'upload_date': '20191228',
1256 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1257 'uploader': 'Projekt Melody',
1258 'description': 'md5:17eccca93a786d51bc67646756894066',
1261 'availability': 'needs_auth',
1262 'uploader_url': 'http://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1263 'channel_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1265 'thumbnail': 'https://i.ytimg.com/vi_webp/Tq92D6wQ1mg/sddefault.webp',
1266 'channel': 'Projekt Melody',
1267 'live_status': 'not_live',
1268 'tags': ['mmd', 'dance', 'mikumikudance', 'kpop', 'vtuber'],
1269 'playable_in_embed': True,
1270 'categories': ['Entertainment'],
1272 'channel_url': 'https://www.youtube.com/channel/UC1yoRdFoFJaCY-AGfD9W0wQ',
1273 'comment_count': int,
1274 'channel_follower_count': int
1278 'note': 'Non-Agegated non-embeddable video',
1279 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1281 'id': 'MeJVWBSsPAY',
1283 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1284 'uploader': 'Herr Lurik',
1285 'uploader_id': 'st3in234',
1286 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1287 'upload_date': '20130730',
1288 'track': 'Such mich find mich',
1290 'tags': ['oomph', 'such mich find mich', 'lyrics', 'german industrial', 'musica industrial'],
1292 'playable_in_embed': False,
1293 'creator': 'OOMPH!',
1294 'thumbnail': 'https://i.ytimg.com/vi/MeJVWBSsPAY/sddefault.jpg',
1296 'alt_title': 'Such mich find mich',
1298 'channel': 'Herr Lurik',
1299 'channel_id': 'UCdR3RSDPqub28LjZx0v9-aA',
1300 'categories': ['Music'],
1301 'availability': 'public',
1302 'uploader_url': 'http://www.youtube.com/user/st3in234',
1303 'channel_url': 'https://www.youtube.com/channel/UCdR3RSDPqub28LjZx0v9-aA',
1304 'live_status': 'not_live',
1306 'channel_follower_count': int
1310 'note': 'Non-bypassable age-gated video',
1311 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1312 'only_matching': True,
1314 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1315 # YouTube Red ad is not captured for creator
1317 'url': '__2ABJjxzNo',
1319 'id': '__2ABJjxzNo',
1322 'upload_date': '20100430',
1323 'uploader_id': 'deadmau5',
1324 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1325 'creator': 'deadmau5',
1326 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1327 'uploader': 'deadmau5',
1328 'title': 'Deadmau5 - Some Chords (HD)',
1329 'alt_title': 'Some Chords',
1330 'availability': 'public',
1332 'channel_id': 'UCYEK6xds6eo-3tr4xRdflmQ',
1334 'live_status': 'not_live',
1335 'channel': 'deadmau5',
1336 'thumbnail': 'https://i.ytimg.com/vi_webp/__2ABJjxzNo/maxresdefault.webp',
1338 'track': 'Some Chords',
1339 'artist': 'deadmau5',
1340 'playable_in_embed': True,
1342 'channel_url': 'https://www.youtube.com/channel/UCYEK6xds6eo-3tr4xRdflmQ',
1343 'categories': ['Music'],
1344 'album': 'Some Chords',
1345 'channel_follower_count': int
1347 'expected_warnings': [
1348 'DASH manifest missing',
1351 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1353 'url': 'lqQg6PlCWgI',
1355 'id': 'lqQg6PlCWgI',
1358 'upload_date': '20150827',
1359 'uploader_id': 'olympic',
1360 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
1361 'description': 'md5:04bbbf3ccceb6795947572ca36f45904',
1362 'uploader': 'Olympics',
1363 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1365 'release_timestamp': 1343767800,
1366 'playable_in_embed': True,
1367 'categories': ['Sports'],
1368 'release_date': '20120731',
1369 'channel': 'Olympics',
1370 'tags': ['Hockey', '2012-07-31', '31 July 2012', 'Riverbank Arena', 'Session', 'Olympics', 'Olympic Games', 'London 2012', '2012 Summer Olympics', 'Summer Games'],
1371 'channel_id': 'UCTl3QQTvqHFjurroKxexy2Q',
1372 'thumbnail': 'https://i.ytimg.com/vi/lqQg6PlCWgI/maxresdefault.jpg',
1374 'availability': 'public',
1375 'live_status': 'was_live',
1377 'channel_url': 'https://www.youtube.com/channel/UCTl3QQTvqHFjurroKxexy2Q',
1378 'channel_follower_count': int
1381 'skip_download': 'requires avconv',
1386 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1388 'id': '_b-2C3KPAM0',
1390 'stretched_ratio': 16 / 9.,
1392 'upload_date': '20110310',
1393 'uploader_id': 'AllenMeow',
1394 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1395 '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',
1397 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1398 'playable_in_embed': True,
1402 'channel_url': 'https://www.youtube.com/channel/UCS-xxCmRaA6BFdmgDPA_BIw',
1403 'channel_id': 'UCS-xxCmRaA6BFdmgDPA_BIw',
1404 'thumbnail': 'https://i.ytimg.com/vi/_b-2C3KPAM0/maxresdefault.jpg',
1406 'categories': ['People & Blogs'],
1408 'live_status': 'not_live',
1409 'availability': 'unlisted',
1410 'comment_count': int,
1411 'channel_follower_count': int
1414 # url_encoded_fmt_stream_map is empty string
1416 'url': 'qEJwOuvDf7I',
1418 'id': 'qEJwOuvDf7I',
1420 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1422 'upload_date': '20150404',
1423 'uploader_id': 'spbelect',
1424 'uploader': 'Наблюдатели Петербурга',
1427 'skip_download': 'requires avconv',
1429 'skip': 'This live event has ended.',
1431 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1433 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1435 'id': 'FIl7x6_3R5Y',
1437 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1438 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1440 'upload_date': '20150625',
1441 'uploader_id': 'dorappi2000',
1442 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1443 'uploader': 'dorappi2000',
1444 'formats': 'mincount:31',
1446 'skip': 'not actual anymore',
1448 # DASH manifest with segment_list
1450 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1451 'md5': '8ce563a1d667b599d21064e982ab9e31',
1453 'id': 'CsmdDsKjzN8',
1455 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1456 'uploader': 'Airtek',
1457 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1458 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1459 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1462 'youtube_include_dash_manifest': True,
1463 'format': '135', # bestvideo
1465 'skip': 'This live event has ended.',
1468 # Multifeed videos (multiple cameras), URL is for Main Camera
1469 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1471 'id': 'jvGDaLqkpTg',
1472 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1473 'description': 'md5:e03b909557865076822aa169218d6a5d',
1477 'id': 'jvGDaLqkpTg',
1479 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1480 'description': 'md5:e03b909557865076822aa169218d6a5d',
1482 'upload_date': '20161111',
1483 'uploader': 'Team PGP',
1484 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1485 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1489 'id': '3AKt1R1aDnw',
1491 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1492 'description': 'md5:e03b909557865076822aa169218d6a5d',
1494 'upload_date': '20161111',
1495 'uploader': 'Team PGP',
1496 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1497 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1501 'id': 'RtAMM00gpVc',
1503 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1504 'description': 'md5:e03b909557865076822aa169218d6a5d',
1506 'upload_date': '20161111',
1507 'uploader': 'Team PGP',
1508 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1509 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1513 'id': '6N2fdlP3C5U',
1515 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1516 'description': 'md5:e03b909557865076822aa169218d6a5d',
1518 'upload_date': '20161111',
1519 'uploader': 'Team PGP',
1520 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1521 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1525 'skip_download': True,
1527 'skip': 'Not multifeed anymore',
1530 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1531 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1533 'id': 'gVfLd0zydlo',
1534 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1536 'playlist_count': 2,
1537 'skip': 'Not multifeed anymore',
1540 'url': 'https://vid.plus/FlRa-iH7PGw',
1541 'only_matching': True,
1544 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1545 'only_matching': True,
1548 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1549 # Also tests cut-off URL expansion in video description (see
1550 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1551 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1552 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1554 'id': 'lsguqyKfVQg',
1556 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1557 'alt_title': 'Dark Walk',
1558 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1560 'upload_date': '20151119',
1561 'uploader_id': 'IronSoulElf',
1562 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1563 'uploader': 'IronSoulElf',
1564 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1565 'track': 'Dark Walk',
1566 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1567 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1568 'thumbnail': 'https://i.ytimg.com/vi_webp/lsguqyKfVQg/maxresdefault.webp',
1569 'categories': ['Film & Animation'],
1571 'live_status': 'not_live',
1572 'channel_url': 'https://www.youtube.com/channel/UCTSRgz5jylBvFt_S7wnsqLQ',
1573 'channel_id': 'UCTSRgz5jylBvFt_S7wnsqLQ',
1575 'availability': 'public',
1576 'channel': 'IronSoulElf',
1577 'playable_in_embed': True,
1580 'channel_follower_count': int
1583 'skip_download': True,
1587 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1588 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1589 'only_matching': True,
1592 # Video with yt:stretch=17:0
1593 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1595 'id': 'Q39EVAstoRM',
1597 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1598 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1599 'upload_date': '20151107',
1600 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1601 'uploader': 'CH GAMER DROID',
1604 'skip_download': True,
1606 'skip': 'This video does not exist.',
1609 # Video with incomplete 'yt:stretch=16:'
1610 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1611 'only_matching': True,
1614 # Video licensed under Creative Commons
1615 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1617 'id': 'M4gD1WSo5mA',
1619 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1620 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1622 'upload_date': '20150128',
1623 'uploader_id': 'BerkmanCenter',
1624 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1625 'uploader': 'The Berkman Klein Center for Internet & Society',
1626 'license': 'Creative Commons Attribution license (reuse allowed)',
1627 'channel_id': 'UCuLGmD72gJDBwmLw06X58SA',
1628 'channel_url': 'https://www.youtube.com/channel/UCuLGmD72gJDBwmLw06X58SA',
1631 'tags': ['Copyright (Legal Subject)', 'Law (Industry)', 'William W. Fisher (Author)'],
1632 'channel': 'The Berkman Klein Center for Internet & Society',
1633 'availability': 'public',
1635 'categories': ['Education'],
1636 'thumbnail': 'https://i.ytimg.com/vi_webp/M4gD1WSo5mA/maxresdefault.webp',
1637 'live_status': 'not_live',
1638 'playable_in_embed': True,
1639 'comment_count': int,
1640 'channel_follower_count': int
1643 'skip_download': True,
1647 # Channel-like uploader_url
1648 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1650 'id': 'eQcmzGIKrzg',
1652 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1653 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1655 'upload_date': '20151120',
1656 'uploader': 'Bernie Sanders',
1657 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1658 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1659 'license': 'Creative Commons Attribution license (reuse allowed)',
1660 'playable_in_embed': True,
1663 'channel_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1665 'availability': 'public',
1666 'categories': ['News & Politics'],
1667 'channel': 'Bernie Sanders',
1668 'thumbnail': 'https://i.ytimg.com/vi_webp/eQcmzGIKrzg/maxresdefault.webp',
1670 'live_status': 'not_live',
1671 'channel_url': 'https://www.youtube.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1672 'comment_count': int,
1673 'channel_follower_count': int
1676 'skip_download': True,
1680 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1681 'only_matching': True,
1684 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1685 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1686 'only_matching': True,
1689 # Rental video preview
1690 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1692 'id': 'uGpuVWrhIzE',
1694 'title': 'Piku - Trailer',
1695 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1696 'upload_date': '20150811',
1697 'uploader': 'FlixMatrix',
1698 'uploader_id': 'FlixMatrixKaravan',
1699 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1700 'license': 'Standard YouTube License',
1703 'skip_download': True,
1705 'skip': 'This video is not available.',
1708 # YouTube Red video with episode data
1709 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1711 'id': 'iqKdEhx-dD4',
1713 'title': 'Isolation - Mind Field (Ep 1)',
1714 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1716 'upload_date': '20170118',
1717 'uploader': 'Vsauce',
1718 'uploader_id': 'Vsauce',
1719 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1720 'series': 'Mind Field',
1722 'episode_number': 1,
1723 'thumbnail': 'https://i.ytimg.com/vi_webp/iqKdEhx-dD4/maxresdefault.webp',
1726 'availability': 'public',
1728 'channel': 'Vsauce',
1729 'episode': 'Episode 1',
1730 'categories': ['Entertainment'],
1731 'season': 'Season 1',
1732 'channel_id': 'UC6nSFpj9HTCZ5t-N3Rm3-HA',
1733 'channel_url': 'https://www.youtube.com/channel/UC6nSFpj9HTCZ5t-N3Rm3-HA',
1735 'playable_in_embed': True,
1736 'live_status': 'not_live',
1737 'channel_follower_count': int
1740 'skip_download': True,
1742 'expected_warnings': [
1743 'Skipping DASH manifest',
1747 # The following content has been identified by the YouTube community
1748 # as inappropriate or offensive to some audiences.
1749 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1751 'id': '6SJNVb0GnPI',
1753 'title': 'Race Differences in Intelligence',
1754 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1756 'upload_date': '20140124',
1757 'uploader': 'New Century Foundation',
1758 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1762 'skip_download': True,
1764 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1768 'url': '1t24XAntNCY',
1769 'only_matching': True,
1772 # geo restricted to JP
1773 'url': 'sJL6WA-aGkQ',
1774 'only_matching': True,
1777 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1778 'only_matching': True,
1781 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1782 'only_matching': True,
1785 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1786 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1787 'only_matching': True,
1791 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1792 'only_matching': True,
1795 # Video with unsupported adaptive stream type formats
1796 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1798 'id': 'Z4Vy8R84T1U',
1800 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1801 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1803 'upload_date': '20130923',
1804 'uploader': 'Amelia Putri Harwita',
1805 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1806 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1807 'formats': 'maxcount:10',
1810 'skip_download': True,
1811 'youtube_include_dash_manifest': False,
1813 'skip': 'not actual anymore',
1816 # Youtube Music Auto-generated description
1817 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1819 'id': 'MgNrAu2pzNs',
1821 'title': 'Voyeur Girl',
1822 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1823 'upload_date': '20190312',
1824 'uploader': 'Stephen - Topic',
1825 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1826 'artist': 'Stephen',
1827 'track': 'Voyeur Girl',
1828 'album': 'it\'s too much love to know my dear',
1829 'release_date': '20190313',
1830 'release_year': 2019,
1831 'alt_title': 'Voyeur Girl',
1833 'uploader_url': 'http://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1834 'playable_in_embed': True,
1836 'categories': ['Music'],
1837 'channel_url': 'https://www.youtube.com/channel/UC-pWHpBjdGG69N9mM2auIAA',
1838 'channel': 'Stephen',
1839 'availability': 'public',
1840 'creator': 'Stephen',
1842 'thumbnail': 'https://i.ytimg.com/vi_webp/MgNrAu2pzNs/maxresdefault.webp',
1844 'channel_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1846 'live_status': 'not_live',
1847 'channel_follower_count': int
1850 'skip_download': True,
1854 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1855 'only_matching': True,
1858 # invalid -> valid video id redirection
1859 'url': 'DJztXj2GPfl',
1861 'id': 'DJztXj2GPfk',
1863 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1864 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1865 'upload_date': '20090125',
1866 'uploader': 'Prochorowka',
1867 'uploader_id': 'Prochorowka',
1868 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1869 'artist': 'Panjabi MC',
1870 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1871 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1874 'skip_download': True,
1876 'skip': 'Video unavailable',
1879 # empty description results in an empty string
1880 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1882 'id': 'x41yOUIvK2k',
1884 'title': 'IMG 3456',
1886 'upload_date': '20170613',
1887 'uploader_id': 'ElevageOrVert',
1888 'uploader': 'ElevageOrVert',
1890 'thumbnail': 'https://i.ytimg.com/vi_webp/x41yOUIvK2k/maxresdefault.webp',
1891 'uploader_url': 'http://www.youtube.com/user/ElevageOrVert',
1893 'channel_id': 'UCo03ZQPBW5U4UC3regpt1nw',
1895 'channel_url': 'https://www.youtube.com/channel/UCo03ZQPBW5U4UC3regpt1nw',
1896 'availability': 'public',
1898 'categories': ['Pets & Animals'],
1900 'playable_in_embed': True,
1901 'live_status': 'not_live',
1902 'channel': 'ElevageOrVert',
1903 'channel_follower_count': int
1906 'skip_download': True,
1910 # with '};' inside yt initial data (see [1])
1911 # see [2] for an example with '};' inside ytInitialPlayerResponse
1912 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1913 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1914 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1916 'id': 'CHqg6qOn4no',
1918 'title': 'Part 77 Sort a list of simple types in c#',
1919 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1920 'upload_date': '20130831',
1921 'uploader_id': 'kudvenkat',
1922 'uploader': 'kudvenkat',
1923 'channel_id': 'UCCTVrRB5KpIiK6V2GGVsR1Q',
1925 'uploader_url': 'http://www.youtube.com/user/kudvenkat',
1926 'channel_url': 'https://www.youtube.com/channel/UCCTVrRB5KpIiK6V2GGVsR1Q',
1927 'live_status': 'not_live',
1928 'categories': ['Education'],
1929 'availability': 'public',
1930 'thumbnail': 'https://i.ytimg.com/vi/CHqg6qOn4no/sddefault.jpg',
1932 'playable_in_embed': True,
1936 'channel': 'kudvenkat',
1937 'comment_count': int,
1938 'channel_follower_count': int
1941 'skip_download': True,
1945 # another example of '};' in ytInitialData
1946 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1947 'only_matching': True,
1950 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1951 'only_matching': True,
1954 # https://github.com/ytdl-org/youtube-dl/pull/28094
1955 'url': 'OtqTfy26tG0',
1957 'id': 'OtqTfy26tG0',
1959 'title': 'Burn Out',
1960 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1961 'upload_date': '20141120',
1962 'uploader': 'The Cinematic Orchestra - Topic',
1963 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1964 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1965 'artist': 'The Cinematic Orchestra',
1966 'track': 'Burn Out',
1967 'album': 'Every Day',
1969 'live_status': 'not_live',
1970 'alt_title': 'Burn Out',
1974 'channel_url': 'https://www.youtube.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1975 'creator': 'The Cinematic Orchestra',
1976 'channel': 'The Cinematic Orchestra',
1977 'tags': ['The Cinematic Orchestra', 'Every Day', 'Burn Out'],
1978 'channel_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1979 'availability': 'public',
1980 'thumbnail': 'https://i.ytimg.com/vi/OtqTfy26tG0/maxresdefault.jpg',
1981 'categories': ['Music'],
1982 'playable_in_embed': True,
1983 'channel_follower_count': int
1986 'skip_download': True,
1990 # controversial video, only works with bpctr when authenticated with cookies
1991 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1992 'only_matching': True,
1995 # controversial video, requires bpctr/contentCheckOk
1996 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1998 'id': 'SZJvDhaSDnc',
2000 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
2001 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
2002 'uploader': 'CBS Mornings',
2003 'uploader_id': 'CBSThisMorning',
2004 'upload_date': '20140716',
2005 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7',
2007 'categories': ['News & Politics'],
2008 'uploader_url': 'http://www.youtube.com/user/CBSThisMorning',
2010 'channel': 'CBS Mornings',
2011 'tags': ['suicide', 'bullying', 'video', 'cbs', 'news'],
2012 'thumbnail': 'https://i.ytimg.com/vi/SZJvDhaSDnc/hqdefault.jpg',
2014 'availability': 'needs_auth',
2015 'channel_url': 'https://www.youtube.com/channel/UC-SJ6nODDmufqBzPBwCvYvQ',
2017 'live_status': 'not_live',
2018 'playable_in_embed': True,
2019 'channel_follower_count': int
2023 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
2024 'url': 'cBvYw8_A0vQ',
2026 'id': 'cBvYw8_A0vQ',
2028 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
2029 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
2030 'upload_date': '20201120',
2031 'uploader': 'Walk around Japan',
2032 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2033 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2035 'categories': ['Travel & Events'],
2036 'channel_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
2038 'channel': 'Walk around Japan',
2039 'tags': ['Ueno Tokyo', 'Okachimachi Tokyo', 'Ameyoko Street', 'Tokyo attraction', 'Travel in Tokyo'],
2040 'thumbnail': 'https://i.ytimg.com/vi_webp/cBvYw8_A0vQ/hqdefault.webp',
2042 'availability': 'public',
2043 'channel_url': 'https://www.youtube.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
2044 'live_status': 'not_live',
2045 'playable_in_embed': True,
2046 'channel_follower_count': int
2049 'skip_download': True,
2052 # Has multiple audio streams
2053 'url': 'WaOKSUlf4TM',
2054 'only_matching': True
2056 # Requires Premium: has format 141 when requested using YTM url
2057 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
2058 'only_matching': True
2060 # multiple subtitles with same lang_code
2061 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
2062 'only_matching': True,
2064 # Force use android client fallback
2065 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
2067 'id': 'YOelRv7fMxY',
2068 'title': 'DIGGING A SECRET TUNNEL Part 1',
2070 'upload_date': '20210624',
2071 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
2072 'uploader': 'colinfurze',
2073 'uploader_id': 'colinfurze',
2074 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
2075 'description': 'md5:5d5991195d599b56cd0c4148907eec50',
2077 'categories': ['Entertainment'],
2078 'uploader_url': 'http://www.youtube.com/user/colinfurze',
2080 'channel': 'colinfurze',
2081 'tags': ['Colin', 'furze', 'Terry', 'tunnel', 'underground', 'bunker'],
2082 'thumbnail': 'https://i.ytimg.com/vi/YOelRv7fMxY/maxresdefault.jpg',
2084 'availability': 'public',
2086 'live_status': 'not_live',
2087 'playable_in_embed': True,
2088 'channel_follower_count': int
2091 'format': '17', # 3gp format available on android
2092 'extractor_args': {'youtube': {'player_client': ['android']}},
2096 # Skip download of additional client configs (remix client config in this case)
2097 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
2098 'only_matching': True,
2100 'extractor_args': {'youtube': {'player_skip': ['configs']}},
2104 'url': 'https://www.youtube.com/shorts/BGQWPY4IigY',
2105 'only_matching': True,
2107 'note': 'Storyboards',
2108 'url': 'https://www.youtube.com/watch?v=5KLPxDtMqe8',
2110 'id': '5KLPxDtMqe8',
2113 'title': 'Your Brain is Plastic',
2114 'uploader_id': 'scishow',
2115 'description': 'md5:89cd86034bdb5466cd87c6ba206cd2bc',
2116 'upload_date': '20140324',
2117 'uploader': 'SciShow',
2119 'channel_id': 'UCZYTClx2T1of7BRZ86-8fow',
2120 'channel_url': 'https://www.youtube.com/channel/UCZYTClx2T1of7BRZ86-8fow',
2122 'thumbnail': 'https://i.ytimg.com/vi/5KLPxDtMqe8/maxresdefault.jpg',
2123 'playable_in_embed': True,
2125 'uploader_url': 'http://www.youtube.com/user/scishow',
2126 'availability': 'public',
2127 'channel': 'SciShow',
2128 'live_status': 'not_live',
2130 'categories': ['Education'],
2132 'channel_follower_count': int
2133 }, 'params': {'format': 'mhtml', 'skip_download': True}
2135 # Ensure video upload_date is in UTC timezone (video was uploaded 1641170939)
2136 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2138 'id': '2NUZ8W2llS4',
2140 'title': 'The NP that test your phone performance 🙂',
2141 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2142 'uploader': 'Leon Nguyen',
2143 'uploader_id': 'VNSXIII',
2144 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2145 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2146 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2150 'categories': ['Gaming'],
2152 'playable_in_embed': True,
2153 'live_status': 'not_live',
2154 'upload_date': '20220103',
2156 'availability': 'public',
2157 'channel': 'Leon Nguyen',
2158 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2159 'comment_count': int,
2160 'channel_follower_count': int
2163 # Same video as above, but with --compat-opt no-youtube-prefer-utc-upload-date
2164 'url': 'https://www.youtube.com/watch?v=2NUZ8W2llS4',
2166 'id': '2NUZ8W2llS4',
2168 'title': 'The NP that test your phone performance 🙂',
2169 'description': 'md5:144494b24d4f9dfacb97c1bbef5de84d',
2170 'uploader': 'Leon Nguyen',
2171 'uploader_id': 'VNSXIII',
2172 'uploader_url': 'http://www.youtube.com/user/VNSXIII',
2173 'channel_id': 'UCRqNBSOHgilHfAczlUmlWHA',
2174 'channel_url': 'https://www.youtube.com/channel/UCRqNBSOHgilHfAczlUmlWHA',
2178 'categories': ['Gaming'],
2180 'playable_in_embed': True,
2181 'live_status': 'not_live',
2182 'upload_date': '20220102',
2184 'availability': 'public',
2185 'channel': 'Leon Nguyen',
2186 'thumbnail': 'https://i.ytimg.com/vi_webp/2NUZ8W2llS4/maxresdefault.webp',
2187 'comment_count': int,
2188 'channel_follower_count': int
2190 'params': {'compat_opts': ['no-youtube-prefer-utc-upload-date']}
2192 # date text is premiered video, ensure upload date in UTC (published 1641172509)
2193 'url': 'https://www.youtube.com/watch?v=mzZzzBU6lrM',
2195 'id': 'mzZzzBU6lrM',
2197 'title': 'I Met GeorgeNotFound In Real Life...',
2198 'description': 'md5:cca98a355c7184e750f711f3a1b22c84',
2199 'uploader': 'Quackity',
2200 'uploader_id': 'QuackityHQ',
2201 'uploader_url': 'http://www.youtube.com/user/QuackityHQ',
2202 'channel_id': 'UC_8NknAFiyhOUaZqHR3lq3Q',
2203 'channel_url': 'https://www.youtube.com/channel/UC_8NknAFiyhOUaZqHR3lq3Q',
2207 'categories': ['Entertainment'],
2209 'playable_in_embed': True,
2210 'live_status': 'not_live',
2211 'release_timestamp': 1641172509,
2212 'release_date': '20220103',
2213 'upload_date': '20220103',
2215 'availability': 'public',
2216 'channel': 'Quackity',
2217 'thumbnail': 'https://i.ytimg.com/vi/mzZzzBU6lrM/maxresdefault.jpg',
2218 'channel_follower_count': int
2221 { # continuous livestream. Microformat upload date should be preferred.
2222 # Upload date was 2021-06-19 (not UTC), while stream start is 2021-11-27
2223 'url': 'https://www.youtube.com/watch?v=kgx4WGK0oNU',
2225 'id': 'kgx4WGK0oNU',
2226 '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}',
2228 'channel_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2229 'availability': 'public',
2231 'release_timestamp': 1637975704,
2232 'upload_date': '20210619',
2233 'channel_url': 'https://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2234 'live_status': 'is_live',
2235 'thumbnail': 'https://i.ytimg.com/vi/kgx4WGK0oNU/maxresdefault.jpg',
2236 'uploader': '阿鲍Abao',
2237 'uploader_url': 'http://www.youtube.com/channel/UC84whx2xxsiA1gXHXXqKGOA',
2238 'channel': 'Abao in Tokyo',
2239 'channel_follower_count': int,
2240 'release_date': '20211127',
2242 'categories': ['People & Blogs'],
2244 'uploader_id': 'UC84whx2xxsiA1gXHXXqKGOA',
2246 'playable_in_embed': True,
2247 'description': 'md5:2ef1d002cad520f65825346e2084e49d',
2249 'params': {'skip_download': True}
2251 # Story. Requires specific player params to work.
2252 'url': 'https://www.youtube.com/watch?v=vv8qTUWmulI',
2254 'id': 'vv8qTUWmulI',
2256 'availability': 'unlisted',
2258 'channel_id': 'UCzIZ8HrzDgc-pNQDUG6avBA',
2259 'upload_date': '20220526',
2260 'categories': ['Education'],
2262 'channel': 'IT\'S HISTORY',
2264 'uploader_id': 'BlastfromthePast',
2266 'uploader': 'IT\'S HISTORY',
2267 'playable_in_embed': True,
2269 'live_status': 'not_live',
2271 'thumbnail': 'https://i.ytimg.com/vi_webp/vv8qTUWmulI/maxresdefault.webp',
2272 'uploader_url': 'http://www.youtube.com/user/BlastfromthePast',
2273 'channel_url': 'https://www.youtube.com/channel/UCzIZ8HrzDgc-pNQDUG6avBA',
2275 'skip': 'stories get removed after some period of time',
2277 'url': 'https://www.youtube.com/watch?v=tjjjtzRLHvA',
2279 'id': 'tjjjtzRLHvA',
2281 'title': 'ハッシュタグ無し };if window.ytcsi',
2282 'upload_date': '20220323',
2284 'availability': 'unlisted',
2285 'channel': 'nao20010128nao',
2286 'thumbnail': 'https://i.ytimg.com/vi_webp/tjjjtzRLHvA/maxresdefault.webp',
2288 'uploader': 'nao20010128nao',
2289 'uploader_id': 'nao20010128nao',
2290 'categories': ['Music'],
2293 'channel_url': 'https://www.youtube.com/channel/UCdqltm_7iv1Vs6kp6Syke5A',
2294 'channel_id': 'UCdqltm_7iv1Vs6kp6Syke5A',
2295 'live_status': 'not_live',
2296 'playable_in_embed': True,
2297 'channel_follower_count': int,
2300 'uploader_url': 'http://www.youtube.com/user/nao20010128nao',
2303 'note': '6 channel audio',
2304 'url': 'https://www.youtube.com/watch?v=zgdo7-RRjgo',
2305 'only_matching': True,
2310 # YouTube <object> embed
2312 'url': 'http://www.improbable.com/2017/04/03/untrained-modern-youths-and-ancient-masters-in-selfie-portraits/',
2313 'md5': '873c81d308b979f0e23ee7e620b312a3',
2315 'id': 'msN87y-iEx0',
2317 'title': 'Feynman: Mirrors FUN TO IMAGINE 6',
2318 'upload_date': '20080526',
2319 'description': 'md5:873c81d308b979f0e23ee7e620b312a3',
2320 'uploader': 'Christopher Sykes',
2321 'uploader_id': 'ChristopherJSykes',
2323 'tags': ['feynman', 'mirror', 'science', 'physics', 'imagination', 'fun', 'cool', 'puzzle'],
2324 'channel_id': 'UCCeo--lls1vna5YJABWAcVA',
2325 'playable_in_embed': True,
2326 'thumbnail': 'https://i.ytimg.com/vi/msN87y-iEx0/hqdefault.jpg',
2328 'comment_count': int,
2329 'channel': 'Christopher Sykes',
2330 'live_status': 'not_live',
2331 'channel_url': 'https://www.youtube.com/channel/UCCeo--lls1vna5YJABWAcVA',
2332 'availability': 'public',
2335 'categories': ['Science & Technology'],
2336 'channel_follower_count': int,
2337 'uploader_url': 'http://www.youtube.com/user/ChristopherJSykes',
2340 'skip_download': True,
2346 def suitable(cls, url):
2347 from ..utils import parse_qs
2350 if qs.get('list', [None])[0]:
2352 return super().suitable(url)
2354 def __init__(self, *args, **kwargs):
2355 super().__init__(*args, **kwargs)
2356 self._code_cache = {}
2357 self._player_cache = {}
2359 def _prepare_live_from_start_formats(self, formats, video_id, live_start_time, url, webpage_url, smuggled_data):
2360 lock = threading.Lock()
2363 start_time = time.time()
2364 formats = [f for f in formats if f.get('is_from_start')]
2366 def refetch_manifest(format_id, delay):
2367 nonlocal formats, start_time, is_live
2368 if time.time() <= start_time + delay:
2371 _, _, prs, player_url = self._download_player_responses(url, smuggled_data, video_id, webpage_url)
2372 video_details = traverse_obj(
2373 prs, (..., 'videoDetails'), expected_type=dict, default=[])
2374 microformats = traverse_obj(
2375 prs, (..., 'microformat', 'playerMicroformatRenderer'),
2376 expected_type=dict, default=[])
2377 _, is_live, _, formats, _ = self._list_formats(video_id, microformats, video_details, prs, player_url)
2378 start_time = time.time()
2380 def mpd_feed(format_id, delay):
2382 @returns (manifest_url, manifest_stream_number, is_live) or None
2385 refetch_manifest(format_id, delay)
2387 f = next((f for f in formats if f['format_id'] == format_id), None)
2390 self.to_screen(f'{video_id}: Video is no longer live')
2392 self.report_warning(
2393 f'Cannot find refreshed manifest for format {format_id}{bug_reports_message()}')
2395 return f['manifest_url'], f['manifest_stream_number'], is_live
2399 f['protocol'] = 'http_dash_segments_generator'
2400 f['fragments'] = functools.partial(
2401 self._live_dash_fragments, f['format_id'], live_start_time, mpd_feed)
2403 def _live_dash_fragments(self, format_id, live_start_time, mpd_feed, ctx):
2404 FETCH_SPAN, MAX_DURATION = 5, 432000
2406 mpd_url, stream_number, is_live = None, None, True
2409 download_start_time = ctx.get('start') or time.time()
2411 lack_early_segments = download_start_time - (live_start_time or download_start_time) > MAX_DURATION
2412 if lack_early_segments:
2413 self.report_warning(bug_reports_message(
2414 'Starting download from the last 120 hours of the live stream since '
2415 'YouTube does not have data before that. If you think this is wrong,'), only_once=True)
2416 lack_early_segments = True
2418 known_idx, no_fragment_score, last_segment_url = begin_index, 0, None
2419 fragments, fragment_base_url = None, None
2421 def _extract_sequence_from_mpd(refresh_sequence, immediate):
2422 nonlocal mpd_url, stream_number, is_live, no_fragment_score, fragments, fragment_base_url
2423 # Obtain from MPD's maximum seq value
2424 old_mpd_url = mpd_url
2425 last_error = ctx.pop('last_error', None)
2426 expire_fast = immediate or last_error and isinstance(last_error, urllib.error.HTTPError) and last_error.code == 403
2427 mpd_url, stream_number, is_live = (mpd_feed(format_id, 5 if expire_fast else 18000)
2428 or (mpd_url, stream_number, False))
2429 if not refresh_sequence:
2430 if expire_fast and not is_live:
2431 return False, last_seq
2432 elif old_mpd_url == mpd_url:
2433 return True, last_seq
2435 fmts, _ = self._extract_mpd_formats_and_subtitles(
2436 mpd_url, None, note=False, errnote=False, fatal=False)
2437 except ExtractorError:
2440 no_fragment_score += 2
2441 return False, last_seq
2442 fmt_info = next(x for x in fmts if x['manifest_stream_number'] == stream_number)
2443 fragments = fmt_info['fragments']
2444 fragment_base_url = fmt_info['fragment_base_url']
2445 assert fragment_base_url
2447 _last_seq = int(re.search(r'(?:/|^)sq/(\d+)', fragments[-1]['path']).group(1))
2448 return True, _last_seq
2451 fetch_time = time.time()
2452 if no_fragment_score > 30:
2454 if last_segment_url:
2455 # Obtain from "X-Head-Seqnum" header value from each segment
2457 urlh = self._request_webpage(
2458 last_segment_url, None, note=False, errnote=False, fatal=False)
2459 except ExtractorError:
2461 last_seq = try_get(urlh, lambda x: int_or_none(x.headers['X-Head-Seqnum']))
2462 if last_seq is None:
2463 no_fragment_score += 2
2464 last_segment_url = None
2467 should_continue, last_seq = _extract_sequence_from_mpd(True, no_fragment_score > 15)
2468 no_fragment_score += 2
2469 if not should_continue:
2472 if known_idx > last_seq:
2473 last_segment_url = None
2478 if begin_index < 0 and known_idx < 0:
2479 # skip from the start when it's negative value
2480 known_idx = last_seq + begin_index
2481 if lack_early_segments:
2482 known_idx = max(known_idx, last_seq - int(MAX_DURATION // fragments[-1]['duration']))
2484 for idx in range(known_idx, last_seq):
2485 # do not update sequence here or you'll get skipped some part of it
2486 should_continue, _ = _extract_sequence_from_mpd(False, False)
2487 if not should_continue:
2489 raise ExtractorError('breaking out of outer loop')
2490 last_segment_url = urljoin(fragment_base_url, 'sq/%d' % idx)
2492 'url': last_segment_url,
2493 'fragment_count': last_seq,
2495 if known_idx == last_seq:
2496 no_fragment_score += 5
2498 no_fragment_score = 0
2499 known_idx = last_seq
2500 except ExtractorError:
2503 time.sleep(max(0, FETCH_SPAN + fetch_time - time.time()))
2505 def _extract_player_url(self, *ytcfgs, webpage=None):
2506 player_url = traverse_obj(
2507 ytcfgs, (..., 'PLAYER_JS_URL'), (..., 'WEB_PLAYER_CONTEXT_CONFIGS', ..., 'jsUrl'),
2508 get_all=False, expected_type=str)
2511 return urljoin('https://www.youtube.com', player_url)
2513 def _download_player_url(self, video_id, fatal=False):
2514 res = self._download_webpage(
2515 'https://www.youtube.com/iframe_api',
2516 note='Downloading iframe API JS', video_id=video_id, fatal=fatal)
2518 player_version = self._search_regex(
2519 r'player\\?/([0-9a-fA-F]{8})\\?/', res, 'player version', fatal=fatal)
2521 return f'https://www.youtube.com/s/player/{player_version}/player_ias.vflset/en_US/base.js'
2523 def _signature_cache_id(self, example_sig):
2524 """ Return a string representation of a signature """
2525 return '.'.join(str(len(part)) for part in example_sig.split('.'))
2528 def _extract_player_info(cls, player_url):
2529 for player_re in cls._PLAYER_INFO_RE:
2530 id_m = re.search(player_re, player_url)
2534 raise ExtractorError('Cannot identify player %r' % player_url)
2535 return id_m.group('id')
2537 def _load_player(self, video_id, player_url, fatal=True):
2538 player_id = self._extract_player_info(player_url)
2539 if player_id not in self._code_cache:
2540 code = self._download_webpage(
2541 player_url, video_id, fatal=fatal,
2542 note='Downloading player ' + player_id,
2543 errnote='Download of %s failed' % player_url)
2545 self._code_cache[player_id] = code
2546 return self._code_cache.get(player_id)
2548 def _extract_signature_function(self, video_id, player_url, example_sig):
2549 player_id = self._extract_player_info(player_url)
2551 # Read from filesystem cache
2552 func_id = f'js_{player_id}_{self._signature_cache_id(example_sig)}'
2553 assert os.path.basename(func_id) == func_id
2555 self.write_debug(f'Extracting signature function {func_id}')
2556 cache_spec, code = self.cache.load('youtube-sigfuncs', func_id), None
2559 code = self._load_player(video_id, player_url)
2561 res = self._parse_sig_js(code)
2562 test_string = ''.join(map(chr, range(len(example_sig))))
2563 cache_spec = [ord(c) for c in res(test_string)]
2564 self.cache.store('youtube-sigfuncs', func_id, cache_spec)
2566 return lambda s: ''.join(s[i] for i in cache_spec)
2568 def _print_sig_code(self, func, example_sig):
2569 if not self.get_param('youtube_print_sig_code'):
2572 def gen_sig_code(idxs):
2573 def _genslice(start, end, step):
2574 starts = '' if start == 0 else str(start)
2575 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
2576 steps = '' if step == 1 else (':%d' % step)
2577 return f's[{starts}{ends}{steps}]'
2580 # Quelch pyflakes warnings - start will be set when step is set
2581 start = '(Never used)'
2582 for i, prev in zip(idxs[1:], idxs[:-1]):
2583 if step is not None:
2584 if i - prev == step:
2586 yield _genslice(start, prev, step)
2589 if i - prev in [-1, 1]:
2594 yield 's[%d]' % prev
2598 yield _genslice(start, i, step)
2600 test_string = ''.join(map(chr, range(len(example_sig))))
2601 cache_res = func(test_string)
2602 cache_spec = [ord(c) for c in cache_res]
2603 expr_code = ' + '.join(gen_sig_code(cache_spec))
2604 signature_id_tuple = '(%s)' % (
2605 ', '.join(str(len(p)) for p in example_sig.split('.')))
2606 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
2607 ' return %s\n') % (signature_id_tuple, expr_code)
2608 self.to_screen('Extracted signature function:\n' + code)
2610 def _parse_sig_js(self, jscode):
2611 funcname = self._search_regex(
2612 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2613 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2614 r'\bm=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(h\.s\)\)',
2615 r'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2,})\(decodeURIComponent\(c\)\)',
2616 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}\(a,\d+\)',
2617 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\(\s*""\s*\)',
2618 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
2620 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2621 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
2622 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2623 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2624 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2625 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2626 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
2627 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
2628 jscode, 'Initial JS player signature function name', group='sig')
2630 jsi = JSInterpreter(jscode)
2631 initial_function = jsi.extract_function(funcname)
2632 return lambda s: initial_function([s])
2634 def _cached(self, func, *cache_id):
2635 def inner(*args, **kwargs):
2636 if cache_id not in self._player_cache:
2638 self._player_cache[cache_id] = func(*args, **kwargs)
2639 except ExtractorError as e:
2640 self._player_cache[cache_id] = e
2641 except Exception as e:
2642 self._player_cache[cache_id] = ExtractorError(traceback.format_exc(), cause=e)
2644 ret = self._player_cache[cache_id]
2645 if isinstance(ret, Exception):
2650 def _decrypt_signature(self, s, video_id, player_url):
2651 """Turn the encrypted s field into a working signature"""
2652 extract_sig = self._cached(
2653 self._extract_signature_function, 'sig', player_url, self._signature_cache_id(s))
2654 func = extract_sig(video_id, player_url, s)
2655 self._print_sig_code(func, s)
2658 def _decrypt_nsig(self, s, video_id, player_url):
2659 """Turn the encrypted n field into a working signature"""
2660 if player_url is None:
2661 raise ExtractorError('Cannot decrypt nsig without player_url')
2662 player_url = urljoin('https://www.youtube.com', player_url)
2665 jsi, player_id, func_code = self._extract_n_function_code(video_id, player_url)
2666 except ExtractorError as e:
2667 raise ExtractorError('Unable to extract nsig function code', cause=e)
2668 if self.get_param('youtube_print_sig_code'):
2669 self.to_screen(f'Extracted nsig function from {player_id}:\n{func_code[1]}\n')
2672 extract_nsig = self._cached(self._extract_n_function_from_code, 'nsig func', player_url)
2673 ret = extract_nsig(jsi, func_code)(s)
2674 except JSInterpreter.Exception as e:
2676 jsi = PhantomJSwrapper(self, timeout=5000)
2677 except ExtractorError:
2679 self.report_warning(
2680 f'Native nsig extraction failed: Trying with PhantomJS\n'
2681 f' n = {s} ; player = {player_url}', video_id)
2684 args, func_body = func_code
2686 f'console.log(function({", ".join(args)}) {{ {func_body} }}({s!r}));',
2687 video_id=video_id, note='Executing signature code').strip()
2689 self.write_debug(f'Decrypted nsig {s} => {ret}')
2692 def _extract_n_function_name(self, jscode):
2693 funcname, idx = self._search_regex(
2694 r'\.get\("n"\)\)&&\(b=(?P<nfunc>[a-zA-Z0-9$]+)(?:\[(?P<idx>\d+)\])?\([a-zA-Z0-9]\)',
2695 jscode, 'Initial JS player n function name', group=('nfunc', 'idx'))
2699 return json.loads(js_to_json(self._search_regex(
2700 rf'var {re.escape(funcname)}\s*=\s*(\[.+?\]);', jscode,
2701 f'Initial JS player n function list ({funcname}.{idx})')))[int(idx)]
2703 def _extract_n_function_code(self, video_id, player_url):
2704 player_id = self._extract_player_info(player_url)
2705 func_code = self.cache.load('youtube-nsig', player_id, min_ver='2022.09.1')
2706 jscode = func_code or self._load_player(video_id, player_url)
2707 jsi = JSInterpreter(jscode)
2710 return jsi, player_id, func_code
2712 func_name = self._extract_n_function_name(jscode)
2715 func_code = self._search_regex(
2716 r'''(?xs
)%s\s
*=\s
*function\s
*\
((?P
<var
>[\w$
]+)\
)\s
*
2717 # NB: The end of the regex is intentionally kept strict
2718 {(?P<code>.+?}\s
*return\
[\w$
]+.join\
(""\
))};''' % func_name,
2719 jscode, 'nsig function', group=('var', 'code'), default=None)
2721 func_code = ([func_code[0]], func_code[1])
2723 self.write_debug('Extracting nsig function with jsinterp')
2724 func_code = jsi.extract_function_code(func_name)
2726 self.cache.store('youtube-nsig', player_id, func_code)
2727 return jsi, player_id, func_code
2729 def _extract_n_function_from_code(self, jsi, func_code):
2730 func = jsi.extract_function_from_code(*func_code)
2732 def extract_nsig(s):
2735 except JSInterpreter.Exception:
2737 except Exception as e:
2738 raise JSInterpreter.Exception(traceback.format_exc(), cause=e)
2740 if ret.startswith('enhanced_except_'):
2741 raise JSInterpreter.Exception('Signature function returned an exception')
2746 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
2748 Extract signatureTimestamp (sts)
2749 Required to tell API what sig/player version is in use.
2752 if isinstance(ytcfg, dict):
2753 sts = int_or_none(ytcfg.get('STS'))
2756 # Attempt to extract from player
2757 if player_url is None:
2758 error_msg = 'Cannot extract signature timestamp without player_url.'
2760 raise ExtractorError(error_msg)
2761 self.report_warning(error_msg)
2763 code = self._load_player(video_id, player_url, fatal=fatal)
2765 sts = int_or_none(self._search_regex(
2766 r'(?:signatureTimestamp|sts)\s*:\s*(?P<sts>[0-9]{5})', code,
2767 'JS player signature timestamp', group='sts', fatal=fatal))
2770 def _mark_watched(self, video_id, player_responses):
2771 for is_full, key in enumerate(('videostatsPlaybackUrl', 'videostatsWatchtimeUrl')):
2772 label = 'fully ' if is_full else ''
2773 url = get_first(player_responses, ('playbackTracking', key, 'baseUrl'),
2774 expected_type=url_or_none)
2776 self.report_warning(f'Unable to mark {label}watched')
2778 parsed_url = urllib.parse.urlparse(url)
2779 qs = urllib.parse.parse_qs(parsed_url.query)
2781 # cpn generation algorithm is reverse engineered from base.js.
2782 # In fact it works even with dummy cpn.
2783 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
2784 cpn = ''.join(CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16))
2786 # # more consistent results setting it to right before the end
2787 video_length = [str(float((qs.get('len') or ['1.5'])[0]) - 1)]
2792 'cmt': video_length,
2793 'el': 'detailpage', # otherwise defaults to "shorts"
2797 # these seem to mark watchtime "history" in the real world
2798 # they're required, so send in a single value
2804 url = urllib.parse.urlunparse(
2805 parsed_url._replace(query=urllib.parse.urlencode(qs, True)))
2807 self._download_webpage(
2808 url, video_id, f'Marking {label}watched',
2809 'Unable to mark watched', fatal=False)
2812 def _extract_from_webpage(cls, url, webpage):
2813 # Invidious Instances
2814 # https://github.com/yt-dlp/yt-dlp/issues/195
2815 # https://github.com/iv-org/invidious/pull/1730
2817 r'<link rel="alternate" href="(?P<url>https://www\.youtube\.com/watch\?v=[0-9A-Za-z_-]{11})"',
2820 yield cls.url_result(mobj.group('url'), cls)
2821 raise cls.StopExtraction()
2823 yield from super()._extract_from_webpage(url, webpage)
2825 # lazyYT YouTube embed
2826 for id_ in re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage):
2827 yield cls.url_result(unescapeHTML(id_), cls, id_)
2829 # Wordpress "YouTube Video Importer" plugin
2830 for m in re.findall(r'''(?x
)<div
[^
>]+
2831 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
2832 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage):
2833 yield cls.url_result(m[-1], cls, m[-1])
2836 def extract_id(cls, url):
2837 video_id = cls.get_temp_id(url)
2839 raise ExtractorError(f'Invalid URL: {url}')
2842 def _extract_chapters_from_json(self, data, duration):
2843 chapter_list = traverse_obj(
2845 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2846 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2847 ), expected_type=list)
2849 return self._extract_chapters(
2851 chapter_time=lambda chapter: float_or_none(
2852 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2853 chapter_title=lambda chapter: traverse_obj(
2854 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2857 def _extract_chapters_from_engagement_panel(self, data, duration):
2858 content_list = traverse_obj(
2860 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2861 expected_type=list, default=[])
2862 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2863 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2865 return next(filter(None, (
2866 self._extract_chapters(traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2867 chapter_time, chapter_title, duration)
2868 for contents in content_list)), [])
2870 def _extract_chapters_from_description(self, description, duration):
2871 return self._extract_chapters(
2872 re.findall(r'(?m)^((?:\d+:)?\d{1,2}:\d{2})\b\W*\s(.+?)\s*$', description or ''),
2873 chapter_time=lambda x: parse_duration(x[0]), chapter_title=lambda x: x[1],
2874 duration=duration, strict=False)
2876 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration, strict=True):
2880 'start_time': chapter_time(chapter),
2881 'title': chapter_title(chapter),
2882 } for chapter in chapter_list or []]
2884 chapter_list.sort(key=lambda c: c['start_time'] or 0)
2886 chapters = [{'start_time': 0}]
2887 for idx, chapter in enumerate(chapter_list):
2888 if chapter['start_time'] is None:
2889 self.report_warning(f'Incomplete chapter {idx}')
2890 elif chapters[-1]['start_time'] <= chapter['start_time'] <= duration:
2891 chapters.append(chapter)
2893 self.report_warning(f'Invalid start time for chapter "{chapter["title"]}
"')
2896 def _extract_comment(self, comment_renderer, parent=None):
2897 comment_id = comment_renderer.get('commentId')
2901 text = self._get_text(comment_renderer, 'contentText')
2903 # note: timestamp is an estimate calculated from the current time and time_text
2904 timestamp, time_text = self._extract_time_text(comment_renderer, 'publishedTimeText')
2905 author = self._get_text(comment_renderer, 'authorText')
2906 author_id = try_get(comment_renderer,
2907 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], str)
2909 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2910 lambda x: x['likeCount']), str)) or 0
2911 author_thumbnail = try_get(comment_renderer,
2912 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], str)
2914 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2915 is_favorited = 'creatorHeart' in (try_get(
2916 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2920 'timestamp': timestamp,
2921 'time_text': time_text,
2922 'like_count': votes,
2923 'is_favorited': is_favorited,
2925 'author_id': author_id,
2926 'author_thumbnail': author_thumbnail,
2927 'author_is_uploader': author_is_uploader,
2928 'parent': parent or 'root'
2931 def _comment_entries(self, root_continuation_data, ytcfg, video_id, parent=None, tracker=None):
2933 get_single_config_arg = lambda c: self._configuration_arg(c, [''])[0]
2935 def extract_header(contents):
2936 _continuation = None
2937 for content in contents:
2938 comments_header_renderer = traverse_obj(content, 'commentsHeaderRenderer')
2939 expected_comment_count = self._get_count(
2940 comments_header_renderer, 'countText', 'commentsCount')
2942 if expected_comment_count:
2943 tracker['est_total'] = expected_comment_count
2944 self.to_screen(f'Downloading ~{expected_comment_count} comments')
2945 comment_sort_index = int(get_single_config_arg('comment_sort') != 'top') # 1 = new, 0 = top
2947 sort_menu_item = try_get(
2948 comments_header_renderer,
2949 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2950 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2952 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2953 if not _continuation:
2956 sort_text = str_or_none(sort_menu_item.get('title'))
2958 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2959 self.to_screen('Sorting comments by %s' % sort_text.lower())
2961 return _continuation
2963 def extract_thread(contents):
2965 tracker['current_page_thread'] = 0
2966 for content in contents:
2967 if not parent and tracker['total_parent_comments'] >= max_parents:
2969 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2970 comment_renderer = get_first(
2971 (comment_thread_renderer, content), [['commentRenderer', ('comment', 'commentRenderer')]],
2972 expected_type=dict, default={})
2974 comment = self._extract_comment(comment_renderer, parent)
2978 tracker['running_total'] += 1
2979 tracker['total_reply_comments' if parent else 'total_parent_comments'] += 1
2982 # Attempt to get the replies
2983 comment_replies_renderer = try_get(
2984 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2986 if comment_replies_renderer:
2987 tracker['current_page_thread'] += 1
2988 comment_entries_iter = self._comment_entries(
2989 comment_replies_renderer, ytcfg, video_id,
2990 parent=comment.get('id'), tracker=tracker)
2991 yield from itertools.islice(comment_entries_iter, min(
2992 max_replies_per_thread, max(0, max_replies - tracker['total_reply_comments'])))
2994 # Keeps track of counts across recursive calls
2999 current_page_thread=0,
3000 total_parent_comments=0,
3001 total_reply_comments=0)
3004 # YouTube comments have a max depth of 2
3005 max_depth = int_or_none(get_single_config_arg('max_comment_depth'))
3007 self._downloader.deprecated_feature('[youtube] max_comment_depth extractor argument is deprecated. '
3008 'Set max replies in the max-comments extractor argument instead')
3009 if max_depth == 1 and parent:
3012 max_comments, max_parents, max_replies, max_replies_per_thread, *_ = map(
3013 lambda p: int_or_none(p, default=sys.maxsize), self._configuration_arg('max_comments', ) + [''] * 4)
3015 continuation = self._extract_continuation(root_continuation_data)
3018 is_forced_continuation = False
3019 is_first_continuation = parent is None
3020 if is_first_continuation and not continuation:
3021 # Sometimes you can get comments by generating the continuation yourself,
3022 # even if YouTube initially reports them being disabled - e.g. stories comments.
3023 # Note: if the comment section is actually disabled, YouTube may return a response with
3024 # required check_get_keys missing. So we will disable that check initially in this case.
3025 continuation = self._build_api_continuation_query(self._generate_comment_continuation(video_id))
3026 is_forced_continuation = True
3028 for page_num in itertools.count(0):
3029 if not continuation:
3031 headers = self.generate_api_headers(ytcfg=ytcfg, visitor_data=self._extract_visitor_data(response))
3032 comment_prog_str = f"({tracker['running_total']}
/{tracker['est_total']}
)"
3034 if is_first_continuation:
3035 note_prefix = 'Downloading comment section API JSON'
3037 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
3038 tracker['current_page_thread'], comment_prog_str)
3040 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
3041 ' ' if parent else '', ' replies' if parent else '',
3042 page_num, comment_prog_str)
3044 response = self._extract_response(
3045 item_id=None, query=continuation,
3046 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
3047 check_get_keys='onResponseReceivedEndpoints' if not is_forced_continuation else None)
3048 is_forced_continuation = False
3049 continuation_contents = traverse_obj(
3050 response, 'onResponseReceivedEndpoints', expected_type=list, default=[])
3053 for continuation_section in continuation_contents:
3054 continuation_items = traverse_obj(
3055 continuation_section,
3056 (('reloadContinuationItemsCommand', 'appendContinuationItemsAction'), 'continuationItems'),
3057 get_all=False, expected_type=list) or []
3058 if is_first_continuation:
3059 continuation = extract_header(continuation_items)
3060 is_first_continuation = False
3065 for entry in extract_thread(continuation_items):
3069 continuation = self._extract_continuation({'contents': continuation_items})
3073 message = self._get_text(root_continuation_data, ('contents', ..., 'messageRenderer', 'text'), max_runs=1)
3074 if message and not parent and tracker['running_total'] == 0:
3075 self.report_warning(f'Youtube said: {message}', video_id=video_id, only_once=True)
3078 def _generate_comment_continuation(video_id):
3080 Generates initial comment section continuation token from given video id
3082 token = f'\x12\r\x12\x0b{video_id}\x18\x062\'"\x11"\x0b{video_id}0\x00x\x020\x00B\x10comments-section'
3083 return base64.b64encode(token.encode()).decode()
3085 def _get_comments(self, ytcfg, video_id, contents, webpage):
3086 """Entry for comment extraction"""
3087 def _real_comment_extract(contents):
3089 item for item in traverse_obj(contents, (..., 'itemSectionRenderer'), default={})
3090 if item.get('sectionIdentifier') == 'comment-item-section'), None)
3091 yield from self._comment_entries(renderer, ytcfg, video_id)
3093 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0])
3094 return itertools.islice(_real_comment_extract(contents), 0, max_comments)
3097 def _get_checkok_params():
3098 return {'contentCheckOk': True, 'racyCheckOk': True}
3101 def _generate_player_context(cls, sts=None):
3103 'html5Preference': 'HTML5_PREF_WANTS',
3106 context['signatureTimestamp'] = sts
3108 'playbackContext': {
3109 'contentPlaybackContext': context
3111 **cls._get_checkok_params()
3115 def _is_agegated(player_response):
3116 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')):
3119 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
3120 AGE_GATE_REASONS = (
3121 'confirm your age', 'age-restricted', 'inappropriate', # reason
3122 'age_verification_required', 'age_check_required', # status
3124 return any(expected in reason for expected in AGE_GATE_REASONS for reason in reasons)
3127 def _is_unplayable(player_response):
3128 return traverse_obj(player_response, ('playabilityStatus', 'status')) == 'UNPLAYABLE'
3130 _STORY_PLAYER_PARAMS = '8AEB'
3132 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, player_url, initial_pr, smuggled_data):
3134 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
3135 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
3136 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False) if player_url else None
3137 headers = self.generate_api_headers(
3138 ytcfg=player_ytcfg, account_syncid=syncid, session_index=session_index, default_client=client)
3141 'videoId': video_id,
3143 if smuggled_data.get('is_story') or _split_innertube_client(client)[0] == 'android':
3144 yt_query['params'] = self._STORY_PLAYER_PARAMS
3146 yt_query.update(self._generate_player_context(sts))
3147 return self._extract_response(
3148 item_id=video_id, ep='player', query=yt_query,
3149 ytcfg=player_ytcfg, headers=headers, fatal=True,
3150 default_client=client,
3151 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
3154 def _get_requested_clients(self, url, smuggled_data):
3155 requested_clients = []
3156 default = ['android', 'web']
3157 allowed_clients = sorted(
3158 (client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'),
3159 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
3160 for client in self._configuration_arg('player_client'):
3161 if client in allowed_clients:
3162 requested_clients.append(client)
3163 elif client == 'default':
3164 requested_clients.extend(default)
3165 elif client == 'all':
3166 requested_clients.extend(allowed_clients)
3168 self.report_warning(f'Skipping unsupported client {client}')
3169 if not requested_clients:
3170 requested_clients = default
3172 if smuggled_data.get('is_music_url') or self.is_music_url(url):
3173 requested_clients.extend(
3174 f'{client}_music' for client in requested_clients if f'{client}_music' in INNERTUBE_CLIENTS)
3176 return orderedSet(requested_clients)
3178 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, smuggled_data):
3181 initial_pr = self._search_json(
3182 self._YT_INITIAL_PLAYER_RESPONSE_RE, webpage, 'initial player response', video_id, fatal=False)
3184 all_clients = set(clients)
3185 clients = clients[::-1]
3188 def append_client(*client_names):
3189 """ Append the first client name that exists but not already used """
3190 for client_name in client_names:
3191 actual_client = _split_innertube_client(client_name)[0]
3192 if actual_client in INNERTUBE_CLIENTS:
3193 if actual_client not in all_clients:
3194 clients.append(client_name)
3195 all_clients.add(actual_client)
3198 # Android player_response does not have microFormats which are needed for
3199 # extraction of some data. So we return the initial_pr with formats
3200 # stripped out even if not requested by the user
3201 # See: https://github.com/yt-dlp/yt-dlp/issues/501
3203 pr = dict(initial_pr)
3204 pr['streamingData'] = None
3208 tried_iframe_fallback = False
3211 client, base_client, variant = _split_innertube_client(clients.pop())
3212 player_ytcfg = master_ytcfg if client == 'web' else {}
3213 if 'configs' not in self._configuration_arg('player_skip') and client != 'web':
3214 player_ytcfg = self._download_ytcfg(client, video_id) or player_ytcfg
3216 player_url = player_url or self._extract_player_url(master_ytcfg, player_ytcfg, webpage=webpage)
3217 require_js_player = self._get_default_ytcfg(client).get('REQUIRE_JS_PLAYER')
3218 if 'js' in self._configuration_arg('player_skip'):
3219 require_js_player = False
3222 if not player_url and not tried_iframe_fallback and require_js_player:
3223 player_url = self._download_player_url(video_id)
3224 tried_iframe_fallback = True
3227 pr = initial_pr if client == 'web' and initial_pr else self._extract_player_response(
3228 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, player_url if require_js_player else None, initial_pr, smuggled_data)
3229 except ExtractorError as e:
3231 self.report_warning(last_error)
3236 # YouTube may return a different video player response than expected.
3237 # See: https://github.com/TeamNewPipe/NewPipe/issues/8713
3238 pr_video_id = traverse_obj(pr, ('videoDetails', 'videoId'))
3239 if pr_video_id and pr_video_id != video_id:
3240 self.report_warning(
3241 f'Skipping player response from {client} client (got player response for video "{pr_video_id}
" instead of "{video_id}
")' + bug_reports_message())
3245 # creator clients can bypass AGE_VERIFICATION_REQUIRED if logged in
3246 if variant == 'embedded' and self._is_unplayable(pr) and self.is_authenticated:
3247 append_client(f'{base_client}_creator')
3248 elif self._is_agegated(pr):
3249 if variant == 'tv_embedded':
3250 append_client(f'{base_client}_embedded')
3252 append_client(f'tv_embedded.{base_client}', f'{base_client}_embedded')
3257 self.report_warning(last_error)
3258 return prs, player_url
3260 def _extract_formats_and_subtitles(self, streaming_data, video_id, player_url, is_live, duration):
3261 itags, stream_ids = {}, []
3262 itag_qualities, res_qualities = {}, {0: None}
3264 # Normally tiny is the smallest video-only formats. But
3265 # audio-only formats with unknown quality may get tagged as tiny
3267 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
3268 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
3270 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
3272 for fmt in streaming_formats:
3273 if fmt.get('targetDurationSec'):
3276 itag = str_or_none(fmt.get('itag'))
3277 audio_track = fmt.get('audioTrack') or {}
3278 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
3279 if stream_id in stream_ids:
3282 quality = fmt.get('quality')
3283 height = int_or_none(fmt.get('height'))
3284 if quality == 'tiny' or not quality:
3285 quality = fmt.get('audioQuality', '').lower() or quality
3286 # The 3gp format (17) in android client has a quality of "small
",
3287 # but is actually worse than other formats
3292 itag_qualities[itag] = quality
3294 res_qualities[height] = quality
3295 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
3296 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
3297 # number of fragment that would subsequently requested with (`&sq=N`)
3298 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
3301 fmt_url = fmt.get('url')
3303 sc = urllib.parse.parse_qs(fmt.get('signatureCipher'))
3304 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
3305 encrypted_sig = try_get(sc, lambda x: x['s'][0])
3306 if not all((sc, fmt_url, player_url, encrypted_sig)):
3309 fmt_url += '&%s=%s' % (
3310 traverse_obj(sc, ('sp', -1)) or 'signature',
3311 self._decrypt_signature(encrypted_sig, video_id, player_url)
3313 except ExtractorError as e:
3314 self.report_warning('Signature extraction failed: Some formats may be missing',
3315 video_id=video_id, only_once=True)
3316 self.write_debug(e, only_once=True)
3319 query = parse_qs(fmt_url)
3323 decrypt_nsig = self._cached(self._decrypt_nsig, 'nsig', query['n'][0])
3324 fmt_url = update_url_query(fmt_url, {
3325 'n': decrypt_nsig(query['n'][0], video_id, player_url)
3327 except ExtractorError as e:
3329 if isinstance(e, JSInterpreter.Exception):
3330 phantomjs_hint = (f' Install {self._downloader._format_err("PhantomJS", self._downloader.Styles.EMPHASIS)} '
3331 f'to workaround the issue. {PhantomJSwrapper.INSTALL_HINT}\n')
3332 self.report_warning(
3333 f'nsig extraction failed: You may experience throttling for some formats\n{phantomjs_hint}'
3334 f' n = {query["n"][0]} ; player = {player_url}', video_id=video_id, only_once=True)
3335 self.write_debug(e, only_once=True)
3339 itags[itag] = 'https'
3340 stream_ids.append(stream_id)
3342 tbr = float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
3343 language_preference = (
3344 10 if audio_track.get('audioIsDefault') and 10
3345 else -10 if 'descriptive' in (audio_track.get('displayName') or '').lower() and -10
3347 # Some formats may have much smaller duration than others (possibly damaged during encoding)
3348 # E.g. 2-nOtRESiUc Ref: https://github.com/yt-dlp/yt-dlp/issues/2823
3349 # Make sure to avoid false positives with small duration differences.
3350 # E.g. __2ABJjxzNo, ySuUZEjARPY
3351 is_damaged = try_get(fmt, lambda x: float(x['approxDurationMs']) / duration < 500)
3353 self.report_warning(
3354 f'{video_id}: Some formats are possibly damaged. They will be deprioritized', only_once=True)
3356 'asr': int_or_none(fmt.get('audioSampleRate')),
3357 'filesize': int_or_none(fmt.get('contentLength')),
3359 'format_note': join_nonempty(
3360 '%s%s' % (audio_track.get('displayName') or '',
3361 ' (default)' if language_preference > 0 else ''),
3362 fmt.get('qualityLabel') or quality.replace('audio_quality_', ''),
3363 try_get(fmt, lambda x: x['projectionType'].replace('RECTANGULAR', '').lower()),
3364 try_get(fmt, lambda x: x['spatialAudioType'].replace('SPATIAL_AUDIO_TYPE_', '').lower()),
3365 throttled and 'THROTTLED', is_damaged and 'DAMAGED', delim=', '),
3366 # Format 22 is likely to be damaged. See https://github.com/yt-dlp/yt-dlp/issues/3372
3367 'source_preference': -10 if throttled else -5 if itag == '22' else -1,
3368 'fps': int_or_none(fmt.get('fps')) or None,
3369 'audio_channels': fmt.get('audioChannels'),
3371 'quality': q(quality),
3372 'has_drm': bool(fmt.get('drmFamilies')),
3375 'width': int_or_none(fmt.get('width')),
3376 'language': join_nonempty(audio_track.get('id', '').split('.')[0],
3377 'desc' if language_preference < -1 else ''),
3378 'language_preference': language_preference,
3379 # Strictly de-prioritize damaged and 3gp formats
3380 'preference': -10 if is_damaged else -2 if itag == '17' else None,
3382 mime_mobj = re.match(
3383 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^
"]+)")?
', fmt.get('mimeType
') or '')
3385 dct['ext
'] = mimetype2ext(mime_mobj.group(1))
3386 dct.update(parse_codecs(mime_mobj.group(2)))
3387 no_audio = dct.get('acodec
') == 'none
'
3388 no_video = dct.get('vcodec
') == 'none
'
3393 if no_audio or no_video:
3394 dct['downloader_options
'] = {
3395 # Youtube throttles chunks >~10M
3396 'http_chunk_size
': 10485760,
3399 dct['container
'] = dct['ext
'] + '_dash
'
3402 live_from_start = is_live and self.get_param('live_from_start
')
3403 skip_manifests = self._configuration_arg('skip
')
3404 if not self.get_param('youtube_include_hls_manifest
', True):
3405 skip_manifests.append('hls
')
3406 if not self.get_param('youtube_include_dash_manifest
', True):
3407 skip_manifests.append('dash
')
3408 get_dash = 'dash
' not in skip_manifests and (
3409 not is_live or live_from_start or self._configuration_arg('include_live_dash
'))
3410 get_hls = not live_from_start and 'hls
' not in skip_manifests
3412 def process_manifest_format(f, proto, itag):
3414 if itags[itag] == proto or f'{itag}
-{proto}
' in itags:
3416 itag = f'{itag}
-{proto}
'
3418 f['format_id
'] = itag
3421 f['quality
'] = q(itag_qualities.get(try_get(f, lambda f: f['format_id
'].split('-')[0]), -1))
3422 if f['quality
'] == -1 and f.get('height
'):
3423 f['quality
'] = q(res_qualities[min(res_qualities, key=lambda x: abs(x - f['height
']))])
3427 for sd in streaming_data:
3428 hls_manifest_url = get_hls and sd.get('hlsManifestUrl
')
3429 if hls_manifest_url:
3430 fmts, subs = self._extract_m3u8_formats_and_subtitles(hls_manifest_url, video_id, 'mp4
', fatal=False, live=is_live)
3431 subtitles = self._merge_subtitles(subs, subtitles)
3433 if process_manifest_format(f, 'hls
', self._search_regex(
3434 r'/itag
/(\d
+)', f['url
'], 'itag
', default=None)):
3437 dash_manifest_url = get_dash and sd.get('dashManifestUrl
')
3438 if dash_manifest_url:
3439 formats, subs = self._extract_mpd_formats_and_subtitles(dash_manifest_url, video_id, fatal=False)
3440 subtitles = self._merge_subtitles(subs, subtitles) # Prioritize HLS subs over DASH
3442 if process_manifest_format(f, 'dash
', f['format_id
']):
3443 f['filesize
'] = int_or_none(self._search_regex(
3444 r'/clen
/(\d
+)', f.get('fragment_base_url
') or f['url
'], 'file size
', default=None))
3446 f['is_from_start
'] = True
3451 def _extract_storyboard(self, player_responses, duration):
3453 player_responses, ('storyboards
', 'playerStoryboardSpecRenderer
', 'spec
'), default='').split('|
')[::-1]
3454 base_url = url_or_none(urljoin('https
://i
.ytimg
.com
/', spec.pop() or None))
3458 for i, args in enumerate(spec):
3459 args = args.split('#')
3460 counts
= list(map(int_or_none
, args
[:5]))
3461 if len(args
) != 8 or not all(counts
):
3462 self
.report_warning(f
'Malformed storyboard {i}: {"#".join(args)}{bug_reports_message()}')
3464 width
, height
, frame_count
, cols
, rows
= counts
3467 url
= base_url
.replace('$L', str(L
- i
)).replace('$N', N
) + f
'&sigh={sigh}'
3468 fragment_count
= frame_count
/ (cols
* rows
)
3469 fragment_duration
= duration
/ fragment_count
3471 'format_id': f
'sb{i}',
3472 'format_note': 'storyboard',
3474 'protocol': 'mhtml',
3480 'fps': frame_count
/ duration
,
3484 'url': url
.replace('$M', str(j
)),
3485 'duration': min(fragment_duration
, duration
- (j
* fragment_duration
)),
3486 } for j
in range(math
.ceil(fragment_count
))],
3489 def _download_player_responses(self
, url
, smuggled_data
, video_id
, webpage_url
):
3491 if 'webpage' not in self
._configuration
_arg
('player_skip'):
3492 query
= {'bpctr': '9999999999', 'has_verified': '1'}
3493 if smuggled_data
.get('is_story'):
3494 query
['pp'] = self
._STORY
_PLAYER
_PARAMS
3495 webpage
= self
._download
_webpage
(
3496 webpage_url
, video_id
, fatal
=False, query
=query
)
3498 master_ytcfg
= self
.extract_ytcfg(video_id
, webpage
) or self
._get
_default
_ytcfg
()
3500 player_responses
, player_url
= self
._extract
_player
_responses
(
3501 self
._get
_requested
_clients
(url
, smuggled_data
),
3502 video_id
, webpage
, master_ytcfg
, smuggled_data
)
3504 return webpage
, master_ytcfg
, player_responses
, player_url
3506 def _list_formats(self
, video_id
, microformats
, video_details
, player_responses
, player_url
, duration
=None):
3507 live_broadcast_details
= traverse_obj(microformats
, (..., 'liveBroadcastDetails'))
3508 is_live
= get_first(video_details
, 'isLive')
3510 is_live
= get_first(live_broadcast_details
, 'isLiveNow')
3512 streaming_data
= traverse_obj(player_responses
, (..., 'streamingData'), default
=[])
3513 *formats
, subtitles
= self
._extract
_formats
_and
_subtitles
(streaming_data
, video_id
, player_url
, is_live
, duration
)
3515 return live_broadcast_details
, is_live
, streaming_data
, formats
, subtitles
3517 def _real_extract(self
, url
):
3518 url
, smuggled_data
= unsmuggle_url(url
, {})
3519 video_id
= self
._match
_id
(url
)
3521 base_url
= self
.http_scheme() + '//www.youtube.com/'
3522 webpage_url
= base_url
+ 'watch?v=' + video_id
3524 webpage
, master_ytcfg
, player_responses
, player_url
= self
._download
_player
_responses
(url
, smuggled_data
, video_id
, webpage_url
)
3526 playability_statuses
= traverse_obj(
3527 player_responses
, (..., 'playabilityStatus'), expected_type
=dict, default
=[])
3529 trailer_video_id
= get_first(
3530 playability_statuses
,
3531 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
3533 if trailer_video_id
:
3534 return self
.url_result(
3535 trailer_video_id
, self
.ie_key(), trailer_video_id
)
3537 search_meta
= ((lambda x
: self
._html
_search
_meta
(x
, webpage
, default
=None))
3538 if webpage
else (lambda x
: None))
3540 video_details
= traverse_obj(
3541 player_responses
, (..., 'videoDetails'), expected_type
=dict, default
=[])
3542 microformats
= traverse_obj(
3543 player_responses
, (..., 'microformat', 'playerMicroformatRenderer'),
3544 expected_type
=dict, default
=[])
3546 get_first(video_details
, 'title')
3547 or self
._get
_text
(microformats
, (..., 'title'))
3548 or search_meta(['og:title', 'twitter:title', 'title']))
3549 video_description
= get_first(video_details
, 'shortDescription')
3551 multifeed_metadata_list
= get_first(
3553 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
3555 if multifeed_metadata_list
and not smuggled_data
.get('force_singlefeed'):
3556 if self
.get_param('noplaylist'):
3557 self
.to_screen('Downloading just video %s because of --no-playlist' % video_id
)
3561 for feed
in multifeed_metadata_list
.split(','):
3562 # Unquote should take place before split on comma (,) since textual
3563 # fields may contain comma as well (see
3564 # https://github.com/ytdl-org/youtube-dl/issues/8536)
3565 feed_data
= urllib
.parse
.parse_qs(
3566 urllib
.parse
.unquote_plus(feed
))
3568 def feed_entry(name
):
3570 feed_data
, lambda x
: x
[name
][0], str)
3572 feed_id
= feed_entry('id')
3575 feed_title
= feed_entry('title')
3578 title
+= ' (%s)' % feed_title
3580 '_type': 'url_transparent',
3581 'ie_key': 'Youtube',
3583 '%swatch?v=%s' % (base_url
, feed_data
['id'][0]),
3584 {'force_singlefeed': True}
),
3587 feed_ids
.append(feed_id
)
3589 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
3590 % (', '.join(feed_ids
), video_id
))
3591 return self
.playlist_result(
3592 entries
, video_id
, video_title
, video_description
)
3594 duration
= int_or_none(
3595 get_first(video_details
, 'lengthSeconds')
3596 or get_first(microformats
, 'lengthSeconds')
3597 or parse_duration(search_meta('duration'))) or None
3599 live_broadcast_details
, is_live
, streaming_data
, formats
, automatic_captions
= \
3600 self
._list
_formats
(video_id
, microformats
, video_details
, player_responses
, player_url
)
3603 if not self
.get_param('allow_unplayable_formats') and traverse_obj(streaming_data
, (..., 'licenseInfos')):
3604 self
.report_drm(video_id
)
3606 playability_statuses
,
3607 ('errorScreen', 'playerErrorMessageRenderer'), expected_type
=dict) or {}
3608 reason
= self
._get
_text
(pemr
, 'reason') or get_first(playability_statuses
, 'reason')
3609 subreason
= clean_html(self
._get
_text
(pemr
, 'subreason') or '')
3611 if subreason
== 'The uploader has not made this video available in your country.':
3612 countries
= get_first(microformats
, 'availableCountries')
3614 regions_allowed
= search_meta('regionsAllowed')
3615 countries
= regions_allowed
.split(',') if regions_allowed
else None
3616 self
.raise_geo_restricted(subreason
, countries
, metadata_available
=True)
3617 reason
+= f
'. {subreason}'
3619 self
.raise_no_formats(reason
, expected
=True)
3621 keywords
= get_first(video_details
, 'keywords', expected_type
=list) or []
3622 if not keywords
and webpage
:
3624 unescapeHTML(m
.group('content'))
3625 for m
in re
.finditer(self
._meta
_regex
('og:video:tag'), webpage
)]
3626 for keyword
in keywords
:
3627 if keyword
.startswith('yt:stretch='):
3628 mobj
= re
.search(r
'(\d+)\s*:\s*(\d+)', keyword
)
3630 # NB: float is intentional for forcing float division
3631 w
, h
= (float(v
) for v
in mobj
.groups())
3635 if f
.get('vcodec') != 'none':
3636 f
['stretched_ratio'] = ratio
3638 thumbnails
= self
._extract
_thumbnails
((video_details
, microformats
), (..., ..., 'thumbnail'))
3639 thumbnail_url
= search_meta(['og:image', 'twitter:image'])
3642 'url': thumbnail_url
,
3644 original_thumbnails
= thumbnails
.copy()
3646 # The best resolution thumbnails sometimes does not appear in the webpage
3647 # See: https://github.com/yt-dlp/yt-dlp/issues/340
3648 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
3650 # While the *1,*2,*3 thumbnails are just below their corresponding "*default" variants
3651 # in resolution, these are not the custom thumbnail. So de-prioritize them
3652 'maxresdefault', 'hq720', 'sddefault', 'hqdefault', '0', 'mqdefault', 'default',
3653 'sd1', 'sd2', 'sd3', 'hq1', 'hq2', 'hq3', 'mq1', 'mq2', 'mq3', '1', '2', '3'
3655 n_thumbnail_names
= len(thumbnail_names
)
3657 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
3658 video_id
=video_id
, name
=name
, ext
=ext
,
3659 webp
='_webp' if ext
== 'webp' else '', live
='_live' if is_live
else ''),
3660 } for name
in thumbnail_names
for ext
in ('webp', 'jpg'))
3661 for thumb
in thumbnails
:
3662 i
= next((i
for i
, t
in enumerate(thumbnail_names
) if f
'/{video_id}/{t}' in thumb
['url']), n_thumbnail_names
)
3663 thumb
['preference'] = (0 if '.webp' in thumb
['url'] else -1) - (2 * i
)
3664 self
._remove
_duplicate
_formats
(thumbnails
)
3665 self
._downloader
._sort
_thumbnails
(original_thumbnails
)
3667 category
= get_first(microformats
, 'category') or search_meta('genre')
3668 channel_id
= str_or_none(
3669 get_first(video_details
, 'channelId')
3670 or get_first(microformats
, 'externalChannelId')
3671 or search_meta('channelId'))
3672 owner_profile_url
= get_first(microformats
, 'ownerProfileUrl')
3674 live_content
= get_first(video_details
, 'isLiveContent')
3675 is_upcoming
= get_first(video_details
, 'isUpcoming')
3677 if is_upcoming
or live_content
is False:
3679 if is_upcoming
is None and (live_content
or is_live
):
3681 live_start_time
= parse_iso8601(get_first(live_broadcast_details
, 'startTimestamp'))
3682 live_end_time
= parse_iso8601(get_first(live_broadcast_details
, 'endTimestamp'))
3683 if not duration
and live_end_time
and live_start_time
:
3684 duration
= live_end_time
- live_start_time
3686 if is_live
and self
.get_param('live_from_start'):
3687 self
._prepare
_live
_from
_start
_formats
(formats
, video_id
, live_start_time
, url
, webpage_url
, smuggled_data
)
3689 formats
.extend(self
._extract
_storyboard
(player_responses
, duration
))
3691 # source_preference is lower for throttled/potentially damaged formats
3692 self
._sort
_formats
(formats
, (
3693 'quality', 'res', 'fps', 'hdr:12', 'source', 'vcodec:vp9.2', 'channels', 'acodec', 'lang', 'proto'))
3697 'title': video_title
,
3699 'thumbnails': thumbnails
,
3700 # The best thumbnail that we are sure exists. Prevents unnecessary
3701 # URL checking if user don't care about getting the best possible thumbnail
3702 'thumbnail': traverse_obj(original_thumbnails
, (-1, 'url')),
3703 'description': video_description
,
3704 'uploader': get_first(video_details
, 'author'),
3705 'uploader_id': self
._search
_regex
(r
'/(?:channel|user)/([^/?&#]+)', owner_profile_url
, 'uploader id') if owner_profile_url
else None,
3706 'uploader_url': owner_profile_url
,
3707 'channel_id': channel_id
,
3708 'channel_url': format_field(channel_id
, None, 'https://www.youtube.com/channel/%s'),
3709 'duration': duration
,
3710 'view_count': int_or_none(
3711 get_first((video_details
, microformats
), (..., 'viewCount'))
3712 or search_meta('interactionCount')),
3713 'average_rating': float_or_none(get_first(video_details
, 'averageRating')),
3714 'age_limit': 18 if (
3715 get_first(microformats
, 'isFamilySafe') is False
3716 or search_meta('isFamilyFriendly') == 'false'
3717 or search_meta('og:restrictions:age') == '18+') else 0,
3718 'webpage_url': webpage_url
,
3719 'categories': [category
] if category
else None,
3721 'playable_in_embed': get_first(playability_statuses
, 'playableInEmbed'),
3723 'was_live': (False if is_live
or is_upcoming
or live_content
is False
3724 else None if is_live
is None or is_upcoming
is None
3726 'live_status': 'is_upcoming' if is_upcoming
else None, # rest will be set by YoutubeDL
3727 'release_timestamp': live_start_time
,
3730 if get_first(video_details
, 'isPostLiveDvr'):
3731 self
.write_debug('Video is in Post-Live Manifestless mode')
3732 info
['live_status'] = 'post_live'
3733 if (duration
or 0) > 4 * 3600:
3734 self
.report_warning(
3735 'The livestream has not finished processing. Only 4 hours of the video can be currently downloaded. '
3736 'This is a known issue and patches are welcome')
3739 pctr
= traverse_obj(player_responses
, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type
=dict)
3741 def get_lang_code(track
):
3742 return (remove_start(track
.get('vssId') or '', '.').replace('.', '-')
3743 or track
.get('languageCode'))
3745 # Converted into dicts to remove duplicates
3747 get_lang_code(sub
): sub
3748 for sub
in traverse_obj(pctr
, (..., 'captionTracks', ...), default
=[])}
3749 translation_languages
= {
3750 lang
.get('languageCode'): self
._get
_text
(lang
.get('languageName'), max_runs
=1)
3751 for lang
in traverse_obj(pctr
, (..., 'translationLanguages', ...), default
=[])}
3753 def process_language(container
, base_url
, lang_code
, sub_name
, query
):
3754 lang_subs
= container
.setdefault(lang_code
, [])
3755 for fmt
in self
._SUBTITLE
_FORMATS
:
3761 'url': urljoin('https://www.youtube.com', update_url_query(base_url
, query
)),
3765 # NB: Constructing the full subtitle dictionary is slow
3766 get_translated_subs
= 'translated_subs' not in self
._configuration
_arg
('skip') and (
3767 self
.get_param('writeautomaticsub', False) or self
.get_param('listsubtitles'))
3768 for lang_code
, caption_track
in captions
.items():
3769 base_url
= caption_track
.get('baseUrl')
3770 orig_lang
= parse_qs(base_url
).get('lang', [None])[-1]
3773 lang_name
= self
._get
_text
(caption_track
, 'name', max_runs
=1)
3774 if caption_track
.get('kind') != 'asr':
3778 subtitles
, base_url
, lang_code
, lang_name
, {})
3779 if not caption_track
.get('isTranslatable'):
3781 for trans_code
, trans_name
in translation_languages
.items():
3784 orig_trans_code
= trans_code
3785 if caption_track
.get('kind') != 'asr':
3786 if not get_translated_subs
:
3788 trans_code
+= f
'-{lang_code}'
3789 trans_name
+= format_field(lang_name
, None, ' from %s')
3790 # Add an "-orig" label to the original language so that it can be distinguished.
3791 # The subs are returned without "-orig" as well for compatibility
3792 if lang_code
== f
'a-{orig_trans_code}':
3794 automatic_captions
, base_url
, f
'{trans_code}-orig', f
'{trans_name} (Original)', {})
3795 # Setting tlang=lang returns damaged subtitles.
3796 process_language(automatic_captions
, base_url
, trans_code
, trans_name
,
3797 {} if orig_lang == orig_trans_code else {'tlang': trans_code}
)
3799 info
['automatic_captions'] = automatic_captions
3800 info
['subtitles'] = subtitles
3802 parsed_url
= urllib
.parse
.urlparse(url
)
3803 for component
in [parsed_url
.fragment
, parsed_url
.query
]:
3804 query
= urllib
.parse
.parse_qs(component
)
3805 for k
, v
in query
.items():
3806 for d_k
, s_ks
in [('start', ('start', 't')), ('end', ('end',))]:
3808 if d_k
not in info
and k
in s_ks
:
3809 info
[d_k
] = parse_duration(query
[k
][0])
3811 # Youtube Music Auto-generated description
3812 if video_description
:
3815 (?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+
3817 (?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?
3818 (?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?
3819 (.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?
3820 .+\nAuto-generated\ by\ YouTube\.\s*$
3821 ''', video_description
)
3823 release_year
= mobj
.group('release_year')
3824 release_date
= mobj
.group('release_date')
3826 release_date
= release_date
.replace('-', '')
3827 if not release_year
:
3828 release_year
= release_date
[:4]
3830 'album': mobj
.group('album'.strip()),
3831 'artist': mobj
.group('clean_artist') or ', '.join(a
.strip() for a
in mobj
.group('artist').split('·')),
3832 'track': mobj
.group('track').strip(),
3833 'release_date': release_date
,
3834 'release_year': int_or_none(release_year
),
3839 initial_data
= self
.extract_yt_initial_data(video_id
, webpage
, fatal
=False)
3840 if not initial_data
:
3841 query
= {'videoId': video_id}
3842 query
.update(self
._get
_checkok
_params
())
3843 initial_data
= self
._extract
_response
(
3844 item_id
=video_id
, ep
='next', fatal
=False,
3845 ytcfg
=master_ytcfg
, query
=query
,
3846 headers
=self
.generate_api_headers(ytcfg
=master_ytcfg
),
3847 note
='Downloading initial data API JSON')
3849 info
['comment_count'] = traverse_obj(initial_data
, (
3850 'contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents', ..., 'itemSectionRenderer',
3851 'contents', ..., 'commentsEntryPointHeaderRenderer', 'commentCount', 'simpleText'
3853 'engagementPanels', lambda _
, v
: v
['engagementPanelSectionListRenderer']['panelIdentifier'] == 'comment-item-section',
3854 'engagementPanelSectionListRenderer', 'header', 'engagementPanelTitleHeaderRenderer', 'contextualInfo', 'runs', ..., 'text'
3855 ), expected_type
=int_or_none
, get_all
=False)
3857 try: # This will error if there is no livechat
3858 initial_data
['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
3859 except (KeyError, IndexError, TypeError):
3862 info
.setdefault('subtitles', {})['live_chat'] = [{
3863 # url is needed to set cookies
3864 'url': f
'https://www.youtube.com/watch?v={video_id}&bpctr=9999999999&has_verified=1',
3865 'video_id': video_id
,
3867 'protocol': 'youtube_live_chat' if is_live
or is_upcoming
else 'youtube_live_chat_replay',
3871 info
['chapters'] = (
3872 self
._extract
_chapters
_from
_json
(initial_data
, duration
)
3873 or self
._extract
_chapters
_from
_engagement
_panel
(initial_data
, duration
)
3874 or self
._extract
_chapters
_from
_description
(video_description
, duration
)
3877 contents
= traverse_obj(
3878 initial_data
, ('contents', 'twoColumnWatchNextResults', 'results', 'results', 'contents'),
3879 expected_type
=list, default
=[])
3881 vpir
= get_first(contents
, 'videoPrimaryInfoRenderer')
3883 stl
= vpir
.get('superTitleLink')
3885 stl
= self
._get
_text
(stl
)
3888 lambda x
: x
['superTitleIcon']['iconType']) == 'LOCATION_PIN':
3889 info
['location'] = stl
3891 mobj
= re
.search(r
'(.+?)\s*S(\d+)\s*•?\s*E(\d+)', stl
)
3894 'series': mobj
.group(1),
3895 'season_number': int(mobj
.group(2)),
3896 'episode_number': int(mobj
.group(3)),
3898 for tlb
in (try_get(
3900 lambda x
: x
['videoActions']['menuRenderer']['topLevelButtons'],
3902 tbr
= tlb
.get('toggleButtonRenderer') or {}
3903 for getter
, regex
in [(
3904 lambda x
: x
['defaultText']['accessibility']['accessibilityData'],
3905 r
'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3906 lambda x
: x
['accessibility'],
3907 lambda x
: x
['accessibilityData']['accessibilityData'],
3908 ], r
'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3909 label
= (try_get(tbr
, getter
, dict) or {}).get('label')
3911 mobj
= re
.match(regex
, label
)
3913 info
[mobj
.group('type') + '_count'] = str_to_int(mobj
.group('count'))
3915 sbr_tooltip
= try_get(
3916 vpir
, lambda x
: x
['sentimentBar']['sentimentBarRenderer']['tooltip'])
3918 like_count
, dislike_count
= sbr_tooltip
.split(' / ')
3920 'like_count': str_to_int(like_count
),
3921 'dislike_count': str_to_int(dislike_count
),
3923 vsir
= get_first(contents
, 'videoSecondaryInfoRenderer')
3925 vor
= traverse_obj(vsir
, ('owner', 'videoOwnerRenderer'))
3927 'channel': self
._get
_text
(vor
, 'title'),
3928 'channel_follower_count': self
._get
_count
(vor
, 'subscriberCountText')})
3932 lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3934 multiple_songs
= False
3936 if try_get(row
, lambda x
: x
['metadataRowRenderer']['hasDividerLine']) is True:
3937 multiple_songs
= True
3940 mrr
= row
.get('metadataRowRenderer') or {}
3941 mrr_title
= mrr
.get('title')
3944 mrr_title
= self
._get
_text
(mrr
, 'title')
3945 mrr_contents_text
= self
._get
_text
(mrr
, ('contents', 0))
3946 if mrr_title
== 'License':
3947 info
['license'] = mrr_contents_text
3948 elif not multiple_songs
:
3949 if mrr_title
== 'Album':
3950 info
['album'] = mrr_contents_text
3951 elif mrr_title
== 'Artist':
3952 info
['artist'] = mrr_contents_text
3953 elif mrr_title
== 'Song':
3954 info
['track'] = mrr_contents_text
3957 'channel': 'uploader',
3958 'channel_id': 'uploader_id',
3959 'channel_url': 'uploader_url',
3962 # The upload date for scheduled, live and past live streams / premieres in microformats
3963 # may be different from the stream date. Although not in UTC, we will prefer it in this case.
3964 # See: https://github.com/yt-dlp/yt-dlp/pull/2223#issuecomment-1008485139
3966 unified_strdate(get_first(microformats
, 'uploadDate'))
3967 or unified_strdate(search_meta('uploadDate')))
3968 if not upload_date
or (
3969 not info
.get('is_live')
3970 and not info
.get('was_live')
3971 and info
.get('live_status') != 'is_upcoming'
3972 and 'no-youtube-prefer-utc-upload-date' not in self
.get_param('compat_opts', [])
3974 upload_date
= strftime_or_none(self
._extract
_time
_text
(vpir
, 'dateText')[0], '%Y%m%d') or upload_date
3975 info
['upload_date'] = upload_date
3977 for to
, frm
in fallbacks
.items():
3978 if not info
.get(to
):
3979 info
[to
] = info
.get(frm
)
3981 for s_k
, d_k
in [('artist', 'creator'), ('track', 'alt_title')]:
3986 is_private
= get_first(video_details
, 'isPrivate', expected_type
=bool)
3987 is_unlisted
= get_first(microformats
, 'isUnlisted', expected_type
=bool)
3988 is_membersonly
= None
3990 if initial_data
and is_private
is not None:
3991 is_membersonly
= False
3993 contents
= try_get(initial_data
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3994 badge_labels
= set()
3995 for content
in contents
:
3996 if not isinstance(content
, dict):
3998 badge_labels
.update(self
._extract
_badges
(content
.get('videoPrimaryInfoRenderer')))
3999 for badge_label
in badge_labels
:
4000 if badge_label
.lower() == 'members only':
4001 is_membersonly
= True
4002 elif badge_label
.lower() == 'premium':
4004 elif badge_label
.lower() == 'unlisted':
4007 info
['availability'] = self
._availability
(
4008 is_private
=is_private
,
4009 needs_premium
=is_premium
,
4010 needs_subscription
=is_membersonly
,
4011 needs_auth
=info
['age_limit'] >= 18,
4012 is_unlisted
=None if is_private
is None else is_unlisted
)
4014 info
['__post_extractor'] = self
.extract_comments(master_ytcfg
, video_id
, contents
, webpage
)
4016 self
.mark_watched(video_id
, player_responses
)
4021 class YoutubeTabBaseInfoExtractor(YoutubeBaseInfoExtractor
):
4024 def passthrough_smuggled_data(func
):
4025 def _smuggle(entries
, smuggled_data
):
4026 for entry
in entries
:
4027 # TODO: Convert URL to music.youtube instead.
4028 # Do we need to passthrough any other smuggled_data?
4029 entry
['url'] = smuggle_url(entry
['url'], smuggled_data
)
4032 @functools.wraps(func
)
4033 def wrapper(self
, url
):
4034 url
, smuggled_data
= unsmuggle_url(url
, {})
4035 if self
.is_music_url(url
):
4036 smuggled_data
['is_music_url'] = True
4037 info_dict
= func(self
, url
, smuggled_data
)
4038 if smuggled_data
and info_dict
.get('entries'):
4039 info_dict
['entries'] = _smuggle(info_dict
['entries'], smuggled_data
)
4043 def _extract_channel_id(self
, webpage
):
4044 channel_id
= self
._html
_search
_meta
(
4045 'channelId', webpage
, 'channel id', default
=None)
4048 channel_url
= self
._html
_search
_meta
(
4049 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
4050 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
4051 'twitter:app:url:googleplay'), webpage
, 'channel url')
4052 return self
._search
_regex
(
4053 r
'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
4054 channel_url
, 'channel id')
4057 def _extract_basic_item_renderer(item
):
4058 # Modified from _extract_grid_item_renderer
4059 known_basic_renderers
= (
4060 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer', 'reelItemRenderer'
4062 for key
, renderer
in item
.items():
4063 if not isinstance(renderer
, dict):
4065 elif key
in known_basic_renderers
:
4067 elif key
.startswith('grid') and key
.endswith('Renderer'):
4070 def _grid_entries(self
, grid_renderer
):
4071 for item
in grid_renderer
['items']:
4072 if not isinstance(item
, dict):
4074 renderer
= self
._extract
_basic
_item
_renderer
(item
)
4075 if not isinstance(renderer
, dict):
4077 title
= self
._get
_text
(renderer
, 'title')
4080 playlist_id
= renderer
.get('playlistId')
4082 yield self
.url_result(
4083 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4084 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4088 video_id
= renderer
.get('videoId')
4090 yield self
._extract
_video
(renderer
)
4093 channel_id
= renderer
.get('channelId')
4095 yield self
.url_result(
4096 'https://www.youtube.com/channel/%s' % channel_id
,
4097 ie
=YoutubeTabIE
.ie_key(), video_title
=title
)
4099 # generic endpoint URL support
4100 ep_url
= urljoin('https://www.youtube.com/', try_get(
4101 renderer
, lambda x
: x
['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
4104 for ie
in (YoutubeTabIE
, YoutubePlaylistIE
, YoutubeIE
):
4105 if ie
.suitable(ep_url
):
4106 yield self
.url_result(
4107 ep_url
, ie
=ie
.ie_key(), video_id
=ie
._match
_id
(ep_url
), video_title
=title
)
4110 def _music_reponsive_list_entry(self
, renderer
):
4111 video_id
= traverse_obj(renderer
, ('playlistItemData', 'videoId'))
4113 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}',
4114 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
4115 playlist_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'playlistId'))
4117 video_id
= traverse_obj(renderer
, ('navigationEndpoint', 'watchEndpoint', 'videoId'))
4119 return self
.url_result(f
'https://music.youtube.com/watch?v={video_id}&list={playlist_id}',
4120 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4121 return self
.url_result(f
'https://music.youtube.com/playlist?list={playlist_id}',
4122 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4123 browse_id
= traverse_obj(renderer
, ('navigationEndpoint', 'browseEndpoint', 'browseId'))
4125 return self
.url_result(f
'https://music.youtube.com/browse/{browse_id}',
4126 ie
=YoutubeTabIE
.ie_key(), video_id
=browse_id
)
4128 def _shelf_entries_from_content(self
, shelf_renderer
):
4129 content
= shelf_renderer
.get('content')
4130 if not isinstance(content
, dict):
4132 renderer
= content
.get('gridRenderer') or content
.get('expandedShelfContentsRenderer')
4134 # TODO: add support for nested playlists so each shelf is processed
4135 # as separate playlist
4136 # TODO: this includes only first N items
4137 yield from self
._grid
_entries
(renderer
)
4138 renderer
= content
.get('horizontalListRenderer')
4143 def _shelf_entries(self
, shelf_renderer
, skip_channels
=False):
4145 shelf_renderer
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4147 shelf_url
= urljoin('https://www.youtube.com', ep
)
4149 # Skipping links to another channels, note that checking for
4150 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
4152 if skip_channels
and '/channels?' in shelf_url
:
4154 title
= self
._get
_text
(shelf_renderer
, 'title')
4155 yield self
.url_result(shelf_url
, video_title
=title
)
4156 # Shelf may not contain shelf URL, fallback to extraction from content
4157 yield from self
._shelf
_entries
_from
_content
(shelf_renderer
)
4159 def _playlist_entries(self
, video_list_renderer
):
4160 for content
in video_list_renderer
['contents']:
4161 if not isinstance(content
, dict):
4163 renderer
= content
.get('playlistVideoRenderer') or content
.get('playlistPanelVideoRenderer')
4164 if not isinstance(renderer
, dict):
4166 video_id
= renderer
.get('videoId')
4169 yield self
._extract
_video
(renderer
)
4171 def _rich_entries(self
, rich_grid_renderer
):
4173 rich_grid_renderer
, lambda x
: x
['content']['videoRenderer'], dict) or {}
4174 video_id
= renderer
.get('videoId')
4177 yield self
._extract
_video
(renderer
)
4179 def _video_entry(self
, video_renderer
):
4180 video_id
= video_renderer
.get('videoId')
4182 return self
._extract
_video
(video_renderer
)
4184 def _hashtag_tile_entry(self
, hashtag_tile_renderer
):
4185 url
= urljoin('https://youtube.com', traverse_obj(
4186 hashtag_tile_renderer
, ('onTapCommand', 'commandMetadata', 'webCommandMetadata', 'url')))
4188 return self
.url_result(
4189 url
, ie
=YoutubeTabIE
.ie_key(), title
=self
._get
_text
(hashtag_tile_renderer
, 'hashtag'))
4191 def _post_thread_entries(self
, post_thread_renderer
):
4192 post_renderer
= try_get(
4193 post_thread_renderer
, lambda x
: x
['post']['backstagePostRenderer'], dict)
4194 if not post_renderer
:
4197 video_renderer
= try_get(
4198 post_renderer
, lambda x
: x
['backstageAttachment']['videoRenderer'], dict) or {}
4199 video_id
= video_renderer
.get('videoId')
4201 entry
= self
._extract
_video
(video_renderer
)
4204 # playlist attachment
4205 playlist_id
= try_get(
4206 post_renderer
, lambda x
: x
['backstageAttachment']['playlistRenderer']['playlistId'], str)
4208 yield self
.url_result(
4209 'https://www.youtube.com/playlist?list=%s' % playlist_id
,
4210 ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
4211 # inline video links
4212 runs
= try_get(post_renderer
, lambda x
: x
['contentText']['runs'], list) or []
4214 if not isinstance(run
, dict):
4217 run
, lambda x
: x
['navigationEndpoint']['urlEndpoint']['url'], str)
4220 if not YoutubeIE
.suitable(ep_url
):
4222 ep_video_id
= YoutubeIE
._match
_id
(ep_url
)
4223 if video_id
== ep_video_id
:
4225 yield self
.url_result(ep_url
, ie
=YoutubeIE
.ie_key(), video_id
=ep_video_id
)
4227 def _post_thread_continuation_entries(self
, post_thread_continuation
):
4228 contents
= post_thread_continuation
.get('contents')
4229 if not isinstance(contents
, list):
4231 for content
in contents
:
4232 renderer
= content
.get('backstagePostThreadRenderer')
4233 if isinstance(renderer
, dict):
4234 yield from self
._post
_thread
_entries
(renderer
)
4236 renderer
= content
.get('videoRenderer')
4237 if isinstance(renderer
, dict):
4238 yield self
._video
_entry
(renderer
)
4241 def _rich_grid_entries(self, contents):
4242 for content in contents:
4243 video_renderer = try_get(content, lambda x: x['richItemRenderer']['content']['videoRenderer'], dict)
4245 entry = self._video_entry(video_renderer)
4250 def _extract_entries(self
, parent_renderer
, continuation_list
):
4251 # continuation_list is modified in-place with continuation_list = [continuation_token]
4252 continuation_list
[:] = [None]
4253 contents
= try_get(parent_renderer
, lambda x
: x
['contents'], list) or []
4254 for content
in contents
:
4255 if not isinstance(content
, dict):
4257 is_renderer
= traverse_obj(
4258 content
, 'itemSectionRenderer', 'musicShelfRenderer', 'musicShelfContinuation',
4261 renderer
= content
.get('richItemRenderer')
4263 for entry
in self
._rich
_entries
(renderer
):
4265 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4267 isr_contents
= try_get(is_renderer
, lambda x
: x
['contents'], list) or []
4268 for isr_content
in isr_contents
:
4269 if not isinstance(isr_content
, dict):
4273 'playlistVideoListRenderer': self
._playlist
_entries
,
4274 'gridRenderer': self
._grid
_entries
,
4275 'reelShelfRenderer': self
._grid
_entries
,
4276 'shelfRenderer': self
._shelf
_entries
,
4277 'musicResponsiveListItemRenderer': lambda x
: [self
._music
_reponsive
_list
_entry
(x
)],
4278 'backstagePostThreadRenderer': self
._post
_thread
_entries
,
4279 'videoRenderer': lambda x
: [self
._video
_entry
(x
)],
4280 'playlistRenderer': lambda x
: self
._grid
_entries
({'items': [{'playlistRenderer': x}
]}),
4281 'channelRenderer': lambda x
: self
._grid
_entries
({'items': [{'channelRenderer': x}
]}),
4282 'hashtagTileRenderer': lambda x
: [self
._hashtag
_tile
_entry
(x
)]
4284 for key
, renderer
in isr_content
.items():
4285 if key
not in known_renderers
:
4287 for entry
in known_renderers
[key
](renderer
):
4290 continuation_list
[0] = self
._extract
_continuation
(renderer
)
4293 if not continuation_list
[0]:
4294 continuation_list
[0] = self
._extract
_continuation
(is_renderer
)
4296 if not continuation_list
[0]:
4297 continuation_list
[0] = self
._extract
_continuation
(parent_renderer
)
4299 def _entries(self
, tab
, item_id
, ytcfg
, account_syncid
, visitor_data
):
4300 continuation_list
= [None]
4301 extract_entries
= lambda x
: self
._extract
_entries
(x
, continuation_list
)
4302 tab_content
= try_get(tab
, lambda x
: x
['content'], dict)
4306 try_get(tab_content
, lambda x
: x
['sectionListRenderer'], dict)
4307 or try_get(tab_content
, lambda x
: x
['richGridRenderer'], dict) or {})
4308 yield from extract_entries(parent_renderer
)
4309 continuation
= continuation_list
[0]
4311 for page_num
in itertools
.count(1):
4312 if not continuation
:
4314 headers
= self
.generate_api_headers(
4315 ytcfg
=ytcfg
, account_syncid
=account_syncid
, visitor_data
=visitor_data
)
4316 response
= self
._extract
_response
(
4317 item_id
=f
'{item_id} page {page_num}',
4318 query
=continuation
, headers
=headers
, ytcfg
=ytcfg
,
4319 check_get_keys
=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4323 # Extracting updated visitor data is required to prevent an infinite extraction loop in some cases
4324 # See: https://github.com/ytdl-org/youtube-dl/issues/28702
4325 visitor_data
= self
._extract
_visitor
_data
(response
) or visitor_data
4327 known_continuation_renderers
= {
4328 'playlistVideoListContinuation': self
._playlist
_entries
,
4329 'gridContinuation': self
._grid
_entries
,
4330 'itemSectionContinuation': self
._post
_thread
_continuation
_entries
,
4331 'sectionListContinuation': extract_entries
, # for feeds
4333 continuation_contents
= try_get(
4334 response
, lambda x
: x
['continuationContents'], dict) or {}
4335 continuation_renderer
= None
4336 for key
, value
in continuation_contents
.items():
4337 if key
not in known_continuation_renderers
:
4339 continuation_renderer
= value
4340 continuation_list
= [None]
4341 yield from known_continuation_renderers
[key
](continuation_renderer
)
4342 continuation
= continuation_list
[0] or self
._extract
_continuation
(continuation_renderer
)
4344 if continuation_renderer
:
4348 'videoRenderer': (self
._grid
_entries
, 'items'), # for membership tab
4349 'gridPlaylistRenderer': (self
._grid
_entries
, 'items'),
4350 'gridVideoRenderer': (self
._grid
_entries
, 'items'),
4351 'gridChannelRenderer': (self
._grid
_entries
, 'items'),
4352 'playlistVideoRenderer': (self
._playlist
_entries
, 'contents'),
4353 'itemSectionRenderer': (extract_entries
, 'contents'), # for feeds
4354 'richItemRenderer': (extract_entries
, 'contents'), # for hashtag
4355 'backstagePostThreadRenderer': (self
._post
_thread
_continuation
_entries
, 'contents')
4357 on_response_received
= dict_get(response
, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
4358 continuation_items
= try_get(
4359 on_response_received
, lambda x
: x
[0]['appendContinuationItemsAction']['continuationItems'], list)
4360 continuation_item
= try_get(continuation_items
, lambda x
: x
[0], dict) or {}
4361 video_items_renderer
= None
4362 for key
, value
in continuation_item
.items():
4363 if key
not in known_renderers
:
4365 video_items_renderer
= {known_renderers[key][1]: continuation_items}
4366 continuation_list
= [None]
4367 yield from known_renderers
[key
][0](video_items_renderer
)
4368 continuation
= continuation_list
[0] or self
._extract
_continuation
(video_items_renderer
)
4370 if video_items_renderer
:
4375 def _extract_selected_tab(tabs
, fatal
=True):
4377 renderer
= dict_get(tab
, ('tabRenderer', 'expandableTabRenderer')) or {}
4378 if renderer
.get('selected') is True:
4382 raise ExtractorError('Unable to find selected tab')
4384 def _extract_uploader(self
, data
):
4386 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarSecondaryInfoRenderer') or {}
4388 renderer
, lambda x
: x
['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
4390 owner_text
= owner
.get('text')
4391 uploader
['uploader'] = self
._search
_regex
(
4392 r
'^by (.+) and \d+ others?$', owner_text
, 'uploader', default
=owner_text
)
4393 uploader
['uploader_id'] = try_get(
4394 owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['browseId'], str)
4395 uploader
['uploader_url'] = urljoin(
4396 'https://www.youtube.com/',
4397 try_get(owner
, lambda x
: x
['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], str))
4398 return {k: v for k, v in uploader.items() if v is not None}
4400 def _extract_from_tabs(self
, item_id
, ytcfg
, data
, tabs
):
4401 playlist_id
= title
= description
= channel_url
= channel_name
= channel_id
= None
4404 selected_tab
= self
._extract
_selected
_tab
(tabs
)
4405 primary_sidebar_renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4407 data
, lambda x
: x
['metadata']['channelMetadataRenderer'], dict)
4409 channel_name
= renderer
.get('title')
4410 channel_url
= renderer
.get('channelUrl')
4411 channel_id
= renderer
.get('externalId')
4414 data
, lambda x
: x
['metadata']['playlistMetadataRenderer'], dict)
4417 title
= renderer
.get('title')
4418 description
= renderer
.get('description', '')
4419 playlist_id
= channel_id
4420 tags
= renderer
.get('keywords', '').split()
4422 # We can get the uncropped banner/avatar by replacing the crop params with '=s0'
4423 # See: https://github.com/yt-dlp/yt-dlp/issues/2237#issuecomment-1013694714
4424 def _get_uncropped(url
):
4425 return url_or_none((url
or '').split('=')[0] + '=s0')
4427 avatar_thumbnails
= self
._extract
_thumbnails
(renderer
, 'avatar')
4428 if avatar_thumbnails
:
4429 uncropped_avatar
= _get_uncropped(avatar_thumbnails
[0]['url'])
4430 if uncropped_avatar
:
4431 avatar_thumbnails
.append({
4432 'url': uncropped_avatar
,
4433 'id': 'avatar_uncropped',
4437 channel_banners
= self
._extract
_thumbnails
(
4438 data
, ('header', ..., ['banner', 'mobileBanner', 'tvBanner']))
4439 for banner
in channel_banners
:
4440 banner
['preference'] = -10
4443 uncropped_banner
= _get_uncropped(channel_banners
[0]['url'])
4444 if uncropped_banner
:
4445 channel_banners
.append({
4446 'url': uncropped_banner
,
4447 'id': 'banner_uncropped',
4451 primary_thumbnails
= self
._extract
_thumbnails
(
4452 primary_sidebar_renderer
, ('thumbnailRenderer', ('playlistVideoThumbnailRenderer', 'playlistCustomThumbnailRenderer'), 'thumbnail'))
4454 if playlist_id
is None:
4455 playlist_id
= item_id
4457 playlist_stats
= traverse_obj(primary_sidebar_renderer
, 'stats')
4458 last_updated_unix
, _
= self
._extract
_time
_text
(playlist_stats
, 2)
4460 title
= self
._get
_text
(data
, ('header', 'hashtagHeaderRenderer', 'hashtag')) or playlist_id
4461 title
+= format_field(selected_tab
, 'title', ' - %s')
4462 title
+= format_field(selected_tab
, 'expandedText', ' - %s')
4465 'playlist_id': playlist_id
,
4466 'playlist_title': title
,
4467 'playlist_description': description
,
4468 'uploader': channel_name
,
4469 'uploader_id': channel_id
,
4470 'uploader_url': channel_url
,
4471 'thumbnails': primary_thumbnails
+ avatar_thumbnails
+ channel_banners
,
4473 'view_count': self
._get
_count
(playlist_stats
, 1),
4474 'availability': self
._extract
_availability
(data
),
4475 'modified_date': strftime_or_none(last_updated_unix
, '%Y%m%d'),
4476 'playlist_count': self
._get
_count
(playlist_stats
, 0),
4477 'channel_follower_count': self
._get
_count
(data
, ('header', ..., 'subscriberCountText')),
4480 metadata
.update(self
._extract
_uploader
(data
))
4482 'channel': metadata
['uploader'],
4483 'channel_id': metadata
['uploader_id'],
4484 'channel_url': metadata
['uploader_url']})
4485 return self
.playlist_result(
4487 selected_tab
, playlist_id
, ytcfg
,
4488 self
._extract
_account
_syncid
(ytcfg
, data
),
4489 self
._extract
_visitor
_data
(data
, ytcfg
)),
4492 def _extract_inline_playlist(self
, playlist
, playlist_id
, data
, ytcfg
):
4493 first_id
= last_id
= response
= None
4494 for page_num
in itertools
.count(1):
4495 videos
= list(self
._playlist
_entries
(playlist
))
4498 start
= next((i
for i
, v
in enumerate(videos
) if v
['id'] == last_id
), -1) + 1
4499 if start
>= len(videos
):
4501 yield from videos
[start
:]
4502 first_id
= first_id
or videos
[0]['id']
4503 last_id
= videos
[-1]['id']
4504 watch_endpoint
= try_get(
4505 playlist
, lambda x
: x
['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4506 headers
= self
.generate_api_headers(
4507 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4508 visitor_data
=self
._extract
_visitor
_data
(response
, data
, ytcfg
))
4510 'playlistId': playlist_id
,
4511 'videoId': watch_endpoint
.get('videoId') or last_id
,
4512 'index': watch_endpoint
.get('index') or len(videos
),
4513 'params': watch_endpoint
.get('params') or 'OAE%3D'
4515 response
= self
._extract
_response
(
4516 item_id
='%s page %d' % (playlist_id
, page_num
),
4517 query
=query
, ep
='next', headers
=headers
, ytcfg
=ytcfg
,
4518 check_get_keys
='contents'
4521 response
, lambda x
: x
['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4523 def _extract_from_playlist(self
, item_id
, url
, data
, playlist
, ytcfg
):
4524 title
= playlist
.get('title') or try_get(
4525 data
, lambda x
: x
['titleText']['simpleText'], str)
4526 playlist_id
= playlist
.get('playlistId') or item_id
4528 # Delegating everything except mix playlists to regular tab-based playlist URL
4529 playlist_url
= urljoin(url
, try_get(
4530 playlist
, lambda x
: x
['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4533 # Some playlists are unviewable but YouTube still provides a link to the (broken) playlist page [1]
4534 # [1] MLCT, RLTDwFCb4jeqaKWnciAYM-ZVHg
4535 is_known_unviewable
= re
.fullmatch(r
'MLCT|RLTD[\w-]{22}', playlist_id
)
4537 if playlist_url
and playlist_url
!= url
and not is_known_unviewable
:
4538 return self
.url_result(
4539 playlist_url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
,
4542 return self
.playlist_result(
4543 self
._extract
_inline
_playlist
(playlist
, playlist_id
, data
, ytcfg
),
4544 playlist_id
=playlist_id
, playlist_title
=title
)
4546 def _extract_availability(self
, data
):
4548 Gets the availability of a given playlist/tab.
4549 Note: Unless YouTube tells us explicitly, we do not assume it is public
4550 @param data: response
4552 is_private
= is_unlisted
= None
4553 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer') or {}
4554 badge_labels
= self
._extract
_badges
(renderer
)
4556 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4557 privacy_dropdown_entries
= try_get(
4558 renderer
, lambda x
: x
['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4559 for renderer_dict
in privacy_dropdown_entries
:
4560 is_selected
= try_get(
4561 renderer_dict
, lambda x
: x
['privacyDropdownItemRenderer']['isSelected'], bool) or False
4564 label
= self
._get
_text
(renderer_dict
, ('privacyDropdownItemRenderer', 'label'))
4566 badge_labels
.add(label
.lower())
4569 for badge_label
in badge_labels
:
4570 if badge_label
== 'unlisted':
4572 elif badge_label
== 'private':
4574 elif badge_label
== 'public':
4575 is_unlisted
= is_private
= False
4576 return self
._availability
(is_private
, False, False, False, is_unlisted
)
4579 def _extract_sidebar_info_renderer(data
, info_renderer
, expected_type
=dict):
4580 sidebar_renderer
= try_get(
4581 data
, lambda x
: x
['sidebar']['playlistSidebarRenderer']['items'], list) or []
4582 for item
in sidebar_renderer
:
4583 renderer
= try_get(item
, lambda x
: x
[info_renderer
], expected_type
)
4587 def _reload_with_unavailable_videos(self
, item_id
, data
, ytcfg
):
4589 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4591 browse_id
= params
= None
4592 renderer
= self
._extract
_sidebar
_info
_renderer
(data
, 'playlistSidebarPrimaryInfoRenderer')
4595 menu_renderer
= try_get(
4596 renderer
, lambda x
: x
['menu']['menuRenderer']['items'], list) or []
4597 for menu_item
in menu_renderer
:
4598 if not isinstance(menu_item
, dict):
4600 nav_item_renderer
= menu_item
.get('menuNavigationItemRenderer')
4602 nav_item_renderer
, lambda x
: x
['text']['simpleText'], str)
4603 if not text
or text
.lower() != 'show unavailable videos':
4605 browse_endpoint
= try_get(
4606 nav_item_renderer
, lambda x
: x
['navigationEndpoint']['browseEndpoint'], dict) or {}
4607 browse_id
= browse_endpoint
.get('browseId')
4608 params
= browse_endpoint
.get('params')
4611 headers
= self
.generate_api_headers(
4612 ytcfg
=ytcfg
, account_syncid
=self
._extract
_account
_syncid
(ytcfg
, data
),
4613 visitor_data
=self
._extract
_visitor
_data
(data
, ytcfg
))
4615 'params': params
or 'wgYCCAA=',
4616 'browseId': browse_id
or 'VL%s' % item_id
4618 return self
._extract
_response
(
4619 item_id
=item_id
, headers
=headers
, query
=query
,
4620 check_get_keys
='contents', fatal
=False, ytcfg
=ytcfg
,
4621 note
='Downloading API JSON with unavailable videos')
4623 @functools.cached_property
4624 def skip_webpage(self
):
4625 return 'webpage' in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key())
4627 def _extract_webpage(self
, url
, item_id
, fatal
=True):
4628 webpage
, data
= None, None
4629 for retry
in self
.RetryManager(fatal
=fatal
):
4631 webpage
= self
._download
_webpage
(url
, item_id
, note
='Downloading webpage')
4632 data
= self
.extract_yt_initial_data(item_id
, webpage
or '', fatal
=fatal
) or {}
4633 except ExtractorError
as e
:
4634 if isinstance(e
.cause
, network_exceptions
):
4635 if not isinstance(e
.cause
, urllib
.error
.HTTPError
) or e
.cause
.code
not in (403, 429):
4638 self
._error
_or
_warning
(e
, fatal
=fatal
)
4642 self
._extract
_and
_report
_alerts
(data
)
4643 except ExtractorError
as e
:
4644 self
._error
_or
_warning
(e
, fatal
=fatal
)
4647 # Sometimes youtube returns a webpage with incomplete ytInitialData
4648 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4649 if not traverse_obj(data
, 'contents', 'currentVideoEndpoint', 'onResponseReceivedActions'):
4650 retry
.error
= ExtractorError('Incomplete yt initial data received')
4653 return webpage
, data
4655 def _report_playlist_authcheck(self
, ytcfg
, fatal
=True):
4656 """Use if failed to extract ytcfg (and data) from initial webpage"""
4657 if not ytcfg
and self
.is_authenticated
:
4658 msg
= 'Playlists that require authentication may not extract correctly without a successful webpage download'
4659 if 'authcheck' not in self
._configuration
_arg
('skip', ie_key
=YoutubeTabIE
.ie_key()) and fatal
:
4660 raise ExtractorError(
4661 f
'{msg}. If you are not downloading private content, or '
4662 'your cookies are only for the first account and channel,'
4663 ' pass "--extractor-args youtubetab:skip=authcheck" to skip this check',
4665 self
.report_warning(msg
, only_once
=True)
4667 def _extract_data(self
, url
, item_id
, ytcfg
=None, fatal
=True, webpage_fatal
=False, default_client
='web'):
4669 if not self
.skip_webpage
:
4670 webpage
, data
= self
._extract
_webpage
(url
, item_id
, fatal
=webpage_fatal
)
4671 ytcfg
= ytcfg
or self
.extract_ytcfg(item_id
, webpage
)
4672 # Reject webpage data if redirected to home page without explicitly requesting
4673 selected_tab
= self
._extract
_selected
_tab
(traverse_obj(
4674 data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list, default
=[]), fatal
=False) or {}
4675 if (url
!= 'https://www.youtube.com/feed/recommended'
4676 and selected_tab
.get('tabIdentifier') == 'FEwhat_to_watch' # Home page
4677 and 'no-youtube-channel-redirect' not in self
.get_param('compat_opts', [])):
4678 msg
= 'The channel/playlist does not exist and the URL redirected to youtube.com home page'
4680 raise ExtractorError(msg
, expected
=True)
4681 self
.report_warning(msg
, only_once
=True)
4683 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=fatal
)
4684 data
= self
._extract
_tab
_endpoint
(url
, item_id
, ytcfg
, fatal
=fatal
, default_client
=default_client
)
4687 def _extract_tab_endpoint(self
, url
, item_id
, ytcfg
=None, fatal
=True, default_client
='web'):
4688 headers
= self
.generate_api_headers(ytcfg
=ytcfg
, default_client
=default_client
)
4689 resolve_response
= self
._extract
_response
(
4690 item_id
=item_id
, query
={'url': url}
, check_get_keys
='endpoint', headers
=headers
, ytcfg
=ytcfg
, fatal
=fatal
,
4691 ep
='navigation/resolve_url', note
='Downloading API parameters API JSON', default_client
=default_client
)
4692 endpoints
= {'browseEndpoint': 'browse', 'watchEndpoint': 'next'}
4693 for ep_key
, ep
in endpoints
.items():
4694 params
= try_get(resolve_response
, lambda x
: x
['endpoint'][ep_key
], dict)
4696 return self
._extract
_response
(
4697 item_id
=item_id
, query
=params
, ep
=ep
, headers
=headers
,
4698 ytcfg
=ytcfg
, fatal
=fatal
, default_client
=default_client
,
4699 check_get_keys
=('contents', 'currentVideoEndpoint', 'onResponseReceivedActions'))
4700 err_note
= 'Failed to resolve url (does the playlist exist?)'
4702 raise ExtractorError(err_note
, expected
=True)
4703 self
.report_warning(err_note
, item_id
)
4705 _SEARCH_PARAMS
= None
4707 def _search_results(self
, query
, params
=NO_DEFAULT
, default_client
='web'):
4708 data
= {'query': query}
4709 if params
is NO_DEFAULT
:
4710 params
= self
._SEARCH
_PARAMS
4712 data
['params'] = params
4715 ('contents', 'twoColumnSearchResultsRenderer', 'primaryContents', 'sectionListRenderer', 'contents'),
4716 ('onResponseReceivedCommands', 0, 'appendContinuationItemsAction', 'continuationItems'),
4718 ('contents', 'tabbedSearchResultsRenderer', 'tabs', 0, 'tabRenderer', 'content', 'sectionListRenderer', 'contents'),
4719 ('continuationContents', ),
4721 display_id
= f
'query "{query}"'
4722 check_get_keys
= tuple({keys[0] for keys in content_keys}
)
4723 ytcfg
= self
._download
_ytcfg
(default_client
, display_id
) if not self
.skip_webpage
else {}
4724 self
._report
_playlist
_authcheck
(ytcfg
, fatal
=False)
4726 continuation_list
= [None]
4728 for page_num
in itertools
.count(1):
4729 data
.update(continuation_list
[0] or {})
4730 headers
= self
.generate_api_headers(
4731 ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(search
), default_client
=default_client
)
4732 search
= self
._extract
_response
(
4733 item_id
=f
'{display_id} page {page_num}', ep
='search', query
=data
,
4734 default_client
=default_client
, check_get_keys
=check_get_keys
, ytcfg
=ytcfg
, headers
=headers
)
4735 slr_contents
= traverse_obj(search
, *content_keys
)
4736 yield from self
._extract
_entries
({'contents': list(variadic(slr_contents))}
, continuation_list
)
4737 if not continuation_list
[0]:
4741 class YoutubeTabIE(YoutubeTabBaseInfoExtractor
):
4742 IE_DESC
= 'YouTube Tabs'
4743 _VALID_URL
= r
'''(?x:
4747 youtube(?:kids)?\.com|
4751 (?P<channel_type>channel|c|user|browse)/|
4754 (?:playlist|watch)\?.*?\blist=
4756 (?!(?:%(reserved_names)s)\b) # Direct URLs
4760 'reserved_names': YoutubeBaseInfoExtractor
._RESERVED
_NAMES
,
4761 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
4763 IE_NAME
= 'youtube:tab'
4766 'note': 'playlists, multipage',
4767 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
4768 'playlist_mincount': 94,
4770 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4771 'title': 'Igor Kleiner - Playlists',
4772 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4773 'uploader': 'Igor Kleiner',
4774 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4775 'channel': 'Igor Kleiner',
4776 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4777 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4778 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4779 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4780 'channel_follower_count': int
4783 'note': 'playlists, multipage, different order',
4784 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
4785 'playlist_mincount': 94,
4787 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
4788 'title': 'Igor Kleiner - Playlists',
4789 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
4790 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4791 'uploader': 'Igor Kleiner',
4792 'uploader_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4793 'tags': ['"критическое', 'мышление"', '"наука', 'просто"', 'математика', '"анализ', 'данных"'],
4794 'channel_id': 'UCqj7Cz7revf5maW9g5pgNcg',
4795 'channel': 'Igor Kleiner',
4796 'channel_url': 'https://www.youtube.com/channel/UCqj7Cz7revf5maW9g5pgNcg',
4797 'channel_follower_count': int
4800 'note': 'playlists, series',
4801 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
4802 'playlist_mincount': 5,
4804 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4805 'title': '3Blue1Brown - Playlists',
4806 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4807 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4808 'uploader': '3Blue1Brown',
4809 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4810 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4811 'channel': '3Blue1Brown',
4812 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4813 'tags': ['Mathematics'],
4814 'channel_follower_count': int
4817 'note': 'playlists, singlepage',
4818 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
4819 'playlist_mincount': 4,
4821 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4822 'title': 'ThirstForScience - Playlists',
4823 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
4824 'uploader': 'ThirstForScience',
4825 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4826 'uploader_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4827 'channel_url': 'https://www.youtube.com/channel/UCAEtajcuhQ6an9WEzY9LEMQ',
4828 'channel_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
4830 'channel': 'ThirstForScience',
4831 'channel_follower_count': int
4834 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
4835 'only_matching': True,
4837 'note': 'basic, single video playlist',
4838 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4840 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4841 'uploader': 'Sergey M.',
4842 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
4843 'title': 'youtube-dl public playlist',
4847 'modified_date': '20201130',
4848 'channel': 'Sergey M.',
4849 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4850 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4851 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4853 'playlist_count': 1,
4855 'note': 'empty playlist',
4856 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4858 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4859 'uploader': 'Sergey M.',
4860 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
4861 'title': 'youtube-dl empty playlist',
4863 'channel': 'Sergey M.',
4865 'modified_date': '20160902',
4866 'channel_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
4867 'channel_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4868 'uploader_url': 'https://www.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4870 'playlist_count': 0,
4873 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
4875 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4876 'title': 'lex will - Home',
4877 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4878 'uploader': 'lex will',
4879 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4880 'channel': 'lex will',
4881 'tags': ['bible', 'history', 'prophesy'],
4882 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4883 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4884 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4885 'channel_follower_count': int
4887 'playlist_mincount': 2,
4889 'note': 'Videos tab',
4890 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
4892 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4893 'title': 'lex will - Videos',
4894 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4895 'uploader': 'lex will',
4896 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4897 'tags': ['bible', 'history', 'prophesy'],
4898 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4899 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4900 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4901 'channel': 'lex will',
4902 'channel_follower_count': int
4904 'playlist_mincount': 975,
4906 'note': 'Videos tab, sorted by popular',
4907 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
4909 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4910 'title': 'lex will - Videos',
4911 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4912 'uploader': 'lex will',
4913 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4914 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4915 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4916 'channel': 'lex will',
4917 'tags': ['bible', 'history', 'prophesy'],
4918 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4919 'channel_follower_count': int
4921 'playlist_mincount': 199,
4923 'note': 'Playlists tab',
4924 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
4926 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4927 'title': 'lex will - Playlists',
4928 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4929 'uploader': 'lex will',
4930 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4931 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4932 'channel': 'lex will',
4933 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4934 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4935 'tags': ['bible', 'history', 'prophesy'],
4936 'channel_follower_count': int
4938 'playlist_mincount': 17,
4940 'note': 'Community tab',
4941 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
4943 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4944 'title': 'lex will - Community',
4945 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4946 'uploader': 'lex will',
4947 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4948 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4949 'channel': 'lex will',
4950 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4951 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4952 'tags': ['bible', 'history', 'prophesy'],
4953 'channel_follower_count': int
4955 'playlist_mincount': 18,
4957 'note': 'Channels tab',
4958 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
4960 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4961 'title': 'lex will - Channels',
4962 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
4963 'uploader': 'lex will',
4964 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4965 'uploader_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4966 'channel': 'lex will',
4967 'channel_url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
4968 'channel_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
4969 'tags': ['bible', 'history', 'prophesy'],
4970 'channel_follower_count': int
4972 'playlist_mincount': 12,
4974 'note': 'Search tab',
4975 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
4976 'playlist_mincount': 40,
4978 'id': 'UCYO_jab_esuFRV4b17AJtAw',
4979 'title': '3Blue1Brown - Search - linear algebra',
4980 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
4981 'uploader': '3Blue1Brown',
4982 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
4983 'channel_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4984 'uploader_url': 'https://www.youtube.com/channel/UCYO_jab_esuFRV4b17AJtAw',
4985 'tags': ['Mathematics'],
4986 'channel': '3Blue1Brown',
4987 'channel_id': 'UCYO_jab_esuFRV4b17AJtAw',
4988 'channel_follower_count': int
4991 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4992 'only_matching': True,
4994 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4995 'only_matching': True,
4997 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
4998 'only_matching': True,
5000 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
5001 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5003 'title': '29C3: Not my department',
5004 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
5005 'uploader': 'Christiaan008',
5006 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5007 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
5009 'uploader_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5011 'modified_date': '20150605',
5012 'channel_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
5013 'channel_url': 'https://www.youtube.com/c/ChRiStIaAn008',
5014 'channel': 'Christiaan008',
5016 'playlist_count': 96,
5018 'note': 'Large playlist',
5019 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
5021 'title': 'Uploads from Cauchemar',
5022 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
5023 'uploader': 'Cauchemar',
5024 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5025 'channel_url': 'https://www.youtube.com/c/Cauchemar89',
5027 'modified_date': r
're:\d{8}',
5028 'channel': 'Cauchemar',
5029 'uploader_url': 'https://www.youtube.com/c/Cauchemar89',
5032 'channel_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
5034 'playlist_mincount': 1123,
5035 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5037 'note': 'even larger playlist, 8832 videos',
5038 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
5039 'only_matching': True,
5041 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
5042 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
5044 'title': 'Uploads from Interstellar Movie',
5045 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
5046 'uploader': 'Interstellar Movie',
5047 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5048 'uploader_url': 'https://www.youtube.com/c/InterstellarMovie',
5051 'channel_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
5052 'channel_url': 'https://www.youtube.com/c/InterstellarMovie',
5053 'channel': 'Interstellar Movie',
5055 'modified_date': r
're:\d{8}',
5057 'playlist_mincount': 21,
5059 'note': 'Playlist with "show unavailable videos" button',
5060 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
5062 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
5063 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
5064 'uploader': 'Phim Siêu Nhân Nhật Bản',
5065 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5067 'channel': 'Phim Siêu Nhân Nhật Bản',
5069 'uploader_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5071 'channel_url': 'https://www.youtube.com/channel/UCTYLiWFZy8xtPwxFwX9rV7Q',
5072 'channel_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
5073 'modified_date': r
're:\d{8}',
5075 'playlist_mincount': 200,
5076 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5078 'note': 'Playlist with unavailable videos in page 7',
5079 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
5081 'title': 'Uploads from BlankTV',
5082 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
5083 'uploader': 'BlankTV',
5084 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5085 'channel': 'BlankTV',
5086 'channel_url': 'https://www.youtube.com/c/blanktv',
5087 'channel_id': 'UC8l9frL61Yl5KFOl87nIm2w',
5090 'uploader_url': 'https://www.youtube.com/c/blanktv',
5091 'modified_date': r
're:\d{8}',
5094 'playlist_mincount': 1000,
5095 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5097 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
5098 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5100 'title': 'Data Analysis with Dr Mike Pound',
5101 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
5102 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5103 'uploader': 'Computerphile',
5104 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
5105 'uploader_url': 'https://www.youtube.com/user/Computerphile',
5108 'channel_id': 'UC9-y-6csu5WGm29I7JiwpnA',
5109 'channel_url': 'https://www.youtube.com/user/Computerphile',
5110 'channel': 'Computerphile',
5112 'playlist_mincount': 11,
5114 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
5115 'only_matching': True,
5117 'note': 'Playlist URL that does not actually serve a playlist',
5118 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
5120 'id': 'FqZTN594JQw',
5122 'title': "Smiley's People 01 detective, Adventure Series, Action",
5123 'uploader': 'STREEM',
5124 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
5125 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
5126 'upload_date': '20150526',
5127 'license': 'Standard YouTube License',
5128 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
5129 'categories': ['People & Blogs'],
5135 'skip_download': True,
5137 'skip': 'This video is not available.',
5138 'add_ie': [YoutubeIE
.ie_key()],
5140 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
5141 'only_matching': True,
5143 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
5144 'only_matching': True,
5146 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
5148 'id': 'Wq15eF5vCbI', # This will keep changing
5151 'uploader': 'Sky News',
5152 'uploader_id': 'skynews',
5153 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/skynews',
5154 'upload_date': r
're:\d{8}',
5156 'categories': ['News & Politics'],
5159 'release_timestamp': 1642502819,
5160 'channel': 'Sky News',
5161 'channel_id': 'UCoMdktPbSTixAyNGwb-UYkQ',
5164 'thumbnail': 'https://i.ytimg.com/vi/GgL890LIznQ/maxresdefault_live.jpg',
5165 'playable_in_embed': True,
5166 'release_date': '20220118',
5167 'availability': 'public',
5168 'live_status': 'is_live',
5169 'channel_url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ',
5170 'channel_follower_count': int
5173 'skip_download': True,
5175 'expected_warnings': ['Ignoring subtitle tracks found in '],
5177 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
5179 'id': 'a48o2S1cPoo',
5181 'title': 'The Young Turks - Live Main Show',
5182 'uploader': 'The Young Turks',
5183 'uploader_id': 'TheYoungTurks',
5184 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
5185 'upload_date': '20150715',
5186 'license': 'Standard YouTube License',
5187 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
5188 'categories': ['News & Politics'],
5189 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
5193 'skip_download': True,
5195 'only_matching': True,
5197 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
5198 'only_matching': True,
5200 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
5201 'only_matching': True,
5203 'note': 'A channel that is not live. Should raise error',
5204 'url': 'https://www.youtube.com/user/numberphile/live',
5205 'only_matching': True,
5207 'url': 'https://www.youtube.com/feed/trending',
5208 'only_matching': True,
5210 'url': 'https://www.youtube.com/feed/library',
5211 'only_matching': True,
5213 'url': 'https://www.youtube.com/feed/history',
5214 'only_matching': True,
5216 'url': 'https://www.youtube.com/feed/subscriptions',
5217 'only_matching': True,
5219 'url': 'https://www.youtube.com/feed/watch_later',
5220 'only_matching': True,
5222 'note': 'Recommended - redirects to home page.',
5223 'url': 'https://www.youtube.com/feed/recommended',
5224 'only_matching': True,
5226 'note': 'inline playlist with not always working continuations',
5227 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
5228 'only_matching': True,
5230 'url': 'https://www.youtube.com/course',
5231 'only_matching': True,
5233 'url': 'https://www.youtube.com/zsecurity',
5234 'only_matching': True,
5236 'url': 'http://www.youtube.com/NASAgovVideo/videos',
5237 'only_matching': True,
5239 'url': 'https://www.youtube.com/TheYoungTurks/live',
5240 'only_matching': True,
5242 'url': 'https://www.youtube.com/hashtag/cctv9',
5248 'playlist_mincount': 350,
5250 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
5251 'only_matching': True,
5253 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
5254 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5255 'only_matching': True
5257 'note': '/browse/ should redirect to /channel/',
5258 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
5259 'only_matching': True
5261 'note': 'VLPL, should redirect to playlist?list=PL...',
5262 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5264 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
5265 'uploader': 'NoCopyrightSounds',
5266 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
5267 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5268 'title': 'NCS : All Releases 💿',
5269 'uploader_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5270 'channel_url': 'https://www.youtube.com/c/NoCopyrightSounds',
5271 'modified_date': r
're:\d{8}',
5273 'channel_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
5275 'channel': 'NoCopyrightSounds',
5277 'playlist_mincount': 166,
5278 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5280 'note': 'Topic, should redirect to playlist?list=UU...',
5281 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5283 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5284 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5285 'title': 'Uploads from Royalty Free Music - Topic',
5286 'uploader': 'Royalty Free Music - Topic',
5288 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5289 'channel': 'Royalty Free Music - Topic',
5291 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5292 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5293 'modified_date': r
're:\d{8}',
5294 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5297 'expected_warnings': [
5298 'The URL does not have a videos tab',
5299 r
'[Uu]navailable videos (are|will be) hidden',
5301 'playlist_mincount': 101,
5303 'note': 'Topic without a UU playlist',
5304 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
5306 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
5307 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
5310 'expected_warnings': [
5311 'the playlist redirect gave error',
5313 'playlist_mincount': 9,
5315 'note': 'Youtube music Album',
5316 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
5318 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
5319 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
5323 'availability': 'unlisted',
5324 'modified_date': r
're:\d{8}',
5326 'playlist_count': 50,
5328 'note': 'unlisted single video playlist',
5329 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5331 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5332 'uploader': 'colethedj',
5333 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
5334 'title': 'yt-dlp unlisted playlist test',
5335 'availability': 'unlisted',
5337 'modified_date': '20220418',
5338 'channel': 'colethedj',
5341 'uploader_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5342 'channel_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
5343 'channel_url': 'https://www.youtube.com/channel/UC9zHu_mHU96r19o-wV5Qs1Q',
5345 'playlist_count': 1,
5347 'note': 'API Fallback: Recommended - redirects to home page. Requires visitorData',
5348 'url': 'https://www.youtube.com/feed/recommended',
5350 'id': 'recommended',
5351 'title': 'recommended',
5354 'playlist_mincount': 50,
5356 'skip_download': True,
5357 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5360 'note': 'API Fallback: /videos tab, sorted by oldest first',
5361 'url': 'https://www.youtube.com/user/theCodyReeder/videos?view=0&sort=da&flow=grid',
5363 'id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5364 'title': 'Cody\'sLab - Videos',
5365 'description': 'md5:d083b7c2f0c67ee7a6c74c3e9b4243fa',
5366 'uploader': 'Cody\'sLab',
5367 'uploader_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5368 'channel': 'Cody\'sLab',
5369 'channel_id': 'UCu6mSoMNzHQiBIOCkHUa2Aw',
5371 'channel_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5372 'uploader_url': 'https://www.youtube.com/channel/UCu6mSoMNzHQiBIOCkHUa2Aw',
5373 'channel_follower_count': int
5375 'playlist_mincount': 650,
5377 'skip_download': True,
5378 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5381 'note': 'API Fallback: Topic, should redirect to playlist?list=UU...',
5382 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
5384 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
5385 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5386 'title': 'Uploads from Royalty Free Music - Topic',
5387 'uploader': 'Royalty Free Music - Topic',
5388 'modified_date': r
're:\d{8}',
5389 'channel_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
5391 'channel_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5393 'channel': 'Royalty Free Music - Topic',
5395 'uploader_url': 'https://www.youtube.com/channel/UC9ALqqC4aIeG5iDs7i90Bfw',
5397 'expected_warnings': [
5398 'does not have a videos tab',
5399 r
'[Uu]navailable videos (are|will be) hidden',
5401 'playlist_mincount': 101,
5403 'skip_download': True,
5404 'extractor_args': {'youtubetab': {'skip': ['webpage']}
}
5407 'note': 'non-standard redirect to regional channel',
5408 'url': 'https://www.youtube.com/channel/UCwVVpHQ2Cs9iGJfpdFngePQ',
5409 'only_matching': True
5411 'note': 'collaborative playlist (uploader name in the form "by <uploader> and x other(s)")',
5412 'url': 'https://www.youtube.com/playlist?list=PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5414 'id': 'PLx-_-Kk4c89oOHEDQAojOXzEzemXxoqx6',
5415 'modified_date': '20220407',
5416 'channel_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5418 'uploader_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5419 'uploader': 'pukkandan',
5420 'availability': 'unlisted',
5421 'channel_id': 'UCKcqXmCcyqnhgpA5P0oHH_Q',
5422 'channel': 'pukkandan',
5423 'description': 'Test for collaborative playlist',
5424 'title': 'yt-dlp test - collaborative playlist',
5426 'uploader_url': 'https://www.youtube.com/channel/UCKcqXmCcyqnhgpA5P0oHH_Q',
5428 'playlist_mincount': 2
5432 def suitable(cls
, url
):
5433 return False if YoutubeIE
.suitable(url
) else super().suitable(url
)
5435 _URL_RE
= re
.compile(rf
'(?P<pre>{_VALID_URL})(?(not_channel)|(?P<tab>/\w+))?(?P<post>.*)$')
5437 @YoutubeTabBaseInfoExtractor.passthrough_smuggled_data
5438 def _real_extract(self
, url
, smuggled_data
):
5439 item_id
= self
._match
_id
(url
)
5440 url
= urllib
.parse
.urlunparse(
5441 urllib
.parse
.urlparse(url
)._replace
(netloc
='www.youtube.com'))
5442 compat_opts
= self
.get_param('compat_opts', [])
5445 mobj
= self
._URL
_RE
.match(url
).groupdict()
5446 mobj
.update((k
, '') for k
, v
in mobj
.items() if v
is None)
5449 mobj
, redirect_warning
= get_mobj(url
), None
5450 # Youtube returns incomplete data if tabname is not lower case
5451 pre
, tab
, post
, is_channel
= mobj
['pre'], mobj
['tab'].lower(), mobj
['post'], not mobj
['not_channel']
5453 if smuggled_data
.get('is_music_url'):
5454 if item_id
[:2] == 'VL': # Youtube music VL channels have an equivalent playlist
5455 item_id
= item_id
[2:]
5456 pre
, tab
, post
, is_channel
= f
'https://www.youtube.com/playlist?list={item_id}', '', '', False
5457 elif item_id
[:2] == 'MP': # Resolve albums (/[channel/browse]/MP...) to their equivalent playlist
5458 mdata
= self
._extract
_tab
_endpoint
(
5459 f
'https://music.youtube.com/channel/{item_id}', item_id
, default_client
='web_music')
5460 murl
= traverse_obj(mdata
, ('microformat', 'microformatDataRenderer', 'urlCanonical'),
5461 get_all
=False, expected_type
=str)
5463 raise ExtractorError('Failed to resolve album to playlist')
5464 return self
.url_result(murl
, ie
=YoutubeTabIE
.ie_key())
5465 elif mobj
['channel_type'] == 'browse': # Youtube music /browse/ should be changed to /channel/
5466 pre
= f
'https://www.youtube.com/channel/{item_id}'
5468 original_tab_name
= tab
5469 if is_channel
and not tab
and 'no-youtube-channel-redirect' not in compat_opts
:
5470 # Home URLs should redirect to /videos/
5471 redirect_warning
= ('A channel/user page was given. All the channel\'s videos will be downloaded. '
5472 'To download only the videos in the home page, add a "/featured" to the URL')
5475 url
= ''.join((pre
, tab
, post
))
5476 mobj
= get_mobj(url
)
5478 # Handle both video/playlist URLs
5480 video_id
, playlist_id
= (qs
.get(key
, [None])[0] for key
in ('v', 'list'))
5482 if not video_id
and mobj
['not_channel'].startswith('watch'):
5484 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
5485 raise ExtractorError('Unable to recognize tab page')
5486 # Common mistake: https://www.youtube.com/watch?list=playlist_id
5487 self
.report_warning(f
'A video URL was given without video ID. Trying to download playlist {playlist_id}')
5488 url
= f
'https://www.youtube.com/playlist?list={playlist_id}'
5489 mobj
= get_mobj(url
)
5491 if video_id
and playlist_id
:
5492 if self
.get_param('noplaylist'):
5493 self
.to_screen(f
'Downloading just video {video_id} because of --no-playlist')
5494 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5495 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5496 self
.to_screen(f
'Downloading playlist {playlist_id}; add --no-playlist to just download video {video_id}')
5498 data
, ytcfg
= self
._extract
_data
(url
, item_id
)
5500 # YouTube may provide a non-standard redirect to the regional channel
5501 # See: https://github.com/yt-dlp/yt-dlp/issues/2694
5502 redirect_url
= traverse_obj(
5503 data
, ('onResponseReceivedActions', ..., 'navigateAction', 'endpoint', 'commandMetadata', 'webCommandMetadata', 'url'), get_all
=False)
5504 if redirect_url
and 'no-youtube-channel-redirect' not in compat_opts
:
5505 redirect_url
= ''.join((
5506 urljoin('https://www.youtube.com', redirect_url
), mobj
['tab'], mobj
['post']))
5507 self
.to_screen(f
'This playlist is likely not available in your region. Following redirect to regional playlist {redirect_url}')
5508 return self
.url_result(redirect_url
, ie
=YoutubeTabIE
.ie_key())
5510 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5512 selected_tab
= self
._extract
_selected
_tab
(tabs
)
5513 selected_tab_name
= selected_tab
.get('title', '').lower()
5514 if selected_tab_name
== 'home':
5515 selected_tab_name
= 'featured'
5516 requested_tab_name
= mobj
['tab'][1:]
5517 if 'no-youtube-channel-redirect' not in compat_opts
:
5518 if requested_tab_name
== 'live': # Live tab should have redirected to the video
5519 raise UserNotLive(video_id
=mobj
['id'])
5520 if requested_tab_name
not in ('', selected_tab_name
):
5521 redirect_warning
= f
'The channel does not have a {requested_tab_name} tab'
5522 if not original_tab_name
:
5523 if item_id
[:2] == 'UC':
5524 # Topic channels don't have /videos. Use the equivalent playlist instead
5525 pl_id
= f
'UU{item_id[2:]}'
5526 pl_url
= f
'https://www.youtube.com/playlist?list={pl_id}'
5528 data
, ytcfg
= self
._extract
_data
(pl_url
, pl_id
, ytcfg
=ytcfg
, fatal
=True, webpage_fatal
=True)
5529 except ExtractorError
:
5530 redirect_warning
+= ' and the playlist redirect gave error'
5532 item_id
, url
, selected_tab_name
= pl_id
, pl_url
, requested_tab_name
5533 redirect_warning
+= f
'. Redirecting to playlist {pl_id} instead'
5534 if selected_tab_name
and selected_tab_name
!= requested_tab_name
:
5535 redirect_warning
+= f
'. {selected_tab_name} tab is being downloaded instead'
5537 raise ExtractorError(redirect_warning
, expected
=True)
5539 if redirect_warning
:
5540 self
.to_screen(redirect_warning
)
5541 self
.write_debug(f
'Final URL: {url}')
5543 # YouTube sometimes provides a button to reload playlist with unavailable videos.
5544 if 'no-youtube-unavailable-videos' not in compat_opts
:
5545 data
= self
._reload
_with
_unavailable
_videos
(item_id
, data
, ytcfg
) or data
5546 self
._extract
_and
_report
_alerts
(data
, only_once
=True)
5547 tabs
= traverse_obj(data
, ('contents', 'twoColumnBrowseResultsRenderer', 'tabs'), expected_type
=list)
5549 return self
._extract
_from
_tabs
(item_id
, ytcfg
, data
, tabs
)
5551 playlist
= traverse_obj(
5552 data
, ('contents', 'twoColumnWatchNextResults', 'playlist', 'playlist'), expected_type
=dict)
5554 return self
._extract
_from
_playlist
(item_id
, url
, data
, playlist
, ytcfg
)
5556 video_id
= traverse_obj(
5557 data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str) or video_id
5559 if mobj
['tab'] != '/live': # live tab is expected to redirect to video
5560 self
.report_warning(f
'Unable to recognize playlist. Downloading just video {video_id}')
5561 return self
.url_result(f
'https://www.youtube.com/watch?v={video_id}',
5562 ie
=YoutubeIE
.ie_key(), video_id
=video_id
)
5564 raise ExtractorError('Unable to recognize tab page')
5567 class YoutubePlaylistIE(InfoExtractor
):
5568 IE_DESC
= 'YouTube playlists'
5569 _VALID_URL
= r
'''(?x)(?:
5574 youtube(?:kids)?\.com|
5579 (?P<id>%(playlist_id)s)
5581 'playlist_id': YoutubeBaseInfoExtractor
._PLAYLIST
_ID
_RE
,
5582 'invidious': '|'.join(YoutubeBaseInfoExtractor
._INVIDIOUS
_SITES
),
5584 IE_NAME
= 'youtube:playlist'
5586 'note': 'issue #673',
5587 'url': 'PLBB231211A4F62143',
5589 'title': '[OLD]Team Fortress 2 (Class-based LP)',
5590 'id': 'PLBB231211A4F62143',
5591 'uploader': 'Wickman',
5592 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5593 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
5595 'uploader_url': 'https://www.youtube.com/user/Wickydoo',
5596 'modified_date': r
're:\d{8}',
5597 'channel_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
5598 'channel': 'Wickman',
5600 'channel_url': 'https://www.youtube.com/user/Wickydoo',
5602 'playlist_mincount': 29,
5604 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5606 'title': 'YDL_safe_search',
5607 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
5609 'playlist_count': 2,
5610 'skip': 'This playlist is private',
5613 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5614 'playlist_count': 4,
5617 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
5618 'uploader': 'milan',
5619 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5621 'channel_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5623 'modified_date': '20140919',
5626 'channel_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
5627 'uploader_url': 'https://www.youtube.com/channel/UCEI1-PVPcYXjB73Hfelbmaw',
5629 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5631 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5632 'playlist_mincount': 455,
5634 'title': '2018 Chinese New Singles (11/6 updated)',
5635 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
5637 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5638 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
5641 'channel_url': 'https://www.youtube.com/c/愛低音的國王',
5643 'uploader_url': 'https://www.youtube.com/c/愛低音的國王',
5644 'channel_id': 'UC21nz3_MesPLqtDqwdvnoxA',
5645 'modified_date': r
're:\d{8}',
5647 'expected_warnings': [r
'[Uu]navailable videos (are|will be) hidden'],
5649 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
5650 'only_matching': True,
5652 # music album playlist
5653 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
5654 'only_matching': True,
5658 def suitable(cls
, url
):
5659 if YoutubeTabIE
.suitable(url
):
5661 from ..utils
import parse_qs
5663 if qs
.get('v', [None])[0]:
5665 return super().suitable(url
)
5667 def _real_extract(self
, url
):
5668 playlist_id
= self
._match
_id
(url
)
5669 is_music_url
= YoutubeBaseInfoExtractor
.is_music_url(url
)
5670 url
= update_url_query(
5671 'https://www.youtube.com/playlist',
5672 parse_qs(url
) or {'list': playlist_id}
)
5674 url
= smuggle_url(url
, {'is_music_url': True}
)
5675 return self
.url_result(url
, ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5678 class YoutubeYtBeIE(InfoExtractor
):
5679 IE_DESC
= 'youtu.be'
5680 _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}
5682 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
5684 'id': 'yeWKywCrFtk',
5686 'title': 'Small Scale Baler and Braiding Rugs',
5687 'uploader': 'Backus-Page House Museum',
5688 'uploader_id': 'backuspagemuseum',
5689 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
5690 'upload_date': '20161008',
5691 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
5692 'categories': ['Nonprofits & Activism'],
5696 'playable_in_embed': True,
5697 'thumbnail': 'https://i.ytimg.com/vi_webp/yeWKywCrFtk/maxresdefault.webp',
5698 'channel': 'Backus-Page House Museum',
5699 'channel_id': 'UCEfMCQ9bs3tjvjy1s451zaw',
5700 'live_status': 'not_live',
5702 'channel_url': 'https://www.youtube.com/channel/UCEfMCQ9bs3tjvjy1s451zaw',
5703 'availability': 'public',
5705 'comment_count': int,
5706 'channel_follower_count': int
5710 'skip_download': True,
5713 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
5714 'only_matching': True,
5717 def _real_extract(self
, url
):
5718 mobj
= self
._match
_valid
_url
(url
)
5719 video_id
= mobj
.group('id')
5720 playlist_id
= mobj
.group('playlist_id')
5721 return self
.url_result(
5722 update_url_query('https://www.youtube.com/watch', {
5724 'list': playlist_id
,
5725 'feature': 'youtu.be',
5726 }), ie
=YoutubeTabIE
.ie_key(), video_id
=playlist_id
)
5729 class YoutubeLivestreamEmbedIE(InfoExtractor
):
5730 IE_DESC
= 'YouTube livestream embeds'
5731 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/embed/live_stream/?\?(?:[^#]+&)?channel=(?P<id>[^&#]+)'
5733 'url': 'https://www.youtube.com/embed/live_stream?channel=UC2_KI6RB__jGdlnK6dvFEZA',
5734 'only_matching': True,
5737 def _real_extract(self
, url
):
5738 channel_id
= self
._match
_id
(url
)
5739 return self
.url_result(
5740 f
'https://www.youtube.com/channel/{channel_id}/live',
5741 ie
=YoutubeTabIE
.ie_key(), video_id
=channel_id
)
5744 class YoutubeYtUserIE(InfoExtractor
):
5745 IE_DESC
= 'YouTube user videos; "ytuser:" prefix'
5746 IE_NAME
= 'youtube:user'
5747 _VALID_URL
= r
'ytuser:(?P<id>.+)'
5749 'url': 'ytuser:phihag',
5750 'only_matching': True,
5753 def _real_extract(self
, url
):
5754 user_id
= self
._match
_id
(url
)
5755 return self
.url_result(
5756 'https://www.youtube.com/user/%s/videos' % user_id
,
5757 ie
=YoutubeTabIE
.ie_key(), video_id
=user_id
)
5760 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
5761 IE_NAME
= 'youtube:favorites'
5762 IE_DESC
= 'YouTube liked videos; ":ytfav" keyword (requires cookies)'
5763 _VALID_URL
= r
':ytfav(?:ou?rite)?s?'
5764 _LOGIN_REQUIRED
= True
5767 'only_matching': True,
5769 'url': ':ytfavorites',
5770 'only_matching': True,
5773 def _real_extract(self
, url
):
5774 return self
.url_result(
5775 'https://www.youtube.com/playlist?list=LL',
5776 ie
=YoutubeTabIE
.ie_key())
5779 class YoutubeNotificationsIE(YoutubeTabBaseInfoExtractor
):
5780 IE_NAME
= 'youtube:notif'
5781 IE_DESC
= 'YouTube notifications; ":ytnotif" keyword (requires cookies)'
5782 _VALID_URL
= r
':ytnotif(?:ication)?s?'
5783 _LOGIN_REQUIRED
= True
5786 'only_matching': True,
5788 'url': ':ytnotifications',
5789 'only_matching': True,
5792 def _extract_notification_menu(self
, response
, continuation_list
):
5793 notification_list
= traverse_obj(
5795 ('actions', 0, 'openPopupAction', 'popup', 'multiPageMenuRenderer', 'sections', 0, 'multiPageMenuNotificationSectionRenderer', 'items'),
5796 ('actions', 0, 'appendContinuationItemsAction', 'continuationItems'),
5797 expected_type
=list) or []
5798 continuation_list
[0] = None
5799 for item
in notification_list
:
5800 entry
= self
._extract
_notification
_renderer
(item
.get('notificationRenderer'))
5803 continuation
= item
.get('continuationItemRenderer')
5805 continuation_list
[0] = continuation
5807 def _extract_notification_renderer(self
, notification
):
5808 video_id
= traverse_obj(
5809 notification
, ('navigationEndpoint', 'watchEndpoint', 'videoId'), expected_type
=str)
5810 url
= f
'https://www.youtube.com/watch?v={video_id}'
5813 browse_ep
= traverse_obj(
5814 notification
, ('navigationEndpoint', 'browseEndpoint'), expected_type
=dict)
5815 channel_id
= traverse_obj(browse_ep
, 'browseId', expected_type
=str)
5816 post_id
= self
._search
_regex
(
5817 r
'/post/(.+)', traverse_obj(browse_ep
, 'canonicalBaseUrl', expected_type
=str),
5818 'post id', default
=None)
5819 if not channel_id
or not post_id
:
5821 # The direct /post url redirects to this in the browser
5822 url
= f
'https://www.youtube.com/channel/{channel_id}/community?lb={post_id}'
5824 channel
= traverse_obj(
5825 notification
, ('contextualMenu', 'menuRenderer', 'items', 1, 'menuServiceItemRenderer', 'text', 'runs', 1, 'text'),
5827 notification_title
= self
._get
_text
(notification
, 'shortMessage')
5828 if notification_title
:
5829 notification_title
= notification_title
.replace('\xad', '') # remove soft hyphens
5830 # TODO: handle recommended videos
5831 title
= self
._search
_regex
(
5832 rf
'{re.escape(channel or "")}[^:]+: (.+)', notification_title
,
5833 'video title', default
=None)
5834 upload_date
= (strftime_or_none(self
._extract
_time
_text
(notification
, 'sentTimeText')[0], '%Y%m%d')
5835 if self
._configuration
_arg
('approximate_date', ie_key
=YoutubeTabIE
.ie_key())
5840 'ie_key': (YoutubeIE
if video_id
else YoutubeTabIE
).ie_key(),
5841 'video_id': video_id
,
5843 'channel_id': channel_id
,
5845 'thumbnails': self
._extract
_thumbnails
(notification
, 'videoThumbnail'),
5846 'upload_date': upload_date
,
5849 def _notification_menu_entries(self
, ytcfg
):
5850 continuation_list
= [None]
5852 for page
in itertools
.count(1):
5853 ctoken
= traverse_obj(
5854 continuation_list
, (0, 'continuationEndpoint', 'getNotificationMenuEndpoint', 'ctoken'), expected_type
=str)
5855 response
= self
._extract
_response
(
5856 item_id
=f
'page {page}', query
={'ctoken': ctoken}
if ctoken
else {}, ytcfg
=ytcfg
,
5857 ep
='notification/get_notification_menu', check_get_keys
='actions',
5858 headers
=self
.generate_api_headers(ytcfg
=ytcfg
, visitor_data
=self
._extract
_visitor
_data
(response
)))
5859 yield from self
._extract
_notification
_menu
(response
, continuation_list
)
5860 if not continuation_list
[0]:
5863 def _real_extract(self
, url
):
5864 display_id
= 'notifications'
5865 ytcfg
= self
._download
_ytcfg
('web', display_id
) if not self
.skip_webpage
else {}
5866 self
._report
_playlist
_authcheck
(ytcfg
)
5867 return self
.playlist_result(self
._notification
_menu
_entries
(ytcfg
), display_id
, display_id
)
5870 class YoutubeSearchIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5871 IE_DESC
= 'YouTube search'
5872 IE_NAME
= 'youtube:search'
5873 _SEARCH_KEY
= 'ytsearch'
5874 _SEARCH_PARAMS
= 'EgIQAQ%3D%3D' # Videos only
5876 'url': 'ytsearch5:youtube-dl test video',
5877 'playlist_count': 5,
5879 'id': 'youtube-dl test video',
5880 'title': 'youtube-dl test video',
5885 class YoutubeSearchDateIE(YoutubeTabBaseInfoExtractor
, SearchInfoExtractor
):
5886 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
5887 _SEARCH_KEY
= 'ytsearchdate'
5888 IE_DESC
= 'YouTube search, newest videos first'
5889 _SEARCH_PARAMS
= 'CAISAhAB' # Videos only, sorted by date
5891 'url': 'ytsearchdate5:youtube-dl test video',
5892 'playlist_count': 5,
5894 'id': 'youtube-dl test video',
5895 'title': 'youtube-dl test video',
5900 class YoutubeSearchURLIE(YoutubeTabBaseInfoExtractor
):
5901 IE_DESC
= 'YouTube search URLs with sorting and filter support'
5902 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ '_url'
5903 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:results|search)\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5905 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
5906 'playlist_mincount': 5,
5908 'id': 'youtube-dl test video',
5909 'title': 'youtube-dl test video',
5912 'url': 'https://www.youtube.com/results?search_query=python&sp=EgIQAg%253D%253D',
5913 'playlist_mincount': 5,
5919 'url': 'https://www.youtube.com/results?search_query=%23cats',
5920 'playlist_mincount': 1,
5924 # The test suite does not have support for nested playlists
5926 # 'url': r're:https://(www\.)?youtube\.com/hashtag/cats',
5931 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
5932 'only_matching': True,
5935 def _real_extract(self
, url
):
5937 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5938 return self
.playlist_result(self
._search
_results
(query
, qs
.get('sp', (None,))[0]), query
, query
)
5941 class YoutubeMusicSearchURLIE(YoutubeTabBaseInfoExtractor
):
5942 IE_DESC
= 'YouTube music search URLs with selectable sections, e.g. #songs'
5943 IE_NAME
= 'youtube:music:search_url'
5944 _VALID_URL
= r
'https?://music\.youtube\.com/search\?([^#]+&)?(?:search_query|q)=(?:[^&]+)(?:[&#]|$)'
5946 'url': 'https://music.youtube.com/search?q=royalty+free+music',
5947 'playlist_count': 16,
5949 'id': 'royalty free music',
5950 'title': 'royalty free music',
5953 'url': 'https://music.youtube.com/search?q=royalty+free+music&sp=EgWKAQIIAWoKEAoQAxAEEAkQBQ%3D%3D',
5954 'playlist_mincount': 30,
5956 'id': 'royalty free music - songs',
5957 'title': 'royalty free music - songs',
5959 'params': {'extract_flat': 'in_playlist'}
5961 'url': 'https://music.youtube.com/search?q=royalty+free+music#community+playlists',
5962 'playlist_mincount': 30,
5964 'id': 'royalty free music - community playlists',
5965 'title': 'royalty free music - community playlists',
5967 'params': {'extract_flat': 'in_playlist'}
5971 'albums': 'EgWKAQIYAWoKEAoQAxAEEAkQBQ==',
5972 'artists': 'EgWKAQIgAWoKEAoQAxAEEAkQBQ==',
5973 'community playlists': 'EgeKAQQoAEABagoQChADEAQQCRAF',
5974 'featured playlists': 'EgeKAQQoADgBagwQAxAJEAQQDhAKEAU==',
5975 'songs': 'EgWKAQIIAWoKEAoQAxAEEAkQBQ==',
5976 'videos': 'EgWKAQIQAWoKEAoQAxAEEAkQBQ==',
5979 def _real_extract(self
, url
):
5981 query
= (qs
.get('search_query') or qs
.get('q'))[0]
5982 params
= qs
.get('sp', (None,))[0]
5984 section
= next((k
for k
, v
in self
._SECTIONS
.items() if v
== params
), params
)
5986 section
= urllib
.parse
.unquote_plus((url
.split('#') + [''])[1]).lower()
5987 params
= self
._SECTIONS
.get(section
)
5990 title
= join_nonempty(query
, section
, delim
=' - ')
5991 return self
.playlist_result(self
._search
_results
(query
, params
, default_client
='web_music'), title
, title
)
5994 class YoutubeFeedsInfoExtractor(InfoExtractor
):
5996 Base class for feed extractors
5997 Subclasses must re-define the _FEED_NAME property.
5999 _LOGIN_REQUIRED
= True
6000 _FEED_NAME
= 'feeds'
6002 def _real_initialize(self
):
6003 YoutubeBaseInfoExtractor
._check
_login
_required
(self
)
6007 return f
'youtube:{self._FEED_NAME}'
6009 def _real_extract(self
, url
):
6010 return self
.url_result(
6011 f
'https://www.youtube.com/feed/{self._FEED_NAME}', ie
=YoutubeTabIE
.ie_key())
6014 class YoutubeWatchLaterIE(InfoExtractor
):
6015 IE_NAME
= 'youtube:watchlater'
6016 IE_DESC
= 'Youtube watch later list; ":ytwatchlater" keyword (requires cookies)'
6017 _VALID_URL
= r
':ytwatchlater'
6019 'url': ':ytwatchlater',
6020 'only_matching': True,
6023 def _real_extract(self
, url
):
6024 return self
.url_result(
6025 'https://www.youtube.com/playlist?list=WL', ie
=YoutubeTabIE
.ie_key())
6028 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
6029 IE_DESC
= 'YouTube recommended videos; ":ytrec" keyword'
6030 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
6031 _FEED_NAME
= 'recommended'
6032 _LOGIN_REQUIRED
= False
6035 'only_matching': True,
6037 'url': ':ytrecommended',
6038 'only_matching': True,
6040 'url': 'https://youtube.com',
6041 'only_matching': True,
6045 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
6046 IE_DESC
= 'YouTube subscriptions feed; ":ytsubs" keyword (requires cookies)'
6047 _VALID_URL
= r
':ytsub(?:scription)?s?'
6048 _FEED_NAME
= 'subscriptions'
6051 'only_matching': True,
6053 'url': ':ytsubscriptions',
6054 'only_matching': True,
6058 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
6059 IE_DESC
= 'Youtube watch history; ":ythis" keyword (requires cookies)'
6060 _VALID_URL
= r
':ythis(?:tory)?'
6061 _FEED_NAME
= 'history'
6063 'url': ':ythistory',
6064 'only_matching': True,
6068 class YoutubeStoriesIE(InfoExtractor
):
6069 IE_DESC
= 'YouTube channel stories; "ytstories:" prefix'
6070 IE_NAME
= 'youtube:stories'
6071 _VALID_URL
= r
'ytstories:UC(?P<id>[A-Za-z0-9_-]{21}[AQgw])$'
6073 'url': 'ytstories:UCwFCb4jeqaKWnciAYM-ZVHg',
6074 'only_matching': True,
6077 def _real_extract(self
, url
):
6078 playlist_id
= f
'RLTD{self._match_id(url)}'
6079 return self
.url_result(
6080 smuggle_url(f
'https://www.youtube.com/playlist?list={playlist_id}&playnext=1', {'is_story': True}
),
6081 ie
=YoutubeTabIE
, video_id
=playlist_id
)
6084 class YoutubeTruncatedURLIE(InfoExtractor
):
6085 IE_NAME
= 'youtube:truncated_url'
6086 IE_DESC
= False # Do not list
6087 _VALID_URL
= r
'''(?x)
6089 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
6092 annotation_id=annotation_[^&]+|
6098 attribution_link\?a=[^&]+
6104 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
6105 'only_matching': True,
6107 'url': 'https://www.youtube.com/watch?',
6108 'only_matching': True,
6110 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
6111 'only_matching': True,
6113 'url': 'https://www.youtube.com/watch?feature=foo',
6114 'only_matching': True,
6116 'url': 'https://www.youtube.com/watch?hl=en-GB',
6117 'only_matching': True,
6119 'url': 'https://www.youtube.com/watch?t=2372',
6120 'only_matching': True,
6123 def _real_extract(self
, url
):
6124 raise ExtractorError(
6125 'Did you forget to quote the URL? Remember that & is a meta '
6126 'character in most shells, so you want to put the URL in quotes, '
6128 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
6129 ' or simply youtube-dl BaW_jenozKc .',
6133 class YoutubeClipIE(YoutubeTabBaseInfoExtractor
):
6134 IE_NAME
= 'youtube:clip'
6135 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/clip/(?P<id>[^/?#]+)'
6137 # FIXME: Other metadata should be extracted from the clip, not from the base video
6138 'url': 'https://www.youtube.com/clip/UgytZKpehg-hEMBSn3F4AaABCQ',
6140 'id': 'UgytZKpehg-hEMBSn3F4AaABCQ',
6142 'section_start': 29.0,
6143 'section_end': 39.7,
6146 'availability': 'public',
6147 'categories': ['Gaming'],
6148 'channel': 'Scott The Woz',
6149 'channel_id': 'UC4rqhyiTs7XyuODcECvuiiQ',
6150 'channel_url': 'https://www.youtube.com/channel/UC4rqhyiTs7XyuODcECvuiiQ',
6151 'description': 'md5:7a4517a17ea9b4bd98996399d8bb36e7',
6153 'playable_in_embed': True,
6155 'thumbnail': 'https://i.ytimg.com/vi_webp/ScPX26pdQik/maxresdefault.webp',
6156 'title': 'Mobile Games on Console - Scott The Woz',
6157 'upload_date': '20210920',
6158 'uploader': 'Scott The Woz',
6159 'uploader_id': 'scottthewoz',
6160 'uploader_url': 'http://www.youtube.com/user/scottthewoz',
6162 'live_status': 'not_live',
6163 'channel_follower_count': int
6167 def _real_extract(self
, url
):
6168 clip_id
= self
._match
_id
(url
)
6169 _
, data
= self
._extract
_webpage
(url
, clip_id
)
6171 video_id
= traverse_obj(data
, ('currentVideoEndpoint', 'watchEndpoint', 'videoId'))
6173 raise ExtractorError('Unable to find video ID')
6175 clip_data
= traverse_obj(data
, (
6176 'engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'clipSectionRenderer',
6177 'contents', ..., 'clipAttributionRenderer', 'onScrubExit', 'commandExecutorCommand', 'commands', ...,
6178 'openPopupAction', 'popup', 'notificationActionRenderer', 'actionButton', 'buttonRenderer', 'command',
6179 'commandExecutorCommand', 'commands', ..., 'loopCommand'), get_all
=False)
6182 '_type': 'url_transparent',
6183 'url': f
'https://www.youtube.com/watch?v={video_id}',
6184 'ie_key': YoutubeIE
.ie_key(),
6186 'section_start': int(clip_data
['startTimeMs']) / 1000,
6187 'section_end': int(clip_data
['endTimeMs']) / 1000,
6191 class YoutubeTruncatedIDIE(InfoExtractor
):
6192 IE_NAME
= 'youtube:truncated_id'
6193 IE_DESC
= False # Do not list
6194 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
6197 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
6198 'only_matching': True,
6201 def _real_extract(self
, url
):
6202 video_id
= self
._match
_id
(url
)
6203 raise ExtractorError(
6204 f
'Incomplete YouTube ID {video_id}. URL {url} looks truncated.',