3 from __future__
import unicode_literals
17 from .common
import InfoExtractor
, SearchInfoExtractor
18 from ..compat
import (
23 compat_urllib_parse_unquote_plus
,
24 compat_urllib_parse_urlencode
,
25 compat_urllib_parse_urlparse
,
28 from ..jsinterp
import JSInterpreter
62 return compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
65 class YoutubeBaseInfoExtractor(InfoExtractor
):
66 """Provide base functions for Youtube extractors"""
67 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
68 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
70 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
71 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
72 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
75 r
'channel|c|user|browse|playlist|watch|w|v|embed|e|watch_popup|shorts|'
76 r
'movies|results|shared|hashtag|trending|feed|feeds|oembed|get_video_info|'
77 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
79 _NETRC_MACHINE
= 'youtube'
80 # If True it will raise an error if no login info is provided
81 _LOGIN_REQUIRED
= False
83 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
87 Attempt to log in to YouTube.
88 True is returned if successful or skipped.
89 False is returned if login failed.
91 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
95 self
.report_warning(message
)
97 # username+password login is broken
98 if self
._LOGIN
_REQUIRED
and self
.get_param('cookiefile') is None:
99 self
.raise_login_required(
100 'Login details are needed to download this content', method
='cookies')
101 username
, password
= self
._get
_login
_info
()
103 warn('Logging in using username and password is broken. %s' % self
._LOGIN
_HINTS
['cookies'])
106 # Everything below this is broken!
108 # No authentication to be performed
110 if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None:
111 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
112 # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
113 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
116 login_page = self._download_webpage(
117 self._LOGIN_URL, None,
118 note='Downloading login page',
119 errnote='unable to fetch login page', fatal=False)
120 if login_page is False:
123 login_form = self._hidden_inputs(login_page)
125 def req(url, f_req, note, errnote):
126 data = login_form.copy()
129 'checkConnection': 'youtube',
130 'checkedDomains': 'youtube',
132 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
133 'f.req': json.dumps(f_req),
134 'flowName': 'GlifWebSignIn',
135 'flowEntry': 'ServiceLogin',
136 # TODO: reverse actual botguard identifier generation algo
137 'bgRequest': '["identifier",""]',
139 return self._download_json(
140 url, None, note=note, errnote=errnote,
141 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
143 data=urlencode_postdata(data), headers={
144 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
145 'Google-Accounts-XSRF': 1,
150 None, [], None, 'US', None, None, 2, False, True,
154 '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',
156 1, [None, None, []], None, None, None, True
161 lookup_results = req(
162 self._LOOKUP_URL, lookup_req,
163 'Looking up account info', 'Unable to look up account info')
165 if lookup_results is False:
168 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
170 warn('Unable to extract user hash')
175 None, 1, None, [1, None, None, None, [password, None, True]],
177 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],
178 1, [None, None, []], None, None, None, True
181 challenge_results = req(
182 self._CHALLENGE_URL, challenge_req,
183 'Logging in', 'Unable to log in')
185 if challenge_results is False:
188 login_res = try_get(challenge_results, lambda x: x[0][5], list)
190 login_msg = try_get(login_res, lambda x: x[5], compat_str)
192 'Unable to login: %s' % 'Invalid password'
193 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
196 res = try_get(challenge_results, lambda x: x[0][-1], list)
198 warn('Unable to extract result entry')
201 login_challenge = try_get(res, lambda x: x[0][0], list)
203 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
204 if challenge_str == 'TWO_STEP_VERIFICATION':
205 # SEND_SUCCESS - TFA code has been successfully sent to phone
206 # QUOTA_EXCEEDED - reached the limit of TFA codes
207 status = try_get(login_challenge, lambda x: x[5], compat_str)
208 if status == 'QUOTA_EXCEEDED':
209 warn('Exceeded the limit of TFA codes, try later')
212 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
214 warn('Unable to extract TL')
217 tfa_code = self._get_tfa_info('2-step verification code')
221 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
222 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
225 tfa_code = remove_start(tfa_code, 'G-')
228 user_hash, None, 2, None,
230 9, None, None, None, None, None, None, None,
231 [None, tfa_code, True, 2]
235 self._TFA_URL.format(tl), tfa_req,
236 'Submitting TFA code', 'Unable to submit TFA code')
238 if tfa_results is False:
241 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
243 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
245 'Unable to finish TFA: %s' % 'Invalid TFA code'
246 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
249 check_cookie_url = try_get(
250 tfa_results, lambda x: x[0][-1][2], compat_str)
253 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
254 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
255 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
257 challenge = CHALLENGES.get(
259 '%s returned error %s.' % (self.IE_NAME, challenge_str))
260 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
263 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
265 if not check_cookie_url:
266 warn('Unable to extract CheckCookie URL')
269 check_cookie_results = self._download_webpage(
270 check_cookie_url, None, 'Checking cookie', fatal=False)
272 if check_cookie_results is False:
275 if 'https://myaccount.google.com/' not in check_cookie_results:
276 warn('Unable to log in')
282 def _initialize_consent(self
):
283 cookies
= self
._get
_cookies
('https://www.youtube.com/')
284 if cookies
.get('__Secure-3PSID'):
287 consent
= cookies
.get('CONSENT')
289 if 'YES' in consent
.value
:
291 consent_id
= self
._search
_regex
(
292 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
294 consent_id
= random
.randint(100, 999)
295 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
297 def _real_initialize(self
):
298 self
._initialize
_consent
()
299 if self
._downloader
is None:
301 if not self
._login
():
304 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
305 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
306 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
308 _YT_DEFAULT_YTCFGS = {
310 'INNERTUBE_API_VERSION': 'v1',
311 'INNERTUBE_CLIENT_NAME': 'WEB',
312 'INNERTUBE_CLIENT_VERSION': '2.20210622.10.00',
313 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
314 'INNERTUBE_CONTEXT': {
317 'clientVersion': '2.20210622.10.00',
321 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
324 'INNERTUBE_API_VERSION': 'v1',
325 'INNERTUBE_CLIENT_NAME': 'WEB_REMIX',
326 'INNERTUBE_CLIENT_VERSION': '1.20210621.00.00',
327 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
328 'INNERTUBE_CONTEXT': {
330 'clientName': 'WEB_REMIX',
331 'clientVersion': '1.20210621.00.00',
335 'INNERTUBE_CONTEXT_CLIENT_NAME': 67
337 'WEB_EMBEDDED_PLAYER': {
338 'INNERTUBE_API_VERSION': 'v1',
339 'INNERTUBE_CLIENT_NAME': 'WEB_EMBEDDED_PLAYER',
340 'INNERTUBE_CLIENT_VERSION': '1.20210620.0.1',
341 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
342 'INNERTUBE_CONTEXT': {
344 'clientName': 'WEB_EMBEDDED_PLAYER',
345 'clientVersion': '1.20210620.0.1',
349 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
352 'INNERTUBE_API_VERSION': 'v1',
353 'INNERTUBE_CLIENT_NAME': 'ANDROID',
354 'INNERTUBE_CLIENT_VERSION': '16.20',
355 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
356 'INNERTUBE_CONTEXT': {
358 'clientName': 'ANDROID',
359 'clientVersion': '16.20',
363 'INNERTUBE_CONTEXT_CLIENT_NAME': 'ANDROID'
365 'ANDROID_EMBEDDED_PLAYER': {
366 'INNERTUBE_API_VERSION': 'v1',
367 'INNERTUBE_CLIENT_NAME': 'ANDROID_EMBEDDED_PLAYER',
368 'INNERTUBE_CLIENT_VERSION': '16.20',
369 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
370 'INNERTUBE_CONTEXT': {
372 'clientName': 'ANDROID_EMBEDDED_PLAYER',
373 'clientVersion': '16.20',
377 'INNERTUBE_CONTEXT_CLIENT_NAME': 'ANDROID_EMBEDDED_PLAYER'
380 'INNERTUBE_API_VERSION': 'v1',
381 'INNERTUBE_CLIENT_NAME': 'ANDROID_MUSIC',
382 'INNERTUBE_CLIENT_VERSION': '4.32',
383 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
384 'INNERTUBE_CONTEXT': {
386 'clientName': 'ANDROID_MUSIC',
387 'clientVersion': '4.32',
391 'INNERTUBE_CONTEXT_CLIENT_NAME': 'ANDROID_MUSIC'
395 _YT_DEFAULT_INNERTUBE_HOSTS = {
396 'DIRECT': 'youtubei.googleapis.com',
397 'WEB': 'www.youtube.com',
398 'WEB_REMIX': 'music.youtube.com',
399 'ANDROID_MUSIC': 'music.youtube.com'
402 def _get_default_ytcfg(self, client='WEB'):
403 if client in self._YT_DEFAULT_YTCFGS:
404 return copy.deepcopy(self._YT_DEFAULT_YTCFGS[client])
405 self.write_debug(f'INNERTUBE default client {client} does not exist - falling back to WEB client.')
406 return copy.deepcopy(self._YT_DEFAULT_YTCFGS['WEB'])
408 def _get_innertube_host(self, client='WEB'):
409 return dict_get(self._YT_DEFAULT_INNERTUBE_HOSTS, (client, 'WEB'))
411 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='WEB'):
412 # try_get but with fallback to default ytcfg client values when present
413 _func = lambda y: try_get(y, getter, expected_type)
414 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
416 def _extract_client_name(self, ytcfg, default_client='WEB'):
417 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_NAME'], compat_str, default_client)
419 def _extract_client_version(self, ytcfg, default_client='WEB'):
420 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_VERSION'], compat_str, default_client)
422 def _extract_api_key(self, ytcfg=None, default_client='WEB'):
423 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
425 def _extract_context(self, ytcfg=None, default_client='WEB'):
426 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
427 context = _get_context(ytcfg)
431 context = _get_context(self._get_default_ytcfg(default_client))
435 # Recreate the client context (required)
436 context['client'].update({
437 'clientVersion': self._extract_client_version(ytcfg, default_client),
438 'clientName': self._extract_client_name(ytcfg, default_client),
440 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
442 context['client']['visitorData'] = visitor_data
445 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
446 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
447 # See: https://github.com/yt-dlp/yt-dlp/issues/393
448 yt_cookies = self._get_cookies('https://www.youtube.com')
449 sapisid_cookie = dict_get(
450 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
451 if sapisid_cookie is None:
453 time_now = round(time.time())
454 # SAPISID cookie is required if not already present
455 if not yt_cookies.get('SAPISID'):
457 '.youtube.com', 'SAPISID', sapisid_cookie.value, secure=True, expire_time=time_now + 3600)
458 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
459 sapisidhash = hashlib.sha1(
460 f'{time_now} {sapisid_cookie.value} {origin}'.encode('utf-8')).hexdigest()
461 return f'SAPISIDHASH {time_now}_{sapisidhash}'
463 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
464 note='Downloading API JSON', errnote='Unable to download API page',
465 context=None, api_key=None, api_hostname=None, default_client='WEB'):
467 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
469 real_headers = self._generate_api_headers(client=default_client)
470 real_headers.update({'content-type': 'application/json'})
472 real_headers.update(headers)
473 return self._download_json(
474 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
475 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
476 data=json.dumps(data).encode('utf8'), headers=real_headers,
477 query={'key': api_key or self._extract_api_key()})
479 def _extract_yt_initial_data(self, video_id, webpage):
480 return self._parse_json(
482 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
483 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
486 def _extract_identity_token(self, webpage, item_id):
487 ytcfg = self._extract_ytcfg(item_id, webpage)
489 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
492 return self._search_regex(
493 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
494 'identity token
', default=None)
497 def _extract_account_syncid(data):
499 Extract syncId required to download private playlists of secondary channels
500 @param data Either response or ytcfg
503 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
504 lambda x: x['DATASYNC_ID
']), compat_str) or '').split("||")
505 if len(sync_ids) >= 2 and sync_ids[1]:
506 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
507 # and just "user_syncid||" for primary channel. We only want the channel_syncid
509 # ytcfg includes channel_syncid if on secondary channel
510 return data.get('DELEGATED_SESSION_ID
')
512 def _extract_ytcfg(self, video_id, webpage):
515 return self._parse_json(
517 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
518 default='{}'), video_id, fatal=False) or {}
520 def _generate_api_headers(self
, ytcfg
=None, identity_token
=None, account_syncid
=None,
521 visitor_data
=None, api_hostname
=None, client
='WEB'):
522 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(client
))
524 'X-YouTube-Client-Name': compat_str(
525 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=client
)),
526 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, client
),
529 if not visitor_data
and ytcfg
:
530 visitor_data
= try_get(
531 self
._extract
_context
(ytcfg
, client
), lambda x
: x
['client']['visitorData'], compat_str
)
533 headers
['X-Youtube-Identity-Token'] = identity_token
535 headers
['X-Goog-PageId'] = account_syncid
536 headers
['X-Goog-AuthUser'] = 0
538 headers
['X-Goog-Visitor-Id'] = visitor_data
539 auth
= self
._generate
_sapisidhash
_header
(origin
)
541 headers
['Authorization'] = auth
542 headers
['X-Origin'] = origin
546 def _build_api_continuation_query(continuation
, ctp
=None):
548 'continuation': continuation
550 # TODO: Inconsistency with clickTrackingParams.
551 # Currently we have a fixed ctp contained within context (from ytcfg)
552 # and a ctp in root query for continuation.
554 query
['clickTracking'] = {'clickTrackingParams': ctp}
558 def _continuation_query_ajax_to_api(cls
, continuation_query
):
559 continuation
= dict_get(continuation_query
, ('continuation', 'ctoken'))
560 return cls
._build
_api
_continuation
_query
(continuation
, continuation_query
.get('itct'))
563 def _build_continuation_query(continuation
, ctp
=None):
565 'ctoken': continuation
,
566 'continuation': continuation
,
573 def _extract_next_continuation_data(cls
, renderer
):
574 next_continuation
= try_get(
575 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
576 lambda x
: x
['continuation']['reloadContinuationData']), dict)
577 if not next_continuation
:
579 continuation
= next_continuation
.get('continuation')
582 ctp
= next_continuation
.get('clickTrackingParams')
583 return cls
._build
_continuation
_query
(continuation
, ctp
)
586 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
587 if isinstance(continuation_ep
, dict):
588 continuation
= try_get(
589 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
592 ctp
= continuation_ep
.get('clickTrackingParams')
593 return cls
._build
_continuation
_query
(continuation
, ctp
)
596 def _extract_continuation(cls
, renderer
):
597 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
598 if next_continuation
:
599 return next_continuation
601 for key
in ('contents', 'items'):
602 contents
.extend(try_get(renderer
, lambda x
: x
[key
], list) or [])
603 for content
in contents
:
604 if not isinstance(content
, dict):
606 continuation_ep
= try_get(
607 content
, (lambda x
: x
['continuationItemRenderer']['continuationEndpoint'],
608 lambda x
: x
['continuationItemRenderer']['button']['buttonRenderer']['command']),
610 continuation
= cls
._extract
_continuation
_ep
_data
(continuation_ep
)
615 def _extract_alerts(data
):
616 for alert_dict
in try_get(data
, lambda x
: x
['alerts'], list) or []:
617 if not isinstance(alert_dict
, dict):
619 for alert
in alert_dict
.values():
620 alert_type
= alert
.get('type')
623 message
= try_get(alert
, lambda x
: x
['text']['simpleText'], compat_str
) or ''
625 yield alert_type
, message
626 for run
in try_get(alert
, lambda x
: x
['text']['runs'], list) or []:
627 message
+= try_get(run
, lambda x
: x
['text'], compat_str
)
629 yield alert_type
, message
631 def _report_alerts(self
, alerts
, expected
=True):
634 for alert_type
, alert_message
in alerts
:
635 if alert_type
.lower() == 'error':
636 errors
.append([alert_type
, alert_message
])
638 warnings
.append([alert_type
, alert_message
])
640 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
641 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
))
643 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
645 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
646 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
648 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
649 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
650 default_client
='WEB'):
654 retries
= self
.get_param('extractor_retries', 3)
655 if check_get_keys
is None:
657 while count
< retries
:
660 self
.report_warning('%s. Retrying ...' % last_error
)
662 response
= self
._call
_api
(
663 ep
=ep
, fatal
=True, headers
=headers
,
664 video_id
=item_id
, query
=query
,
665 context
=self
._extract
_context
(ytcfg
, default_client
),
666 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
667 api_hostname
=api_hostname
, default_client
=default_client
,
668 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
669 except ExtractorError
as e
:
670 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (500, 503, 404):
671 # Downloading page may result in intermittent 5xx HTTP error
672 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
673 last_error
= 'HTTP Error %s' % e
.cause
.code
679 self
.report_warning(error_to_compat_str(e
))
683 # Youtube may send alerts if there was an issue with the continuation page
685 self
._extract
_and
_report
_alerts
(response
, expected
=False)
686 except ExtractorError
as e
:
689 self
.report_warning(error_to_compat_str(e
))
691 if not check_get_keys
or dict_get(response
, check_get_keys
):
693 # Youtube sometimes sends incomplete data
694 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
695 last_error
= 'Incomplete data received'
698 raise ExtractorError(last_error
)
700 self
.report_warning(last_error
)
705 def is_music_url(url
):
706 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
708 def _extract_video(self
, renderer
):
709 video_id
= renderer
.get('videoId')
712 (lambda x
: x
['title']['runs'][0]['text'],
713 lambda x
: x
['title']['simpleText']), compat_str
)
714 description
= try_get(
715 renderer
, lambda x
: x
['descriptionSnippet']['runs'][0]['text'],
717 duration
= parse_duration(try_get(
718 renderer
, lambda x
: x
['lengthText']['simpleText'], compat_str
))
719 view_count_text
= try_get(
720 renderer
, lambda x
: x
['viewCountText']['simpleText'], compat_str
) or ''
721 view_count
= str_to_int(self
._search
_regex
(
722 r
'^([\d,]+)', re
.sub(r
'\s', '', view_count_text
),
723 'view count', default
=None))
726 (lambda x
: x
['ownerText']['runs'][0]['text'],
727 lambda x
: x
['shortBylineText']['runs'][0]['text']), compat_str
)
730 'ie_key': YoutubeIE
.ie_key(),
734 'description': description
,
735 'duration': duration
,
736 'view_count': view_count
,
737 'uploader': uploader
,
741 class YoutubeIE(YoutubeBaseInfoExtractor
):
742 IE_DESC
= 'YouTube.com'
744 # invidious-redirect websites
745 r
'(?:www\.)?redirect\.invidious\.io',
746 r
'(?:(?:www|dev)\.)?invidio\.us',
747 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
748 r
'(?:www\.)?invidious\.pussthecat\.org',
749 r
'(?:www\.)?invidious\.zee\.li',
750 r
'(?:www\.)?invidious\.ethibox\.fr',
751 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
752 # youtube-dl invidious instances list
753 r
'(?:(?:www|no)\.)?invidiou\.sh',
754 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
755 r
'(?:www\.)?invidious\.kabi\.tk',
756 r
'(?:www\.)?invidious\.mastodon\.host',
757 r
'(?:www\.)?invidious\.zapashcanon\.fr',
758 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
759 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
760 r
'(?:www\.)?invidious\.himiko\.cloud',
761 r
'(?:www\.)?invidious\.reallyancient\.tech',
762 r
'(?:www\.)?invidious\.tube',
763 r
'(?:www\.)?invidiou\.site',
764 r
'(?:www\.)?invidious\.site',
765 r
'(?:www\.)?invidious\.xyz',
766 r
'(?:www\.)?invidious\.nixnet\.xyz',
767 r
'(?:www\.)?invidious\.048596\.xyz',
768 r
'(?:www\.)?invidious\.drycat\.fr',
769 r
'(?:www\.)?inv\.skyn3t\.in',
770 r
'(?:www\.)?tube\.poal\.co',
771 r
'(?:www\.)?tube\.connect\.cafe',
772 r
'(?:www\.)?vid\.wxzm\.sx',
773 r
'(?:www\.)?vid\.mint\.lgbt',
774 r
'(?:www\.)?vid\.puffyan\.us',
775 r
'(?:www\.)?yewtu\.be',
776 r
'(?:www\.)?yt\.elukerio\.org',
777 r
'(?:www\.)?yt\.lelux\.fi',
778 r
'(?:www\.)?invidious\.ggc-project\.de',
779 r
'(?:www\.)?yt\.maisputain\.ovh',
780 r
'(?:www\.)?ytprivate\.com',
781 r
'(?:www\.)?invidious\.13ad\.de',
782 r
'(?:www\.)?invidious\.toot\.koeln',
783 r
'(?:www\.)?invidious\.fdn\.fr',
784 r
'(?:www\.)?watch\.nettohikari\.com',
785 r
'(?:www\.)?invidious\.namazso\.eu',
786 r
'(?:www\.)?invidious\.silkky\.cloud',
787 r
'(?:www\.)?invidious\.exonip\.de',
788 r
'(?:www\.)?invidious\.riverside\.rocks',
789 r
'(?:www\.)?invidious\.blamefran\.net',
790 r
'(?:www\.)?invidious\.moomoo\.de',
791 r
'(?:www\.)?ytb\.trom\.tf',
792 r
'(?:www\.)?yt\.cyberhost\.uk',
793 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
794 r
'(?:www\.)?qklhadlycap4cnod\.onion',
795 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
796 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
797 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
798 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
799 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
800 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
801 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
802 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
803 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
804 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
806 _VALID_URL
= r
"""(?x)^
808 (?:https?://|//) # http(s):// or protocol-independent URL
809 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
810 (?:www\.)?deturl\.com/www\.youtube\.com|
811 (?:www\.)?pwnyoutube\.com|
812 (?:www\.)?hooktube\.com|
813 (?:www\.)?yourepeat\.com|
816 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
817 (?:.*?\#/)? # handle anchor (#/) redirect urls
818 (?: # the various things that can precede the ID:
819 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
820 |(?: # or the v= param in all its forms
821 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
822 (?:\?|\#!?) # the params delimiter ? or # or #!
823 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
828 youtu\.be| # just youtu.be/xxxx
829 vid\.plus| # or vid.plus/xxxx
830 zwearz\.com/watch| # or zwearz.com/watch/xxxx
833 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
835 )? # all until now is optional -> you can pass the naked ID
836 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
837 (?(1).+)? # if we found the ID, everything can follow
839 'invidious': '|'.join(_INVIDIOUS_SITES
),
842 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
843 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$',
844 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
847 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
848 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
849 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
850 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
851 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
852 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
853 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
854 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
855 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
856 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
857 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
858 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
859 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
860 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
861 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
862 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
863 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
864 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
868 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
869 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
870 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
871 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
872 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
873 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
874 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
876 # Apple HTTP Live Streaming
877 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
878 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
879 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
880 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
881 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
882 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
883 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
884 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
887 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
888 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
889 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
890 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
891 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
892 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
893 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
894 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
895 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
896 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
897 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
898 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
901 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
902 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
903 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
904 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
905 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
906 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
907 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
910 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
911 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
912 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
913 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
914 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
915 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
916 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
917 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
918 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
919 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
920 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
921 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
922 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
923 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
924 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
925 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
926 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
927 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
928 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
929 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
930 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
931 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
934 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
935 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
937 # Dash webm audio with opus inside
938 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
939 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
940 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
943 '_rtmp': {'protocol': 'rtmp'}
,
945 # av01 video only formats sometimes served with "unknown" codecs
946 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
947 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
948 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
949 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
951 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
953 _AGE_GATE_REASONS
= (
954 'Sign in to confirm your age',
955 'This video may be inappropriate for some users.',
956 'Sorry, this content is age-restricted.')
963 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
967 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
968 'uploader': 'Philipp Hagemeister',
969 'uploader_id': 'phihag',
970 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
971 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
972 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
973 'upload_date': '20121002',
974 '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 .',
975 'categories': ['Science & Technology'],
976 'tags': ['youtube-dl'],
980 'dislike_count': int,
986 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
987 'note': 'Embed-only video (#1746)',
991 'upload_date': '20120608',
992 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
993 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
994 'uploader': 'SET India',
995 'uploader_id': 'setindia',
996 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
999 'skip': 'Private video',
1002 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1003 'note': 'Use the first video ID in the URL',
1005 'id': 'BaW_jenozKc',
1007 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1008 'uploader': 'Philipp Hagemeister',
1009 'uploader_id': 'phihag',
1010 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1011 'upload_date': '20121002',
1012 '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 .',
1013 'categories': ['Science & Technology'],
1014 'tags': ['youtube-dl'],
1018 'dislike_count': int,
1021 'skip_download': True,
1025 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1026 'note': '256k DASH audio (format 141) via DASH manifest',
1028 'id': 'a9LDPn-MO4I',
1030 'upload_date': '20121002',
1031 'uploader_id': '8KVIDEO',
1032 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1034 'uploader': '8KVIDEO',
1035 'title': 'UHDTV TEST 8K VIDEO.mp4'
1038 'youtube_include_dash_manifest': True,
1041 'skip': 'format 141 not served anymore',
1043 # DASH manifest with encrypted signature
1045 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1047 'id': 'IB3lcPjvWLA',
1049 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1050 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1052 'uploader': 'AfrojackVEVO',
1053 'uploader_id': 'AfrojackVEVO',
1054 'upload_date': '20131011',
1058 'youtube_include_dash_manifest': True,
1059 'format': '141/bestaudio[ext=m4a]',
1064 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
1066 'id': 'T4XJQO3qol8',
1069 'upload_date': '20100909',
1070 'uploader': 'Amazing Atheist',
1071 'uploader_id': 'TheAmazingAtheist',
1072 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
1073 'title': 'Burning Everyone\'s Koran',
1074 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
1077 # Normal age-gate video (embed allowed)
1079 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
1081 'id': 'HtVdAasjOgU',
1083 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
1084 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
1086 'uploader': 'The Witcher',
1087 'uploader_id': 'WitcherGame',
1088 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
1089 'upload_date': '20140605',
1093 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
1094 # YouTube Red ad is not captured for creator
1096 'url': '__2ABJjxzNo',
1098 'id': '__2ABJjxzNo',
1101 'upload_date': '20100430',
1102 'uploader_id': 'deadmau5',
1103 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
1104 'creator': 'deadmau5',
1105 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
1106 'uploader': 'deadmau5',
1107 'title': 'Deadmau5 - Some Chords (HD)',
1108 'alt_title': 'Some Chords',
1110 'expected_warnings': [
1111 'DASH manifest missing',
1114 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
1116 'url': 'lqQg6PlCWgI',
1118 'id': 'lqQg6PlCWgI',
1121 'upload_date': '20150827',
1122 'uploader_id': 'olympic',
1123 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
1124 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
1125 'uploader': 'Olympic',
1126 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
1129 'skip_download': 'requires avconv',
1134 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
1136 'id': '_b-2C3KPAM0',
1138 'stretched_ratio': 16 / 9.,
1140 'upload_date': '20110310',
1141 'uploader_id': 'AllenMeow',
1142 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
1143 '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',
1145 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
1148 # url_encoded_fmt_stream_map is empty string
1150 'url': 'qEJwOuvDf7I',
1152 'id': 'qEJwOuvDf7I',
1154 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
1156 'upload_date': '20150404',
1157 'uploader_id': 'spbelect',
1158 'uploader': 'Наблюдатели Петербурга',
1161 'skip_download': 'requires avconv',
1163 'skip': 'This live event has ended.',
1165 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
1167 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
1169 'id': 'FIl7x6_3R5Y',
1171 'title': 'md5:7b81415841e02ecd4313668cde88737a',
1172 'description': 'md5:116377fd2963b81ec4ce64b542173306',
1174 'upload_date': '20150625',
1175 'uploader_id': 'dorappi2000',
1176 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
1177 'uploader': 'dorappi2000',
1178 'formats': 'mincount:31',
1180 'skip': 'not actual anymore',
1182 # DASH manifest with segment_list
1184 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
1185 'md5': '8ce563a1d667b599d21064e982ab9e31',
1187 'id': 'CsmdDsKjzN8',
1189 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
1190 'uploader': 'Airtek',
1191 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
1192 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
1193 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
1196 'youtube_include_dash_manifest': True,
1197 'format': '135', # bestvideo
1199 'skip': 'This live event has ended.',
1202 # Multifeed videos (multiple cameras), URL is for Main Camera
1203 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
1205 'id': 'jvGDaLqkpTg',
1206 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
1207 'description': 'md5:e03b909557865076822aa169218d6a5d',
1211 'id': 'jvGDaLqkpTg',
1213 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
1214 'description': 'md5:e03b909557865076822aa169218d6a5d',
1216 'upload_date': '20161111',
1217 'uploader': 'Team PGP',
1218 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1219 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1223 'id': '3AKt1R1aDnw',
1225 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
1226 'description': 'md5:e03b909557865076822aa169218d6a5d',
1228 'upload_date': '20161111',
1229 'uploader': 'Team PGP',
1230 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1231 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1235 'id': 'RtAMM00gpVc',
1237 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
1238 'description': 'md5:e03b909557865076822aa169218d6a5d',
1240 'upload_date': '20161111',
1241 'uploader': 'Team PGP',
1242 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1243 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1247 'id': '6N2fdlP3C5U',
1249 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
1250 'description': 'md5:e03b909557865076822aa169218d6a5d',
1252 'upload_date': '20161111',
1253 'uploader': 'Team PGP',
1254 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
1255 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
1259 'skip_download': True,
1263 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
1264 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
1266 'id': 'gVfLd0zydlo',
1267 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
1269 'playlist_count': 2,
1270 'skip': 'Not multifeed anymore',
1273 'url': 'https://vid.plus/FlRa-iH7PGw',
1274 'only_matching': True,
1277 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
1278 'only_matching': True,
1281 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1282 # Also tests cut-off URL expansion in video description (see
1283 # https://github.com/ytdl-org/youtube-dl/issues/1892,
1284 # https://github.com/ytdl-org/youtube-dl/issues/8164)
1285 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
1287 'id': 'lsguqyKfVQg',
1289 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
1290 'alt_title': 'Dark Walk - Position Music',
1291 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
1293 'upload_date': '20151119',
1294 'uploader_id': 'IronSoulElf',
1295 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
1296 'uploader': 'IronSoulElf',
1297 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
1298 'track': 'Dark Walk - Position Music',
1299 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
1300 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
1303 'skip_download': True,
1307 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
1308 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
1309 'only_matching': True,
1312 # Video with yt:stretch=17:0
1313 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
1315 'id': 'Q39EVAstoRM',
1317 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
1318 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1319 'upload_date': '20151107',
1320 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1321 'uploader': 'CH GAMER DROID',
1324 'skip_download': True,
1326 'skip': 'This video does not exist.',
1329 # Video with incomplete 'yt:stretch=16:'
1330 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1331 'only_matching': True,
1334 # Video licensed under Creative Commons
1335 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1337 'id': 'M4gD1WSo5mA',
1339 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1340 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1342 'upload_date': '20150127',
1343 'uploader_id': 'BerkmanCenter',
1344 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1345 'uploader': 'The Berkman Klein Center for Internet & Society',
1346 'license': 'Creative Commons Attribution license (reuse allowed)',
1349 'skip_download': True,
1353 # Channel-like uploader_url
1354 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1356 'id': 'eQcmzGIKrzg',
1358 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1359 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1361 'upload_date': '20151119',
1362 'uploader': 'Bernie Sanders',
1363 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1364 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1365 'license': 'Creative Commons Attribution license (reuse allowed)',
1368 'skip_download': True,
1372 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1373 'only_matching': True,
1376 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1377 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1378 'only_matching': True,
1381 # Rental video preview
1382 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1384 'id': 'uGpuVWrhIzE',
1386 'title': 'Piku - Trailer',
1387 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1388 'upload_date': '20150811',
1389 'uploader': 'FlixMatrix',
1390 'uploader_id': 'FlixMatrixKaravan',
1391 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1392 'license': 'Standard YouTube License',
1395 'skip_download': True,
1397 'skip': 'This video is not available.',
1400 # YouTube Red video with episode data
1401 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1403 'id': 'iqKdEhx-dD4',
1405 'title': 'Isolation - Mind Field (Ep 1)',
1406 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1408 'upload_date': '20170118',
1409 'uploader': 'Vsauce',
1410 'uploader_id': 'Vsauce',
1411 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1412 'series': 'Mind Field',
1414 'episode_number': 1,
1417 'skip_download': True,
1419 'expected_warnings': [
1420 'Skipping DASH manifest',
1424 # The following content has been identified by the YouTube community
1425 # as inappropriate or offensive to some audiences.
1426 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1428 'id': '6SJNVb0GnPI',
1430 'title': 'Race Differences in Intelligence',
1431 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1433 'upload_date': '20140124',
1434 'uploader': 'New Century Foundation',
1435 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1436 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1439 'skip_download': True,
1441 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1445 'url': '1t24XAntNCY',
1446 'only_matching': True,
1449 # geo restricted to JP
1450 'url': 'sJL6WA-aGkQ',
1451 'only_matching': True,
1454 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1455 'only_matching': True,
1458 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1459 'only_matching': True,
1462 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1463 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1464 'only_matching': True,
1468 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1469 'only_matching': True,
1472 # Video with unsupported adaptive stream type formats
1473 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1475 'id': 'Z4Vy8R84T1U',
1477 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1478 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1480 'upload_date': '20130923',
1481 'uploader': 'Amelia Putri Harwita',
1482 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1483 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1484 'formats': 'maxcount:10',
1487 'skip_download': True,
1488 'youtube_include_dash_manifest': False,
1490 'skip': 'not actual anymore',
1493 # Youtube Music Auto-generated description
1494 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1496 'id': 'MgNrAu2pzNs',
1498 'title': 'Voyeur Girl',
1499 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1500 'upload_date': '20190312',
1501 'uploader': 'Stephen - Topic',
1502 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1503 'artist': 'Stephen',
1504 'track': 'Voyeur Girl',
1505 'album': 'it\'s too much love to know my dear',
1506 'release_date': '20190313',
1507 'release_year': 2019,
1510 'skip_download': True,
1514 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1515 'only_matching': True,
1518 # invalid -> valid video id redirection
1519 'url': 'DJztXj2GPfl',
1521 'id': 'DJztXj2GPfk',
1523 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1524 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1525 'upload_date': '20090125',
1526 'uploader': 'Prochorowka',
1527 'uploader_id': 'Prochorowka',
1528 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1529 'artist': 'Panjabi MC',
1530 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1531 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1534 'skip_download': True,
1536 'skip': 'Video unavailable',
1539 # empty description results in an empty string
1540 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1542 'id': 'x41yOUIvK2k',
1544 'title': 'IMG 3456',
1546 'upload_date': '20170613',
1547 'uploader_id': 'ElevageOrVert',
1548 'uploader': 'ElevageOrVert',
1551 'skip_download': True,
1555 # with '};' inside yt initial data (see [1])
1556 # see [2] for an example with '};' inside ytInitialPlayerResponse
1557 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1558 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1559 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1561 'id': 'CHqg6qOn4no',
1563 'title': 'Part 77 Sort a list of simple types in c#',
1564 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1565 'upload_date': '20130831',
1566 'uploader_id': 'kudvenkat',
1567 'uploader': 'kudvenkat',
1570 'skip_download': True,
1574 # another example of '};' in ytInitialData
1575 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1576 'only_matching': True,
1579 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1580 'only_matching': True,
1583 # https://github.com/ytdl-org/youtube-dl/pull/28094
1584 'url': 'OtqTfy26tG0',
1586 'id': 'OtqTfy26tG0',
1588 'title': 'Burn Out',
1589 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1590 'upload_date': '20141120',
1591 'uploader': 'The Cinematic Orchestra - Topic',
1592 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1593 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1594 'artist': 'The Cinematic Orchestra',
1595 'track': 'Burn Out',
1596 'album': 'Every Day',
1597 'release_data': None,
1598 'release_year': None,
1601 'skip_download': True,
1605 # controversial video, only works with bpctr when authenticated with cookies
1606 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1607 'only_matching': True,
1610 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1611 'url': 'cBvYw8_A0vQ',
1613 'id': 'cBvYw8_A0vQ',
1615 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1616 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1617 'upload_date': '20201120',
1618 'uploader': 'Walk around Japan',
1619 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1620 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1623 'skip_download': True,
1626 # Has multiple audio streams
1627 'url': 'WaOKSUlf4TM',
1628 'only_matching': True
1630 # Requires Premium: has format 141 when requested using YTM url
1631 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1632 'only_matching': True
1634 # multiple subtitles with same lang_code
1635 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1636 'only_matching': True,
1638 # Force use android client fallback
1639 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1641 'id': 'YOelRv7fMxY',
1642 'title': 'Digging a Secret Tunnel from my Workshop',
1644 'upload_date': '20210624',
1645 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1646 'uploader': 'colinfurze',
1647 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
1648 'description': 'md5:ecb672623246d98c6c562eed6ae798c3'
1651 'format': '17', # 3gp format available on android
1652 'extractor_args': {'youtube': {'player_client': ['android']}
},
1656 # Skip download of additional client configs (remix client config in this case)
1657 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1658 'only_matching': True,
1660 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
1666 def suitable(cls
, url
):
1667 # Hack for lazy extractors until more generic solution is implemented
1669 from .youtube
import parse_qs
1671 if qs
.get('list', [None])[0]:
1673 return super(YoutubeIE
, cls
).suitable(url
)
1675 def __init__(self
, *args
, **kwargs
):
1676 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1677 self
._code
_cache
= {}
1678 self
._player
_cache
= {}
1680 def _extract_player_url(self
, ytcfg
=None, webpage
=None):
1681 player_url
= try_get(ytcfg
, (lambda x
: x
['PLAYER_JS_URL']), str)
1683 player_url
= self
._search
_regex
(
1684 r
'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1685 webpage
, 'player URL', fatal
=False)
1686 if player_url
.startswith('//'):
1687 player_url
= 'https:' + player_url
1688 elif not re
.match(r
'https?://', player_url
):
1689 player_url
= compat_urlparse
.urljoin(
1690 'https://www.youtube.com', player_url
)
1693 def _signature_cache_id(self
, example_sig
):
1694 """ Return a string representation of a signature """
1695 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1698 def _extract_player_info(cls
, player_url
):
1699 for player_re
in cls
._PLAYER
_INFO
_RE
:
1700 id_m
= re
.search(player_re
, player_url
)
1704 raise ExtractorError('Cannot identify player %r' % player_url
)
1705 return id_m
.group('id')
1707 def _load_player(self
, video_id
, player_url
, fatal
=True) -> bool:
1708 player_id
= self
._extract
_player
_info
(player_url
)
1709 if player_id
not in self
._code
_cache
:
1710 self
._code
_cache
[player_id
] = self
._download
_webpage
(
1711 player_url
, video_id
, fatal
=fatal
,
1712 note
='Downloading player ' + player_id
,
1713 errnote
='Download of %s failed' % player_url
)
1714 return player_id
in self
._code
_cache
1716 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1717 player_id
= self
._extract
_player
_info
(player_url
)
1719 # Read from filesystem cache
1720 func_id
= 'js_%s_%s' % (
1721 player_id
, self
._signature
_cache
_id
(example_sig
))
1722 assert os
.path
.basename(func_id
) == func_id
1724 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1725 if cache_spec
is not None:
1726 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1728 if self
._load
_player
(video_id
, player_url
):
1729 code
= self
._code
_cache
[player_id
]
1730 res
= self
._parse
_sig
_js
(code
)
1732 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1733 cache_res
= res(test_string
)
1734 cache_spec
= [ord(c
) for c
in cache_res
]
1736 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1739 def _print_sig_code(self
, func
, example_sig
):
1740 def gen_sig_code(idxs
):
1741 def _genslice(start
, end
, step
):
1742 starts
= '' if start
== 0 else str(start
)
1743 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1744 steps
= '' if step
== 1 else (':%d' % step
)
1745 return 's[%s%s%s]' % (starts
, ends
, steps
)
1748 # Quelch pyflakes warnings - start will be set when step is set
1749 start
= '(Never used)'
1750 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1751 if step
is not None:
1752 if i
- prev
== step
:
1754 yield _genslice(start
, prev
, step
)
1757 if i
- prev
in [-1, 1]:
1762 yield 's[%d]' % prev
1766 yield _genslice(start
, i
, step
)
1768 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1769 cache_res
= func(test_string
)
1770 cache_spec
= [ord(c
) for c
in cache_res
]
1771 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1772 signature_id_tuple
= '(%s)' % (
1773 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1774 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1775 ' return %s\n') % (signature_id_tuple
, expr_code
)
1776 self
.to_screen('Extracted signature function:\n' + code
)
1778 def _parse_sig_js(self
, jscode
):
1779 funcname
= self
._search
_regex
(
1780 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1781 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1782 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
1783 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
1784 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}\(a,\d+\)',
1785 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\(\s*""\s*\)',
1786 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1788 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1789 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1790 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1791 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1792 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1793 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1794 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1795 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1796 jscode, 'Initial JS player signature function name
', group='sig
')
1798 jsi = JSInterpreter(jscode)
1799 initial_function = jsi.extract_function(funcname)
1800 return lambda s: initial_function([s])
1802 def _decrypt_signature(self, s, video_id, player_url):
1803 """Turn the encrypted s field into a working signature"""
1805 if player_url is None:
1806 raise ExtractorError('Cannot decrypt signature without player_url
')
1809 player_id = (player_url, self._signature_cache_id(s))
1810 if player_id not in self._player_cache:
1811 func = self._extract_signature_function(
1812 video_id, player_url, s
1814 self._player_cache[player_id] = func
1815 func = self._player_cache[player_id]
1816 if self.get_param('youtube_print_sig_code
'):
1817 self._print_sig_code(func, s)
1819 except Exception as e:
1820 tb = traceback.format_exc()
1821 raise ExtractorError(
1822 'Signature extraction failed
: ' + tb, cause=e)
1824 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
1826 Extract signatureTimestamp (sts)
1827 Required to tell API what sig/player version is in use.
1830 if isinstance(ytcfg, dict):
1831 sts = int_or_none(ytcfg.get('STS
'))
1834 # Attempt to extract from player
1835 if player_url is None:
1836 error_msg = 'Cannot extract signature timestamp without player_url
.'
1838 raise ExtractorError(error_msg)
1839 self.report_warning(error_msg)
1841 if self._load_player(video_id, player_url, fatal=fatal):
1842 player_id = self._extract_player_info(player_url)
1843 code = self._code_cache[player_id]
1844 sts = int_or_none(self._search_regex(
1845 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
1846 'JS player signature timestamp
', group='sts
', fatal=fatal))
1849 def _mark_watched(self, video_id, player_response):
1850 playback_url = url_or_none(try_get(
1852 lambda x: x['playbackTracking
']['videostatsPlaybackUrl
']['baseUrl
']))
1853 if not playback_url:
1855 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1856 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1858 # cpn generation algorithm is reverse engineered from base.js.
1859 # In fact it works even with dummy cpn.
1860 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
1861 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1867 playback_url = compat_urlparse.urlunparse(
1868 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1870 self._download_webpage(
1871 playback_url, video_id, 'Marking watched
',
1872 'Unable to mark watched
', fatal=False)
1875 def _extract_urls(webpage):
1876 # Embedded YouTube player
1878 unescapeHTML(mobj.group('url
'))
1879 for mobj in re.finditer(r'''(?x)
1889 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1890 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1893 # lazyYT YouTube embed
1894 entries.extend(list(map(
1896 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
1898 # Wordpress "YouTube Video Importer
" plugin
1899 matches = re.findall(r'''(?x)<div[^>]+
1900 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
1901 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
1902 entries.extend(m[-1] for m in matches)
1907 def _extract_url(webpage):
1908 urls = YoutubeIE._extract_urls(webpage)
1909 return urls[0] if urls else None
1912 def extract_id(cls, url):
1913 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1915 raise ExtractorError('Invalid URL: %s' % url)
1916 video_id = mobj.group(2)
1919 def _extract_chapters_from_json(self, data, video_id, duration):
1920 chapters_list = try_get(
1922 lambda x: x['playerOverlays']
1923 ['playerOverlayRenderer']
1924 ['decoratedPlayerBarRenderer']
1925 ['decoratedPlayerBarRenderer']
1927 ['chapteredPlayerBarRenderer']
1930 if not chapters_list:
1933 def chapter_time(chapter):
1934 return float_or_none(
1937 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1941 for next_num, chapter in enumerate(chapters_list, start=1):
1942 start_time = chapter_time(chapter)
1943 if start_time is None:
1945 end_time = (chapter_time(chapters_list[next_num])
1946 if next_num < len(chapters_list) else duration)
1947 if end_time is None:
1950 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1953 'start_time': start_time,
1954 'end_time': end_time,
1959 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
1960 return self._parse_json(self._search_regex(
1961 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
1962 regex), webpage, name, default='{}'), video_id, fatal=False)
1965 def parse_time_text(time_text):
1967 Parse the comment time text
1968 time_text is in the format 'X units ago (edited)'
1970 time_text_split = time_text.split(' ')
1971 if len(time_text_split) >= 3:
1972 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
1975 def _join_text_entries(runs):
1978 if not isinstance(run, dict):
1980 sub_text = try_get(run, lambda x: x['text'], compat_str)
1988 def _extract_comment(self, comment_renderer, parent=None):
1989 comment_id = comment_renderer.get('commentId')
1992 comment_text_runs = try_get(comment_renderer, lambda x: x['contentText']['runs']) or []
1993 text = self._join_text_entries(comment_text_runs) or ''
1994 comment_time_text = try_get(comment_renderer, lambda x: x['publishedTimeText']['runs']) or []
1995 time_text = self._join_text_entries(comment_time_text)
1996 # note: timestamp is an estimate calculated from the current time and time_text
1997 timestamp = calendar.timegm(self.parse_time_text(time_text).timetuple())
1998 author = try_get(comment_renderer, lambda x: x['authorText']['simpleText'], compat_str)
1999 author_id = try_get(comment_renderer,
2000 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2001 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2002 lambda x: x['likeCount']), compat_str)) or 0
2003 author_thumbnail = try_get(comment_renderer,
2004 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2006 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2007 is_favorited = 'creatorHeart' in (try_get(
2008 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2012 'timestamp': timestamp,
2013 'time_text': time_text,
2014 'like_count': votes,
2015 'is_favorited': is_favorited,
2017 'author_id': author_id,
2018 'author_thumbnail': author_thumbnail,
2019 'author_is_uploader': author_is_uploader,
2020 'parent': parent or 'root'
2023 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
2024 ytcfg, video_id, parent=None, comment_counts=None):
2026 def extract_header(contents):
2028 _continuation = None
2029 for content in contents:
2030 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
2031 expected_comment_count = try_get(comments_header_renderer,
2032 (lambda x: x['countText']['runs'][0]['text'],
2033 lambda x: x['commentsCount']['runs'][0]['text']),
2035 if expected_comment_count:
2036 comment_counts[1] = str_to_int(expected_comment_count)
2037 self.to_screen('Downloading ~%d comments' % str_to_int(expected_comment_count))
2038 _total_comments = comment_counts[1]
2039 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2040 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2042 sort_menu_item = try_get(
2043 comments_header_renderer,
2044 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2045 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2047 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2048 if not _continuation:
2051 sort_text = sort_menu_item.get('title')
2052 if isinstance(sort_text, compat_str):
2053 sort_text = sort_text.lower()
2055 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2056 self.to_screen('Sorting comments by %s' % sort_text)
2058 return _total_comments, _continuation
2060 def extract_thread(contents):
2062 comment_counts[2] = 0
2063 for content in contents:
2064 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2065 comment_renderer = try_get(
2066 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2067 content, (lambda x: x['commentRenderer'], dict))
2069 if not comment_renderer:
2071 comment = self._extract_comment(comment_renderer, parent)
2074 comment_counts[0] += 1
2076 # Attempt to get the replies
2077 comment_replies_renderer = try_get(
2078 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2080 if comment_replies_renderer:
2081 comment_counts[2] += 1
2082 comment_entries_iter = self._comment_entries(
2083 comment_replies_renderer, identity_token, account_syncid, ytcfg,
2084 video_id, parent=comment.get('id'), comment_counts=comment_counts)
2086 for reply_comment in comment_entries_iter:
2089 # YouTube comments have a max depth of 2
2090 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2091 if max_depth == 1 and parent:
2093 if not comment_counts:
2094 # comment so far, est. total comments, current comment thread #
2095 comment_counts = [0, 0, 0]
2097 continuation = self._extract_continuation(root_continuation_data)
2098 if continuation and len(continuation['ctoken']) < 27:
2099 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2100 continuation_token = self._generate_comment_continuation(video_id)
2101 continuation = self._build_continuation_query(continuation_token, None)
2104 is_first_continuation = parent is None
2106 for page_num in itertools.count(0):
2107 if not continuation:
2109 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
2110 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2112 if is_first_continuation:
2113 note_prefix = 'Downloading comment section API JSON'
2115 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2116 comment_counts[2], comment_prog_str)
2118 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2119 ' ' if parent else '', ' replies' if parent else '',
2120 page_num, comment_prog_str)
2122 response = self._extract_response(
2123 item_id=None, query=self._continuation_query_ajax_to_api(continuation),
2124 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2125 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
2128 visitor_data = try_get(
2130 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2131 compat_str) or visitor_data
2133 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
2136 if isinstance(continuation_contents, list):
2137 for continuation_section in continuation_contents:
2138 if not isinstance(continuation_section, dict):
2140 continuation_items = try_get(
2141 continuation_section,
2142 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2143 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2145 if is_first_continuation:
2146 total_comments, continuation = extract_header(continuation_items)
2148 yield total_comments
2149 is_first_continuation = False
2154 for count, entry in enumerate(extract_thread(continuation_items)):
2156 continuation = self._extract_continuation({'contents': continuation_items})
2158 # Sometimes YouTube provides a continuation without any comments
2159 # In most cases we end up just downloading these with very little comments to come.
2162 self.report_warning('No comments received - assuming end of comments')
2166 # Deprecated response structure
2167 elif isinstance(continuation_contents, dict):
2168 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2169 for key, continuation_renderer in continuation_contents.items():
2170 if key not in known_continuation_renderers:
2172 if not isinstance(continuation_renderer, dict):
2174 if is_first_continuation:
2175 header_continuation_items = [continuation_renderer.get('header') or {}]
2176 total_comments, continuation = extract_header(header_continuation_items)
2178 yield total_comments
2179 is_first_continuation = False
2183 # Sometimes YouTube provides a continuation without any comments
2184 # In most cases we end up just downloading these with very little comments to come.
2186 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2188 continuation = self._extract_continuation(continuation_renderer)
2191 self.report_warning('No comments received - assuming end of comments')
2196 def _generate_comment_continuation(video_id):
2198 Generates initial comment section continuation token from given video id
2200 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2201 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2202 new_continuation_intlist = list(itertools.chain.from_iterable(
2203 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2204 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2206 def _extract_comments(self, ytcfg, video_id, contents, webpage):
2207 """Entry for comment extraction"""
2208 def _real_comment_extract(contents):
2209 if isinstance(contents, list):
2210 for entry in contents:
2211 for key, renderer in entry.items():
2212 if key not in known_entry_comment_renderers:
2214 yield from self._comment_entries(
2215 renderer, video_id=video_id, ytcfg=ytcfg,
2216 identity_token=self._extract_identity_token(webpage, item_id=video_id),
2217 account_syncid=self._extract_account_syncid(ytcfg))
2220 known_entry_comment_renderers = ('itemSectionRenderer',)
2222 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf')
2225 for comment in _real_comment_extract(contents):
2226 if len(comments) >= max_comments:
2228 if isinstance(comment, int):
2229 estimated_total = comment
2231 comments.append(comment)
2232 except KeyboardInterrupt:
2233 self.to_screen('Interrupted by user')
2234 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
2236 'comments': comments,
2237 'comment_count': len(comments),
2241 def _generate_player_context(sts=None):
2243 'html5Preference': 'HTML5_PREF_WANTS',
2246 context['signatureTimestamp'] = sts
2248 'playbackContext': {
2249 'contentPlaybackContext': context
2254 def _get_video_info_params(video_id, client='TVHTML5'):
2262 'cver': '6.20180913',
2266 'video_id': video_id,
2267 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
2270 query.update(GVI_CLIENTS.get(client))
2273 def _real_extract(self, url):
2274 url, smuggled_data = unsmuggle_url(url, {})
2275 video_id = self._match_id(url)
2277 is_music_url = smuggled_data.get('is_music_url') or self.is_music_url(url)
2279 base_url = self.http_scheme() + '//www.youtube.com/'
2280 webpage_url = base_url + 'watch?v=' + video_id
2281 webpage = self._download_webpage(
2282 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
2284 ytcfg = self._extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
2285 identity_token = self._extract_identity_token(webpage, video_id)
2286 syncid = self._extract_account_syncid(ytcfg)
2287 headers = self._generate_api_headers(ytcfg, identity_token, syncid)
2289 player_url = self._extract_player_url(ytcfg, webpage)
2291 player_client = self._configuration_arg('player_client', [''])[0]
2292 if player_client not in ('web', 'android', ''):
2293 self.report_warning(f'Invalid player_client {player_client} given. Falling back to android client.')
2294 force_mobile_client = player_client != 'web'
2295 player_skip = self._configuration_arg('player_skip')
2300 text = x.get('simpleText')
2301 if text and isinstance(text, compat_str):
2303 runs = x.get('runs')
2304 if not isinstance(runs, list):
2306 return ''.join([r['text'] for r in runs if isinstance(r.get('text'), compat_str)])
2308 ytm_streaming_data = {}
2311 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2312 if sts and not force_mobile_client and 'configs' not in player_skip:
2313 ytm_webpage = self._download_webpage(
2314 'https://music.youtube.com',
2315 video_id, fatal=False, note='Downloading remix client config')
2317 ytm_cfg = self._extract_ytcfg(video_id, ytm_webpage) or {}
2318 ytm_client = 'WEB_REMIX'
2319 if not sts or force_mobile_client:
2320 # Android client already has signature descrambled
2321 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2323 self.report_warning('Falling back to android remix client for player API.')
2324 ytm_client = 'ANDROID_MUSIC'
2327 ytm_headers = self._generate_api_headers(
2328 ytm_cfg, identity_token, syncid,
2330 ytm_query = {'videoId': video_id}
2331 ytm_query.update(self._generate_player_context(sts))
2333 ytm_player_response = self._extract_response(
2334 item_id=video_id, ep='player', query=ytm_query,
2335 ytcfg=ytm_cfg, headers=ytm_headers, fatal=False,
2336 default_client=ytm_client,
2337 note='Downloading %sremix player API JSON' % ('android ' if force_mobile_client else ''))
2338 ytm_streaming_data = try_get(ytm_player_response, lambda x: x['streamingData'], dict) or {}
2340 player_response = None
2342 player_response = self._extract_yt_initial_variable(
2343 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2344 video_id, 'initial player response')
2346 if not player_response or force_mobile_client:
2347 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2350 ytp_headers = headers
2351 if not sts or force_mobile_client:
2352 # Android client already has signature descrambled
2353 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2355 self.report_warning('Falling back to android client for player API.')
2356 yt_client = 'ANDROID'
2358 ytp_headers = self._generate_api_headers(ytpcfg, identity_token, syncid, yt_client)
2360 yt_query = {'videoId': video_id}
2361 yt_query.update(self._generate_player_context(sts))
2362 player_response = self._extract_response(
2363 item_id=video_id, ep='player', query=yt_query,
2364 ytcfg=ytpcfg, headers=ytp_headers, fatal=False,
2365 default_client=yt_client,
2366 note='Downloading %splayer API JSON' % ('android ' if force_mobile_client else '')
2367 ) or player_response
2369 # Age-gate workarounds
2370 playability_status = player_response.get('playabilityStatus') or {}
2371 if playability_status.get('reason') in self._AGE_GATE_REASONS:
2372 gvi_clients = ('ANDROID', 'TVHTML5') if force_mobile_client else ('TVHTML5', 'ANDROID')
2373 for gvi_client in gvi_clients:
2374 pr = self._parse_json(try_get(compat_parse_qs(
2375 self._download_webpage(
2376 base_url + 'get_video_info', video_id,
2377 'Refetching age-gated %s info webpage' % gvi_client.lower(),
2378 'unable to download video info webpage', fatal=False,
2379 query=self._get_video_info_params(video_id, client=gvi_client))),
2380 lambda x: x['player_response'][0],
2381 compat_str) or '{}', video_id)
2385 self.report_warning('Falling back to embedded-only age-gate workaround.')
2386 embed_webpage = None
2387 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2388 if sts and not force_mobile_client and 'configs' not in player_skip:
2389 embed_webpage = self._download_webpage(
2390 'https://www.youtube.com/embed/%s?html5=1' % video_id,
2391 video_id=video_id, note='Downloading age-gated embed config')
2393 ytcfg_age = self._extract_ytcfg(video_id, embed_webpage) or {}
2394 # If we extracted the embed webpage, it'll tell us if we can view the video
2395 embedded_pr = self._parse_json(
2396 try_get(ytcfg_age, lambda x: x['PLAYER_VARS']['embedded_player_response'], str) or '{}',
2398 embedded_ps_reason = try_get(embedded_pr, lambda x: x['playabilityStatus']['reason'], str) or ''
2399 if embedded_ps_reason not in self._AGE_GATE_REASONS:
2400 yt_client = 'WEB_EMBEDDED_PLAYER'
2401 if not sts or force_mobile_client:
2402 # Android client already has signature descrambled
2403 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2405 self.report_warning(
2406 'Falling back to android embedded client for player API (note: some formats may be missing).')
2407 yt_client = 'ANDROID_EMBEDDED_PLAYER'
2410 ytage_headers = self._generate_api_headers(
2411 ytcfg_age, identity_token, syncid, client=yt_client)
2412 yt_age_query = {'videoId': video_id}
2413 yt_age_query.update(self._generate_player_context(sts))
2414 pr = self._extract_response(
2415 item_id=video_id, ep='player', query=yt_age_query,
2416 ytcfg=ytcfg_age, headers=ytage_headers, fatal=False,
2417 default_client=yt_client,
2418 note='Downloading %sage-gated player API JSON' % ('android ' if force_mobile_client else '')
2422 player_response = pr
2424 trailer_video_id = try_get(
2426 lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'],
2428 if trailer_video_id:
2429 return self.url_result(
2430 trailer_video_id, self.ie_key(), trailer_video_id)
2433 lambda x: self._html_search_meta(x, webpage, default=None)) \
2434 if webpage else lambda x: None
2436 video_details = player_response.get('videoDetails') or {}
2437 microformat = try_get(
2439 lambda x: x['microformat']['playerMicroformatRenderer'],
2441 video_title = video_details.get('title') \
2442 or get_text(microformat.get('title')) \
2443 or search_meta(['og:title', 'twitter:title', 'title'])
2444 video_description = video_details.get('shortDescription')
2446 if not smuggled_data.get('force_singlefeed', False):
2447 if not self.get_param('noplaylist'):
2448 multifeed_metadata_list = try_get(
2450 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
2452 if multifeed_metadata_list:
2455 for feed in multifeed_metadata_list.split(','):
2456 # Unquote should take place before split on comma (,) since textual
2457 # fields may contain comma as well (see
2458 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2459 feed_data = compat_parse_qs(
2460 compat_urllib_parse_unquote_plus(feed))
2462 def feed_entry(name):
2464 feed_data, lambda x: x[name][0], compat_str)
2466 feed_id = feed_entry('id')
2469 feed_title = feed_entry('title')
2472 title += ' (%s)' % feed_title
2474 '_type': 'url_transparent',
2475 'ie_key': 'Youtube',
2477 base_url + 'watch?v=' + feed_data['id'][0],
2478 {'force_singlefeed': True}),
2481 feed_ids.append(feed_id)
2483 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2484 % (', '.join(feed_ids), video_id))
2485 return self.playlist_result(
2486 entries, video_id, video_title, video_description)
2488 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2490 formats, itags, stream_ids = [], [], []
2493 # "tiny" is the smallest video-only format. But some audio-only formats
2494 # was also labeled "tiny". It is not clear if such formats still exist
2495 'tiny', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2496 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2499 streaming_data = player_response.get('streamingData') or {}
2500 streaming_formats = streaming_data.get('formats') or []
2501 streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
2502 streaming_formats.extend(ytm_streaming_data.get('formats') or [])
2503 streaming_formats.extend(ytm_streaming_data.get('adaptiveFormats') or [])
2505 for fmt in streaming_formats:
2506 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2509 itag = str_or_none(fmt.get('itag'))
2510 audio_track = fmt.get('audioTrack') or {}
2511 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2512 if stream_id in stream_ids:
2515 quality = fmt.get('quality')
2516 if quality == 'tiny' or not quality:
2517 quality = fmt.get('audioQuality', '').lower() or quality
2518 if itag and quality:
2519 itag_qualities[itag] = quality
2520 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2521 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2522 # number of fragment that would subsequently requested with (`&sq=N`)
2523 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2526 fmt_url = fmt.get('url')
2528 sc = compat_parse_qs(fmt.get('signatureCipher'))
2529 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2530 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2531 if not (sc and fmt_url and encrypted_sig):
2535 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2536 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2537 fmt_url += '&' + sp + '=' + signature
2541 stream_ids.append(stream_id)
2543 tbr = float_or_none(
2544 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
2546 'asr': int_or_none(fmt.get('audioSampleRate')),
2547 'filesize': int_or_none(fmt.get('contentLength')),
2549 'format_note': audio_track.get('displayName') or fmt.get('qualityLabel') or quality,
2550 'fps': int_or_none(fmt.get('fps')),
2551 'height': int_or_none(fmt.get('height')),
2552 'quality': q(quality),
2555 'width': fmt.get('width'),
2556 'language': audio_track.get('id', '').split('.')[0],
2558 mime_mobj = re.match(
2559 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2561 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2562 dct.update(parse_codecs(mime_mobj.group(2)))
2563 # The 3gp format in android client has a quality of "small",
2564 # but is actually worse than all other formats
2565 if dct['ext'] == '3gp':
2566 dct['quality'] = q('tiny')
2567 no_audio = dct.get('acodec') == 'none'
2568 no_video = dct.get('vcodec') == 'none'
2573 if no_audio or no_video:
2574 dct['downloader_options'] = {
2575 # Youtube throttles chunks >~10M
2576 'http_chunk_size': 10485760,
2579 dct['container'] = dct['ext'] + '_dash'
2582 skip_manifests = self._configuration_arg('skip')
2583 get_dash = 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True)
2584 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2586 for sd in (streaming_data, ytm_streaming_data):
2587 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
2588 if hls_manifest_url:
2589 for f in self._extract_m3u8_formats(
2590 hls_manifest_url, video_id, 'mp4', fatal=False):
2591 itag = self._search_regex(
2592 r'/itag/(\d+)', f['url'], 'itag', default=None)
2594 f['format_id'] = itag
2597 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2598 if dash_manifest_url:
2599 for f in self._extract_mpd_formats(
2600 dash_manifest_url, video_id, fatal=False):
2601 itag = f['format_id']
2604 if itag in itag_qualities:
2605 f['quality'] = q(itag_qualities[itag])
2606 filesize = int_or_none(self._search_regex(
2607 r'/clen/(\d+)', f.get('fragment_base_url')
2608 or f['url'], 'file size', default=None))
2610 f['filesize'] = filesize
2614 if not self.get_param('allow_unplayable_formats') and streaming_data.get('licenseInfos'):
2615 self.raise_no_formats(
2616 'This video is DRM protected.', expected=True)
2619 lambda x: x['errorScreen']['playerErrorMessageRenderer'],
2621 reason = get_text(pemr.get('reason')) or playability_status.get('reason')
2622 subreason = pemr.get('subreason')
2624 subreason = clean_html(get_text(subreason))
2625 if subreason == 'The uploader has not made this video available in your country.':
2626 countries = microformat.get('availableCountries')
2628 regions_allowed = search_meta('regionsAllowed')
2629 countries = regions_allowed.split(',') if regions_allowed else None
2630 self.raise_geo_restricted(subreason, countries, metadata_available=True)
2631 reason += '\n' + subreason
2633 self.raise_no_formats(reason, expected=True)
2635 self._sort_formats(formats)
2637 keywords = video_details.get('keywords') or []
2638 if not keywords and webpage:
2640 unescapeHTML(m.group('content'))
2641 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2642 for keyword in keywords:
2643 if keyword.startswith('yt:stretch='):
2644 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2646 # NB: float is intentional for forcing float division
2647 w, h = (float(v) for v in mobj.groups())
2651 if f.get('vcodec') != 'none':
2652 f['stretched_ratio'] = ratio
2656 for container in (video_details, microformat):
2657 for thumbnail in (try_get(
2659 lambda x: x['thumbnail']['thumbnails'], list) or []):
2660 thumbnail_url = thumbnail.get('url')
2661 if not thumbnail_url:
2663 # Sometimes youtube gives a wrong thumbnail URL. See:
2664 # https://github.com/yt-dlp/yt-dlp/issues/233
2665 # https://github.com/ytdl-org/youtube-dl/issues/28023
2666 if 'maxresdefault' in thumbnail_url:
2667 thumbnail_url = thumbnail_url.split('?')[0]
2669 'url': thumbnail_url,
2670 'height': int_or_none(thumbnail.get('height')),
2671 'width': int_or_none(thumbnail.get('width')),
2672 'preference': 1 if 'maxresdefault' in thumbnail_url else -1
2674 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2677 'url': thumbnail_url,
2678 'preference': 1 if 'maxresdefault' in thumbnail_url else -1
2680 # All videos have a maxresdefault thumbnail, but sometimes it does not appear in the webpage
2681 # See: https://github.com/ytdl-org/youtube-dl/issues/29049
2683 'url': 'https://i.ytimg.com/vi/%s/maxresdefault.jpg' % video_id,
2686 self._remove_duplicate_formats(thumbnails)
2688 category = microformat.get('category') or search_meta('genre')
2689 channel_id = video_details.get('channelId') \
2690 or microformat.get('externalChannelId') \
2691 or search_meta('channelId')
2692 duration = int_or_none(
2693 video_details.get('lengthSeconds')
2694 or microformat.get('lengthSeconds')) \
2695 or parse_duration(search_meta('duration'))
2696 is_live = video_details.get('isLive')
2697 is_upcoming = video_details.get('isUpcoming')
2698 owner_profile_url = microformat.get('ownerProfileUrl')
2702 'title': self._live_title(video_title) if is_live else video_title,
2704 'thumbnails': thumbnails,
2705 'description': video_description,
2706 'upload_date': unified_strdate(
2707 microformat.get('uploadDate')
2708 or search_meta('uploadDate')),
2709 'uploader': video_details['author'],
2710 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2711 'uploader_url': owner_profile_url,
2712 'channel_id': channel_id,
2713 'channel_url': 'https://www.youtube.com/channel/' + channel_id if channel_id else None,
2714 'duration': duration,
2715 'view_count': int_or_none(
2716 video_details.get('viewCount')
2717 or microformat.get('viewCount')
2718 or search_meta('interactionCount')),
2719 'average_rating': float_or_none(video_details.get('averageRating')),
2720 'age_limit': 18 if (
2721 microformat.get('isFamilySafe') is False
2722 or search_meta('isFamilyFriendly') == 'false'
2723 or search_meta('og:restrictions:age') == '18+') else 0,
2724 'webpage_url': webpage_url,
2725 'categories': [category] if category else None,
2728 'playable_in_embed': playability_status.get('playableInEmbed'),
2729 'was_live': video_details.get('isLiveContent'),
2734 lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
2737 def process_language(container, base_url, lang_code, sub_name, query):
2738 lang_subs = container.setdefault(lang_code, [])
2739 for fmt in self._SUBTITLE_FORMATS:
2745 'url': update_url_query(base_url, query),
2749 for caption_track in (pctr.get('captionTracks') or []):
2750 base_url = caption_track.get('baseUrl')
2753 if caption_track.get('kind') != 'asr':
2755 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2756 or caption_track.get('languageCode'))
2760 subtitles, base_url, lang_code,
2761 try_get(caption_track, lambda x: x['name']['simpleText']),
2764 automatic_captions = {}
2765 for translation_language in (pctr.get('translationLanguages') or []):
2766 translation_language_code = translation_language.get('languageCode')
2767 if not translation_language_code:
2770 automatic_captions, base_url, translation_language_code,
2771 try_get(translation_language, (
2772 lambda x: x['languageName']['simpleText'],
2773 lambda x: x['languageName']['runs'][0]['text'])),
2774 {'tlang': translation_language_code})
2775 info['automatic_captions'] = automatic_captions
2776 info['subtitles'] = subtitles
2778 parsed_url = compat_urllib_parse_urlparse(url)
2779 for component in [parsed_url.fragment, parsed_url.query]:
2780 query = compat_parse_qs(component)
2781 for k, v in query.items():
2782 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2784 if d_k not in info and k in s_ks:
2785 info[d_k] = parse_duration(query[k][0])
2787 # Youtube Music Auto-generated description
2788 if video_description:
2789 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)
2791 release_year = mobj.group('release_year')
2792 release_date = mobj.group('release_date')
2794 release_date = release_date.replace('-', '')
2795 if not release_year:
2796 release_year = release_date[:4]
2798 'album': mobj.group('album'.strip()),
2799 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2800 'track': mobj.group('track').strip(),
2801 'release_date': release_date,
2802 'release_year': int_or_none(release_year),
2807 initial_data = self._extract_yt_initial_variable(
2808 webpage, self._YT_INITIAL_DATA_RE, video_id,
2810 if not initial_data:
2811 initial_data = self._extract_response(
2812 item_id=video_id, ep='next', fatal=False,
2813 ytcfg=ytcfg, headers=headers, query={'videoId': video_id},
2814 note='Downloading initial data API JSON')
2817 # This will error if there is no livechat
2818 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2819 info['subtitles']['live_chat'] = [{
2820 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2821 'video_id': video_id,
2823 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
2825 except (KeyError, IndexError, TypeError):
2829 chapters = self._extract_chapters_from_json(
2830 initial_data, video_id, duration)
2832 for engagment_pannel in (initial_data.get('engagementPanels') or []):
2834 engagment_pannel, lambda x: x['engagementPanelSectionListRenderer']['content']['macroMarkersListRenderer']['contents'],
2839 def chapter_time(mmlir):
2840 return parse_duration(
2841 get_text(mmlir.get('timeDescription')))
2844 for next_num, content in enumerate(contents, start=1):
2845 mmlir = content.get('macroMarkersListItemRenderer') or {}
2846 start_time = chapter_time(mmlir)
2847 end_time = chapter_time(try_get(
2848 contents, lambda x: x[next_num]['macroMarkersListItemRenderer'])) \
2849 if next_num < len(contents) else duration
2850 if start_time is None or end_time is None:
2853 'start_time': start_time,
2854 'end_time': end_time,
2855 'title': get_text(mmlir.get('title')),
2860 info['chapters'] = chapters
2864 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2866 for content in contents:
2867 vpir = content.get('videoPrimaryInfoRenderer')
2869 stl = vpir.get('superTitleLink')
2874 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2875 info['location'] = stl
2877 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2880 'series': mobj.group(1),
2881 'season_number': int(mobj.group(2)),
2882 'episode_number': int(mobj.group(3)),
2884 for tlb in (try_get(
2886 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
2888 tbr = tlb.get('toggleButtonRenderer') or {}
2889 for getter, regex in [(
2890 lambda x: x['defaultText']['accessibility']['accessibilityData'],
2891 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
2892 lambda x: x['accessibility'],
2893 lambda x: x['accessibilityData']['accessibilityData'],
2894 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
2895 label = (try_get(tbr, getter, dict) or {}).get('label')
2897 mobj = re.match(regex, label)
2899 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
2901 sbr_tooltip = try_get(
2902 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
2904 like_count, dislike_count = sbr_tooltip.split(' / ')
2906 'like_count': str_to_int(like_count),
2907 'dislike_count': str_to_int(dislike_count),
2909 vsir = content.get('videoSecondaryInfoRenderer')
2911 info['channel'] = get_text(try_get(
2913 lambda x: x['owner']['videoOwnerRenderer']['title'],
2917 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
2919 multiple_songs = False
2921 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
2922 multiple_songs = True
2925 mrr = row.get('metadataRowRenderer') or {}
2926 mrr_title = mrr.get('title')
2929 mrr_title = get_text(mrr['title'])
2930 mrr_contents_text = get_text(mrr['contents'][0])
2931 if mrr_title == 'License':
2932 info['license'] = mrr_contents_text
2933 elif not multiple_songs:
2934 if mrr_title == 'Album':
2935 info['album'] = mrr_contents_text
2936 elif mrr_title == 'Artist':
2937 info['artist'] = mrr_contents_text
2938 elif mrr_title == 'Song':
2939 info['track'] = mrr_contents_text
2942 'channel': 'uploader',
2943 'channel_id': 'uploader_id',
2944 'channel_url': 'uploader_url',
2946 for to, frm in fallbacks.items():
2947 if not info.get(to):
2948 info[to] = info.get(frm)
2950 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
2955 is_private = bool_or_none(video_details.get('isPrivate'))
2956 is_unlisted = bool_or_none(microformat.get('isUnlisted'))
2957 is_membersonly = None
2959 if initial_data and is_private is not None:
2960 is_membersonly = False
2962 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list)
2963 for content in contents or []:
2964 badges = try_get(content, lambda x: x['videoPrimaryInfoRenderer']['badges'], list)
2965 for badge in badges or []:
2966 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label']) or ''
2967 if label.lower() == 'members only':
2968 is_membersonly = True
2970 elif label.lower() == 'premium':
2973 if is_membersonly or is_premium:
2976 # TODO: Add this for playlists
2977 info['availability'] = self._availability(
2978 is_private=is_private,
2979 needs_premium=is_premium,
2980 needs_subscription=is_membersonly,
2981 needs_auth=info['age_limit'] >= 18,
2982 is_unlisted=None if is_private is None else is_unlisted)
2984 # get xsrf for annotations or comments
2985 get_annotations = self.get_param('writeannotations', False)
2986 get_comments = self.get_param('getcomments', False)
2987 if get_annotations or get_comments:
2989 ytcfg = self._extract_ytcfg(video_id, webpage)
2991 xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
2993 xsrf_token = self._search_regex(
2994 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
2995 webpage, 'xsrf token', group='xsrf_token', fatal=False)
2999 invideo_url = try_get(
3000 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
3001 if xsrf_token and invideo_url:
3002 xsrf_field_name = None
3004 xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
3005 if not xsrf_field_name:
3006 xsrf_field_name = self._search_regex(
3007 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
3008 webpage, 'xsrf field name',
3009 group='xsrf_field_name', default='session_token')
3010 info['annotations'] = self._download_webpage(
3011 self._proto_relative_url(invideo_url),
3012 video_id, note='Downloading annotations',
3013 errnote='Unable to download video annotations', fatal=False,
3014 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
3017 info['__post_extractor'] = lambda: self._extract_comments(ytcfg, video_id, contents, webpage)
3019 self.mark_watched(video_id, player_response)
3024 class YoutubeTabIE(YoutubeBaseInfoExtractor):
3025 IE_DESC = 'YouTube.com tab'
3026 _VALID_URL = r'''(?x
)
3030 youtube(?
:kids
)?\
.com|
3034 (?P
<channel_type
>channel|c|user|browse
)/|
3037 (?
:playlist|watch
)\?.*?
\blist
=
3039 (?
!(?
:%s)\b) # Direct URLs
3042 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
3043 IE_NAME = 'youtube:tab'
3046 'note': 'playlists, multipage',
3047 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3048 'playlist_mincount': 94,
3050 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3051 'title': 'Игорь Клейнер - Playlists',
3052 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3053 'uploader': 'Игорь Клейнер',
3054 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3057 'note': 'playlists, multipage, different order',
3058 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3059 'playlist_mincount': 94,
3061 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3062 'title': 'Игорь Клейнер - Playlists',
3063 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3064 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3065 'uploader': 'Игорь Клейнер',
3068 'note': 'playlists, series',
3069 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3070 'playlist_mincount': 5,
3072 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3073 'title': '3Blue1Brown - Playlists',
3074 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3075 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3076 'uploader': '3Blue1Brown',
3079 'note': 'playlists, singlepage',
3080 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3081 'playlist_mincount': 4,
3083 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3084 'title': 'ThirstForScience - Playlists',
3085 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
3086 'uploader': 'ThirstForScience',
3087 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3090 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3091 'only_matching': True,
3093 'note': 'basic, single video playlist',
3094 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3096 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3097 'uploader': 'Sergey M.',
3098 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3099 'title': 'youtube-dl public playlist',
3101 'playlist_count': 1,
3103 'note': 'empty playlist',
3104 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3106 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3107 'uploader': 'Sergey M.',
3108 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3109 'title': 'youtube-dl empty playlist',
3111 'playlist_count': 0,
3114 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
3116 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3117 'title': 'lex will - Home',
3118 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3119 'uploader': 'lex will',
3120 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3122 'playlist_mincount': 2,
3124 'note': 'Videos tab',
3125 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
3127 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3128 'title': 'lex will - Videos',
3129 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3130 'uploader': 'lex will',
3131 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3133 'playlist_mincount': 975,
3135 'note': 'Videos tab, sorted by popular',
3136 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
3138 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3139 'title': 'lex will - Videos',
3140 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3141 'uploader': 'lex will',
3142 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3144 'playlist_mincount': 199,
3146 'note': 'Playlists tab',
3147 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
3149 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3150 'title': 'lex will - Playlists',
3151 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3152 'uploader': 'lex will',
3153 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3155 'playlist_mincount': 17,
3157 'note': 'Community tab',
3158 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
3160 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3161 'title': 'lex will - Community',
3162 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3163 'uploader': 'lex will',
3164 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3166 'playlist_mincount': 18,
3168 'note': 'Channels tab',
3169 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
3171 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3172 'title': 'lex will - Channels',
3173 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3174 'uploader': 'lex will',
3175 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3177 'playlist_mincount': 12,
3179 'note': 'Search tab',
3180 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3181 'playlist_mincount': 40,
3183 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3184 'title': '3Blue1Brown - Search - linear algebra',
3185 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3186 'uploader': '3Blue1Brown',
3187 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3190 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3191 'only_matching': True,
3193 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3194 'only_matching': True,
3196 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3197 'only_matching': True,
3199 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3200 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3202 'title': '29C3: Not my department',
3203 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3204 'uploader': 'Christiaan008',
3205 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
3206 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
3208 'playlist_count': 96,
3210 'note': 'Large playlist',
3211 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
3213 'title': 'Uploads from Cauchemar',
3214 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3215 'uploader': 'Cauchemar',
3216 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
3218 'playlist_mincount': 1123,
3220 'note': 'even larger playlist, 8832 videos',
3221 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3222 'only_matching': True,
3224 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3225 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3227 'title': 'Uploads from Interstellar Movie',
3228 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
3229 'uploader': 'Interstellar Movie',
3230 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
3232 'playlist_mincount': 21,
3234 'note': 'Playlist with "show unavailable videos" button',
3235 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3237 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3238 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3239 'uploader': 'Phim Siêu Nhân Nhật Bản',
3240 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3242 'playlist_mincount': 200,
3244 'note': 'Playlist with unavailable videos in page 7',
3245 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3247 'title': 'Uploads from BlankTV',
3248 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3249 'uploader': 'BlankTV',
3250 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3252 'playlist_mincount': 1000,
3254 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
3255 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3257 'title': 'Data Analysis with Dr Mike Pound',
3258 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3259 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3260 'uploader': 'Computerphile',
3261 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
3263 'playlist_mincount': 11,
3265 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3266 'only_matching': True,
3268 'note': 'Playlist URL that does not actually serve a playlist',
3269 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3271 'id': 'FqZTN594JQw',
3273 'title': "Smiley's People 01 detective, Adventure Series, Action",
3274 'uploader': 'STREEM',
3275 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
3276 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
3277 'upload_date': '20150526',
3278 'license': 'Standard YouTube License',
3279 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3280 'categories': ['People & Blogs'],
3284 'dislike_count': int,
3287 'skip_download': True,
3289 'skip': 'This video is not available.',
3290 'add_ie': [YoutubeIE.ie_key()],
3292 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
3293 'only_matching': True,
3295 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
3296 'only_matching': True,
3298 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3300 'id': 'X1whbWASnNQ', # This will keep changing
3302 'title': compat_str,
3303 'uploader': 'Sky News',
3304 'uploader_id': 'skynews',
3305 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
3306 'upload_date': r're:\d{8}',
3307 'description': compat_str,
3308 'categories': ['News & Politics'],
3311 'dislike_count': int,
3314 'skip_download': True,
3316 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
3318 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3320 'id': 'a48o2S1cPoo',
3322 'title': 'The Young Turks - Live Main Show',
3323 'uploader': 'The Young Turks',
3324 'uploader_id': 'TheYoungTurks',
3325 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3326 'upload_date': '20150715',
3327 'license': 'Standard YouTube License',
3328 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3329 'categories': ['News & Politics'],
3330 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3332 'dislike_count': int,
3335 'skip_download': True,
3337 'only_matching': True,
3339 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3340 'only_matching': True,
3342 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3343 'only_matching': True,
3345 'note': 'A channel that is not live. Should raise error',
3346 'url': 'https://www.youtube.com/user/numberphile/live',
3347 'only_matching': True,
3349 'url': 'https://www.youtube.com/feed/trending',
3350 'only_matching': True,
3352 'url': 'https://www.youtube.com/feed/library',
3353 'only_matching': True,
3355 'url': 'https://www.youtube.com/feed/history',
3356 'only_matching': True,
3358 'url': 'https://www.youtube.com/feed/subscriptions',
3359 'only_matching': True,
3361 'url': 'https://www.youtube.com/feed/watch_later',
3362 'only_matching': True,
3364 'note': 'Recommended - redirects to home page',
3365 'url': 'https://www.youtube.com/feed/recommended',
3366 'only_matching': True,
3368 'note': 'inline playlist with not always working continuations',
3369 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3370 'only_matching': True,
3372 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3373 'only_matching': True,
3375 'url': 'https://www.youtube.com/course',
3376 'only_matching': True,
3378 'url': 'https://www.youtube.com/zsecurity',
3379 'only_matching': True,
3381 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3382 'only_matching': True,
3384 'url': 'https://www.youtube.com/TheYoungTurks/live',
3385 'only_matching': True,
3387 'url': 'https://www.youtube.com/hashtag/cctv9',
3392 'playlist_mincount': 350,
3394 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3395 'only_matching': True,
3397 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
3398 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3399 'only_matching': True
3401 'note': '/browse/ should redirect to /channel/',
3402 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3403 'only_matching': True
3405 'note': 'VLPL, should redirect to playlist?list=PL...',
3406 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3408 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3409 'uploader': 'NoCopyrightSounds',
3410 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3411 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3412 'title': 'NCS Releases',
3414 'playlist_mincount': 166,
3416 'note': 'Topic, should redirect to playlist?list=UU...',
3417 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3419 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3420 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3421 'title': 'Uploads from Royalty Free Music - Topic',
3422 'uploader': 'Royalty Free Music - Topic',
3424 'expected_warnings': [
3425 'A channel/user page was given',
3426 'The URL does not have a videos tab',
3428 'playlist_mincount': 101,
3430 'note': 'Topic without a UU playlist',
3431 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3433 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3434 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3436 'expected_warnings': [
3437 'A channel/user page was given',
3438 'The URL does not have a videos tab',
3439 'Falling back to channel URL',
3441 'playlist_mincount': 9,
3443 'note': 'Youtube music Album',
3444 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3446 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3447 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3449 'playlist_count': 50,
3453 def suitable(cls, url):
3454 return False if YoutubeIE.suitable(url) else super(
3455 YoutubeTabIE, cls).suitable(url)
3457 def _extract_channel_id(self, webpage):
3458 channel_id = self._html_search_meta(
3459 'channelId', webpage, 'channel id', default=None)
3462 channel_url = self._html_search_meta(
3463 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3464 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3465 'twitter:app:url:googleplay'), webpage, 'channel url')
3466 return self._search_regex(
3467 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3468 channel_url, 'channel id')
3471 def _extract_basic_item_renderer(item):
3472 # Modified from _extract_grid_item_renderer
3473 known_basic_renderers = (
3474 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3476 for key, renderer in item.items():
3477 if not isinstance(renderer, dict):
3479 elif key in known_basic_renderers:
3481 elif key.startswith('grid') and key.endswith('Renderer'):
3484 def _grid_entries(self, grid_renderer):
3485 for item in grid_renderer['items']:
3486 if not isinstance(item, dict):
3488 renderer = self._extract_basic_item_renderer(item)
3489 if not isinstance(renderer, dict):
3492 renderer, (lambda x: x['title']['runs'][0]['text'],
3493 lambda x: x['title']['simpleText']), compat_str)
3495 playlist_id = renderer.get('playlistId')
3497 yield self.url_result(
3498 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3499 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3503 video_id = renderer.get('videoId')
3505 yield self._extract_video(renderer)
3508 channel_id = renderer.get('channelId')
3511 renderer, lambda x: x['title']['simpleText'], compat_str)
3512 yield self.url_result(
3513 'https://www.youtube.com/channel/%s' % channel_id,
3514 ie=YoutubeTabIE.ie_key(), video_title=title)
3516 # generic endpoint URL support
3517 ep_url = urljoin('https://www.youtube.com/', try_get(
3518 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3521 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3522 if ie.suitable(ep_url):
3523 yield self.url_result(
3524 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3527 def _shelf_entries_from_content(self, shelf_renderer):
3528 content = shelf_renderer.get('content')
3529 if not isinstance(content, dict):
3531 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3533 # TODO: add support for nested playlists so each shelf is processed
3534 # as separate playlist
3535 # TODO: this includes only first N items
3536 for entry in self._grid_entries(renderer):
3538 renderer = content.get('horizontalListRenderer')
3543 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3545 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3547 shelf_url = urljoin('https://www.youtube.com', ep)
3549 # Skipping links to another channels, note that checking for
3550 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3552 if skip_channels and '/channels?' in shelf_url:
3555 shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
3556 yield self.url_result(shelf_url, video_title=title)
3557 # Shelf may not contain shelf URL, fallback to extraction from content
3558 for entry in self._shelf_entries_from_content(shelf_renderer):
3561 def _playlist_entries(self, video_list_renderer):
3562 for content in video_list_renderer['contents']:
3563 if not isinstance(content, dict):
3565 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3566 if not isinstance(renderer, dict):
3568 video_id = renderer.get('videoId')
3571 yield self._extract_video(renderer)
3573 def _rich_entries(self, rich_grid_renderer):
3575 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3576 video_id = renderer.get('videoId')
3579 yield self._extract_video(renderer)
3581 def _video_entry(self, video_renderer):
3582 video_id = video_renderer.get('videoId')
3584 return self._extract_video(video_renderer)
3586 def _post_thread_entries(self, post_thread_renderer):
3587 post_renderer = try_get(
3588 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3589 if not post_renderer:
3592 video_renderer = try_get(
3593 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3594 video_id = video_renderer.get('videoId')
3596 entry = self._extract_video(video_renderer)
3599 # playlist attachment
3600 playlist_id = try_get(
3601 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3603 yield self.url_result(
3604 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3605 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3606 # inline video links
3607 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3609 if not isinstance(run, dict):
3612 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3615 if not YoutubeIE.suitable(ep_url):
3617 ep_video_id = YoutubeIE._match_id(ep_url)
3618 if video_id == ep_video_id:
3620 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3622 def _post_thread_continuation_entries(self, post_thread_continuation):
3623 contents = post_thread_continuation.get('contents')
3624 if not isinstance(contents, list):
3626 for content in contents:
3627 renderer = content.get('backstagePostThreadRenderer')
3628 if not isinstance(renderer, dict):
3630 for entry in self._post_thread_entries(renderer):
3634 def _rich_grid_entries(self
, contents
):
3635 for content
in contents
:
3636 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3638 entry
= self
._video
_entry
(video_renderer
)
3642 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3644 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3645 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3646 for content in contents:
3647 if not isinstance(content, dict):
3649 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3651 renderer = content.get('richItemRenderer')
3653 for entry in self._rich_entries(renderer):
3655 continuation_list[0] = self._extract_continuation(parent_renderer)
3657 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3658 for isr_content in isr_contents:
3659 if not isinstance(isr_content, dict):
3663 'playlistVideoListRenderer': self._playlist_entries,
3664 'gridRenderer': self._grid_entries,
3665 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3666 'backstagePostThreadRenderer': self._post_thread_entries,
3667 'videoRenderer': lambda x: [self._video_entry(x)],
3669 for key, renderer in isr_content.items():
3670 if key not in known_renderers:
3672 for entry in known_renderers[key](renderer):
3675 continuation_list[0] = self._extract_continuation(renderer)
3678 if not continuation_list[0]:
3679 continuation_list[0] = self._extract_continuation(is_renderer)
3681 if not continuation_list[0]:
3682 continuation_list[0] = self._extract_continuation(parent_renderer)
3684 continuation_list = [None] # Python 2 doesnot support nonlocal
3685 tab_content = try_get(tab, lambda x: x['content'], dict)
3689 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3690 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3691 for entry in extract_entries(parent_renderer):
3693 continuation = continuation_list[0]
3694 context = self._extract_context(ytcfg)
3695 visitor_data = try_get(context, lambda x: x['client']['visitorData'], compat_str)
3697 for page_num in itertools.count(1):
3698 if not continuation:
3701 'continuation': continuation['continuation'],
3702 'clickTracking': {'clickTrackingParams': continuation['itct']}
3704 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
3705 response = self._extract_response(
3706 item_id='%s page %s' % (item_id, page_num),
3707 query=query, headers=headers, ytcfg=ytcfg,
3708 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3712 visitor_data = try_get(
3713 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
3715 known_continuation_renderers = {
3716 'playlistVideoListContinuation': self._playlist_entries,
3717 'gridContinuation': self._grid_entries,
3718 'itemSectionContinuation': self._post_thread_continuation_entries,
3719 'sectionListContinuation': extract_entries, # for feeds
3721 continuation_contents = try_get(
3722 response, lambda x: x['continuationContents'], dict) or {}
3723 continuation_renderer = None
3724 for key, value in continuation_contents.items():
3725 if key not in known_continuation_renderers:
3727 continuation_renderer = value
3728 continuation_list = [None]
3729 for entry in known_continuation_renderers[key](continuation_renderer):
3731 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3733 if continuation_renderer:
3737 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3738 'gridVideoRenderer': (self._grid_entries, 'items'),
3739 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3740 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3741 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3742 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3744 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3745 continuation_items = try_get(
3746 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3747 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3748 video_items_renderer = None
3749 for key, value in continuation_item.items():
3750 if key not in known_renderers:
3752 video_items_renderer = {known_renderers[key][1]: continuation_items}
3753 continuation_list = [None]
3754 for entry in known_renderers[key][0](video_items_renderer):
3756 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3758 if video_items_renderer:
3763 def _extract_selected_tab(tabs):
3765 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3766 if renderer.get('selected') is True:
3769 raise ExtractorError('Unable to find selected tab')
3772 def _extract_uploader(data):
3774 sidebar_renderer = try_get(
3775 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
3776 if sidebar_renderer:
3777 for item in sidebar_renderer:
3778 if not isinstance(item, dict):
3780 renderer = item.get('playlistSidebarSecondaryInfoRenderer')
3781 if not isinstance(renderer, dict):
3784 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3786 uploader['uploader'] = owner.get('text')
3787 uploader['uploader_id'] = try_get(
3788 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3789 uploader['uploader_url'] = urljoin(
3790 'https://www.youtube.com/',
3791 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3792 return {k: v for k, v in uploader.items() if v is not None}
3794 def _extract_from_tabs(self, item_id, webpage, data, tabs):
3795 playlist_id = title = description = channel_url = channel_name = channel_id = None
3796 thumbnails_list = tags = []
3798 selected_tab = self._extract_selected_tab(tabs)
3800 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3802 channel_name = renderer.get('title')
3803 channel_url = renderer.get('channelUrl')
3804 channel_id = renderer.get('externalId')
3807 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3810 title = renderer.get('title')
3811 description = renderer.get('description', '')
3812 playlist_id = channel_id
3813 tags = renderer.get('keywords', '').split()
3815 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
3818 lambda x: x['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
3823 for t in thumbnails_list:
3824 if not isinstance(t, dict):
3826 thumbnail_url = url_or_none(t.get('url'))
3827 if not thumbnail_url:
3830 'url': thumbnail_url,
3831 'width': int_or_none(t.get('width')),
3832 'height': int_or_none(t.get('height')),
3834 if playlist_id is None:
3835 playlist_id = item_id
3838 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3840 title += format_field(selected_tab, 'title', ' - %s')
3841 title += format_field(selected_tab, 'expandedText', ' - %s')
3844 'playlist_id': playlist_id,
3845 'playlist_title': title,
3846 'playlist_description': description,
3847 'uploader': channel_name,
3848 'uploader_id': channel_id,
3849 'uploader_url': channel_url,
3850 'thumbnails': thumbnails,
3854 metadata.update(self._extract_uploader(data))
3856 'channel': metadata['uploader'],
3857 'channel_id': metadata['uploader_id'],
3858 'channel_url': metadata['uploader_url']})
3859 return self.playlist_result(
3861 selected_tab, playlist_id,
3862 self._extract_identity_token(webpage, item_id),
3863 self._extract_account_syncid(data),
3864 self._extract_ytcfg(item_id, webpage)),
3867 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
3868 first_id = last_id = None
3869 ytcfg = self._extract_ytcfg(playlist_id, webpage)
3870 headers = self._generate_api_headers(
3871 ytcfg, account_syncid=self._extract_account_syncid(data),
3872 identity_token=self._extract_identity_token(webpage, item_id=playlist_id),
3873 visitor_data=try_get(self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
3874 for page_num in itertools.count(1):
3875 videos = list(self._playlist_entries(playlist))
3878 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3879 if start >= len(videos):
3881 for video in videos[start:]:
3882 if video['id'] == first_id:
3883 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3886 first_id = first_id or videos[0]['id']
3887 last_id = videos[-1]['id']
3888 watch_endpoint = try_get(
3889 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
3891 'playlistId': playlist_id,
3892 'videoId': watch_endpoint.get('videoId') or last_id,
3893 'index': watch_endpoint.get('index') or len(videos),
3894 'params': watch_endpoint.get('params') or 'OAE%3D'
3896 response = self._extract_response(
3897 item_id='%s page %d' % (playlist_id, page_num),
3901 check_get_keys='contents'
3904 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
3906 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
3907 title = playlist.get('title') or try_get(
3908 data, lambda x: x['titleText']['simpleText'], compat_str)
3909 playlist_id = playlist.get('playlistId') or item_id
3911 # Delegating everything except mix playlists to regular tab-based playlist URL
3912 playlist_url = urljoin(url, try_get(
3913 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3915 if playlist_url and playlist_url != url:
3916 return self.url_result(
3917 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3920 return self.playlist_result(
3921 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
3922 playlist_id=playlist_id, playlist_title=title)
3924 def _reload_with_unavailable_videos(self, item_id, data, webpage):
3926 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
3928 sidebar_renderer = try_get(
3929 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
3930 if not sidebar_renderer:
3932 browse_id = params = None
3933 for item in sidebar_renderer:
3934 if not isinstance(item, dict):
3936 renderer = item.get('playlistSidebarPrimaryInfoRenderer')
3937 menu_renderer = try_get(
3938 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
3939 for menu_item in menu_renderer:
3940 if not isinstance(menu_item, dict):
3942 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
3944 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
3945 if not text or text.lower() != 'show unavailable videos':
3947 browse_endpoint = try_get(
3948 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
3949 browse_id = browse_endpoint.get('browseId')
3950 params = browse_endpoint.get('params')
3953 ytcfg = self._extract_ytcfg(item_id, webpage)
3954 headers = self._generate_api_headers(
3955 ytcfg, account_syncid=self._extract_account_syncid(ytcfg),
3956 identity_token=self._extract_identity_token(webpage, item_id=item_id),
3957 visitor_data=try_get(
3958 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
3960 'params': params or 'wgYCCAA=',
3961 'browseId': browse_id or 'VL%s' % item_id
3963 return self._extract_response(
3964 item_id=item_id, headers=headers, query=query,
3965 check_get_keys='contents', fatal=False,
3966 note='Downloading API JSON with unavailable videos')
3968 def _extract_webpage(self, url, item_id):
3969 retries = self.get_param('extractor_retries', 3)
3971 last_error = 'Incomplete yt initial data recieved'
3972 while count < retries:
3974 # Sometimes youtube returns a webpage with incomplete ytInitialData
3975 # See: https://github.com/yt-dlp/yt-dlp/issues/116
3977 self.report_warning('%s. Retrying ...' % last_error)
3978 webpage = self._download_webpage(
3980 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
3981 data = self._extract_yt_initial_data(item_id, webpage)
3982 if data.get('contents') or data.get('currentVideoEndpoint'):
3984 # Extract alerts here only when there is error
3985 self._extract_and_report_alerts(data)
3986 if count >= retries:
3987 raise ExtractorError(last_error)
3988 return webpage, data
3991 def _smuggle_data(entries, data):
3992 for entry in entries:
3994 entry['url'] = smuggle_url(entry['url'], data)
3997 def _real_extract(self, url):
3998 url, smuggled_data = unsmuggle_url(url, {})
3999 if self.is_music_url(url):
4000 smuggled_data['is_music_url'] = True
4001 info_dict = self.__real_extract(url, smuggled_data)
4002 if info_dict.get('entries'):
4003 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4006 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4008 def __real_extract(self, url, smuggled_data):
4009 item_id = self._match_id(url)
4010 url = compat_urlparse.urlunparse(
4011 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4012 compat_opts = self.get_param('compat_opts', [])
4015 mobj = self._url_re.match(url).groupdict()
4016 mobj.update((k, '') for k, v in mobj.items() if v is None)
4019 mobj = get_mobj(url)
4020 # Youtube returns incomplete data if tabname is not lower case
4021 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4024 if smuggled_data.get('is_music_url'):
4025 if item_id[:2] == 'VL':
4026 # Youtube music VL channels have an equivalent playlist
4027 item_id = item_id[2:]
4028 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4029 elif item_id[:2] == 'MP':
4030 # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage
4031 item_id = self._search_regex(
4032 r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22',
4033 self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id),
4035 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4036 elif mobj['channel_type'] == 'browse':
4037 # Youtube music /browse/ should be changed to /channel/
4038 pre = 'https://www.youtube.com/channel/%s' % item_id
4039 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4040 # Home URLs should redirect to /videos/
4041 self.report_warning(
4042 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4043 'To download only the videos in the home page, add a "/featured" to the URL')
4046 url = ''.join((pre, tab, post))
4047 mobj = get_mobj(url)
4049 # Handle both video/playlist URLs
4051 video_id = qs.get('v', [None])[0]
4052 playlist_id = qs.get('list', [None])[0]
4054 if not video_id and mobj['not_channel'].startswith('watch'):
4056 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4057 raise ExtractorError('Unable to recognize tab page')
4058 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4059 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
4060 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
4061 mobj = get_mobj(url)
4063 if video_id and playlist_id:
4064 if self.get_param('noplaylist'):
4065 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
4066 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4067 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4069 webpage, data = self._extract_webpage(url, item_id)
4072 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4074 selected_tab = self._extract_selected_tab(tabs)
4075 tab_name = selected_tab.get('title', '')
4076 if 'no-youtube-channel-redirect' not in compat_opts:
4077 if mobj['tab'] == '/live':
4078 # Live tab should have redirected to the video
4079 raise ExtractorError('The channel is not currently live', expected=True)
4080 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4081 if not mobj['not_channel'] and item_id[:2] == 'UC':
4082 # Topic channels don't have /videos. Use the equivalent playlist instead
4083 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:]))
4084 pl_id = 'UU%s' % item_id[2:]
4085 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4087 pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id)
4088 for alert_type, alert_message in self._extract_alerts(pl_data):
4089 if alert_type == 'error':
4090 raise ExtractorError('Youtube said: %s' % alert_message)
4091 item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data
4092 except ExtractorError:
4093 self.report_warning('The playlist gave error. Falling back to channel URL')
4095 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
4097 self.write_debug('Final URL: %s' % url)
4099 # YouTube sometimes provides a button to reload playlist with unavailable videos.
4100 if 'no-youtube-unavailable-videos' not in compat_opts:
4101 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
4102 self._extract_and_report_alerts(data)
4105 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4107 return self._extract_from_tabs(item_id, webpage, data, tabs)
4110 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4112 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
4115 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4116 compat_str) or video_id
4118 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4119 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
4120 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4122 raise ExtractorError('Unable to recognize tab page')
4125 class YoutubePlaylistIE(InfoExtractor):
4126 IE_DESC = 'YouTube.com playlists'
4127 _VALID_URL = r'''(?x
)(?
:
4132 youtube(?
:kids
)?\
.com|
4137 (?P
<id>%(playlist_id)s)
4138 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4139 IE_NAME = 'youtube:playlist'
4141 'note': 'issue #673',
4142 'url': 'PLBB231211A4F62143',
4144 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4145 'id': 'PLBB231211A4F62143',
4146 'uploader': 'Wickydoo',
4147 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
4149 'playlist_mincount': 29,
4151 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4153 'title': 'YDL_safe_search',
4154 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4156 'playlist_count': 2,
4157 'skip': 'This playlist is private',
4160 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4161 'playlist_count': 4,
4164 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4165 'uploader': 'milan',
4166 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
4169 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4170 'playlist_mincount': 982,
4172 'title': '2018 Chinese New Singles (11/6 updated)',
4173 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4175 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
4178 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4179 'only_matching': True,
4181 # music album playlist
4182 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4183 'only_matching': True,
4187 def suitable(cls, url):
4188 if YoutubeTabIE.suitable(url):
4190 # Hack for lazy extractors until more generic solution is implemented
4192 from .youtube import parse_qs
4194 if qs.get('v', [None])[0]:
4196 return super(YoutubePlaylistIE, cls).suitable(url)
4198 def _real_extract(self, url):
4199 playlist_id = self._match_id(url)
4200 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
4201 url = update_url_query(
4202 'https://www.youtube.com/playlist',
4203 parse_qs(url) or {'list': playlist_id})
4205 url = smuggle_url(url, {'is_music_url': True})
4206 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4209 class YoutubeYtBeIE(InfoExtractor):
4210 IE_DESC = 'youtu.be'
4211 _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}
4213 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4215 'id': 'yeWKywCrFtk',
4217 'title': 'Small Scale Baler and Braiding Rugs',
4218 'uploader': 'Backus-Page House Museum',
4219 'uploader_id': 'backuspagemuseum',
4220 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4221 'upload_date': '20161008',
4222 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4223 'categories': ['Nonprofits & Activism'],
4226 'dislike_count': int,
4230 'skip_download': True,
4233 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
4234 'only_matching': True,
4237 def _real_extract(self, url):
4238 mobj = re.match(self._VALID_URL, url)
4239 video_id = mobj.group('id')
4240 playlist_id = mobj.group('playlist_id')
4241 return self.url_result(
4242 update_url_query('https://www.youtube.com/watch', {
4244 'list': playlist_id,
4245 'feature': 'youtu.be',
4246 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4249 class YoutubeYtUserIE(InfoExtractor):
4250 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
4251 _VALID_URL = r'ytuser:(?P<id>.+)'
4253 'url': 'ytuser:phihag',
4254 'only_matching': True,
4257 def _real_extract(self, url):
4258 user_id = self._match_id(url)
4259 return self.url_result(
4260 'https://www.youtube.com/user/%s' % user_id,
4261 ie=YoutubeTabIE.ie_key(), video_id=user_id)
4264 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
4265 IE_NAME = 'youtube:favorites'
4266 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
4267 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4268 _LOGIN_REQUIRED = True
4271 'only_matching': True,
4273 'url': ':ytfavorites',
4274 'only_matching': True,
4277 def _real_extract(self, url):
4278 return self.url_result(
4279 'https://www.youtube.com/playlist?list=LL',
4280 ie=YoutubeTabIE.ie_key())
4283 class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
4284 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
4285 # there doesn't appear to be a real limit, for example if you search for
4286 # 'python' you get more than 8.000.000 results
4287 _MAX_RESULTS = float('inf')
4288 IE_NAME = 'youtube:search'
4289 _SEARCH_KEY = 'ytsearch'
4290 _SEARCH_PARAMS = None
4293 def _entries(self, query, n):
4294 data = {'query': query}
4295 if self._SEARCH_PARAMS:
4296 data['params'] = self._SEARCH_PARAMS
4298 for page_num in itertools.count(1):
4299 search = self._extract_response(
4300 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4301 check_get_keys=('contents', 'onResponseReceivedCommands')
4305 slr_contents = try_get(
4307 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4308 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4310 if not slr_contents:
4313 # Youtube sometimes adds promoted content to searches,
4314 # changing the index location of videos and token.
4315 # So we search through all entries till we find them.
4316 continuation_token = None
4317 for slr_content in slr_contents:
4318 if continuation_token is None:
4319 continuation_token = try_get(
4321 lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
4324 isr_contents = try_get(
4326 lambda x: x['itemSectionRenderer']['contents'],
4328 if not isr_contents:
4330 for content in isr_contents:
4331 if not isinstance(content, dict):
4333 video = content.get('videoRenderer')
4334 if not isinstance(video, dict):
4336 video_id = video.get('videoId')
4340 yield self._extract_video(video)
4345 if not continuation_token:
4347 data['continuation'] = continuation_token
4349 def _get_n_results(self, query, n):
4350 """Get a specified number of results for a query"""
4351 return self.playlist_result(self._entries(query, n), query)
4354 class YoutubeSearchDateIE(YoutubeSearchIE):
4355 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
4356 _SEARCH_KEY = 'ytsearchdate'
4357 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
4358 _SEARCH_PARAMS = 'CAI%3D'
4361 class YoutubeSearchURLIE(YoutubeSearchIE):
4362 IE_DESC = 'YouTube.com search URLs'
4363 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
4364 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
4365 # _MAX_RESULTS = 100
4367 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4368 'playlist_mincount': 5,
4370 'title': 'youtube-dl test video',
4373 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4374 'only_matching': True,
4378 def _make_valid_url(cls):
4379 return cls._VALID_URL
4381 def _real_extract(self, url):
4382 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
4383 query = (qs.get('search_query') or qs.get('q'))[0]
4384 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4385 return self._get_n_results(query, self._MAX_RESULTS)
4388 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
4390 Base class for feed extractors
4391 Subclasses must define the _FEED_NAME property.
4393 _LOGIN_REQUIRED = True
4398 return 'youtube:%s' % self._FEED_NAME
4400 def _real_extract(self, url):
4401 return self.url_result(
4402 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4403 ie=YoutubeTabIE.ie_key())
4406 class YoutubeWatchLaterIE(InfoExtractor):
4407 IE_NAME = 'youtube:watchlater'
4408 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
4409 _VALID_URL = r':ytwatchlater'
4411 'url': ':ytwatchlater',
4412 'only_matching': True,
4415 def _real_extract(self, url):
4416 return self.url_result(
4417 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
4420 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
4421 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
4422 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
4423 _FEED_NAME = 'recommended'
4424 _LOGIN_REQUIRED = False
4427 'only_matching': True,
4429 'url': ':ytrecommended',
4430 'only_matching': True,
4432 'url': 'https://youtube.com',
4433 'only_matching': True,
4437 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
4438 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
4439 _VALID_URL = r':ytsub(?:scription)?s?'
4440 _FEED_NAME = 'subscriptions'
4443 'only_matching': True,
4445 'url': ':ytsubscriptions',
4446 'only_matching': True,
4450 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
4451 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
4452 _VALID_URL = r':ythis(?:tory)?'
4453 _FEED_NAME = 'history'
4455 'url': ':ythistory',
4456 'only_matching': True,
4460 class YoutubeTruncatedURLIE(InfoExtractor):
4461 IE_NAME = 'youtube:truncated_url'
4462 IE_DESC = False # Do not list
4463 _VALID_URL = r'''(?x
)
4465 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
4468 annotation_id
=annotation_
[^
&]+|
4474 attribution_link
\?a
=[^
&]+
4480 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
4481 'only_matching': True,
4483 'url': 'https://www.youtube.com/watch?',
4484 'only_matching': True,
4486 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4487 'only_matching': True,
4489 'url': 'https://www.youtube.com/watch?feature=foo',
4490 'only_matching': True,
4492 'url': 'https://www.youtube.com/watch?hl=en-GB',
4493 'only_matching': True,
4495 'url': 'https://www.youtube.com/watch?t=2372',
4496 'only_matching': True,
4499 def _real_extract(self, url):
4500 raise ExtractorError(
4501 'Did you forget to quote the URL? Remember that & is a meta '
4502 'character in most shells, so you want to put the URL in quotes, '
4504 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
4505 ' or simply youtube-dl BaW_jenozKc .',
4509 class YoutubeTruncatedIDIE(InfoExtractor):
4510 IE_NAME = 'youtube:truncated_id'
4511 IE_DESC = False # Do not list
4512 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
4515 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4516 'only_matching': True,
4519 def _real_extract(self, url):
4520 video_id = self._match_id(url)
4521 raise ExtractorError(
4522 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),