3 from __future__
import unicode_literals
18 from .common
import InfoExtractor
, SearchInfoExtractor
19 from ..compat
import (
24 compat_urllib_parse_unquote_plus
,
25 compat_urllib_parse_urlencode
,
26 compat_urllib_parse_urlparse
,
29 from ..jsinterp
import JSInterpreter
67 return compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
70 # any clients starting with _ cannot be explicity requested by the user
73 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
74 'INNERTUBE_CONTEXT': {
77 'clientVersion': '2.20210622.10.00',
80 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
83 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
84 'INNERTUBE_CONTEXT': {
86 'clientName': 'WEB_EMBEDDED_PLAYER',
87 'clientVersion': '1.20210620.0.1',
90 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
93 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
94 'INNERTUBE_HOST': 'music.youtube.com',
95 'INNERTUBE_CONTEXT': {
97 'clientName': 'WEB_REMIX',
98 'clientVersion': '1.20210621.00.00',
101 'INNERTUBE_CONTEXT_CLIENT_NAME': 67,
104 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
105 'INNERTUBE_CONTEXT': {
107 'clientName': 'ANDROID',
108 'clientVersion': '16.20',
111 'INNERTUBE_CONTEXT_CLIENT_NAME': 3,
113 'android_embedded': {
114 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
115 'INNERTUBE_CONTEXT': {
117 'clientName': 'ANDROID_EMBEDDED_PLAYER',
118 'clientVersion': '16.20',
121 'INNERTUBE_CONTEXT_CLIENT_NAME': 55
124 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
125 'INNERTUBE_HOST': 'music.youtube.com',
126 'INNERTUBE_CONTEXT': {
128 'clientName': 'ANDROID_MUSIC',
129 'clientVersion': '4.32',
132 'INNERTUBE_CONTEXT_CLIENT_NAME': 21,
135 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
136 'INNERTUBE_CONTEXT': {
139 'clientVersion': '16.20',
142 'INNERTUBE_CONTEXT_CLIENT_NAME': 5
145 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
146 'INNERTUBE_CONTEXT': {
148 'clientName': 'IOS_MESSAGES_EXTENSION',
149 'clientVersion': '16.20',
152 'INNERTUBE_CONTEXT_CLIENT_NAME': 66
155 'INNERTUBE_API_KEY': 'AIzaSyDK3iBpDP9nHVTk2qL73FLJICfOC3c51Og',
156 'INNERTUBE_HOST': 'music.youtube.com',
157 'INNERTUBE_CONTEXT': {
159 'clientName': 'IOS_MUSIC',
160 'clientVersion': '4.32',
163 'INNERTUBE_CONTEXT_CLIENT_NAME': 26
166 'INNERTUBE_API_KEY': 'AIzaSyDCU8hByM-4DrUqRUYnGn-3llEO78bcxq8',
167 'INNERTUBE_CONTEXT': {
169 'clientName': 'MWEB',
170 'clientVersion': '2.20210721.07.00',
173 'INNERTUBE_CONTEXT_CLIENT_NAME': 2
178 def build_innertube_clients():
180 'embedUrl': 'https://google.com', # Can be any valid URL
182 base_clients
= ('android', 'web', 'ios', 'mweb')
183 priority
= qualities(base_clients
[::-1])
185 for client
, ytcfg
in tuple(INNERTUBE_CLIENTS
.items()):
186 ytcfg
.setdefault('INNERTUBE_API_KEY', 'AIzaSyDCU8hByM4DrUqRUYnGn3llEO78bcxq8')
187 ytcfg
.setdefault('INNERTUBE_HOST', 'www.youtube.com')
188 ytcfg
['INNERTUBE_CONTEXT']['client'].setdefault('hl', 'en')
189 ytcfg
['priority'] = 10 * priority(client
.split('_', 1)[0])
191 if client
in base_clients
:
192 INNERTUBE_CLIENTS
[f
'{client}_agegate'] = agegate_ytcfg
= copy
.deepcopy(ytcfg
)
193 agegate_ytcfg
['INNERTUBE_CONTEXT']['client']['clientScreen'] = 'EMBED'
194 agegate_ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
195 agegate_ytcfg
['priority'] -= 1
196 elif client
.endswith('_embedded'):
197 ytcfg
['INNERTUBE_CONTEXT']['thirdParty'] = third_party
198 ytcfg
['priority'] -= 2
200 ytcfg
['priority'] -= 3
203 build_innertube_clients()
206 class YoutubeBaseInfoExtractor(InfoExtractor
):
207 """Provide base functions for Youtube extractors"""
208 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
209 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
211 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
212 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
213 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
216 r
'channel|c|user|browse|playlist|watch|w|v|embed|e|watch_popup|shorts|'
217 r
'movies|results|shared|hashtag|trending|feed|feeds|oembed|get_video_info|'
218 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
220 _NETRC_MACHINE
= 'youtube'
221 # If True it will raise an error if no login info is provided
222 _LOGIN_REQUIRED
= False
224 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
228 Attempt to log in to YouTube.
229 True is returned if successful or skipped.
230 False is returned if login failed.
232 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
236 self
.report_warning(message
)
238 # username+password login is broken
239 if (self
._LOGIN
_REQUIRED
240 and self
.get_param('cookiefile') is None
241 and self
.get_param('cookiesfrombrowser') is None):
242 self
.raise_login_required(
243 'Login details are needed to download this content', method
='cookies')
244 username
, password
= self
._get
_login
_info
()
246 warn('Logging in using username and password is broken. %s' % self
._LOGIN
_HINTS
['cookies'])
249 # Everything below this is broken!
251 # No authentication to be performed
253 if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None:
254 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
255 # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
256 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
259 login_page = self._download_webpage(
260 self._LOGIN_URL, None,
261 note='Downloading login page',
262 errnote='unable to fetch login page', fatal=False)
263 if login_page is False:
266 login_form = self._hidden_inputs(login_page)
268 def req(url, f_req, note, errnote):
269 data = login_form.copy()
272 'checkConnection': 'youtube',
273 'checkedDomains': 'youtube',
275 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
276 'f.req': json.dumps(f_req),
277 'flowName': 'GlifWebSignIn',
278 'flowEntry': 'ServiceLogin',
279 # TODO: reverse actual botguard identifier generation algo
280 'bgRequest': '["identifier",""]',
282 return self._download_json(
283 url, None, note=note, errnote=errnote,
284 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
286 data=urlencode_postdata(data), headers={
287 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
288 'Google-Accounts-XSRF': 1,
293 None, [], None, 'US', None, None, 2, False, True,
297 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn',
299 1, [None, None, []], None, None, None, True
304 lookup_results = req(
305 self._LOOKUP_URL, lookup_req,
306 'Looking up account info', 'Unable to look up account info')
308 if lookup_results is False:
311 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
313 warn('Unable to extract user hash')
318 None, 1, None, [1, None, None, None, [password, None, True]],
320 None, None, [2, 1, None, 1, 'https://accounts.google.com/ServiceLogin?passive=true&continue=https%3A%2F%2Fwww.youtube.com%2Fsignin%3Fnext%3D%252F%26action_handle_signin%3Dtrue%26hl%3Den%26app%3Ddesktop%26feature%3Dsign_in_button&hl=en&service=youtube&uilel=3&requestPath=%2FServiceLogin&Page=PasswordSeparationSignIn', None, [], 4],
321 1, [None, None, []], None, None, None, True
324 challenge_results = req(
325 self._CHALLENGE_URL, challenge_req,
326 'Logging in', 'Unable to log in')
328 if challenge_results is False:
331 login_res = try_get(challenge_results, lambda x: x[0][5], list)
333 login_msg = try_get(login_res, lambda x: x[5], compat_str)
335 'Unable to login: %s' % 'Invalid password'
336 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
339 res = try_get(challenge_results, lambda x: x[0][-1], list)
341 warn('Unable to extract result entry')
344 login_challenge = try_get(res, lambda x: x[0][0], list)
346 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
347 if challenge_str == 'TWO_STEP_VERIFICATION':
348 # SEND_SUCCESS - TFA code has been successfully sent to phone
349 # QUOTA_EXCEEDED - reached the limit of TFA codes
350 status = try_get(login_challenge, lambda x: x[5], compat_str)
351 if status == 'QUOTA_EXCEEDED':
352 warn('Exceeded the limit of TFA codes, try later')
355 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
357 warn('Unable to extract TL')
360 tfa_code = self._get_tfa_info('2-step verification code')
364 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
365 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
368 tfa_code = remove_start(tfa_code, 'G-')
371 user_hash, None, 2, None,
373 9, None, None, None, None, None, None, None,
374 [None, tfa_code, True, 2]
378 self._TFA_URL.format(tl), tfa_req,
379 'Submitting TFA code', 'Unable to submit TFA code')
381 if tfa_results is False:
384 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
386 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
388 'Unable to finish TFA: %s' % 'Invalid TFA code'
389 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
392 check_cookie_url = try_get(
393 tfa_results, lambda x: x[0][-1][2], compat_str)
396 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
397 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
398 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
400 challenge = CHALLENGES.get(
402 '%s returned error %s.' % (self.IE_NAME, challenge_str))
403 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
406 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
408 if not check_cookie_url:
409 warn('Unable to extract CheckCookie URL')
412 check_cookie_results = self._download_webpage(
413 check_cookie_url, None, 'Checking cookie', fatal=False)
415 if check_cookie_results is False:
418 if 'https://myaccount.google.com/' not in check_cookie_results:
419 warn('Unable to log in')
425 def _initialize_consent(self
):
426 cookies
= self
._get
_cookies
('https://www.youtube.com/')
427 if cookies
.get('__Secure-3PSID'):
430 consent
= cookies
.get('CONSENT')
432 if 'YES' in consent
.value
:
434 consent_id
= self
._search
_regex
(
435 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
437 consent_id
= random
.randint(100, 999)
438 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
440 def _real_initialize(self
):
441 self
._initialize
_consent
()
442 if self
._downloader
is None:
444 if not self
._login
():
447 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
448 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
449 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
451 def _get_default_ytcfg(self, client='web'):
452 return copy.deepcopy(INNERTUBE_CLIENTS[client])
454 def _get_innertube_host(self, client='web'):
455 return INNERTUBE_CLIENTS[client]['INNERTUBE_HOST']
457 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='web'):
458 # try_get but with fallback to default ytcfg client values when present
459 _func = lambda y: try_get(y, getter, expected_type)
460 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
462 def _extract_client_name(self, ytcfg, default_client='web'):
464 try_get(ytcfg, lambda x: x['INNERTUBE_CLIENT_NAME'], compat_str)
465 or self._ytcfg_get_safe(
466 ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['clientName'], compat_str, default_client))
469 def _extract_session_index(*data):
471 session_index = int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
472 if session_index is not None:
475 def _extract_client_version(self, ytcfg, default_client='web'):
477 try_get(ytcfg, lambda x: x['INNERTUBE_CLIENT_VERSION'], compat_str)
478 or self._ytcfg_get_safe(
479 ytcfg, lambda x: x['INNERTUBE_CONTEXT']['client']['clientVersion'], compat_str, default_client))
481 def _extract_api_key(self, ytcfg=None, default_client='web'):
482 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
484 def _extract_context(self, ytcfg=None, default_client='web'):
485 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
486 context = _get_context(ytcfg)
490 context = _get_context(self._get_default_ytcfg(default_client))
494 # Recreate the client context (required)
495 context['client'].update({
496 'clientVersion': self._extract_client_version(ytcfg, default_client),
497 'clientName': self._extract_client_name(ytcfg, default_client),
499 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
501 context['client']['visitorData'] = visitor_data
504 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
505 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
506 # See: https://github.com/yt-dlp/yt-dlp/issues/393
507 yt_cookies = self._get_cookies('https://www.youtube.com')
508 sapisid_cookie = dict_get(
509 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
510 if sapisid_cookie is None or not sapisid_cookie.value:
512 time_now = round(time.time())
513 # SAPISID cookie is required if not already present
514 if not yt_cookies.get('SAPISID'):
515 self.write_debug('Copying __Secure-3PAPISID cookie to SAPISID cookie', only_once=True)
517 '.youtube.com', 'SAPISID', sapisid_cookie.value, secure=True, expire_time=time_now + 3600)
518 self.write_debug('Extracted SAPISID cookie', only_once=True)
519 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
520 sapisidhash = hashlib.sha1(
521 f'{time_now} {sapisid_cookie.value} {origin}'.encode('utf-8')).hexdigest()
522 return f'SAPISIDHASH {time_now}_{sapisidhash}'
524 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
525 note='Downloading API JSON', errnote='Unable to download API page',
526 context=None, api_key=None, api_hostname=None, default_client='web'):
528 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
530 real_headers = self.generate_api_headers(default_client=default_client)
531 real_headers.update({'content-type': 'application/json'})
533 real_headers.update(headers)
534 return self._download_json(
535 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
536 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
537 data=json.dumps(data).encode('utf8'), headers=real_headers,
538 query={'key': api_key or self._extract_api_key()})
540 def extract_yt_initial_data(self, video_id, webpage):
541 return self._parse_json(
543 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
544 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
547 def _extract_identity_token(self, webpage, item_id):
550 ytcfg = self.extract_ytcfg(item_id, webpage)
552 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
555 return self._search_regex(
556 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
557 'identity token
', default=None)
560 def _extract_account_syncid(*args):
562 Extract syncId required to download private playlists of secondary channels
563 @params response and/or ytcfg
566 # ytcfg includes channel_syncid if on secondary channel
567 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
571 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
572 lambda x: x['DATASYNC_ID
']), compat_str) or '').split("||")
573 if len(sync_ids) >= 2 and sync_ids[1]:
574 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
575 # and just "user_syncid||" for primary channel. We only want the channel_syncid
578 def extract_ytcfg(self, video_id, webpage):
581 return self._parse_json(
583 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
584 default='{}'), video_id, fatal=False) or {}
586 def generate_api_headers(
587 self
, ytcfg
=None, identity_token
=None, account_syncid
=None,
588 visitor_data
=None, api_hostname
=None, default_client
='web', session_index
=None):
589 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(default_client
))
591 'X-YouTube-Client-Name': compat_str(
592 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=default_client
)),
593 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, default_client
),
596 if not visitor_data
and ytcfg
:
597 visitor_data
= try_get(
598 self
._extract
_context
(ytcfg
, default_client
), lambda x
: x
['client']['visitorData'], compat_str
)
600 headers
['X-Youtube-Identity-Token'] = identity_token
602 headers
['X-Goog-PageId'] = account_syncid
603 if session_index
is None and ytcfg
:
604 session_index
= self
._extract
_session
_index
(ytcfg
)
605 if account_syncid
or session_index
is not None:
606 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
608 headers
['X-Goog-Visitor-Id'] = visitor_data
609 auth
= self
._generate
_sapisidhash
_header
(origin
)
611 headers
['Authorization'] = auth
612 headers
['X-Origin'] = origin
616 def _build_api_continuation_query(continuation
, ctp
=None):
618 'continuation': continuation
620 # TODO: Inconsistency with clickTrackingParams.
621 # Currently we have a fixed ctp contained within context (from ytcfg)
622 # and a ctp in root query for continuation.
624 query
['clickTracking'] = {'clickTrackingParams': ctp}
628 def _extract_next_continuation_data(cls
, renderer
):
629 next_continuation
= try_get(
630 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
631 lambda x
: x
['continuation']['reloadContinuationData']), dict)
632 if not next_continuation
:
634 continuation
= next_continuation
.get('continuation')
637 ctp
= next_continuation
.get('clickTrackingParams')
638 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
641 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
642 if isinstance(continuation_ep
, dict):
643 continuation
= try_get(
644 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
647 ctp
= continuation_ep
.get('clickTrackingParams')
648 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
651 def _extract_continuation(cls
, renderer
):
652 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
653 if next_continuation
:
654 return next_continuation
657 for key
in ('contents', 'items'):
658 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
660 for content
in contents
:
661 if not isinstance(content
, dict):
663 continuation_ep
= try_get(
664 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
665 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
667 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
672 def _extract_alerts(cls
, data
):
673 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
674 if not isinstance(alert_dict
, dict):
676 for alert
in alert_dict
.values():
677 alert_type
= alert
.get('type')
680 message
= cls
._get
_text
(alert
, 'text')
682 yield alert_type
, message
684 def _report_alerts(self
, alerts
, expected
=True):
687 for alert_type
, alert_message
in alerts
:
688 if alert_type
.lower() == 'error':
689 errors
.append([alert_type
, alert_message
])
691 warnings
.append([alert_type
, alert_message
])
693 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
694 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
))
696 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
698 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
699 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
701 def _extract_badges(self
, renderer
: dict):
703 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
704 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
706 badges
.add(label
.lower())
710 def _get_text(data
, *path_list
, max_runs
=None):
711 for path
in path_list
or [None]:
715 obj
= traverse_obj(data
, path
, default
=[])
716 if not any(key
is ... or isinstance(key
, (list, tuple)) for key
in variadic(path
)):
719 text
= try_get(item
, lambda x
: x
['simpleText'], compat_str
)
722 runs
= try_get(item
, lambda x
: x
['runs'], list) or []
723 if not runs
and isinstance(item
, list):
726 runs
= runs
[:min(len(runs
), max_runs
or len(runs
))]
727 text
= ''.join(traverse_obj(runs
, (..., 'text'), expected_type
=str, default
=[]))
731 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
732 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
733 default_client
='web'):
737 retries
= self
.get_param('extractor_retries', 3)
738 if check_get_keys
is None:
740 while count
< retries
:
743 self
.report_warning('%s. Retrying ...' % last_error
)
745 response
= self
._call
_api
(
746 ep
=ep
, fatal
=True, headers
=headers
,
747 video_id
=item_id
, query
=query
,
748 context
=self
._extract
_context
(ytcfg
, default_client
),
749 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
750 api_hostname
=api_hostname
, default_client
=default_client
,
751 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
752 except ExtractorError
as e
:
753 if isinstance(e
.cause
, network_exceptions
):
754 # Downloading page may result in intermittent 5xx HTTP error
755 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
756 # We also want to catch all other network exceptions since errors in later pages can be troublesome
757 # See https://github.com/yt-dlp/yt-dlp/issues/507#issuecomment-880188210
758 if not isinstance(e
.cause
, compat_HTTPError
) or e
.cause
.code
not in (403, 429):
759 last_error
= error_to_compat_str(e
.cause
or e
)
765 self
.report_warning(error_to_compat_str(e
))
769 # Youtube may send alerts if there was an issue with the continuation page
771 self
._extract
_and
_report
_alerts
(response
, expected
=False)
772 except ExtractorError
as e
:
775 self
.report_warning(error_to_compat_str(e
))
777 if not check_get_keys
or dict_get(response
, check_get_keys
):
779 # Youtube sometimes sends incomplete data
780 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
781 last_error
= 'Incomplete data received'
784 raise ExtractorError(last_error
)
786 self
.report_warning(last_error
)
791 def is_music_url(url
):
792 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
794 def _extract_video(self
, renderer
):
795 video_id
= renderer
.get('videoId')
796 title
= self
._get
_text
(renderer
, 'title')
797 description
= self
._get
_text
(renderer
, 'descriptionSnippet')
798 duration
= parse_duration(self
._get
_text
(
799 renderer
, 'lengthText', ('thumbnailOverlays', ..., 'thumbnailOverlayTimeStatusRenderer', 'text')))
800 view_count_text
= self
._get
_text
(renderer
, 'viewCountText') or ''
801 view_count
= str_to_int(self
._search
_regex
(
802 r
'^([\d,]+)', re
.sub(r
'\s', '', view_count_text
),
803 'view count', default
=None))
805 uploader
= self
._get
_text
(renderer
, 'ownerText', 'shortBylineText')
809 'ie_key': YoutubeIE
.ie_key(),
813 'description': description
,
814 'duration': duration
,
815 'view_count': view_count
,
816 'uploader': uploader
,
820 class YoutubeIE(YoutubeBaseInfoExtractor
):
821 IE_DESC
= 'YouTube.com'
823 # invidious-redirect websites
824 r
'(?:www\.)?redirect\.invidious\.io',
825 r
'(?:(?:www|dev)\.)?invidio\.us',
826 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
827 r
'(?:www\.)?invidious\.pussthecat\.org',
828 r
'(?:www\.)?invidious\.zee\.li',
829 r
'(?:www\.)?invidious\.ethibox\.fr',
830 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
831 # youtube-dl invidious instances list
832 r
'(?:(?:www|no)\.)?invidiou\.sh',
833 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
834 r
'(?:www\.)?invidious\.kabi\.tk',
835 r
'(?:www\.)?invidious\.mastodon\.host',
836 r
'(?:www\.)?invidious\.zapashcanon\.fr',
837 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
838 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
839 r
'(?:www\.)?invidious\.himiko\.cloud',
840 r
'(?:www\.)?invidious\.reallyancient\.tech',
841 r
'(?:www\.)?invidious\.tube',
842 r
'(?:www\.)?invidiou\.site',
843 r
'(?:www\.)?invidious\.site',
844 r
'(?:www\.)?invidious\.xyz',
845 r
'(?:www\.)?invidious\.nixnet\.xyz',
846 r
'(?:www\.)?invidious\.048596\.xyz',
847 r
'(?:www\.)?invidious\.drycat\.fr',
848 r
'(?:www\.)?inv\.skyn3t\.in',
849 r
'(?:www\.)?tube\.poal\.co',
850 r
'(?:www\.)?tube\.connect\.cafe',
851 r
'(?:www\.)?vid\.wxzm\.sx',
852 r
'(?:www\.)?vid\.mint\.lgbt',
853 r
'(?:www\.)?vid\.puffyan\.us',
854 r
'(?:www\.)?yewtu\.be',
855 r
'(?:www\.)?yt\.elukerio\.org',
856 r
'(?:www\.)?yt\.lelux\.fi',
857 r
'(?:www\.)?invidious\.ggc-project\.de',
858 r
'(?:www\.)?yt\.maisputain\.ovh',
859 r
'(?:www\.)?ytprivate\.com',
860 r
'(?:www\.)?invidious\.13ad\.de',
861 r
'(?:www\.)?invidious\.toot\.koeln',
862 r
'(?:www\.)?invidious\.fdn\.fr',
863 r
'(?:www\.)?watch\.nettohikari\.com',
864 r
'(?:www\.)?invidious\.namazso\.eu',
865 r
'(?:www\.)?invidious\.silkky\.cloud',
866 r
'(?:www\.)?invidious\.exonip\.de',
867 r
'(?:www\.)?invidious\.riverside\.rocks',
868 r
'(?:www\.)?invidious\.blamefran\.net',
869 r
'(?:www\.)?invidious\.moomoo\.de',
870 r
'(?:www\.)?ytb\.trom\.tf',
871 r
'(?:www\.)?yt\.cyberhost\.uk',
872 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
873 r
'(?:www\.)?qklhadlycap4cnod\.onion',
874 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
875 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
876 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
877 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
878 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
879 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
880 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
881 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
882 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
883 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
885 _VALID_URL
= r
"""(?x)^
887 (?:https?://|//) # http(s):// or protocol-independent URL
888 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
889 (?:www\.)?deturl\.com/www\.youtube\.com|
890 (?:www\.)?pwnyoutube\.com|
891 (?:www\.)?hooktube\.com|
892 (?:www\.)?yourepeat\.com|
895 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
896 (?:.*?\#/)? # handle anchor (#/) redirect urls
897 (?: # the various things that can precede the ID:
898 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
899 |(?: # or the v= param in all its forms
900 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
901 (?:\?|\#!?) # the params delimiter ? or # or #!
902 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
907 youtu\.be| # just youtu.be/xxxx
908 vid\.plus| # or vid.plus/xxxx
909 zwearz\.com/watch| # or zwearz.com/watch/xxxx
912 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
914 )? # all until now is optional -> you can pass the naked ID
915 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
916 (?(1).+)? # if we found the ID, everything can follow
918 'invidious': '|'.join(_INVIDIOUS_SITES
),
921 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
922 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$',
923 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
926 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
927 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
928 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
929 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
930 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
931 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
932 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
933 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
934 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
935 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
936 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
937 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
938 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
939 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
940 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
941 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
942 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
943 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
947 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
948 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
949 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
950 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
951 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
952 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
953 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
955 # Apple HTTP Live Streaming
956 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
957 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
958 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
959 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
960 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
961 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
962 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
963 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
966 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
967 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
968 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
969 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
970 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
971 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
972 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
973 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
974 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
975 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
976 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
977 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
980 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
981 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
982 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
983 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
984 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
985 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
986 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
989 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
990 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
991 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
992 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
993 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
994 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
995 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
996 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
997 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
998 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
999 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1000 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1001 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1002 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1003 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1004 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
1005 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1006 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1007 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1008 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1009 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
1010 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
1013 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
1014 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
1016 # Dash webm audio with opus inside
1017 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
1018 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
1019 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
1022 '_rtmp': {'protocol': 'rtmp'}
,
1024 # av01 video only formats sometimes served with "unknown" codecs
1025 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
1026 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
1027 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
1028 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
1030 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
1032 _AGE_GATE_REASONS
= (
1033 'Sign in to confirm your age',
1034 'This video may be inappropriate for some users.',
1035 'Sorry, this content is age-restricted.',
1036 'Please confirm your age.')
1038 _AGE_GATE_STATUS_REASONS
= (
1039 'AGE_VERIFICATION_REQUIRED',
1040 'AGE_CHECK_REQUIRED'
1048 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
1050 'id': 'BaW_jenozKc',
1052 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1053 'uploader': 'Philipp Hagemeister',
1054 'uploader_id': 'phihag',
1055 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1056 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
1057 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
1058 'upload_date': '20121002',
1059 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
1060 'categories': ['Science & Technology'],
1061 'tags': ['youtube-dl'],
1065 'dislike_count': int,
1071 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1072 'note': 'Embed-only video (#1746)',
1074 'id': 'yZIXLfi8CZQ',
1076 'upload_date': '20120608',
1077 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1078 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1079 'uploader': 'SET India',
1080 'uploader_id': 'setindia',
1081 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1084 'skip': 'Private video',
1087 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1088 'note': 'Use the first video ID in the URL',
1090 'id': 'BaW_jenozKc',
1092 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1093 'uploader': 'Philipp Hagemeister',
1094 'uploader_id': 'phihag',
1095 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1096 'upload_date': '20121002',
1097 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
1098 'categories': ['Science & Technology'],
1099 'tags': ['youtube-dl'],
1103 'dislike_count': int,
1106 'skip_download': True,
1110 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1111 'note': '256k DASH audio (format 141) via DASH manifest',
1113 'id': 'a9LDPn-MO4I',
1115 'upload_date': '20121002',
1116 'uploader_id': '8KVIDEO',
1117 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1119 'uploader': '8KVIDEO',
1120 'title': 'UHDTV TEST 8K VIDEO.mp4'
1123 'youtube_include_dash_manifest': True,
1126 'skip': 'format 141 not served anymore',
1128 # DASH manifest with encrypted signature
1130 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1132 'id': 'IB3lcPjvWLA',
1134 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1135 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1137 'uploader': 'AfrojackVEVO',
1138 'uploader_id': 'AfrojackVEVO',
1139 'upload_date': '20131011',
1143 'youtube_include_dash_manifest': True,
1144 'format': '141/bestaudio[ext=m4a]',
1147 # Age-gate videos. See https://github.com/yt-dlp/yt-dlp/pull/575#issuecomment-888837000
1149 'note': 'Embed allowed age-gate video',
1150 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1152 'id': 'HtVdAasjOgU',
1154 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1155 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1157 'uploader': 'The Witcher',
1158 'uploader_id': 'WitcherGame',
1159 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1160 'upload_date': '20140605',
1165 'note': 'Age-gate video with embed allowed in public site',
1166 'url': 'https://youtube.com/watch?v=HsUATh_Nc2U',
1168 'id': 'HsUATh_Nc2U',
1170 'title': 'Godzilla 2 (Official Video)',
1171 'description': 'md5:bf77e03fcae5529475e500129b05668a',
1172 'upload_date': '20200408',
1173 'uploader_id': 'FlyingKitty900',
1174 'uploader': 'FlyingKitty',
1179 'note': 'Age-gate video embedable only with clientScreen=EMBED',
1180 'url': 'https://youtube.com/watch?v=Tq92D6wQ1mg',
1182 'id': 'Tq92D6wQ1mg',
1183 'title': '[MMD] Adios - EVERGLOW [+Motion DL]',
1184 'ext': 'mp4','upload_date': '20191227',
1185 'uploader_id': 'UC1yoRdFoFJaCY-AGfD9W0wQ',
1186 'uploader': 'Projekt Melody',
1187 'description': 'md5:17eccca93a786d51bc67646756894066',
1192 'note': 'Non-Agegated non-embeddable video',
1193 'url': 'https://youtube.com/watch?v=MeJVWBSsPAY',
1195 'id': 'MeJVWBSsPAY',
1197 'title': 'OOMPH! - Such Mich Find Mich (Lyrics)',
1198 'uploader': 'Herr Lurik',
1199 'uploader_id': 'st3in234',
1200 'description': 'Fan Video. Music & Lyrics by OOMPH!.',
1201 'upload_date': '20130730',
1205 'note': 'Non-bypassable age-gated video',
1206 'url': 'https://youtube.com/watch?v=Cr381pDsSsA',
1207 'only_matching': True,
1209 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1210 # YouTube Red ad is not captured for creator
1212 'url': '__2ABJjxzNo',
1214 'id': '__2ABJjxzNo',
1217 'upload_date': '20100430',
1218 'uploader_id': 'deadmau5',
1219 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1220 'creator': 'deadmau5',
1221 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1222 'uploader': 'deadmau5',
1223 'title': 'Deadmau5 - Some Chords (HD)',
1224 'alt_title': 'Some Chords',
1226 'expected_warnings': [
1227 'DASH manifest missing',
1230 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1232 'url': 'lqQg6PlCWgI',
1234 'id': 'lqQg6PlCWgI',
1237 'upload_date': '20150827',
1238 'uploader_id': 'olympic',
1239 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1240 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1241 'uploader': 'Olympics',
1242 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1245 'skip_download': 'requires avconv',
1250 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1252 'id': '_b-2C3KPAM0',
1254 'stretched_ratio': 16 / 9.,
1256 'upload_date': '20110310',
1257 'uploader_id': 'AllenMeow',
1258 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1259 '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',
1261 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1264 # url_encoded_fmt_stream_map is empty string
1266 'url': 'qEJwOuvDf7I',
1268 'id': 'qEJwOuvDf7I',
1270 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1272 'upload_date': '20150404',
1273 'uploader_id': 'spbelect',
1274 'uploader': 'Наблюдатели Петербурга',
1277 'skip_download': 'requires avconv',
1279 'skip': 'This live event has ended.',
1281 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1283 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1285 'id': 'FIl7x6_3R5Y',
1287 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1288 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1290 'upload_date': '20150625',
1291 'uploader_id': 'dorappi2000',
1292 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1293 'uploader': 'dorappi2000',
1294 'formats': 'mincount:31',
1296 'skip': 'not actual anymore',
1298 # DASH manifest with segment_list
1300 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1301 'md5': '8ce563a1d667b599d21064e982ab9e31',
1303 'id': 'CsmdDsKjzN8',
1305 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1306 'uploader': 'Airtek',
1307 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1308 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1309 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1312 'youtube_include_dash_manifest': True,
1313 'format': '135', # bestvideo
1315 'skip': 'This live event has ended.',
1318 # Multifeed videos (multiple cameras), URL is for Main Camera
1319 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1321 'id': 'jvGDaLqkpTg',
1322 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1323 'description': 'md5:e03b909557865076822aa169218d6a5d',
1327 'id': 'jvGDaLqkpTg',
1329 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1330 'description': 'md5:e03b909557865076822aa169218d6a5d',
1332 'upload_date': '20161111',
1333 'uploader': 'Team PGP',
1334 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1335 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1339 'id': '3AKt1R1aDnw',
1341 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1342 'description': 'md5:e03b909557865076822aa169218d6a5d',
1344 'upload_date': '20161111',
1345 'uploader': 'Team PGP',
1346 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1347 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1351 'id': 'RtAMM00gpVc',
1353 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1354 'description': 'md5:e03b909557865076822aa169218d6a5d',
1356 'upload_date': '20161111',
1357 'uploader': 'Team PGP',
1358 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1359 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1363 'id': '6N2fdlP3C5U',
1365 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1366 'description': 'md5:e03b909557865076822aa169218d6a5d',
1368 'upload_date': '20161111',
1369 'uploader': 'Team PGP',
1370 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1371 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1375 'skip_download': True,
1377 'skip': 'Not multifeed anymore',
1380 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1381 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1383 'id': 'gVfLd0zydlo',
1384 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1386 'playlist_count': 2,
1387 'skip': 'Not multifeed anymore',
1390 'url': 'https://vid.plus/FlRa-iH7PGw',
1391 'only_matching': True,
1394 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1395 'only_matching': True,
1398 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1399 # Also tests cut-off URL expansion in video description (see
1400 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1401 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1402 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1404 'id': 'lsguqyKfVQg',
1406 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1407 'alt_title': 'Dark Walk',
1408 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1410 'upload_date': '20151119',
1411 'uploader_id': 'IronSoulElf',
1412 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1413 'uploader': 'IronSoulElf',
1414 'creator': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1415 'track': 'Dark Walk',
1416 'artist': 'Todd Haberman;\nDaniel Law Heath and Aaron Kaplan',
1417 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1420 'skip_download': True,
1424 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1425 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1426 'only_matching': True,
1429 # Video with yt:stretch=17:0
1430 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1432 'id': 'Q39EVAstoRM',
1434 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1435 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1436 'upload_date': '20151107',
1437 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1438 'uploader': 'CH GAMER DROID',
1441 'skip_download': True,
1443 'skip': 'This video does not exist.',
1446 # Video with incomplete 'yt:stretch=16:'
1447 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1448 'only_matching': True,
1451 # Video licensed under Creative Commons
1452 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1454 'id': 'M4gD1WSo5mA',
1456 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1457 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1459 'upload_date': '20150127',
1460 'uploader_id': 'BerkmanCenter',
1461 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1462 'uploader': 'The Berkman Klein Center for Internet & Society',
1463 'license': 'Creative Commons Attribution license (reuse allowed)',
1466 'skip_download': True,
1470 # Channel-like uploader_url
1471 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1473 'id': 'eQcmzGIKrzg',
1475 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1476 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1478 'upload_date': '20151119',
1479 'uploader': 'Bernie Sanders',
1480 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1481 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1482 'license': 'Creative Commons Attribution license (reuse allowed)',
1485 'skip_download': True,
1489 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1490 'only_matching': True,
1493 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1494 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1495 'only_matching': True,
1498 # Rental video preview
1499 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1501 'id': 'uGpuVWrhIzE',
1503 'title': 'Piku - Trailer',
1504 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1505 'upload_date': '20150811',
1506 'uploader': 'FlixMatrix',
1507 'uploader_id': 'FlixMatrixKaravan',
1508 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1509 'license': 'Standard YouTube License',
1512 'skip_download': True,
1514 'skip': 'This video is not available.',
1517 # YouTube Red video with episode data
1518 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1520 'id': 'iqKdEhx-dD4',
1522 'title': 'Isolation - Mind Field (Ep 1)',
1523 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1525 'upload_date': '20170118',
1526 'uploader': 'Vsauce',
1527 'uploader_id': 'Vsauce',
1528 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1529 'series': 'Mind Field',
1531 'episode_number': 1,
1534 'skip_download': True,
1536 'expected_warnings': [
1537 'Skipping DASH manifest',
1541 # The following content has been identified by the YouTube community
1542 # as inappropriate or offensive to some audiences.
1543 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1545 'id': '6SJNVb0GnPI',
1547 'title': 'Race Differences in Intelligence',
1548 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1550 'upload_date': '20140124',
1551 'uploader': 'New Century Foundation',
1552 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1553 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1556 'skip_download': True,
1558 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1562 'url': '1t24XAntNCY',
1563 'only_matching': True,
1566 # geo restricted to JP
1567 'url': 'sJL6WA-aGkQ',
1568 'only_matching': True,
1571 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1572 'only_matching': True,
1575 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1576 'only_matching': True,
1579 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1580 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1581 'only_matching': True,
1585 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1586 'only_matching': True,
1589 # Video with unsupported adaptive stream type formats
1590 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1592 'id': 'Z4Vy8R84T1U',
1594 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1595 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1597 'upload_date': '20130923',
1598 'uploader': 'Amelia Putri Harwita',
1599 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1600 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1601 'formats': 'maxcount:10',
1604 'skip_download': True,
1605 'youtube_include_dash_manifest': False,
1607 'skip': 'not actual anymore',
1610 # Youtube Music Auto-generated description
1611 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1613 'id': 'MgNrAu2pzNs',
1615 'title': 'Voyeur Girl',
1616 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1617 'upload_date': '20190312',
1618 'uploader': 'Stephen - Topic',
1619 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1620 'artist': 'Stephen',
1621 'track': 'Voyeur Girl',
1622 'album': 'it\'s too much love to know my dear',
1623 'release_date': '20190313',
1624 'release_year': 2019,
1627 'skip_download': True,
1631 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1632 'only_matching': True,
1635 # invalid -> valid video id redirection
1636 'url': 'DJztXj2GPfl',
1638 'id': 'DJztXj2GPfk',
1640 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1641 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1642 'upload_date': '20090125',
1643 'uploader': 'Prochorowka',
1644 'uploader_id': 'Prochorowka',
1645 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1646 'artist': 'Panjabi MC',
1647 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1648 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1651 'skip_download': True,
1653 'skip': 'Video unavailable',
1656 # empty description results in an empty string
1657 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1659 'id': 'x41yOUIvK2k',
1661 'title': 'IMG 3456',
1663 'upload_date': '20170613',
1664 'uploader_id': 'ElevageOrVert',
1665 'uploader': 'ElevageOrVert',
1668 'skip_download': True,
1672 # with '};' inside yt initial data (see [1])
1673 # see [2] for an example with '};' inside ytInitialPlayerResponse
1674 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1675 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1676 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1678 'id': 'CHqg6qOn4no',
1680 'title': 'Part 77 Sort a list of simple types in c#',
1681 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1682 'upload_date': '20130831',
1683 'uploader_id': 'kudvenkat',
1684 'uploader': 'kudvenkat',
1687 'skip_download': True,
1691 # another example of '};' in ytInitialData
1692 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1693 'only_matching': True,
1696 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1697 'only_matching': True,
1700 # https://github.com/ytdl-org/youtube-dl/pull/28094
1701 'url': 'OtqTfy26tG0',
1703 'id': 'OtqTfy26tG0',
1705 'title': 'Burn Out',
1706 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1707 'upload_date': '20141120',
1708 'uploader': 'The Cinematic Orchestra - Topic',
1709 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1710 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1711 'artist': 'The Cinematic Orchestra',
1712 'track': 'Burn Out',
1713 'album': 'Every Day',
1714 'release_data': None,
1715 'release_year': None,
1718 'skip_download': True,
1722 # controversial video, only works with bpctr when authenticated with cookies
1723 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1724 'only_matching': True,
1727 # controversial video, requires bpctr/contentCheckOk
1728 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1730 'id': 'SZJvDhaSDnc',
1732 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1733 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1734 'uploader': 'CBS This Morning',
1735 'uploader_id': 'CBSThisMorning',
1736 'upload_date': '20140716',
1737 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
1741 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1742 'url': 'cBvYw8_A0vQ',
1744 'id': 'cBvYw8_A0vQ',
1746 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1747 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1748 'upload_date': '20201120',
1749 'uploader': 'Walk around Japan',
1750 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1751 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1754 'skip_download': True,
1757 # Has multiple audio streams
1758 'url': 'WaOKSUlf4TM',
1759 'only_matching': True
1761 # Requires Premium: has format 141 when requested using YTM url
1762 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1763 'only_matching': True
1765 # multiple subtitles with same lang_code
1766 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1767 'only_matching': True,
1769 # Force use android client fallback
1770 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1772 'id': 'YOelRv7fMxY',
1773 'title': 'DIGGING A SECRET TUNNEL Part 1',
1775 'upload_date': '20210624',
1776 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1777 'uploader': 'colinfurze',
1778 'uploader_id': 'colinfurze',
1779 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
1780 'description': 'md5:b5096f56af7ccd7a555c84db81738b22'
1783 'format': '17', # 3gp format available on android
1784 'extractor_args': {'youtube': {'player_client': ['android']}
},
1788 # Skip download of additional client configs (remix client config in this case)
1789 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1790 'only_matching': True,
1792 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
1798 def suitable(cls
, url
):
1799 # Hack for lazy extractors until more generic solution is implemented
1801 from .youtube
import parse_qs
1803 if qs
.get('list', [None])[0]:
1805 return super(YoutubeIE
, cls
).suitable(url
)
1807 def __init__(self
, *args
, **kwargs
):
1808 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1809 self
._code
_cache
= {}
1810 self
._player
_cache
= {}
1812 def _extract_player_url(self
, ytcfg
=None, webpage
=None):
1813 player_url
= try_get(ytcfg
, (lambda x
: x
['PLAYER_JS_URL']), str)
1814 if not player_url
and webpage
:
1815 player_url
= self
._search
_regex
(
1816 r
'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1817 webpage
, 'player URL', fatal
=False)
1820 if player_url
.startswith('//'):
1821 player_url
= 'https:' + player_url
1822 elif not re
.match(r
'https?://', player_url
):
1823 player_url
= compat_urlparse
.urljoin(
1824 'https://www.youtube.com', player_url
)
1827 def _signature_cache_id(self
, example_sig
):
1828 """ Return a string representation of a signature """
1829 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1832 def _extract_player_info(cls
, player_url
):
1833 for player_re
in cls
._PLAYER
_INFO
_RE
:
1834 id_m
= re
.search(player_re
, player_url
)
1838 raise ExtractorError('Cannot identify player %r' % player_url
)
1839 return id_m
.group('id')
1841 def _load_player(self
, video_id
, player_url
, fatal
=True) -> bool:
1842 player_id
= self
._extract
_player
_info
(player_url
)
1843 if player_id
not in self
._code
_cache
:
1844 self
._code
_cache
[player_id
] = self
._download
_webpage
(
1845 player_url
, video_id
, fatal
=fatal
,
1846 note
='Downloading player ' + player_id
,
1847 errnote
='Download of %s failed' % player_url
)
1848 return player_id
in self
._code
_cache
1850 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1851 player_id
= self
._extract
_player
_info
(player_url
)
1853 # Read from filesystem cache
1854 func_id
= 'js_%s_%s' % (
1855 player_id
, self
._signature
_cache
_id
(example_sig
))
1856 assert os
.path
.basename(func_id
) == func_id
1858 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1859 if cache_spec
is not None:
1860 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1862 if self
._load
_player
(video_id
, player_url
):
1863 code
= self
._code
_cache
[player_id
]
1864 res
= self
._parse
_sig
_js
(code
)
1866 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1867 cache_res
= res(test_string
)
1868 cache_spec
= [ord(c
) for c
in cache_res
]
1870 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1873 def _print_sig_code(self
, func
, example_sig
):
1874 def gen_sig_code(idxs
):
1875 def _genslice(start
, end
, step
):
1876 starts
= '' if start
== 0 else str(start
)
1877 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1878 steps
= '' if step
== 1 else (':%d' % step
)
1879 return 's[%s%s%s]' % (starts
, ends
, steps
)
1882 # Quelch pyflakes warnings - start will be set when step is set
1883 start
= '(Never used)'
1884 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1885 if step
is not None:
1886 if i
- prev
== step
:
1888 yield _genslice(start
, prev
, step
)
1891 if i
- prev
in [-1, 1]:
1896 yield 's[%d]' % prev
1900 yield _genslice(start
, i
, step
)
1902 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1903 cache_res
= func(test_string
)
1904 cache_spec
= [ord(c
) for c
in cache_res
]
1905 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1906 signature_id_tuple
= '(%s)' % (
1907 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1908 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1909 ' return %s\n') % (signature_id_tuple
, expr_code
)
1910 self
.to_screen('Extracted signature function:\n' + code
)
1912 def _parse_sig_js(self
, jscode
):
1913 funcname
= self
._search
_regex
(
1914 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1915 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1916 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
1917 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
1918 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}\(a,\d+\)',
1919 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\(\s*""\s*\)',
1920 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1922 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1923 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1924 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1925 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1926 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1927 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1928 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1929 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1930 jscode, 'Initial JS player signature function name
', group='sig
')
1932 jsi = JSInterpreter(jscode)
1933 initial_function = jsi.extract_function(funcname)
1934 return lambda s: initial_function([s])
1936 def _decrypt_signature(self, s, video_id, player_url):
1937 """Turn the encrypted s field into a working signature"""
1939 if player_url is None:
1940 raise ExtractorError('Cannot decrypt signature without player_url
')
1943 player_id = (player_url, self._signature_cache_id(s))
1944 if player_id not in self._player_cache:
1945 func = self._extract_signature_function(
1946 video_id, player_url, s
1948 self._player_cache[player_id] = func
1949 func = self._player_cache[player_id]
1950 if self.get_param('youtube_print_sig_code
'):
1951 self._print_sig_code(func, s)
1953 except Exception as e:
1954 tb = traceback.format_exc()
1955 raise ExtractorError(
1956 'Signature extraction failed
: ' + tb, cause=e)
1958 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
1960 Extract signatureTimestamp (sts)
1961 Required to tell API what sig/player version is in use.
1964 if isinstance(ytcfg, dict):
1965 sts = int_or_none(ytcfg.get('STS
'))
1968 # Attempt to extract from player
1969 if player_url is None:
1970 error_msg = 'Cannot extract signature timestamp without player_url
.'
1972 raise ExtractorError(error_msg)
1973 self.report_warning(error_msg)
1975 if self._load_player(video_id, player_url, fatal=fatal):
1976 player_id = self._extract_player_info(player_url)
1977 code = self._code_cache[player_id]
1978 sts = int_or_none(self._search_regex(
1979 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
1980 'JS player signature timestamp
', group='sts
', fatal=fatal))
1983 def _mark_watched(self, video_id, player_responses):
1984 playback_url = traverse_obj(
1985 player_responses, (..., 'playbackTracking
', 'videostatsPlaybackUrl
', 'baseUrl
'),
1986 expected_type=url_or_none, get_all=False)
1987 if not playback_url:
1988 self.report_warning('Unable to mark watched
')
1990 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1991 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1993 # cpn generation algorithm is reverse engineered from base.js.
1994 # In fact it works even with dummy cpn.
1995 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
1996 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
2002 playback_url = compat_urlparse.urlunparse(
2003 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
2005 self._download_webpage(
2006 playback_url, video_id, 'Marking watched
',
2007 'Unable to mark watched
', fatal=False)
2010 def _extract_urls(webpage):
2011 # Embedded YouTube player
2013 unescapeHTML(mobj.group('url
'))
2014 for mobj in re.finditer(r'''(?x)
2024 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
2025 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
2028 # lazyYT YouTube embed
2029 entries.extend(list(map(
2031 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
2033 # Wordpress "YouTube Video Importer
" plugin
2034 matches = re.findall(r'''(?x)<div[^>]+
2035 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
2036 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
2037 entries.extend(m[-1] for m in matches)
2042 def _extract_url(webpage):
2043 urls = YoutubeIE._extract_urls(webpage)
2044 return urls[0] if urls else None
2047 def extract_id(cls, url):
2048 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
2050 raise ExtractorError('Invalid URL: %s' % url)
2051 video_id = mobj.group(2)
2054 def _extract_chapters_from_json(self, data, duration):
2055 chapter_list = traverse_obj(
2057 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
2058 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
2059 ), expected_type=list)
2061 return self._extract_chapters(
2063 chapter_time=lambda chapter: float_or_none(
2064 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
2065 chapter_title=lambda chapter: traverse_obj(
2066 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
2069 def _extract_chapters_from_engagement_panel(self, data, duration):
2070 content_list = traverse_obj(
2072 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
2073 expected_type=list, default=[])
2074 chapter_time = lambda chapter: parse_duration(self._get_text(chapter, 'timeDescription'))
2075 chapter_title = lambda chapter: self._get_text(chapter, 'title')
2079 self._extract_chapters(
2080 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
2081 chapter_time, chapter_title, duration)
2082 for contents in content_list
2085 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
2087 last_chapter = {'start_time': 0}
2088 for idx, chapter in enumerate(chapter_list or []):
2089 title = chapter_title(chapter)
2090 start_time = chapter_time(chapter)
2091 if start_time is None:
2093 last_chapter['end_time'] = start_time
2094 if start_time < last_chapter['start_time']:
2097 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
2099 self.report_warning(f'Invalid start time for chapter "{title}"')
2101 last_chapter = {'start_time': start_time, 'title': title}
2102 chapters.append(last_chapter)
2103 last_chapter['end_time'] = duration
2106 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
2107 return self._parse_json(self._search_regex(
2108 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
2109 regex), webpage, name, default='{}'), video_id, fatal=False)
2112 def parse_time_text(time_text):
2114 Parse the comment time text
2115 time_text is in the format 'X units ago (edited)'
2117 time_text_split = time_text.split(' ')
2118 if len(time_text_split) >= 3:
2120 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
2124 def _extract_comment(self, comment_renderer, parent=None):
2125 comment_id = comment_renderer.get('commentId')
2129 text = self._get_text(comment_renderer, 'contentText')
2131 # note: timestamp is an estimate calculated from the current time and time_text
2132 time_text = self._get_text(comment_renderer, 'publishedTimeText') or ''
2133 time_text_dt = self.parse_time_text(time_text)
2134 if isinstance(time_text_dt, datetime.datetime):
2135 timestamp = calendar.timegm(time_text_dt.timetuple())
2136 author = self._get_text(comment_renderer, 'authorText')
2137 author_id = try_get(comment_renderer,
2138 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2140 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2141 lambda x: x['likeCount']), compat_str)) or 0
2142 author_thumbnail = try_get(comment_renderer,
2143 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2145 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2146 is_favorited = 'creatorHeart' in (try_get(
2147 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2151 'timestamp': timestamp,
2152 'time_text': time_text,
2153 'like_count': votes,
2154 'is_favorited': is_favorited,
2156 'author_id': author_id,
2157 'author_thumbnail': author_thumbnail,
2158 'author_is_uploader': author_is_uploader,
2159 'parent': parent or 'root'
2162 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
2163 ytcfg, video_id, parent=None, comment_counts=None):
2165 def extract_header(contents):
2167 _continuation = None
2168 for content in contents:
2169 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
2170 expected_comment_count = parse_count(self._get_text(
2171 comments_header_renderer, 'countText', 'commentsCount', max_runs=1))
2173 if expected_comment_count:
2174 comment_counts[1] = expected_comment_count
2175 self.to_screen('Downloading ~%d comments' % expected_comment_count)
2176 _total_comments = comment_counts[1]
2177 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2178 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2180 sort_menu_item = try_get(
2181 comments_header_renderer,
2182 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2183 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2185 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2186 if not _continuation:
2189 sort_text = sort_menu_item.get('title')
2190 if isinstance(sort_text, compat_str):
2191 sort_text = sort_text.lower()
2193 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2194 self.to_screen('Sorting comments by %s' % sort_text)
2196 return _total_comments, _continuation
2198 def extract_thread(contents):
2200 comment_counts[2] = 0
2201 for content in contents:
2202 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2203 comment_renderer = try_get(
2204 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2205 content, (lambda x: x['commentRenderer'], dict))
2207 if not comment_renderer:
2209 comment = self._extract_comment(comment_renderer, parent)
2212 comment_counts[0] += 1
2214 # Attempt to get the replies
2215 comment_replies_renderer = try_get(
2216 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2218 if comment_replies_renderer:
2219 comment_counts[2] += 1
2220 comment_entries_iter = self._comment_entries(
2221 comment_replies_renderer, identity_token, account_syncid, ytcfg,
2222 video_id, parent=comment.get('id'), comment_counts=comment_counts)
2224 for reply_comment in comment_entries_iter:
2227 # YouTube comments have a max depth of 2
2228 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2229 if max_depth == 1 and parent:
2231 if not comment_counts:
2232 # comment so far, est. total comments, current comment thread #
2233 comment_counts = [0, 0, 0]
2235 continuation = self._extract_continuation(root_continuation_data)
2236 if continuation and len(continuation['continuation']) < 27:
2237 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2238 continuation_token = self._generate_comment_continuation(video_id)
2239 continuation = self._build_api_continuation_query(continuation_token, None)
2242 is_first_continuation = parent is None
2244 for page_num in itertools.count(0):
2245 if not continuation:
2247 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
2248 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2250 if is_first_continuation:
2251 note_prefix = 'Downloading comment section API JSON'
2253 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2254 comment_counts[2], comment_prog_str)
2256 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2257 ' ' if parent else '', ' replies' if parent else '',
2258 page_num, comment_prog_str)
2260 response = self._extract_response(
2261 item_id=None, query=continuation,
2262 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2263 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
2266 visitor_data = try_get(
2268 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2269 compat_str) or visitor_data
2271 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
2274 if isinstance(continuation_contents, list):
2275 for continuation_section in continuation_contents:
2276 if not isinstance(continuation_section, dict):
2278 continuation_items = try_get(
2279 continuation_section,
2280 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2281 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2283 if is_first_continuation:
2284 total_comments, continuation = extract_header(continuation_items)
2286 yield total_comments
2287 is_first_continuation = False
2292 for count, entry in enumerate(extract_thread(continuation_items)):
2294 continuation = self._extract_continuation({'contents': continuation_items})
2296 # Sometimes YouTube provides a continuation without any comments
2297 # In most cases we end up just downloading these with very little comments to come.
2300 self.report_warning('No comments received - assuming end of comments')
2304 # Deprecated response structure
2305 elif isinstance(continuation_contents, dict):
2306 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2307 for key, continuation_renderer in continuation_contents.items():
2308 if key not in known_continuation_renderers:
2310 if not isinstance(continuation_renderer, dict):
2312 if is_first_continuation:
2313 header_continuation_items = [continuation_renderer.get('header') or {}]
2314 total_comments, continuation = extract_header(header_continuation_items)
2316 yield total_comments
2317 is_first_continuation = False
2321 # Sometimes YouTube provides a continuation without any comments
2322 # In most cases we end up just downloading these with very little comments to come.
2324 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2326 continuation = self._extract_continuation(continuation_renderer)
2329 self.report_warning('No comments received - assuming end of comments')
2334 def _generate_comment_continuation(video_id):
2336 Generates initial comment section continuation token from given video id
2338 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2339 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2340 new_continuation_intlist = list(itertools.chain.from_iterable(
2341 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2342 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2344 def _extract_comments(self, ytcfg, video_id, contents, webpage):
2345 """Entry for comment extraction"""
2346 def _real_comment_extract(contents):
2347 if isinstance(contents, list):
2348 for entry in contents:
2349 for key, renderer in entry.items():
2350 if key not in known_entry_comment_renderers:
2352 yield from self._comment_entries(
2353 renderer, video_id=video_id, ytcfg=ytcfg,
2354 identity_token=self._extract_identity_token(webpage, item_id=video_id),
2355 account_syncid=self._extract_account_syncid(ytcfg))
2358 known_entry_comment_renderers = ('itemSectionRenderer',)
2360 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf')
2361 # Force English regardless of account setting to prevent parsing issues
2362 # See: https://github.com/yt-dlp/yt-dlp/issues/532
2363 ytcfg = copy.deepcopy(ytcfg)
2365 ytcfg, ('INNERTUBE_CONTEXT', 'client'), expected_type=dict, default={})['hl'] = 'en'
2367 for comment in _real_comment_extract(contents):
2368 if len(comments) >= max_comments:
2370 if isinstance(comment, int):
2371 estimated_total = comment
2373 comments.append(comment)
2374 except KeyboardInterrupt:
2375 self.to_screen('Interrupted by user')
2376 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
2378 'comments': comments,
2379 'comment_count': len(comments),
2383 def _generate_player_context(sts=None):
2385 'html5Preference': 'HTML5_PREF_WANTS',
2388 context['signatureTimestamp'] = sts
2390 'playbackContext': {
2391 'contentPlaybackContext': context
2393 'contentCheckOk': True,
2397 def _is_agegated(self, player_response):
2398 reasons = traverse_obj(player_response, ('playabilityStatus', ('status', 'reason')), default=[])
2399 for reason in reasons:
2400 if reason in self._AGE_GATE_REASONS + self._AGE_GATE_STATUS_REASONS:
2402 if traverse_obj(player_response, ('playabilityStatus', 'desktopLegacyAgeGateReason')) is not None:
2406 def _extract_player_response(self, client, video_id, master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr):
2408 session_index = self._extract_session_index(player_ytcfg, master_ytcfg)
2409 syncid = self._extract_account_syncid(player_ytcfg, master_ytcfg, initial_pr)
2410 sts = self._extract_signature_timestamp(video_id, player_url, master_ytcfg, fatal=False)
2411 headers = self.generate_api_headers(
2412 player_ytcfg, identity_token, syncid,
2413 default_client=client, session_index=session_index)
2415 yt_query = {'videoId': video_id}
2416 yt_query.update(self._generate_player_context(sts))
2417 return self._extract_response(
2418 item_id=video_id, ep='player', query=yt_query,
2419 ytcfg=player_ytcfg, headers=headers, fatal=False,
2420 default_client=client,
2421 note='Downloading %s player API JSON' % client.replace('_', ' ').strip()
2424 def _get_requested_clients(self, url, smuggled_data):
2425 requested_clients = []
2426 allowed_clients = sorted(
2427 [client for client in INNERTUBE_CLIENTS.keys() if client[:1] != '_'],
2428 key=lambda client: INNERTUBE_CLIENTS[client]['priority'], reverse=True)
2429 for client in self._configuration_arg('player_client'):
2430 if client in allowed_clients:
2431 requested_clients.append(client)
2432 elif client == 'all':
2433 requested_clients.extend(allowed_clients)
2435 self.report_warning(f'Skipping unsupported client {client}')
2436 if not requested_clients:
2437 requested_clients = ['android', 'web']
2439 if smuggled_data.get('is_music_url') or self.is_music_url(url):
2440 requested_clients.extend(
2441 f'{client}_music' for client in requested_clients if not client.endswith('_music'))
2443 return orderedSet(requested_clients)
2445 def _extract_player_ytcfg(self, client, video_id):
2447 'web_music': 'https://music.youtube.com',
2448 'web_embedded': f'https://www.youtube.com/embed/{video_id}?html5=1'
2452 webpage = self._download_webpage(url, video_id, fatal=False, note=f'Downloading {client} config')
2453 return self.extract_ytcfg(video_id, webpage) or {}
2455 def _extract_player_responses(self, clients, video_id, webpage, master_ytcfg, player_url, identity_token):
2458 initial_pr = self._extract_yt_initial_variable(
2459 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2460 video_id, 'initial player response')
2462 original_clients = clients
2463 clients = clients[::-1]
2465 client = clients.pop()
2466 player_ytcfg = master_ytcfg if client == 'web' else {}
2467 if 'configs' not in self._configuration_arg('player_skip'):
2468 player_ytcfg = self._extract_player_ytcfg(client, video_id) or player_ytcfg
2471 initial_pr if client == 'web' and initial_pr
2472 else self._extract_player_response(
2473 client, video_id, player_ytcfg or master_ytcfg, player_ytcfg, identity_token, player_url, initial_pr))
2477 if self._is_agegated(pr):
2478 client = f'{client}_agegate'
2479 if client in INNERTUBE_CLIENTS and client not in original_clients:
2480 clients.append(client)
2482 # Android player_response does not have microFormats which are needed for
2483 # extraction of some data. So we return the initial_pr with formats
2484 # stripped out even if not requested by the user
2485 # See: https://github.com/yt-dlp/yt-dlp/issues/501
2486 if initial_pr and 'web' not in original_clients:
2487 initial_pr['streamingData'] = None
2490 def _extract_formats(self, streaming_data, video_id, player_url, is_live):
2491 itags, stream_ids = [], []
2492 itag_qualities, res_qualities = {}, {}
2494 # Normally tiny is the smallest video-only formats. But
2495 # audio-only formats with unknown quality may get tagged as tiny
2497 'audio_quality_ultralow', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2498 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2500 streaming_formats = traverse_obj(streaming_data, (..., ('formats', 'adaptiveFormats'), ...), default=[])
2502 for fmt in streaming_formats:
2503 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2506 itag = str_or_none(fmt.get('itag'))
2507 audio_track = fmt.get('audioTrack') or {}
2508 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2509 if stream_id in stream_ids:
2512 quality = fmt.get('quality')
2513 height = int_or_none(fmt.get('height'))
2514 if quality == 'tiny' or not quality:
2515 quality = fmt.get('audioQuality', '').lower() or quality
2516 # The 3gp format (17) in android client has a quality of "small",
2517 # but is actually worse than other formats
2522 itag_qualities[itag] = quality
2524 res_qualities[height] = quality
2525 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2526 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2527 # number of fragment that would subsequently requested with (`&sq=N`)
2528 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2531 fmt_url = fmt.get('url')
2533 sc = compat_parse_qs(fmt.get('signatureCipher'))
2534 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2535 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2536 if not (sc and fmt_url and encrypted_sig):
2540 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2541 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2542 fmt_url += '&' + sp + '=' + signature
2546 stream_ids.append(stream_id)
2548 tbr = float_or_none(
2549 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
2551 'asr': int_or_none(fmt.get('audioSampleRate')),
2552 'filesize': int_or_none(fmt.get('contentLength')),
2554 'format_note': ', '.join(filter(None, (
2555 audio_track.get('displayName'),
2556 fmt.get('qualityLabel') or quality.replace('audio_quality_', '')))),
2557 'fps': int_or_none(fmt.get('fps')),
2559 'quality': q(quality),
2562 'width': int_or_none(fmt.get('width')),
2563 'language': audio_track.get('id', '').split('.')[0],
2565 mime_mobj = re.match(
2566 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2568 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2569 dct.update(parse_codecs(mime_mobj.group(2)))
2570 no_audio = dct.get('acodec') == 'none'
2571 no_video = dct.get('vcodec') == 'none'
2576 if no_audio or no_video:
2577 dct['downloader_options'] = {
2578 # Youtube throttles chunks >~10M
2579 'http_chunk_size': 10485760,
2582 dct['container'] = dct['ext'] + '_dash'
2585 skip_manifests = self._configuration_arg('skip')
2586 get_dash = not is_live and 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True)
2587 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2589 def guess_quality(f):
2590 for val, qdict in ((f.get('format_id'), itag_qualities), (f.get('height'), res_qualities)):
2592 return q(qdict[val])
2595 for sd in streaming_data:
2596 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
2597 if hls_manifest_url:
2598 for f in self._extract_m3u8_formats(hls_manifest_url, video_id, 'mp4', fatal=False):
2599 itag = self._search_regex(
2600 r'/itag/(\d+)', f['url'], 'itag', default=None)
2604 f['format_id'] = itag
2606 f['quality'] = guess_quality(f)
2609 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2610 if dash_manifest_url:
2611 for f in self._extract_mpd_formats(dash_manifest_url, video_id, fatal=False):
2612 itag = f['format_id']
2617 f['quality'] = guess_quality(f)
2618 filesize = int_or_none(self._search_regex(
2619 r'/clen/(\d+)', f.get('fragment_base_url')
2620 or f['url'], 'file size', default=None))
2622 f['filesize'] = filesize
2625 def _real_extract(self, url):
2626 url, smuggled_data = unsmuggle_url(url, {})
2627 video_id = self._match_id(url)
2629 base_url = self.http_scheme() + '//www.youtube.com/'
2630 webpage_url = base_url + 'watch?v=' + video_id
2631 webpage = self._download_webpage(
2632 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
2634 master_ytcfg = self.extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
2635 player_url = self._extract_player_url(master_ytcfg, webpage)
2636 identity_token = self._extract_identity_token(webpage, video_id)
2638 player_responses = list(self._extract_player_responses(
2639 self._get_requested_clients(url, smuggled_data),
2640 video_id, webpage, master_ytcfg, player_url, identity_token))
2642 get_first = lambda obj, keys, **kwargs: traverse_obj(obj, (..., *variadic(keys)), **kwargs, get_all=False)
2644 playability_statuses = traverse_obj(
2645 player_responses, (..., 'playabilityStatus'), expected_type=dict, default=[])
2647 trailer_video_id = get_first(
2648 playability_statuses,
2649 ('errorScreen', 'playerLegacyDesktopYpcTrailerRenderer', 'trailerVideoId'),
2651 if trailer_video_id:
2652 return self.url_result(
2653 trailer_video_id, self.ie_key(), trailer_video_id)
2655 search_meta = ((lambda x: self._html_search_meta(x, webpage, default=None))
2656 if webpage else (lambda x: None))
2658 video_details = traverse_obj(
2659 player_responses, (..., 'videoDetails'), expected_type=dict, default=[])
2660 microformats = traverse_obj(
2661 player_responses, (..., 'microformat', 'playerMicroformatRenderer'),
2662 expected_type=dict, default=[])
2664 get_first(video_details, 'title')
2665 or self._get_text(microformats, (..., 'title'))
2666 or search_meta(['og:title', 'twitter:title', 'title']))
2667 video_description = get_first(video_details, 'shortDescription')
2669 if not smuggled_data.get('force_singlefeed', False):
2670 if not self.get_param('noplaylist'):
2671 multifeed_metadata_list = get_first(
2673 ('multicamera', 'playerLegacyMulticameraRenderer', 'metadataList'),
2675 if multifeed_metadata_list:
2678 for feed in multifeed_metadata_list.split(','):
2679 # Unquote should take place before split on comma (,) since textual
2680 # fields may contain comma as well (see
2681 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2682 feed_data = compat_parse_qs(
2683 compat_urllib_parse_unquote_plus(feed))
2685 def feed_entry(name):
2687 feed_data, lambda x: x[name][0], compat_str)
2689 feed_id = feed_entry('id')
2692 feed_title = feed_entry('title')
2695 title += ' (%s)' % feed_title
2697 '_type': 'url_transparent',
2698 'ie_key': 'Youtube',
2700 '%swatch?v=%s' % (base_url, feed_data['id'][0]),
2701 {'force_singlefeed': True}),
2704 feed_ids.append(feed_id)
2706 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2707 % (', '.join(feed_ids), video_id))
2708 return self.playlist_result(
2709 entries, video_id, video_title, video_description)
2711 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2713 live_broadcast_details = traverse_obj(microformats, (..., 'liveBroadcastDetails'))
2714 is_live = get_first(video_details, 'isLive')
2716 is_live = get_first(live_broadcast_details, 'isLiveNow')
2718 streaming_data = traverse_obj(player_responses, (..., 'streamingData'), default=[])
2719 formats = list(self._extract_formats(streaming_data, video_id, player_url, is_live))
2722 if not self.get_param('allow_unplayable_formats') and traverse_obj(streaming_data, (..., 'licenseInfos')):
2723 self.raise_no_formats(
2724 'This video is DRM protected.', expected=True)
2726 playability_statuses,
2727 ('errorScreen', 'playerErrorMessageRenderer'), expected_type=dict) or {}
2728 reason = self._get_text(pemr, 'reason') or get_first(playability_statuses, 'reason')
2729 subreason = clean_html(self._get_text(pemr, 'subreason') or '')
2731 if subreason == 'The uploader has not made this video available in your country.':
2732 countries = get_first(microformats, 'availableCountries')
2734 regions_allowed = search_meta('regionsAllowed')
2735 countries = regions_allowed.split(',') if regions_allowed else None
2736 self.raise_geo_restricted(subreason, countries, metadata_available=True)
2737 reason += f'. {subreason}'
2739 self.raise_no_formats(reason, expected=True)
2742 if '&c=WEB&' in f['url'] and '&ratebypass=yes&' not in f['url']: # throttled
2743 f['source_preference'] = -10
2744 note = f.get('format_note')
2745 f['format_note'] = f'{note} (throttled)' if note else '(throttled)'
2747 # Source is given priority since formats that throttle are given lower source_preference
2748 # When throttling issue is fully fixed, remove this
2749 self._sort_formats(formats, ('quality', 'height', 'fps', 'source'))
2751 keywords = get_first(video_details, 'keywords', expected_type=list) or []
2752 if not keywords and webpage:
2754 unescapeHTML(m.group('content'))
2755 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2756 for keyword in keywords:
2757 if keyword.startswith('yt:stretch='):
2758 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2760 # NB: float is intentional for forcing float division
2761 w, h = (float(v) for v in mobj.groups())
2765 if f.get('vcodec') != 'none':
2766 f['stretched_ratio'] = ratio
2770 thumbnail_dicts = traverse_obj(
2771 (video_details, microformats), (..., ..., 'thumbnail', 'thumbnails', ...),
2772 expected_type=dict, default=[])
2773 for thumbnail in thumbnail_dicts:
2774 thumbnail_url = thumbnail.get('url')
2775 if not thumbnail_url:
2777 # Sometimes youtube gives a wrong thumbnail URL. See:
2778 # https://github.com/yt-dlp/yt-dlp/issues/233
2779 # https://github.com/ytdl-org/youtube-dl/issues/28023
2780 if 'maxresdefault' in thumbnail_url:
2781 thumbnail_url = thumbnail_url.split('?')[0]
2783 'url': thumbnail_url,
2784 'height': int_or_none(thumbnail.get('height')),
2785 'width': int_or_none(thumbnail.get('width')),
2787 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2790 'url': thumbnail_url,
2792 # The best resolution thumbnails sometimes does not appear in the webpage
2793 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
2794 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
2795 hq_thumbnail_names = ['maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3']
2796 # TODO: Test them also? - For some videos, even these don't exist
2797 guaranteed_thumbnail_names = [
2798 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
2799 'mqdefault', 'mq1', 'mq2', 'mq3',
2800 'default', '1', '2', '3'
2802 thumbnail_names = hq_thumbnail_names + guaranteed_thumbnail_names
2803 n_thumbnail_names = len(thumbnail_names)
2806 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
2807 video_id=video_id, name=name, ext=ext,
2808 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
2809 '_test_url': name in hq_thumbnail_names,
2810 } for name in thumbnail_names for ext in ('webp', 'jpg'))
2811 for thumb in thumbnails:
2812 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
2813 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
2814 self._remove_duplicate_formats(thumbnails)
2816 category = get_first(microformats, 'category') or search_meta('genre')
2817 channel_id = str_or_none(
2818 get_first(video_details, 'channelId')
2819 or get_first(microformats, 'externalChannelId')
2820 or search_meta('channelId'))
2821 duration = int_or_none(
2822 get_first(video_details, 'lengthSeconds')
2823 or get_first(microformats, 'lengthSeconds')
2824 or parse_duration(search_meta('duration'))) or None
2825 owner_profile_url = get_first(microformats, 'ownerProfileUrl')
2827 live_content = get_first(video_details, 'isLiveContent')
2828 is_upcoming = get_first(video_details, 'isUpcoming')
2830 if is_upcoming or live_content is False:
2832 if is_upcoming is None and (live_content or is_live):
2834 live_starttime = parse_iso8601(get_first(live_broadcast_details, 'startTimestamp'))
2835 live_endtime = parse_iso8601(get_first(live_broadcast_details, 'endTimestamp'))
2836 if not duration and live_endtime and live_starttime:
2837 duration = live_endtime - live_starttime
2841 'title': self._live_title(video_title) if is_live else video_title,
2843 'thumbnails': thumbnails,
2844 'description': video_description,
2845 'upload_date': unified_strdate(
2846 get_first(microformats, 'uploadDate')
2847 or search_meta('uploadDate')),
2848 'uploader': get_first(video_details, 'author'),
2849 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2850 'uploader_url': owner_profile_url,
2851 'channel_id': channel_id,
2852 'channel_url': f'https://www.youtube.com/channel/{channel_id}' if channel_id else None,
2853 'duration': duration,
2854 'view_count': int_or_none(
2855 get_first((video_details, microformats), (..., 'viewCount'))
2856 or search_meta('interactionCount')),
2857 'average_rating': float_or_none(get_first(video_details, 'averageRating')),
2858 'age_limit': 18 if (
2859 get_first(microformats, 'isFamilySafe') is False
2860 or search_meta('isFamilyFriendly') == 'false'
2861 or search_meta('og:restrictions:age') == '18+') else 0,
2862 'webpage_url': webpage_url,
2863 'categories': [category] if category else None,
2865 'playable_in_embed': get_first(playability_statuses, 'playableInEmbed'),
2867 'was_live': (False if is_live or is_upcoming or live_content is False
2868 else None if is_live is None or is_upcoming is None
2870 'live_status': 'is_upcoming' if is_upcoming else None, # rest will be set by YoutubeDL
2871 'release_timestamp': live_starttime,
2874 pctr = traverse_obj(player_responses, (..., 'captions', 'playerCaptionsTracklistRenderer'), expected_type=dict)
2875 # Converted into dicts to remove duplicates
2877 sub.get('baseUrl'): sub
2878 for sub in traverse_obj(pctr, (..., 'captionTracks', ...), default=[])}
2879 translation_languages = {
2880 lang.get('languageCode'): lang.get('languageName')
2881 for lang in traverse_obj(pctr, (..., 'translationLanguages', ...), default=[])}
2884 def process_language(container, base_url, lang_code, sub_name, query):
2885 lang_subs = container.setdefault(lang_code, [])
2886 for fmt in self._SUBTITLE_FORMATS:
2892 'url': update_url_query(base_url, query),
2896 for base_url, caption_track in captions.items():
2899 if caption_track.get('kind') != 'asr':
2901 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2902 or caption_track.get('languageCode'))
2906 subtitles, base_url, lang_code,
2907 traverse_obj(caption_track, ('name', 'simpleText')),
2910 automatic_captions = {}
2911 for trans_code, trans_name in translation_languages.items():
2915 automatic_captions, base_url, trans_code,
2916 self._get_text(trans_name, max_runs=1),
2917 {'tlang': trans_code})
2918 info['automatic_captions'] = automatic_captions
2919 info['subtitles'] = subtitles
2921 parsed_url = compat_urllib_parse_urlparse(url)
2922 for component in [parsed_url.fragment, parsed_url.query]:
2923 query = compat_parse_qs(component)
2924 for k, v in query.items():
2925 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2927 if d_k not in info and k in s_ks:
2928 info[d_k] = parse_duration(query[k][0])
2930 # Youtube Music Auto-generated description
2931 if video_description:
2932 mobj = re.search(r'(?s)(?P<track>[^·\n]+)·(?P<artist>[^\n]+)\n+(?P<album>[^\n]+)(?:.+?℗\s*(?P<release_year>\d{4})(?!\d))?(?:.+?Released on\s*:\s*(?P<release_date>\d{4}-\d{2}-\d{2}))?(.+?\nArtist\s*:\s*(?P<clean_artist>[^\n]+))?.+\nAuto-generated by YouTube\.\s*$', video_description)
2934 release_year = mobj.group('release_year')
2935 release_date = mobj.group('release_date')
2937 release_date = release_date.replace('-', '')
2938 if not release_year:
2939 release_year = release_date[:4]
2941 'album': mobj.group('album'.strip()),
2942 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2943 'track': mobj.group('track').strip(),
2944 'release_date': release_date,
2945 'release_year': int_or_none(release_year),
2950 initial_data = self._extract_yt_initial_variable(
2951 webpage, self._YT_INITIAL_DATA_RE, video_id,
2953 if not initial_data:
2954 headers = self.generate_api_headers(
2955 master_ytcfg, identity_token, self._extract_account_syncid(master_ytcfg),
2956 session_index=self._extract_session_index(master_ytcfg))
2958 initial_data = self._extract_response(
2959 item_id=video_id, ep='next', fatal=False,
2960 ytcfg=master_ytcfg, headers=headers, query={'videoId': video_id},
2961 note='Downloading initial data API JSON')
2964 # This will error if there is no livechat
2965 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2966 info['subtitles']['live_chat'] = [{
2967 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2968 'video_id': video_id,
2970 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
2972 except (KeyError, IndexError, TypeError):
2976 info['chapters'] = (
2977 self._extract_chapters_from_json(initial_data, duration)
2978 or self._extract_chapters_from_engagement_panel(initial_data, duration)
2983 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2985 for content in contents:
2986 vpir = content.get('videoPrimaryInfoRenderer')
2988 stl = vpir.get('superTitleLink')
2990 stl = self._get_text(stl)
2993 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2994 info['location'] = stl
2996 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2999 'series': mobj.group(1),
3000 'season_number': int(mobj.group(2)),
3001 'episode_number': int(mobj.group(3)),
3003 for tlb in (try_get(
3005 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
3007 tbr = tlb.get('toggleButtonRenderer') or {}
3008 for getter, regex in [(
3009 lambda x: x['defaultText']['accessibility']['accessibilityData'],
3010 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
3011 lambda x: x['accessibility'],
3012 lambda x: x['accessibilityData']['accessibilityData'],
3013 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
3014 label = (try_get(tbr, getter, dict) or {}).get('label')
3016 mobj = re.match(regex, label)
3018 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
3020 sbr_tooltip = try_get(
3021 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
3023 like_count, dislike_count = sbr_tooltip.split(' / ')
3025 'like_count': str_to_int(like_count),
3026 'dislike_count': str_to_int(dislike_count),
3028 vsir = content.get('videoSecondaryInfoRenderer')
3030 info['channel'] = self._get_text(vsir, ('owner', 'videoOwnerRenderer', 'title'))
3033 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
3035 multiple_songs = False
3037 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
3038 multiple_songs = True
3041 mrr = row.get('metadataRowRenderer') or {}
3042 mrr_title = mrr.get('title')
3045 mrr_title = self._get_text(mrr, 'title')
3046 mrr_contents_text = self._get_text(mrr, ('contents', 0))
3047 if mrr_title == 'License':
3048 info['license'] = mrr_contents_text
3049 elif not multiple_songs:
3050 if mrr_title == 'Album':
3051 info['album'] = mrr_contents_text
3052 elif mrr_title == 'Artist':
3053 info['artist'] = mrr_contents_text
3054 elif mrr_title == 'Song':
3055 info['track'] = mrr_contents_text
3058 'channel': 'uploader',
3059 'channel_id': 'uploader_id',
3060 'channel_url': 'uploader_url',
3062 for to, frm in fallbacks.items():
3063 if not info.get(to):
3064 info[to] = info.get(frm)
3066 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
3071 is_private = get_first(video_details, 'isPrivate', expected_type=bool)
3072 is_unlisted = get_first(microformats, 'isUnlisted', expected_type=bool)
3073 is_membersonly = None
3075 if initial_data and is_private is not None:
3076 is_membersonly = False
3078 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
3079 badge_labels = set()
3080 for content in contents:
3081 if not isinstance(content, dict):
3083 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
3084 for badge_label in badge_labels:
3085 if badge_label.lower() == 'members only':
3086 is_membersonly = True
3087 elif badge_label.lower() == 'premium':
3089 elif badge_label.lower() == 'unlisted':
3092 info['availability'] = self._availability(
3093 is_private=is_private,
3094 needs_premium=is_premium,
3095 needs_subscription=is_membersonly,
3096 needs_auth=info['age_limit'] >= 18,
3097 is_unlisted=None if is_private is None else is_unlisted)
3099 # get xsrf for annotations or comments
3100 get_annotations = self.get_param('writeannotations', False)
3101 get_comments = self.get_param('getcomments', False)
3102 if get_annotations or get_comments:
3105 xsrf_token = try_get(master_ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
3107 xsrf_token = self._search_regex(
3108 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
3109 webpage, 'xsrf token', group='xsrf_token', fatal=False)
3113 invideo_url = get_first(
3115 ('annotations', 0, 'playerAnnotationsUrlsRenderer', 'invideoUrl'),
3117 if xsrf_token and invideo_url:
3118 xsrf_field_name = None
3120 xsrf_field_name = try_get(master_ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
3121 if not xsrf_field_name:
3122 xsrf_field_name = self._search_regex(
3123 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
3124 webpage, 'xsrf field name',
3125 group='xsrf_field_name', default='session_token')
3126 info['annotations'] = self._download_webpage(
3127 self._proto_relative_url(invideo_url),
3128 video_id, note='Downloading annotations',
3129 errnote='Unable to download video annotations', fatal=False,
3130 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
3133 info['__post_extractor'] = lambda: self._extract_comments(master_ytcfg, video_id, contents, webpage)
3135 self.mark_watched(video_id, player_responses)
3140 class YoutubeTabIE(YoutubeBaseInfoExtractor):
3141 IE_DESC = 'YouTube.com tab'
3142 _VALID_URL = r'''(?x
)
3146 youtube(?
:kids
)?\
.com|
3150 (?P
<channel_type
>channel|c|user|browse
)/|
3153 (?
:playlist|watch
)\?.*?
\blist
=
3155 (?
!(?
:%s)\b) # Direct URLs
3158 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
3159 IE_NAME = 'youtube:tab'
3162 'note': 'playlists, multipage',
3163 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3164 'playlist_mincount': 94,
3166 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3167 'title': 'Игорь Клейнер - Playlists',
3168 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3169 'uploader': 'Игорь Клейнер',
3170 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3173 'note': 'playlists, multipage, different order',
3174 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3175 'playlist_mincount': 94,
3177 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3178 'title': 'Игорь Клейнер - Playlists',
3179 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3180 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3181 'uploader': 'Игорь Клейнер',
3184 'note': 'playlists, series',
3185 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3186 'playlist_mincount': 5,
3188 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3189 'title': '3Blue1Brown - Playlists',
3190 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3191 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3192 'uploader': '3Blue1Brown',
3195 'note': 'playlists, singlepage',
3196 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3197 'playlist_mincount': 4,
3199 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3200 'title': 'ThirstForScience - Playlists',
3201 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
3202 'uploader': 'ThirstForScience',
3203 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3206 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3207 'only_matching': True,
3209 'note': 'basic, single video playlist',
3210 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3212 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3213 'uploader': 'Sergey M.',
3214 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3215 'title': 'youtube-dl public playlist',
3217 'playlist_count': 1,
3219 'note': 'empty playlist',
3220 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3222 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3223 'uploader': 'Sergey M.',
3224 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3225 'title': 'youtube-dl empty playlist',
3227 'playlist_count': 0,
3230 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
3232 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3233 'title': 'lex will - Home',
3234 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3235 'uploader': 'lex will',
3236 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3238 'playlist_mincount': 2,
3240 'note': 'Videos tab',
3241 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
3243 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3244 'title': 'lex will - Videos',
3245 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3246 'uploader': 'lex will',
3247 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3249 'playlist_mincount': 975,
3251 'note': 'Videos tab, sorted by popular',
3252 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
3254 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3255 'title': 'lex will - Videos',
3256 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3257 'uploader': 'lex will',
3258 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3260 'playlist_mincount': 199,
3262 'note': 'Playlists tab',
3263 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
3265 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3266 'title': 'lex will - Playlists',
3267 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3268 'uploader': 'lex will',
3269 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3271 'playlist_mincount': 17,
3273 'note': 'Community tab',
3274 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
3276 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3277 'title': 'lex will - Community',
3278 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3279 'uploader': 'lex will',
3280 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3282 'playlist_mincount': 18,
3284 'note': 'Channels tab',
3285 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
3287 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3288 'title': 'lex will - Channels',
3289 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3290 'uploader': 'lex will',
3291 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3293 'playlist_mincount': 12,
3295 'note': 'Search tab',
3296 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3297 'playlist_mincount': 40,
3299 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3300 'title': '3Blue1Brown - Search - linear algebra',
3301 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3302 'uploader': '3Blue1Brown',
3303 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3306 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3307 'only_matching': True,
3309 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3310 'only_matching': True,
3312 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3313 'only_matching': True,
3315 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3316 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3318 'title': '29C3: Not my department',
3319 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3320 'uploader': 'Christiaan008',
3321 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
3322 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
3324 'playlist_count': 96,
3326 'note': 'Large playlist',
3327 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
3329 'title': 'Uploads from Cauchemar',
3330 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3331 'uploader': 'Cauchemar',
3332 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
3334 'playlist_mincount': 1123,
3336 'note': 'even larger playlist, 8832 videos',
3337 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3338 'only_matching': True,
3340 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3341 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3343 'title': 'Uploads from Interstellar Movie',
3344 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
3345 'uploader': 'Interstellar Movie',
3346 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
3348 'playlist_mincount': 21,
3350 'note': 'Playlist with "show unavailable videos" button',
3351 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3353 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3354 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3355 'uploader': 'Phim Siêu Nhân Nhật Bản',
3356 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3358 'playlist_mincount': 200,
3360 'note': 'Playlist with unavailable videos in page 7',
3361 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3363 'title': 'Uploads from BlankTV',
3364 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3365 'uploader': 'BlankTV',
3366 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3368 'playlist_mincount': 1000,
3370 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
3371 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3373 'title': 'Data Analysis with Dr Mike Pound',
3374 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3375 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3376 'uploader': 'Computerphile',
3377 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
3379 'playlist_mincount': 11,
3381 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3382 'only_matching': True,
3384 'note': 'Playlist URL that does not actually serve a playlist',
3385 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3387 'id': 'FqZTN594JQw',
3389 'title': "Smiley's People 01 detective, Adventure Series, Action",
3390 'uploader': 'STREEM',
3391 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
3392 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
3393 'upload_date': '20150526',
3394 'license': 'Standard YouTube License',
3395 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3396 'categories': ['People & Blogs'],
3400 'dislike_count': int,
3403 'skip_download': True,
3405 'skip': 'This video is not available.',
3406 'add_ie': [YoutubeIE.ie_key()],
3408 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
3409 'only_matching': True,
3411 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
3412 'only_matching': True,
3414 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3416 'id': 'FMtPN8yp5LU', # This will keep changing
3418 'title': compat_str,
3419 'uploader': 'Sky News',
3420 'uploader_id': 'skynews',
3421 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
3422 'upload_date': r're:\d{8}',
3423 'description': compat_str,
3424 'categories': ['News & Politics'],
3427 'dislike_count': int,
3430 'skip_download': True,
3432 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
3434 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3436 'id': 'a48o2S1cPoo',
3438 'title': 'The Young Turks - Live Main Show',
3439 'uploader': 'The Young Turks',
3440 'uploader_id': 'TheYoungTurks',
3441 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3442 'upload_date': '20150715',
3443 'license': 'Standard YouTube License',
3444 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3445 'categories': ['News & Politics'],
3446 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3448 'dislike_count': int,
3451 'skip_download': True,
3453 'only_matching': True,
3455 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3456 'only_matching': True,
3458 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3459 'only_matching': True,
3461 'note': 'A channel that is not live. Should raise error',
3462 'url': 'https://www.youtube.com/user/numberphile/live',
3463 'only_matching': True,
3465 'url': 'https://www.youtube.com/feed/trending',
3466 'only_matching': True,
3468 'url': 'https://www.youtube.com/feed/library',
3469 'only_matching': True,
3471 'url': 'https://www.youtube.com/feed/history',
3472 'only_matching': True,
3474 'url': 'https://www.youtube.com/feed/subscriptions',
3475 'only_matching': True,
3477 'url': 'https://www.youtube.com/feed/watch_later',
3478 'only_matching': True,
3480 'note': 'Recommended - redirects to home page',
3481 'url': 'https://www.youtube.com/feed/recommended',
3482 'only_matching': True,
3484 'note': 'inline playlist with not always working continuations',
3485 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3486 'only_matching': True,
3488 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3489 'only_matching': True,
3491 'url': 'https://www.youtube.com/course',
3492 'only_matching': True,
3494 'url': 'https://www.youtube.com/zsecurity',
3495 'only_matching': True,
3497 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3498 'only_matching': True,
3500 'url': 'https://www.youtube.com/TheYoungTurks/live',
3501 'only_matching': True,
3503 'url': 'https://www.youtube.com/hashtag/cctv9',
3508 'playlist_mincount': 350,
3510 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3511 'only_matching': True,
3513 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
3514 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3515 'only_matching': True
3517 'note': '/browse/ should redirect to /channel/',
3518 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3519 'only_matching': True
3521 'note': 'VLPL, should redirect to playlist?list=PL...',
3522 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3524 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3525 'uploader': 'NoCopyrightSounds',
3526 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3527 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3528 'title': 'NCS Releases',
3530 'playlist_mincount': 166,
3532 'note': 'Topic, should redirect to playlist?list=UU...',
3533 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3535 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3536 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3537 'title': 'Uploads from Royalty Free Music - Topic',
3538 'uploader': 'Royalty Free Music - Topic',
3540 'expected_warnings': [
3541 'A channel/user page was given',
3542 'The URL does not have a videos tab',
3544 'playlist_mincount': 101,
3546 'note': 'Topic without a UU playlist',
3547 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3549 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3550 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3552 'expected_warnings': [
3553 'A channel/user page was given',
3554 'The URL does not have a videos tab',
3555 'Falling back to channel URL',
3557 'playlist_mincount': 9,
3559 'note': 'Youtube music Album',
3560 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3562 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3563 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3565 'playlist_count': 50,
3567 'note': 'unlisted single video playlist',
3568 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3570 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
3571 'uploader': 'colethedj',
3572 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3573 'title': 'yt-dlp unlisted playlist test',
3574 'availability': 'unlisted'
3576 'playlist_count': 1,
3580 def suitable(cls, url):
3581 return False if YoutubeIE.suitable(url) else super(
3582 YoutubeTabIE, cls).suitable(url)
3584 def _extract_channel_id(self, webpage):
3585 channel_id = self._html_search_meta(
3586 'channelId', webpage, 'channel id', default=None)
3589 channel_url = self._html_search_meta(
3590 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3591 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3592 'twitter:app:url:googleplay'), webpage, 'channel url')
3593 return self._search_regex(
3594 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3595 channel_url, 'channel id')
3598 def _extract_basic_item_renderer(item):
3599 # Modified from _extract_grid_item_renderer
3600 known_basic_renderers = (
3601 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3603 for key, renderer in item.items():
3604 if not isinstance(renderer, dict):
3606 elif key in known_basic_renderers:
3608 elif key.startswith('grid') and key.endswith('Renderer'):
3611 def _grid_entries(self, grid_renderer):
3612 for item in grid_renderer['items']:
3613 if not isinstance(item, dict):
3615 renderer = self._extract_basic_item_renderer(item)
3616 if not isinstance(renderer, dict):
3618 title = self._get_text(renderer, 'title')
3621 playlist_id = renderer.get('playlistId')
3623 yield self.url_result(
3624 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3625 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3629 video_id = renderer.get('videoId')
3631 yield self._extract_video(renderer)
3634 channel_id = renderer.get('channelId')
3636 yield self.url_result(
3637 'https://www.youtube.com/channel/%s' % channel_id,
3638 ie=YoutubeTabIE.ie_key(), video_title=title)
3640 # generic endpoint URL support
3641 ep_url = urljoin('https://www.youtube.com/', try_get(
3642 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3645 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3646 if ie.suitable(ep_url):
3647 yield self.url_result(
3648 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3651 def _shelf_entries_from_content(self, shelf_renderer):
3652 content = shelf_renderer.get('content')
3653 if not isinstance(content, dict):
3655 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3657 # TODO: add support for nested playlists so each shelf is processed
3658 # as separate playlist
3659 # TODO: this includes only first N items
3660 for entry in self._grid_entries(renderer):
3662 renderer = content.get('horizontalListRenderer')
3667 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3669 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3671 shelf_url = urljoin('https://www.youtube.com', ep)
3673 # Skipping links to another channels, note that checking for
3674 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3676 if skip_channels and '/channels?' in shelf_url:
3678 title = self._get_text(shelf_renderer, 'title')
3679 yield self.url_result(shelf_url, video_title=title)
3680 # Shelf may not contain shelf URL, fallback to extraction from content
3681 for entry in self._shelf_entries_from_content(shelf_renderer):
3684 def _playlist_entries(self, video_list_renderer):
3685 for content in video_list_renderer['contents']:
3686 if not isinstance(content, dict):
3688 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3689 if not isinstance(renderer, dict):
3691 video_id = renderer.get('videoId')
3694 yield self._extract_video(renderer)
3696 def _rich_entries(self, rich_grid_renderer):
3698 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3699 video_id = renderer.get('videoId')
3702 yield self._extract_video(renderer)
3704 def _video_entry(self, video_renderer):
3705 video_id = video_renderer.get('videoId')
3707 return self._extract_video(video_renderer)
3709 def _post_thread_entries(self, post_thread_renderer):
3710 post_renderer = try_get(
3711 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3712 if not post_renderer:
3715 video_renderer = try_get(
3716 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3717 video_id = video_renderer.get('videoId')
3719 entry = self._extract_video(video_renderer)
3722 # playlist attachment
3723 playlist_id = try_get(
3724 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3726 yield self.url_result(
3727 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3728 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3729 # inline video links
3730 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3732 if not isinstance(run, dict):
3735 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3738 if not YoutubeIE.suitable(ep_url):
3740 ep_video_id = YoutubeIE._match_id(ep_url)
3741 if video_id == ep_video_id:
3743 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3745 def _post_thread_continuation_entries(self, post_thread_continuation):
3746 contents = post_thread_continuation.get('contents')
3747 if not isinstance(contents, list):
3749 for content in contents:
3750 renderer = content.get('backstagePostThreadRenderer')
3751 if not isinstance(renderer, dict):
3753 for entry in self._post_thread_entries(renderer):
3757 def _rich_grid_entries(self
, contents
):
3758 for content
in contents
:
3759 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3761 entry
= self
._video
_entry
(video_renderer
)
3765 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3767 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3768 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3769 for content in contents:
3770 if not isinstance(content, dict):
3772 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3774 renderer = content.get('richItemRenderer')
3776 for entry in self._rich_entries(renderer):
3778 continuation_list[0] = self._extract_continuation(parent_renderer)
3780 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3781 for isr_content in isr_contents:
3782 if not isinstance(isr_content, dict):
3786 'playlistVideoListRenderer': self._playlist_entries,
3787 'gridRenderer': self._grid_entries,
3788 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3789 'backstagePostThreadRenderer': self._post_thread_entries,
3790 'videoRenderer': lambda x: [self._video_entry(x)],
3792 for key, renderer in isr_content.items():
3793 if key not in known_renderers:
3795 for entry in known_renderers[key](renderer):
3798 continuation_list[0] = self._extract_continuation(renderer)
3801 if not continuation_list[0]:
3802 continuation_list[0] = self._extract_continuation(is_renderer)
3804 if not continuation_list[0]:
3805 continuation_list[0] = self._extract_continuation(parent_renderer)
3807 continuation_list = [None] # Python 2 doesnot support nonlocal
3808 tab_content = try_get(tab, lambda x: x['content'], dict)
3812 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3813 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3814 for entry in extract_entries(parent_renderer):
3816 continuation = continuation_list[0]
3819 for page_num in itertools.count(1):
3820 if not continuation:
3822 headers = self.generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
3823 response = self._extract_response(
3824 item_id='%s page %s' % (item_id, page_num),
3825 query=continuation, headers=headers, ytcfg=ytcfg,
3826 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3830 visitor_data = try_get(
3831 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
3833 known_continuation_renderers = {
3834 'playlistVideoListContinuation': self._playlist_entries,
3835 'gridContinuation': self._grid_entries,
3836 'itemSectionContinuation': self._post_thread_continuation_entries,
3837 'sectionListContinuation': extract_entries, # for feeds
3839 continuation_contents = try_get(
3840 response, lambda x: x['continuationContents'], dict) or {}
3841 continuation_renderer = None
3842 for key, value in continuation_contents.items():
3843 if key not in known_continuation_renderers:
3845 continuation_renderer = value
3846 continuation_list = [None]
3847 for entry in known_continuation_renderers[key](continuation_renderer):
3849 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3851 if continuation_renderer:
3855 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3856 'gridVideoRenderer': (self._grid_entries, 'items'),
3857 'gridChannelRenderer': (self._grid_entries, 'items'),
3858 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3859 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3860 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3861 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3863 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3864 continuation_items = try_get(
3865 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3866 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3867 video_items_renderer = None
3868 for key, value in continuation_item.items():
3869 if key not in known_renderers:
3871 video_items_renderer = {known_renderers[key][1]: continuation_items}
3872 continuation_list = [None]
3873 for entry in known_renderers[key][0](video_items_renderer):
3875 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3877 if video_items_renderer:
3882 def _extract_selected_tab(tabs):
3884 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3885 if renderer.get('selected') is True:
3888 raise ExtractorError('Unable to find selected tab')
3891 def _extract_uploader(cls, data):
3893 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3895 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3897 uploader['uploader'] = owner.get('text')
3898 uploader['uploader_id'] = try_get(
3899 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3900 uploader['uploader_url'] = urljoin(
3901 'https://www.youtube.com/',
3902 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3903 return {k: v for k, v in uploader.items() if v is not None}
3905 def _extract_from_tabs(self, item_id, webpage, data, tabs):
3906 playlist_id = title = description = channel_url = channel_name = channel_id = None
3907 thumbnails_list = tags = []
3909 selected_tab = self._extract_selected_tab(tabs)
3911 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3913 channel_name = renderer.get('title')
3914 channel_url = renderer.get('channelUrl')
3915 channel_id = renderer.get('externalId')
3918 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3921 title = renderer.get('title')
3922 description = renderer.get('description', '')
3923 playlist_id = channel_id
3924 tags = renderer.get('keywords', '').split()
3926 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
3928 self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
3929 lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
3934 for t in thumbnails_list:
3935 if not isinstance(t, dict):
3937 thumbnail_url = url_or_none(t.get('url'))
3938 if not thumbnail_url:
3941 'url': thumbnail_url,
3942 'width': int_or_none(t.get('width')),
3943 'height': int_or_none(t.get('height')),
3945 if playlist_id is None:
3946 playlist_id = item_id
3949 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3951 title += format_field(selected_tab, 'title', ' - %s')
3952 title += format_field(selected_tab, 'expandedText', ' - %s')
3954 'playlist_id': playlist_id,
3955 'playlist_title': title,
3956 'playlist_description': description,
3957 'uploader': channel_name,
3958 'uploader_id': channel_id,
3959 'uploader_url': channel_url,
3960 'thumbnails': thumbnails,
3963 availability = self._extract_availability(data)
3965 metadata['availability'] = availability
3967 metadata.update(self._extract_uploader(data))
3969 'channel': metadata['uploader'],
3970 'channel_id': metadata['uploader_id'],
3971 'channel_url': metadata['uploader_url']})
3972 ytcfg = self.extract_ytcfg(item_id, webpage)
3973 return self.playlist_result(
3975 selected_tab, playlist_id,
3976 self._extract_identity_token(webpage, item_id),
3977 self._extract_account_syncid(ytcfg, data), ytcfg),
3980 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
3981 first_id = last_id = None
3982 ytcfg = self.extract_ytcfg(playlist_id, webpage)
3983 headers = self.generate_api_headers(
3984 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
3985 identity_token=self._extract_identity_token(webpage, item_id=playlist_id))
3986 for page_num in itertools.count(1):
3987 videos = list(self._playlist_entries(playlist))
3990 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3991 if start >= len(videos):
3993 for video in videos[start:]:
3994 if video['id'] == first_id:
3995 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3998 first_id = first_id or videos[0]['id']
3999 last_id = videos[-1]['id']
4000 watch_endpoint = try_get(
4001 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
4003 'playlistId': playlist_id,
4004 'videoId': watch_endpoint.get('videoId') or last_id,
4005 'index': watch_endpoint.get('index') or len(videos),
4006 'params': watch_endpoint.get('params') or 'OAE%3D'
4008 response = self._extract_response(
4009 item_id='%s page %d' % (playlist_id, page_num),
4010 query=query, ep='next', headers=headers, ytcfg=ytcfg,
4011 check_get_keys='contents'
4014 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4016 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
4017 title = playlist.get('title') or try_get(
4018 data, lambda x: x['titleText']['simpleText'], compat_str)
4019 playlist_id = playlist.get('playlistId') or item_id
4021 # Delegating everything except mix playlists to regular tab-based playlist URL
4022 playlist_url = urljoin(url, try_get(
4023 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
4025 if playlist_url and playlist_url != url:
4026 return self.url_result(
4027 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
4030 return self.playlist_result(
4031 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
4032 playlist_id=playlist_id, playlist_title=title)
4034 def _extract_availability(self, data):
4036 Gets the availability of a given playlist/tab.
4037 Note: Unless YouTube tells us explicitly, we do not assume it is public
4038 @param data: response
4040 is_private = is_unlisted = None
4041 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
4042 badge_labels = self._extract_badges(renderer)
4044 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
4045 privacy_dropdown_entries = try_get(
4046 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
4047 for renderer_dict in privacy_dropdown_entries:
4048 is_selected = try_get(
4049 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
4052 label = self._get_text(renderer_dict, ('privacyDropdownItemRenderer', 'label'))
4054 badge_labels.add(label.lower())
4057 for badge_label in badge_labels:
4058 if badge_label == 'unlisted':
4060 elif badge_label == 'private':
4062 elif badge_label == 'public':
4063 is_unlisted = is_private = False
4064 return self._availability(is_private, False, False, False, is_unlisted)
4067 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
4068 sidebar_renderer = try_get(
4069 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
4070 for item in sidebar_renderer:
4071 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
4075 def _reload_with_unavailable_videos(self, item_id, data, webpage):
4077 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
4079 browse_id = params = None
4080 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
4083 menu_renderer = try_get(
4084 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
4085 for menu_item in menu_renderer:
4086 if not isinstance(menu_item, dict):
4088 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
4090 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
4091 if not text or text.lower() != 'show unavailable videos':
4093 browse_endpoint = try_get(
4094 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
4095 browse_id = browse_endpoint.get('browseId')
4096 params = browse_endpoint.get('params')
4099 ytcfg = self.extract_ytcfg(item_id, webpage)
4100 headers = self.generate_api_headers(
4101 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
4102 identity_token=self._extract_identity_token(webpage, item_id=item_id),
4103 visitor_data=try_get(
4104 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
4106 'params': params or 'wgYCCAA=',
4107 'browseId': browse_id or 'VL%s' % item_id
4109 return self._extract_response(
4110 item_id=item_id, headers=headers, query=query,
4111 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
4112 note='Downloading API JSON with unavailable videos')
4114 def _extract_webpage(self, url, item_id):
4115 retries = self.get_param('extractor_retries', 3)
4117 last_error = 'Incomplete yt initial data recieved'
4118 while count < retries:
4120 # Sometimes youtube returns a webpage with incomplete ytInitialData
4121 # See: https://github.com/yt-dlp/yt-dlp/issues/116
4123 self.report_warning('%s. Retrying ...' % last_error)
4124 webpage = self._download_webpage(
4126 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
4127 data = self.extract_yt_initial_data(item_id, webpage)
4128 if data.get('contents') or data.get('currentVideoEndpoint'):
4130 # Extract alerts here only when there is error
4131 self._extract_and_report_alerts(data)
4132 if count >= retries:
4133 raise ExtractorError(last_error)
4134 return webpage, data
4137 def _smuggle_data(entries, data):
4138 for entry in entries:
4140 entry['url'] = smuggle_url(entry['url'], data)
4143 def _real_extract(self, url):
4144 url, smuggled_data = unsmuggle_url(url, {})
4145 if self.is_music_url(url):
4146 smuggled_data['is_music_url'] = True
4147 info_dict = self.__real_extract(url, smuggled_data)
4148 if info_dict.get('entries'):
4149 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4152 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4154 def __real_extract(self, url, smuggled_data):
4155 item_id = self._match_id(url)
4156 url = compat_urlparse.urlunparse(
4157 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4158 compat_opts = self.get_param('compat_opts', [])
4161 mobj = self._url_re.match(url).groupdict()
4162 mobj.update((k, '') for k, v in mobj.items() if v is None)
4165 mobj = get_mobj(url)
4166 # Youtube returns incomplete data if tabname is not lower case
4167 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4170 if smuggled_data.get('is_music_url'):
4171 if item_id[:2] == 'VL':
4172 # Youtube music VL channels have an equivalent playlist
4173 item_id = item_id[2:]
4174 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4175 elif item_id[:2] == 'MP':
4176 # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage
4177 item_id = self._search_regex(
4178 r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22',
4179 self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id),
4181 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4182 elif mobj['channel_type'] == 'browse':
4183 # Youtube music /browse/ should be changed to /channel/
4184 pre = 'https://www.youtube.com/channel/%s' % item_id
4185 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4186 # Home URLs should redirect to /videos/
4187 self.report_warning(
4188 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4189 'To download only the videos in the home page, add a "/featured" to the URL')
4192 url = ''.join((pre, tab, post))
4193 mobj = get_mobj(url)
4195 # Handle both video/playlist URLs
4197 video_id = qs.get('v', [None])[0]
4198 playlist_id = qs.get('list', [None])[0]
4200 if not video_id and mobj['not_channel'].startswith('watch'):
4202 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4203 raise ExtractorError('Unable to recognize tab page')
4204 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4205 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
4206 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
4207 mobj = get_mobj(url)
4209 if video_id and playlist_id:
4210 if self.get_param('noplaylist'):
4211 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
4212 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4213 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4215 webpage, data = self._extract_webpage(url, item_id)
4218 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4220 selected_tab = self._extract_selected_tab(tabs)
4221 tab_name = selected_tab.get('title', '')
4222 if 'no-youtube-channel-redirect' not in compat_opts:
4223 if mobj['tab'] == '/live':
4224 # Live tab should have redirected to the video
4225 raise ExtractorError('The channel is not currently live', expected=True)
4226 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4227 if not mobj['not_channel'] and item_id[:2] == 'UC':
4228 # Topic channels don't have /videos. Use the equivalent playlist instead
4229 self.report_warning('The URL does not have a %s tab. Trying to redirect to playlist UU%s instead' % (mobj['tab'][1:], item_id[2:]))
4230 pl_id = 'UU%s' % item_id[2:]
4231 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4233 pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id)
4234 for alert_type, alert_message in self._extract_alerts(pl_data):
4235 if alert_type == 'error':
4236 raise ExtractorError('Youtube said: %s' % alert_message)
4237 item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data
4238 except ExtractorError:
4239 self.report_warning('The playlist gave error. Falling back to channel URL')
4241 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
4243 self.write_debug('Final URL: %s' % url)
4245 # YouTube sometimes provides a button to reload playlist with unavailable videos.
4246 if 'no-youtube-unavailable-videos' not in compat_opts:
4247 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
4248 self._extract_and_report_alerts(data)
4250 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4252 return self._extract_from_tabs(item_id, webpage, data, tabs)
4255 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4257 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
4260 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4261 compat_str) or video_id
4263 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4264 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
4265 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4267 raise ExtractorError('Unable to recognize tab page')
4270 class YoutubePlaylistIE(InfoExtractor):
4271 IE_DESC = 'YouTube.com playlists'
4272 _VALID_URL = r'''(?x
)(?
:
4277 youtube(?
:kids
)?\
.com|
4282 (?P
<id>%(playlist_id)s)
4283 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4284 IE_NAME = 'youtube:playlist'
4286 'note': 'issue #673',
4287 'url': 'PLBB231211A4F62143',
4289 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4290 'id': 'PLBB231211A4F62143',
4291 'uploader': 'Wickydoo',
4292 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
4293 'description': 'md5:8fa6f52abb47a9552002fa3ddfc57fc2',
4295 'playlist_mincount': 29,
4297 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4299 'title': 'YDL_safe_search',
4300 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4302 'playlist_count': 2,
4303 'skip': 'This playlist is private',
4306 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4307 'playlist_count': 4,
4310 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4311 'uploader': 'milan',
4312 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
4315 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4316 'playlist_mincount': 654,
4318 'title': '2018 Chinese New Singles (11/6 updated)',
4319 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4321 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
4322 'description': 'md5:da521864744d60a198e3a88af4db0d9d',
4325 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4326 'only_matching': True,
4328 # music album playlist
4329 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4330 'only_matching': True,
4334 def suitable(cls, url):
4335 if YoutubeTabIE.suitable(url):
4337 # Hack for lazy extractors until more generic solution is implemented
4339 from .youtube import parse_qs
4341 if qs.get('v', [None])[0]:
4343 return super(YoutubePlaylistIE, cls).suitable(url)
4345 def _real_extract(self, url):
4346 playlist_id = self._match_id(url)
4347 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
4348 url = update_url_query(
4349 'https://www.youtube.com/playlist',
4350 parse_qs(url) or {'list': playlist_id})
4352 url = smuggle_url(url, {'is_music_url': True})
4353 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4356 class YoutubeYtBeIE(InfoExtractor):
4357 IE_DESC = 'youtu.be'
4358 _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}
4360 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4362 'id': 'yeWKywCrFtk',
4364 'title': 'Small Scale Baler and Braiding Rugs',
4365 'uploader': 'Backus-Page House Museum',
4366 'uploader_id': 'backuspagemuseum',
4367 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4368 'upload_date': '20161008',
4369 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4370 'categories': ['Nonprofits & Activism'],
4373 'dislike_count': int,
4377 'skip_download': True,
4380 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
4381 'only_matching': True,
4384 def _real_extract(self, url):
4385 mobj = re.match(self._VALID_URL, url)
4386 video_id = mobj.group('id')
4387 playlist_id = mobj.group('playlist_id')
4388 return self.url_result(
4389 update_url_query('https://www.youtube.com/watch', {
4391 'list': playlist_id,
4392 'feature': 'youtu.be',
4393 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4396 class YoutubeYtUserIE(InfoExtractor):
4397 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
4398 _VALID_URL = r'ytuser:(?P<id>.+)'
4400 'url': 'ytuser:phihag',
4401 'only_matching': True,
4404 def _real_extract(self, url):
4405 user_id = self._match_id(url)
4406 return self.url_result(
4407 'https://www.youtube.com/user/%s' % user_id,
4408 ie=YoutubeTabIE.ie_key(), video_id=user_id)
4411 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
4412 IE_NAME = 'youtube:favorites'
4413 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
4414 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4415 _LOGIN_REQUIRED = True
4418 'only_matching': True,
4420 'url': ':ytfavorites',
4421 'only_matching': True,
4424 def _real_extract(self, url):
4425 return self.url_result(
4426 'https://www.youtube.com/playlist?list=LL',
4427 ie=YoutubeTabIE.ie_key())
4430 class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
4431 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
4432 # there doesn't appear to be a real limit, for example if you search for
4433 # 'python' you get more than 8.000.000 results
4434 _MAX_RESULTS = float('inf')
4435 IE_NAME = 'youtube:search'
4436 _SEARCH_KEY = 'ytsearch'
4437 _SEARCH_PARAMS = None
4440 def _entries(self, query, n):
4441 data = {'query': query}
4442 if self._SEARCH_PARAMS:
4443 data['params'] = self._SEARCH_PARAMS
4446 for page_num in itertools.count(1):
4447 data.update(continuation)
4448 search = self._extract_response(
4449 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4450 check_get_keys=('contents', 'onResponseReceivedCommands')
4454 slr_contents = try_get(
4456 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4457 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4459 if not slr_contents:
4462 # Youtube sometimes adds promoted content to searches,
4463 # changing the index location of videos and token.
4464 # So we search through all entries till we find them.
4466 for slr_content in slr_contents:
4467 if not continuation:
4468 continuation = self._extract_continuation({'contents': [slr_content]})
4470 isr_contents = try_get(
4472 lambda x: x['itemSectionRenderer']['contents'],
4474 if not isr_contents:
4476 for content in isr_contents:
4477 if not isinstance(content, dict):
4479 video = content.get('videoRenderer')
4480 if not isinstance(video, dict):
4482 video_id = video.get('videoId')
4486 yield self._extract_video(video)
4491 if not continuation:
4494 def _get_n_results(self, query, n):
4495 """Get a specified number of results for a query"""
4496 return self.playlist_result(self._entries(query, n), query, query)
4499 class YoutubeSearchDateIE(YoutubeSearchIE):
4500 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
4501 _SEARCH_KEY = 'ytsearchdate'
4502 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
4503 _SEARCH_PARAMS = 'CAI%3D'
4506 class YoutubeSearchURLIE(YoutubeSearchIE):
4507 IE_DESC = 'YouTube.com search URLs'
4508 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
4509 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
4510 # _MAX_RESULTS = 100
4512 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4513 'playlist_mincount': 5,
4515 'id': 'youtube-dl test video',
4516 'title': 'youtube-dl test video',
4519 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4520 'only_matching': True,
4524 def _make_valid_url(cls):
4525 return cls._VALID_URL
4527 def _real_extract(self, url):
4528 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
4529 query = (qs.get('search_query') or qs.get('q'))[0]
4530 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4531 return self._get_n_results(query, self._MAX_RESULTS)
4534 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
4536 Base class for feed extractors
4537 Subclasses must define the _FEED_NAME property.
4539 _LOGIN_REQUIRED = True
4544 return 'youtube:%s' % self._FEED_NAME
4546 def _real_extract(self, url):
4547 return self.url_result(
4548 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4549 ie=YoutubeTabIE.ie_key())
4552 class YoutubeWatchLaterIE(InfoExtractor):
4553 IE_NAME = 'youtube:watchlater'
4554 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
4555 _VALID_URL = r':ytwatchlater'
4557 'url': ':ytwatchlater',
4558 'only_matching': True,
4561 def _real_extract(self, url):
4562 return self.url_result(
4563 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
4566 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
4567 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
4568 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
4569 _FEED_NAME = 'recommended'
4570 _LOGIN_REQUIRED = False
4573 'only_matching': True,
4575 'url': ':ytrecommended',
4576 'only_matching': True,
4578 'url': 'https://youtube.com',
4579 'only_matching': True,
4583 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
4584 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
4585 _VALID_URL = r':ytsub(?:scription)?s?'
4586 _FEED_NAME = 'subscriptions'
4589 'only_matching': True,
4591 'url': ':ytsubscriptions',
4592 'only_matching': True,
4596 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
4597 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
4598 _VALID_URL = r':ythis(?:tory)?'
4599 _FEED_NAME = 'history'
4601 'url': ':ythistory',
4602 'only_matching': True,
4606 class YoutubeTruncatedURLIE(InfoExtractor):
4607 IE_NAME = 'youtube:truncated_url'
4608 IE_DESC = False # Do not list
4609 _VALID_URL = r'''(?x
)
4611 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
4614 annotation_id
=annotation_
[^
&]+|
4620 attribution_link
\?a
=[^
&]+
4626 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
4627 'only_matching': True,
4629 'url': 'https://www.youtube.com/watch?',
4630 'only_matching': True,
4632 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4633 'only_matching': True,
4635 'url': 'https://www.youtube.com/watch?feature=foo',
4636 'only_matching': True,
4638 'url': 'https://www.youtube.com/watch?hl=en-GB',
4639 'only_matching': True,
4641 'url': 'https://www.youtube.com/watch?t=2372',
4642 'only_matching': True,
4645 def _real_extract(self, url):
4646 raise ExtractorError(
4647 'Did you forget to quote the URL? Remember that & is a meta '
4648 'character in most shells, so you want to put the URL in quotes, '
4650 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
4651 ' or simply youtube-dl BaW_jenozKc .',
4655 class YoutubeTruncatedIDIE(InfoExtractor):
4656 IE_NAME = 'youtube:truncated_id'
4657 IE_DESC = False # Do not list
4658 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
4661 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4662 'only_matching': True,
4665 def _real_extract(self, url):
4666 video_id = self._match_id(url)
4667 raise ExtractorError(
4668 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),