3 from __future__
import unicode_literals
18 from .common
import InfoExtractor
, SearchInfoExtractor
19 from ..compat
import (
24 compat_urllib_parse_unquote_plus
,
25 compat_urllib_parse_urlencode
,
26 compat_urllib_parse_urlparse
,
29 from ..jsinterp
import JSInterpreter
65 return compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
68 class YoutubeBaseInfoExtractor(InfoExtractor
):
69 """Provide base functions for Youtube extractors"""
70 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
71 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
73 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
74 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
75 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
78 r
'channel|c|user|browse|playlist|watch|w|v|embed|e|watch_popup|shorts|'
79 r
'movies|results|shared|hashtag|trending|feed|feeds|oembed|get_video_info|'
80 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
82 _NETRC_MACHINE
= 'youtube'
83 # If True it will raise an error if no login info is provided
84 _LOGIN_REQUIRED
= False
86 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
90 Attempt to log in to YouTube.
91 True is returned if successful or skipped.
92 False is returned if login failed.
94 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
98 self
.report_warning(message
)
100 # username+password login is broken
101 if self
._LOGIN
_REQUIRED
and self
.get_param('cookiefile') is None:
102 self
.raise_login_required(
103 'Login details are needed to download this content', method
='cookies')
104 username
, password
= self
._get
_login
_info
()
106 warn('Logging in using username and password is broken. %s' % self
._LOGIN
_HINTS
['cookies'])
109 # Everything below this is broken!
111 # No authentication to be performed
113 if self._LOGIN_REQUIRED and self.get_param('cookiefile') is None:
114 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
115 # if self.get_param('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
116 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
119 login_page = self._download_webpage(
120 self._LOGIN_URL, None,
121 note='Downloading login page',
122 errnote='unable to fetch login page', fatal=False)
123 if login_page is False:
126 login_form = self._hidden_inputs(login_page)
128 def req(url, f_req, note, errnote):
129 data = login_form.copy()
132 'checkConnection': 'youtube',
133 'checkedDomains': 'youtube',
135 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
136 'f.req': json.dumps(f_req),
137 'flowName': 'GlifWebSignIn',
138 'flowEntry': 'ServiceLogin',
139 # TODO: reverse actual botguard identifier generation algo
140 'bgRequest': '["identifier",""]',
142 return self._download_json(
143 url, None, note=note, errnote=errnote,
144 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
146 data=urlencode_postdata(data), headers={
147 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
148 'Google-Accounts-XSRF': 1,
153 None, [], None, 'US', None, None, 2, False, True,
157 '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',
159 1, [None, None, []], None, None, None, True
164 lookup_results = req(
165 self._LOOKUP_URL, lookup_req,
166 'Looking up account info', 'Unable to look up account info')
168 if lookup_results is False:
171 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
173 warn('Unable to extract user hash')
178 None, 1, None, [1, None, None, None, [password, None, True]],
180 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],
181 1, [None, None, []], None, None, None, True
184 challenge_results = req(
185 self._CHALLENGE_URL, challenge_req,
186 'Logging in', 'Unable to log in')
188 if challenge_results is False:
191 login_res = try_get(challenge_results, lambda x: x[0][5], list)
193 login_msg = try_get(login_res, lambda x: x[5], compat_str)
195 'Unable to login: %s' % 'Invalid password'
196 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
199 res = try_get(challenge_results, lambda x: x[0][-1], list)
201 warn('Unable to extract result entry')
204 login_challenge = try_get(res, lambda x: x[0][0], list)
206 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
207 if challenge_str == 'TWO_STEP_VERIFICATION':
208 # SEND_SUCCESS - TFA code has been successfully sent to phone
209 # QUOTA_EXCEEDED - reached the limit of TFA codes
210 status = try_get(login_challenge, lambda x: x[5], compat_str)
211 if status == 'QUOTA_EXCEEDED':
212 warn('Exceeded the limit of TFA codes, try later')
215 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
217 warn('Unable to extract TL')
220 tfa_code = self._get_tfa_info('2-step verification code')
224 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
225 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
228 tfa_code = remove_start(tfa_code, 'G-')
231 user_hash, None, 2, None,
233 9, None, None, None, None, None, None, None,
234 [None, tfa_code, True, 2]
238 self._TFA_URL.format(tl), tfa_req,
239 'Submitting TFA code', 'Unable to submit TFA code')
241 if tfa_results is False:
244 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
246 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
248 'Unable to finish TFA: %s' % 'Invalid TFA code'
249 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
252 check_cookie_url = try_get(
253 tfa_results, lambda x: x[0][-1][2], compat_str)
256 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
257 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
258 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
260 challenge = CHALLENGES.get(
262 '%s returned error %s.' % (self.IE_NAME, challenge_str))
263 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
266 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
268 if not check_cookie_url:
269 warn('Unable to extract CheckCookie URL')
272 check_cookie_results = self._download_webpage(
273 check_cookie_url, None, 'Checking cookie', fatal=False)
275 if check_cookie_results is False:
278 if 'https://myaccount.google.com/' not in check_cookie_results:
279 warn('Unable to log in')
285 def _initialize_consent(self
):
286 cookies
= self
._get
_cookies
('https://www.youtube.com/')
287 if cookies
.get('__Secure-3PSID'):
290 consent
= cookies
.get('CONSENT')
292 if 'YES' in consent
.value
:
294 consent_id
= self
._search
_regex
(
295 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
297 consent_id
= random
.randint(100, 999)
298 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
300 def _real_initialize(self
):
301 self
._initialize
_consent
()
302 if self
._downloader
is None:
304 if not self
._login
():
307 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
308 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
309 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
311 _YT_DEFAULT_YTCFGS = {
313 'INNERTUBE_API_VERSION': 'v1',
314 'INNERTUBE_CLIENT_NAME': 'WEB',
315 'INNERTUBE_CLIENT_VERSION': '2.20210622.10.00',
316 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
317 'INNERTUBE_CONTEXT': {
320 'clientVersion': '2.20210622.10.00',
324 'INNERTUBE_CONTEXT_CLIENT_NAME': 1
327 'INNERTUBE_API_VERSION': 'v1',
328 'INNERTUBE_CLIENT_NAME': 'WEB_REMIX',
329 'INNERTUBE_CLIENT_VERSION': '1.20210621.00.00',
330 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
331 'INNERTUBE_CONTEXT': {
333 'clientName': 'WEB_REMIX',
334 'clientVersion': '1.20210621.00.00',
338 'INNERTUBE_CONTEXT_CLIENT_NAME': 67
340 'WEB_EMBEDDED_PLAYER': {
341 'INNERTUBE_API_VERSION': 'v1',
342 'INNERTUBE_CLIENT_NAME': 'WEB_EMBEDDED_PLAYER',
343 'INNERTUBE_CLIENT_VERSION': '1.20210620.0.1',
344 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
345 'INNERTUBE_CONTEXT': {
347 'clientName': 'WEB_EMBEDDED_PLAYER',
348 'clientVersion': '1.20210620.0.1',
352 'INNERTUBE_CONTEXT_CLIENT_NAME': 56
355 'INNERTUBE_API_VERSION': 'v1',
356 'INNERTUBE_CLIENT_NAME': 'ANDROID',
357 'INNERTUBE_CLIENT_VERSION': '16.20',
358 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
359 'INNERTUBE_CONTEXT': {
361 'clientName': 'ANDROID',
362 'clientVersion': '16.20',
366 'INNERTUBE_CONTEXT_CLIENT_NAME': 3
368 'ANDROID_EMBEDDED_PLAYER': {
369 'INNERTUBE_API_VERSION': 'v1',
370 'INNERTUBE_CLIENT_NAME': 'ANDROID_EMBEDDED_PLAYER',
371 'INNERTUBE_CLIENT_VERSION': '16.20',
372 'INNERTUBE_API_KEY': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
373 'INNERTUBE_CONTEXT': {
375 'clientName': 'ANDROID_EMBEDDED_PLAYER',
376 'clientVersion': '16.20',
380 'INNERTUBE_CONTEXT_CLIENT_NAME': 55
383 'INNERTUBE_API_VERSION': 'v1',
384 'INNERTUBE_CLIENT_NAME': 'ANDROID_MUSIC',
385 'INNERTUBE_CLIENT_VERSION': '4.32',
386 'INNERTUBE_API_KEY': 'AIzaSyC9XL3ZjWddXya6X74dJoCTL-WEYFDNX30',
387 'INNERTUBE_CONTEXT': {
389 'clientName': 'ANDROID_MUSIC',
390 'clientVersion': '4.32',
394 'INNERTUBE_CONTEXT_CLIENT_NAME': 21
398 _YT_DEFAULT_INNERTUBE_HOSTS = {
399 'DIRECT': 'youtubei.googleapis.com',
400 'WEB': 'www.youtube.com',
401 'WEB_REMIX': 'music.youtube.com',
402 'ANDROID_MUSIC': 'music.youtube.com'
405 def _get_default_ytcfg(self, client='WEB'):
406 if client in self._YT_DEFAULT_YTCFGS:
407 return copy.deepcopy(self._YT_DEFAULT_YTCFGS[client])
408 self.write_debug(f'INNERTUBE default client {client} does not exist - falling back to WEB client.')
409 return copy.deepcopy(self._YT_DEFAULT_YTCFGS['WEB'])
411 def _get_innertube_host(self, client='WEB'):
412 return dict_get(self._YT_DEFAULT_INNERTUBE_HOSTS, (client, 'WEB'))
414 def _ytcfg_get_safe(self, ytcfg, getter, expected_type=None, default_client='WEB'):
415 # try_get but with fallback to default ytcfg client values when present
416 _func = lambda y: try_get(y, getter, expected_type)
417 return _func(ytcfg) or _func(self._get_default_ytcfg(default_client))
419 def _extract_client_name(self, ytcfg, default_client='WEB'):
420 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_NAME'], compat_str, default_client)
423 def _extract_session_index(ytcfg):
424 return int_or_none(try_get(ytcfg, lambda x: x['SESSION_INDEX']))
426 def _extract_client_version(self, ytcfg, default_client='WEB'):
427 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_CLIENT_VERSION'], compat_str, default_client)
429 def _extract_api_key(self, ytcfg=None, default_client='WEB'):
430 return self._ytcfg_get_safe(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str, default_client)
432 def _extract_context(self, ytcfg=None, default_client='WEB'):
433 _get_context = lambda y: try_get(y, lambda x: x['INNERTUBE_CONTEXT'], dict)
434 context = _get_context(ytcfg)
438 context = _get_context(self._get_default_ytcfg(default_client))
442 # Recreate the client context (required)
443 context['client'].update({
444 'clientVersion': self._extract_client_version(ytcfg, default_client),
445 'clientName': self._extract_client_name(ytcfg, default_client),
447 visitor_data = try_get(ytcfg, lambda x: x['VISITOR_DATA'], compat_str)
449 context['client']['visitorData'] = visitor_data
452 def _generate_sapisidhash_header(self, origin='https://www.youtube.com'):
453 # Sometimes SAPISID cookie isn't present but __Secure-3PAPISID is.
454 # See: https://github.com/yt-dlp/yt-dlp/issues/393
455 yt_cookies = self._get_cookies('https://www.youtube.com')
456 sapisid_cookie = dict_get(
457 yt_cookies, ('__Secure-3PAPISID', 'SAPISID'))
458 if sapisid_cookie is None:
460 time_now = round(time.time())
461 # SAPISID cookie is required if not already present
462 if not yt_cookies.get('SAPISID'):
464 '.youtube.com', 'SAPISID', sapisid_cookie.value, secure=True, expire_time=time_now + 3600)
465 # SAPISIDHASH algorithm from https://stackoverflow.com/a/32065323
466 sapisidhash = hashlib.sha1(
467 f'{time_now} {sapisid_cookie.value} {origin}'.encode('utf-8')).hexdigest()
468 return f'SAPISIDHASH {time_now}_{sapisidhash}'
470 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
471 note='Downloading API JSON', errnote='Unable to download API page',
472 context=None, api_key=None, api_hostname=None, default_client='WEB'):
474 data = {'context': context} if context else {'context': self._extract_context(default_client=default_client)}
476 real_headers = self._generate_api_headers(client=default_client)
477 real_headers.update({'content-type': 'application/json'})
479 real_headers.update(headers)
480 return self._download_json(
481 'https://%s/youtubei/v1/%s' % (api_hostname or self._get_innertube_host(default_client), ep),
482 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
483 data=json.dumps(data).encode('utf8'), headers=real_headers,
484 query={'key': api_key or self._extract_api_key()})
486 def _extract_yt_initial_data(self, video_id, webpage):
487 return self._parse_json(
489 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
490 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
493 def _extract_identity_token(self, webpage, item_id):
494 ytcfg = self._extract_ytcfg(item_id, webpage)
496 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
499 return self._search_regex(
500 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
501 'identity token
', default=None)
504 def _extract_account_syncid(*args):
506 Extract syncId required to download private playlists of secondary channels
507 @params response and/or ytcfg
510 # ytcfg includes channel_syncid if on secondary channel
511 delegated_sid = try_get(data, lambda x: x['DELEGATED_SESSION_ID
'], compat_str)
515 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
516 lambda x: x['DATASYNC_ID
']), compat_str) or '').split("||")
517 if len(sync_ids) >= 2 and sync_ids[1]:
518 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
519 # and just "user_syncid||" for primary channel. We only want the channel_syncid
522 def _extract_ytcfg(self, video_id, webpage):
525 return self._parse_json(
527 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
528 default='{}'), video_id, fatal=False) or {}
530 def _generate_api_headers(self
, ytcfg
=None, identity_token
=None, account_syncid
=None,
531 visitor_data
=None, api_hostname
=None, client
='WEB', session_index
=None):
532 origin
= 'https://' + (api_hostname
if api_hostname
else self
._get
_innertube
_host
(client
))
534 'X-YouTube-Client-Name': compat_str(
535 self
._ytcfg
_get
_safe
(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT_CLIENT_NAME'], default_client
=client
)),
536 'X-YouTube-Client-Version': self
._extract
_client
_version
(ytcfg
, client
),
539 if not visitor_data
and ytcfg
:
540 visitor_data
= try_get(
541 self
._extract
_context
(ytcfg
, client
), lambda x
: x
['client']['visitorData'], compat_str
)
543 headers
['X-Youtube-Identity-Token'] = identity_token
545 headers
['X-Goog-PageId'] = account_syncid
546 if session_index
is None and ytcfg
:
547 session_index
= self
._extract
_session
_index
(ytcfg
)
548 if account_syncid
or session_index
is not None:
549 headers
['X-Goog-AuthUser'] = session_index
if session_index
is not None else 0
551 headers
['X-Goog-Visitor-Id'] = visitor_data
552 auth
= self
._generate
_sapisidhash
_header
(origin
)
554 headers
['Authorization'] = auth
555 headers
['X-Origin'] = origin
559 def _build_api_continuation_query(continuation
, ctp
=None):
561 'continuation': continuation
563 # TODO: Inconsistency with clickTrackingParams.
564 # Currently we have a fixed ctp contained within context (from ytcfg)
565 # and a ctp in root query for continuation.
567 query
['clickTracking'] = {'clickTrackingParams': ctp}
571 def _extract_next_continuation_data(cls
, renderer
):
572 next_continuation
= try_get(
573 renderer
, (lambda x
: x
['continuations'][0]['nextContinuationData'],
574 lambda x
: x
['continuation']['reloadContinuationData']), dict)
575 if not next_continuation
:
577 continuation
= next_continuation
.get('continuation')
580 ctp
= next_continuation
.get('clickTrackingParams')
581 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
584 def _extract_continuation_ep_data(cls
, continuation_ep
: dict):
585 if isinstance(continuation_ep
, dict):
586 continuation
= try_get(
587 continuation_ep
, lambda x
: x
['continuationCommand']['token'], compat_str
)
590 ctp
= continuation_ep
.get('clickTrackingParams')
591 return cls
._build
_api
_continuation
_query
(continuation
, ctp
)
594 def _extract_continuation(cls
, renderer
):
595 next_continuation
= cls
._extract
_next
_continuation
_data
(renderer
)
596 if next_continuation
:
597 return next_continuation
600 for key
in ('contents', 'items'):
601 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(cls
, 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
= cls
._get
_text
(alert
.get('text'))
625 yield alert_type
, message
627 def _report_alerts(self
, alerts
, expected
=True):
630 for alert_type
, alert_message
in alerts
:
631 if alert_type
.lower() == 'error':
632 errors
.append([alert_type
, alert_message
])
634 warnings
.append([alert_type
, alert_message
])
636 for alert_type
, alert_message
in (warnings
+ errors
[:-1]):
637 self
.report_warning('YouTube said: %s - %s' % (alert_type
, alert_message
))
639 raise ExtractorError('YouTube said: %s' % errors
[-1][1], expected
=expected
)
641 def _extract_and_report_alerts(self
, data
, *args
, **kwargs
):
642 return self
._report
_alerts
(self
._extract
_alerts
(data
), *args
, **kwargs
)
644 def _extract_badges(self
, renderer
: dict):
646 for badge
in try_get(renderer
, lambda x
: x
['badges'], list) or []:
647 label
= try_get(badge
, lambda x
: x
['metadataBadgeRenderer']['label'], compat_str
)
649 badges
.add(label
.lower())
653 def _get_text(data
, getter
=None, max_runs
=None):
654 for get
in variadic(getter
):
655 d
= try_get(data
, get
) if get
is not None else data
656 text
= try_get(d
, lambda x
: x
['simpleText'], compat_str
)
659 runs
= try_get(d
, lambda x
: x
['runs'], list) or []
660 if not runs
and isinstance(d
, list):
664 for run
in runs
[:min(len(runs
), max_runs
or len(runs
))]:
665 yield try_get(run
, lambda x
: x
['text'], compat_str
) or ''
667 text
= ''.join(get_runs(runs
))
671 def _extract_response(self
, item_id
, query
, note
='Downloading API JSON', headers
=None,
672 ytcfg
=None, check_get_keys
=None, ep
='browse', fatal
=True, api_hostname
=None,
673 default_client
='WEB'):
677 retries
= self
.get_param('extractor_retries', 3)
678 if check_get_keys
is None:
680 while count
< retries
:
683 self
.report_warning('%s. Retrying ...' % last_error
)
685 response
= self
._call
_api
(
686 ep
=ep
, fatal
=True, headers
=headers
,
687 video_id
=item_id
, query
=query
,
688 context
=self
._extract
_context
(ytcfg
, default_client
),
689 api_key
=self
._extract
_api
_key
(ytcfg
, default_client
),
690 api_hostname
=api_hostname
, default_client
=default_client
,
691 note
='%s%s' % (note
, ' (retry #%d)' % count
if count
else ''))
692 except ExtractorError
as e
:
693 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (500, 503, 404):
694 # Downloading page may result in intermittent 5xx HTTP error
695 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
696 last_error
= 'HTTP Error %s' % e
.cause
.code
702 self
.report_warning(error_to_compat_str(e
))
706 # Youtube may send alerts if there was an issue with the continuation page
708 self
._extract
_and
_report
_alerts
(response
, expected
=False)
709 except ExtractorError
as e
:
712 self
.report_warning(error_to_compat_str(e
))
714 if not check_get_keys
or dict_get(response
, check_get_keys
):
716 # Youtube sometimes sends incomplete data
717 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
718 last_error
= 'Incomplete data received'
721 raise ExtractorError(last_error
)
723 self
.report_warning(last_error
)
728 def is_music_url(url
):
729 return re
.match(r
'https?://music\.youtube\.com/', url
) is not None
731 def _extract_video(self
, renderer
):
732 video_id
= renderer
.get('videoId')
733 title
= self
._get
_text
(renderer
.get('title'))
734 description
= self
._get
_text
(renderer
.get('descriptionSnippet'))
735 duration
= parse_duration(self
._get
_text
(renderer
.get('lengthText')))
736 view_count_text
= self
._get
_text
(renderer
.get('viewCountText')) or ''
737 view_count
= str_to_int(self
._search
_regex
(
738 r
'^([\d,]+)', re
.sub(r
'\s', '', view_count_text
),
739 'view count', default
=None))
741 uploader
= self
._get
_text
(renderer
, (lambda x
: x
['ownerText'], lambda x
: x
['shortBylineText']))
745 'ie_key': YoutubeIE
.ie_key(),
749 'description': description
,
750 'duration': duration
,
751 'view_count': view_count
,
752 'uploader': uploader
,
756 class YoutubeIE(YoutubeBaseInfoExtractor
):
757 IE_DESC
= 'YouTube.com'
759 # invidious-redirect websites
760 r
'(?:www\.)?redirect\.invidious\.io',
761 r
'(?:(?:www|dev)\.)?invidio\.us',
762 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
763 r
'(?:www\.)?invidious\.pussthecat\.org',
764 r
'(?:www\.)?invidious\.zee\.li',
765 r
'(?:www\.)?invidious\.ethibox\.fr',
766 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
767 # youtube-dl invidious instances list
768 r
'(?:(?:www|no)\.)?invidiou\.sh',
769 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
770 r
'(?:www\.)?invidious\.kabi\.tk',
771 r
'(?:www\.)?invidious\.mastodon\.host',
772 r
'(?:www\.)?invidious\.zapashcanon\.fr',
773 r
'(?:www\.)?(?:invidious(?:-us)?|piped)\.kavin\.rocks',
774 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
775 r
'(?:www\.)?invidious\.himiko\.cloud',
776 r
'(?:www\.)?invidious\.reallyancient\.tech',
777 r
'(?:www\.)?invidious\.tube',
778 r
'(?:www\.)?invidiou\.site',
779 r
'(?:www\.)?invidious\.site',
780 r
'(?:www\.)?invidious\.xyz',
781 r
'(?:www\.)?invidious\.nixnet\.xyz',
782 r
'(?:www\.)?invidious\.048596\.xyz',
783 r
'(?:www\.)?invidious\.drycat\.fr',
784 r
'(?:www\.)?inv\.skyn3t\.in',
785 r
'(?:www\.)?tube\.poal\.co',
786 r
'(?:www\.)?tube\.connect\.cafe',
787 r
'(?:www\.)?vid\.wxzm\.sx',
788 r
'(?:www\.)?vid\.mint\.lgbt',
789 r
'(?:www\.)?vid\.puffyan\.us',
790 r
'(?:www\.)?yewtu\.be',
791 r
'(?:www\.)?yt\.elukerio\.org',
792 r
'(?:www\.)?yt\.lelux\.fi',
793 r
'(?:www\.)?invidious\.ggc-project\.de',
794 r
'(?:www\.)?yt\.maisputain\.ovh',
795 r
'(?:www\.)?ytprivate\.com',
796 r
'(?:www\.)?invidious\.13ad\.de',
797 r
'(?:www\.)?invidious\.toot\.koeln',
798 r
'(?:www\.)?invidious\.fdn\.fr',
799 r
'(?:www\.)?watch\.nettohikari\.com',
800 r
'(?:www\.)?invidious\.namazso\.eu',
801 r
'(?:www\.)?invidious\.silkky\.cloud',
802 r
'(?:www\.)?invidious\.exonip\.de',
803 r
'(?:www\.)?invidious\.riverside\.rocks',
804 r
'(?:www\.)?invidious\.blamefran\.net',
805 r
'(?:www\.)?invidious\.moomoo\.de',
806 r
'(?:www\.)?ytb\.trom\.tf',
807 r
'(?:www\.)?yt\.cyberhost\.uk',
808 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
809 r
'(?:www\.)?qklhadlycap4cnod\.onion',
810 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
811 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
812 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
813 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
814 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
815 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
816 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
817 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
818 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
819 r
'(?:www\.)?hpniueoejy4opn7bc4ftgazyqjoeqwlvh2uiku2xqku6zpoa4bf5ruid\.onion',
821 _VALID_URL
= r
"""(?x)^
823 (?:https?://|//) # http(s):// or protocol-independent URL
824 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
825 (?:www\.)?deturl\.com/www\.youtube\.com|
826 (?:www\.)?pwnyoutube\.com|
827 (?:www\.)?hooktube\.com|
828 (?:www\.)?yourepeat\.com|
831 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
832 (?:.*?\#/)? # handle anchor (#/) redirect urls
833 (?: # the various things that can precede the ID:
834 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
835 |(?: # or the v= param in all its forms
836 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
837 (?:\?|\#!?) # the params delimiter ? or # or #!
838 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
843 youtu\.be| # just youtu.be/xxxx
844 vid\.plus| # or vid.plus/xxxx
845 zwearz\.com/watch| # or zwearz.com/watch/xxxx
848 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
850 )? # all until now is optional -> you can pass the naked ID
851 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
852 (?(1).+)? # if we found the ID, everything can follow
854 'invidious': '|'.join(_INVIDIOUS_SITES
),
857 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
858 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$',
859 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
862 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
863 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
864 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
865 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
866 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
867 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
868 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
869 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
870 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
871 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
872 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
873 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
874 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
875 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
876 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
877 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
878 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
879 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
883 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
884 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
885 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
886 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
887 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
888 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
889 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
891 # Apple HTTP Live Streaming
892 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
893 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
894 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
895 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
896 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
897 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
898 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
899 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
902 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
903 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
904 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
905 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
906 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
907 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
908 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
909 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
910 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
911 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
912 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
913 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
916 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
917 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
918 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
919 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
920 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
921 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
922 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
925 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
926 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
927 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
928 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
929 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
930 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
931 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
932 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
933 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
934 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
935 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
936 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
937 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
938 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
939 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
940 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
941 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
942 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
943 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
944 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
945 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
946 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
949 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
950 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
952 # Dash webm audio with opus inside
953 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
954 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
955 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
958 '_rtmp': {'protocol': 'rtmp'}
,
960 # av01 video only formats sometimes served with "unknown" codecs
961 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
962 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
963 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
964 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
966 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
968 _AGE_GATE_REASONS
= (
969 'Sign in to confirm your age',
970 'This video may be inappropriate for some users.',
971 'Sorry, this content is age-restricted.')
978 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
982 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
983 'uploader': 'Philipp Hagemeister',
984 'uploader_id': 'phihag',
985 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
986 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
987 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
988 'upload_date': '20121002',
989 '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 .',
990 'categories': ['Science & Technology'],
991 'tags': ['youtube-dl'],
995 'dislike_count': int,
1001 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
1002 'note': 'Embed-only video (#1746)',
1004 'id': 'yZIXLfi8CZQ',
1006 'upload_date': '20120608',
1007 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
1008 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
1009 'uploader': 'SET India',
1010 'uploader_id': 'setindia',
1011 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
1014 'skip': 'Private video',
1017 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
1018 'note': 'Use the first video ID in the URL',
1020 'id': 'BaW_jenozKc',
1022 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
1023 'uploader': 'Philipp Hagemeister',
1024 'uploader_id': 'phihag',
1025 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
1026 'upload_date': '20121002',
1027 '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 .',
1028 'categories': ['Science & Technology'],
1029 'tags': ['youtube-dl'],
1033 'dislike_count': int,
1036 'skip_download': True,
1040 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
1041 'note': '256k DASH audio (format 141) via DASH manifest',
1043 'id': 'a9LDPn-MO4I',
1045 'upload_date': '20121002',
1046 'uploader_id': '8KVIDEO',
1047 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
1049 'uploader': '8KVIDEO',
1050 'title': 'UHDTV TEST 8K VIDEO.mp4'
1053 'youtube_include_dash_manifest': True,
1056 'skip': 'format 141 not served anymore',
1058 # DASH manifest with encrypted signature
1060 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
1062 'id': 'IB3lcPjvWLA',
1064 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
1065 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
1067 'uploader': 'AfrojackVEVO',
1068 'uploader_id': 'AfrojackVEVO',
1069 'upload_date': '20131011',
1073 'youtube_include_dash_manifest': True,
1074 'format': '141/bestaudio[ext=m4a]',
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 # controversial video, requires bpctr/contentCheckOk
1611 'url': 'https://www.youtube.com/watch?v=SZJvDhaSDnc',
1613 'id': 'SZJvDhaSDnc',
1615 'title': 'San Diego teen commits suicide after bullying over embarrassing video',
1616 'channel_id': 'UC-SJ6nODDmufqBzPBwCvYvQ',
1617 'uploader': 'CBS This Morning',
1618 'upload_date': '20140716',
1619 'description': 'md5:acde3a73d3f133fc97e837a9f76b53b7'
1623 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1624 'url': 'cBvYw8_A0vQ',
1626 'id': 'cBvYw8_A0vQ',
1628 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1629 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1630 'upload_date': '20201120',
1631 'uploader': 'Walk around Japan',
1632 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1633 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1636 'skip_download': True,
1639 # Has multiple audio streams
1640 'url': 'WaOKSUlf4TM',
1641 'only_matching': True
1643 # Requires Premium: has format 141 when requested using YTM url
1644 'url': 'https://music.youtube.com/watch?v=XclachpHxis',
1645 'only_matching': True
1647 # multiple subtitles with same lang_code
1648 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1649 'only_matching': True,
1651 # Force use android client fallback
1652 'url': 'https://www.youtube.com/watch?v=YOelRv7fMxY',
1654 'id': 'YOelRv7fMxY',
1655 'title': 'Digging a Secret Tunnel from my Workshop',
1657 'upload_date': '20210624',
1658 'channel_id': 'UCp68_FLety0O-n9QU6phsgw',
1659 'uploader': 'colinfurze',
1660 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCp68_FLety0O-n9QU6phsgw',
1661 'description': 'md5:ecb672623246d98c6c562eed6ae798c3'
1664 'format': '17', # 3gp format available on android
1665 'extractor_args': {'youtube': {'player_client': ['android']}
},
1669 # Skip download of additional client configs (remix client config in this case)
1670 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1671 'only_matching': True,
1673 'extractor_args': {'youtube': {'player_skip': ['configs']}
},
1679 def suitable(cls
, url
):
1680 # Hack for lazy extractors until more generic solution is implemented
1682 from .youtube
import parse_qs
1684 if qs
.get('list', [None])[0]:
1686 return super(YoutubeIE
, cls
).suitable(url
)
1688 def __init__(self
, *args
, **kwargs
):
1689 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1690 self
._code
_cache
= {}
1691 self
._player
_cache
= {}
1693 def _extract_player_url(self
, ytcfg
=None, webpage
=None):
1694 player_url
= try_get(ytcfg
, (lambda x
: x
['PLAYER_JS_URL']), str)
1696 player_url
= self
._search
_regex
(
1697 r
'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1698 webpage
, 'player URL', fatal
=False)
1699 if player_url
.startswith('//'):
1700 player_url
= 'https:' + player_url
1701 elif not re
.match(r
'https?://', player_url
):
1702 player_url
= compat_urlparse
.urljoin(
1703 'https://www.youtube.com', player_url
)
1706 def _signature_cache_id(self
, example_sig
):
1707 """ Return a string representation of a signature """
1708 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1711 def _extract_player_info(cls
, player_url
):
1712 for player_re
in cls
._PLAYER
_INFO
_RE
:
1713 id_m
= re
.search(player_re
, player_url
)
1717 raise ExtractorError('Cannot identify player %r' % player_url
)
1718 return id_m
.group('id')
1720 def _load_player(self
, video_id
, player_url
, fatal
=True) -> bool:
1721 player_id
= self
._extract
_player
_info
(player_url
)
1722 if player_id
not in self
._code
_cache
:
1723 self
._code
_cache
[player_id
] = self
._download
_webpage
(
1724 player_url
, video_id
, fatal
=fatal
,
1725 note
='Downloading player ' + player_id
,
1726 errnote
='Download of %s failed' % player_url
)
1727 return player_id
in self
._code
_cache
1729 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1730 player_id
= self
._extract
_player
_info
(player_url
)
1732 # Read from filesystem cache
1733 func_id
= 'js_%s_%s' % (
1734 player_id
, self
._signature
_cache
_id
(example_sig
))
1735 assert os
.path
.basename(func_id
) == func_id
1737 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1738 if cache_spec
is not None:
1739 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1741 if self
._load
_player
(video_id
, player_url
):
1742 code
= self
._code
_cache
[player_id
]
1743 res
= self
._parse
_sig
_js
(code
)
1745 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1746 cache_res
= res(test_string
)
1747 cache_spec
= [ord(c
) for c
in cache_res
]
1749 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1752 def _print_sig_code(self
, func
, example_sig
):
1753 def gen_sig_code(idxs
):
1754 def _genslice(start
, end
, step
):
1755 starts
= '' if start
== 0 else str(start
)
1756 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1757 steps
= '' if step
== 1 else (':%d' % step
)
1758 return 's[%s%s%s]' % (starts
, ends
, steps
)
1761 # Quelch pyflakes warnings - start will be set when step is set
1762 start
= '(Never used)'
1763 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1764 if step
is not None:
1765 if i
- prev
== step
:
1767 yield _genslice(start
, prev
, step
)
1770 if i
- prev
in [-1, 1]:
1775 yield 's[%d]' % prev
1779 yield _genslice(start
, i
, step
)
1781 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1782 cache_res
= func(test_string
)
1783 cache_spec
= [ord(c
) for c
in cache_res
]
1784 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1785 signature_id_tuple
= '(%s)' % (
1786 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1787 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1788 ' return %s\n') % (signature_id_tuple
, expr_code
)
1789 self
.to_screen('Extracted signature function:\n' + code
)
1791 def _parse_sig_js(self
, jscode
):
1792 funcname
= self
._search
_regex
(
1793 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1794 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1795 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
1796 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
1797 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}\(a,\d+\)',
1798 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\(\s*""\s*\)',
1799 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1801 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1802 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1803 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1804 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1805 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1806 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1807 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1808 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1809 jscode, 'Initial JS player signature function name
', group='sig
')
1811 jsi = JSInterpreter(jscode)
1812 initial_function = jsi.extract_function(funcname)
1813 return lambda s: initial_function([s])
1815 def _decrypt_signature(self, s, video_id, player_url):
1816 """Turn the encrypted s field into a working signature"""
1818 if player_url is None:
1819 raise ExtractorError('Cannot decrypt signature without player_url
')
1822 player_id = (player_url, self._signature_cache_id(s))
1823 if player_id not in self._player_cache:
1824 func = self._extract_signature_function(
1825 video_id, player_url, s
1827 self._player_cache[player_id] = func
1828 func = self._player_cache[player_id]
1829 if self.get_param('youtube_print_sig_code
'):
1830 self._print_sig_code(func, s)
1832 except Exception as e:
1833 tb = traceback.format_exc()
1834 raise ExtractorError(
1835 'Signature extraction failed
: ' + tb, cause=e)
1837 def _extract_signature_timestamp(self, video_id, player_url, ytcfg=None, fatal=False):
1839 Extract signatureTimestamp (sts)
1840 Required to tell API what sig/player version is in use.
1843 if isinstance(ytcfg, dict):
1844 sts = int_or_none(ytcfg.get('STS
'))
1847 # Attempt to extract from player
1848 if player_url is None:
1849 error_msg = 'Cannot extract signature timestamp without player_url
.'
1851 raise ExtractorError(error_msg)
1852 self.report_warning(error_msg)
1854 if self._load_player(video_id, player_url, fatal=fatal):
1855 player_id = self._extract_player_info(player_url)
1856 code = self._code_cache[player_id]
1857 sts = int_or_none(self._search_regex(
1858 r'(?
:signatureTimestamp|sts
)\s
*:\s
*(?P
<sts
>[0-9]{5}
)', code,
1859 'JS player signature timestamp
', group='sts
', fatal=fatal))
1862 def _mark_watched(self, video_id, player_response):
1863 playback_url = url_or_none(try_get(
1865 lambda x: x['playbackTracking
']['videostatsPlaybackUrl
']['baseUrl
']))
1866 if not playback_url:
1868 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1869 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1871 # cpn generation algorithm is reverse engineered from base.js.
1872 # In fact it works even with dummy cpn.
1873 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
1874 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1880 playback_url = compat_urlparse.urlunparse(
1881 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1883 self._download_webpage(
1884 playback_url, video_id, 'Marking watched
',
1885 'Unable to mark watched
', fatal=False)
1888 def _extract_urls(webpage):
1889 # Embedded YouTube player
1891 unescapeHTML(mobj.group('url
'))
1892 for mobj in re.finditer(r'''(?x)
1902 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1903 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1906 # lazyYT YouTube embed
1907 entries.extend(list(map(
1909 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
1911 # Wordpress "YouTube Video Importer
" plugin
1912 matches = re.findall(r'''(?x)<div[^>]+
1913 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
1914 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
1915 entries.extend(m[-1] for m in matches)
1920 def _extract_url(webpage):
1921 urls = YoutubeIE._extract_urls(webpage)
1922 return urls[0] if urls else None
1925 def extract_id(cls, url):
1926 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1928 raise ExtractorError('Invalid URL: %s' % url)
1929 video_id = mobj.group(2)
1932 def _extract_chapters_from_json(self, data, duration):
1933 chapter_list = traverse_obj(
1935 'playerOverlays', 'playerOverlayRenderer', 'decoratedPlayerBarRenderer',
1936 'decoratedPlayerBarRenderer', 'playerBar', 'chapteredPlayerBarRenderer', 'chapters'
1937 ), expected_type=list)
1939 return self._extract_chapters(
1941 chapter_time=lambda chapter: float_or_none(
1942 traverse_obj(chapter, ('chapterRenderer', 'timeRangeStartMillis')), scale=1000),
1943 chapter_title=lambda chapter: traverse_obj(
1944 chapter, ('chapterRenderer', 'title', 'simpleText'), expected_type=str),
1947 def _extract_chapters_from_engagement_panel(self, data, duration):
1948 content_list = traverse_obj(
1950 ('engagementPanels', ..., 'engagementPanelSectionListRenderer', 'content', 'macroMarkersListRenderer', 'contents'),
1951 expected_type=list, default=[])
1952 chapter_time = lambda chapter: parse_duration(self._get_text(chapter.get('timeDescription')))
1953 chapter_title = lambda chapter: self._get_text(chapter.get('title'))
1957 self._extract_chapters(
1958 traverse_obj(contents, (..., 'macroMarkersListItemRenderer')),
1959 chapter_time, chapter_title, duration)
1960 for contents in content_list
1963 def _extract_chapters(self, chapter_list, chapter_time, chapter_title, duration):
1965 last_chapter = {'start_time': 0}
1966 for idx, chapter in enumerate(chapter_list or []):
1967 title = chapter_title(chapter)
1968 start_time = chapter_time(chapter)
1969 if start_time is None:
1971 last_chapter['end_time'] = start_time
1972 if start_time < last_chapter['start_time']:
1975 self.report_warning('Invalid start time for chapter "%s"' % last_chapter['title'])
1977 self.report_warning(f'Invalid start time for chapter "{title}"')
1979 last_chapter = {'start_time': start_time, 'title': title}
1980 chapters.append(last_chapter)
1981 last_chapter['end_time'] = duration
1984 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
1985 return self._parse_json(self._search_regex(
1986 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
1987 regex), webpage, name, default='{}'), video_id, fatal=False)
1990 def parse_time_text(time_text):
1992 Parse the comment time text
1993 time_text is in the format 'X units ago (edited)'
1995 time_text_split = time_text.split(' ')
1996 if len(time_text_split) >= 3:
1998 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
2002 def _extract_comment(self, comment_renderer, parent=None):
2003 comment_id = comment_renderer.get('commentId')
2007 text = self._get_text(comment_renderer.get('contentText'))
2009 # note: timestamp is an estimate calculated from the current time and time_text
2010 time_text = self._get_text(comment_renderer.get('publishedTimeText')) or ''
2011 time_text_dt = self.parse_time_text(time_text)
2012 if isinstance(time_text_dt, datetime.datetime):
2013 timestamp = calendar.timegm(time_text_dt.timetuple())
2014 author = self._get_text(comment_renderer.get('authorText'))
2015 author_id = try_get(comment_renderer,
2016 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
2018 votes = parse_count(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
2019 lambda x: x['likeCount']), compat_str)) or 0
2020 author_thumbnail = try_get(comment_renderer,
2021 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
2023 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
2024 is_favorited = 'creatorHeart' in (try_get(
2025 comment_renderer, lambda x: x['actionButtons']['commentActionButtonsRenderer'], dict) or {})
2029 'timestamp': timestamp,
2030 'time_text': time_text,
2031 'like_count': votes,
2032 'is_favorited': is_favorited,
2034 'author_id': author_id,
2035 'author_thumbnail': author_thumbnail,
2036 'author_is_uploader': author_is_uploader,
2037 'parent': parent or 'root'
2040 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
2041 ytcfg, video_id, parent=None, comment_counts=None):
2043 def extract_header(contents):
2045 _continuation = None
2046 for content in contents:
2047 comments_header_renderer = try_get(content, lambda x: x['commentsHeaderRenderer'])
2048 expected_comment_count = parse_count(self._get_text(
2049 comments_header_renderer, (lambda x: x['countText'], lambda x: x['commentsCount']), max_runs=1))
2051 if expected_comment_count:
2052 comment_counts[1] = expected_comment_count
2053 self.to_screen('Downloading ~%d comments' % expected_comment_count)
2054 _total_comments = comment_counts[1]
2055 sort_mode_str = self._configuration_arg('comment_sort', [''])[0]
2056 comment_sort_index = int(sort_mode_str != 'top') # 1 = new, 0 = top
2058 sort_menu_item = try_get(
2059 comments_header_renderer,
2060 lambda x: x['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems'][comment_sort_index], dict) or {}
2061 sort_continuation_ep = sort_menu_item.get('serviceEndpoint') or {}
2063 _continuation = self._extract_continuation_ep_data(sort_continuation_ep) or self._extract_continuation(sort_menu_item)
2064 if not _continuation:
2067 sort_text = sort_menu_item.get('title')
2068 if isinstance(sort_text, compat_str):
2069 sort_text = sort_text.lower()
2071 sort_text = 'top comments' if comment_sort_index == 0 else 'newest first'
2072 self.to_screen('Sorting comments by %s' % sort_text)
2074 return _total_comments, _continuation
2076 def extract_thread(contents):
2078 comment_counts[2] = 0
2079 for content in contents:
2080 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
2081 comment_renderer = try_get(
2082 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
2083 content, (lambda x: x['commentRenderer'], dict))
2085 if not comment_renderer:
2087 comment = self._extract_comment(comment_renderer, parent)
2090 comment_counts[0] += 1
2092 # Attempt to get the replies
2093 comment_replies_renderer = try_get(
2094 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
2096 if comment_replies_renderer:
2097 comment_counts[2] += 1
2098 comment_entries_iter = self._comment_entries(
2099 comment_replies_renderer, identity_token, account_syncid, ytcfg,
2100 video_id, parent=comment.get('id'), comment_counts=comment_counts)
2102 for reply_comment in comment_entries_iter:
2105 # YouTube comments have a max depth of 2
2106 max_depth = int_or_none(self._configuration_arg('max_comment_depth', [''])[0]) or float('inf')
2107 if max_depth == 1 and parent:
2109 if not comment_counts:
2110 # comment so far, est. total comments, current comment thread #
2111 comment_counts = [0, 0, 0]
2113 continuation = self._extract_continuation(root_continuation_data)
2114 if continuation and len(continuation['continuation']) < 27:
2115 self.write_debug('Detected old API continuation token. Generating new API compatible token.')
2116 continuation_token = self._generate_comment_continuation(video_id)
2117 continuation = self._build_api_continuation_query(continuation_token, None)
2120 is_first_continuation = parent is None
2122 for page_num in itertools.count(0):
2123 if not continuation:
2125 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
2126 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
2128 if is_first_continuation:
2129 note_prefix = 'Downloading comment section API JSON'
2131 note_prefix = ' Downloading comment API JSON reply thread %d %s' % (
2132 comment_counts[2], comment_prog_str)
2134 note_prefix = '%sDownloading comment%s API JSON page %d %s' % (
2135 ' ' if parent else '', ' replies' if parent else '',
2136 page_num, comment_prog_str)
2138 response = self._extract_response(
2139 item_id=None, query=continuation,
2140 ep='next', ytcfg=ytcfg, headers=headers, note=note_prefix,
2141 check_get_keys=('onResponseReceivedEndpoints', 'continuationContents'))
2144 visitor_data = try_get(
2146 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
2147 compat_str) or visitor_data
2149 continuation_contents = dict_get(response, ('onResponseReceivedEndpoints', 'continuationContents'))
2152 if isinstance(continuation_contents, list):
2153 for continuation_section in continuation_contents:
2154 if not isinstance(continuation_section, dict):
2156 continuation_items = try_get(
2157 continuation_section,
2158 (lambda x: x['reloadContinuationItemsCommand']['continuationItems'],
2159 lambda x: x['appendContinuationItemsAction']['continuationItems']),
2161 if is_first_continuation:
2162 total_comments, continuation = extract_header(continuation_items)
2164 yield total_comments
2165 is_first_continuation = False
2170 for count, entry in enumerate(extract_thread(continuation_items)):
2172 continuation = self._extract_continuation({'contents': continuation_items})
2174 # Sometimes YouTube provides a continuation without any comments
2175 # In most cases we end up just downloading these with very little comments to come.
2178 self.report_warning('No comments received - assuming end of comments')
2182 # Deprecated response structure
2183 elif isinstance(continuation_contents, dict):
2184 known_continuation_renderers = ('itemSectionContinuation', 'commentRepliesContinuation')
2185 for key, continuation_renderer in continuation_contents.items():
2186 if key not in known_continuation_renderers:
2188 if not isinstance(continuation_renderer, dict):
2190 if is_first_continuation:
2191 header_continuation_items = [continuation_renderer.get('header') or {}]
2192 total_comments, continuation = extract_header(header_continuation_items)
2194 yield total_comments
2195 is_first_continuation = False
2199 # Sometimes YouTube provides a continuation without any comments
2200 # In most cases we end up just downloading these with very little comments to come.
2202 for count, entry in enumerate(extract_thread(continuation_renderer.get('contents') or {})):
2204 continuation = self._extract_continuation(continuation_renderer)
2207 self.report_warning('No comments received - assuming end of comments')
2212 def _generate_comment_continuation(video_id):
2214 Generates initial comment section continuation token from given video id
2216 b64_vid_id = base64.b64encode(bytes(video_id.encode('utf-8')))
2217 parts = ('Eg0SCw==', b64_vid_id, 'GAYyJyIRIgs=', b64_vid_id, 'MAB4AjAAQhBjb21tZW50cy1zZWN0aW9u')
2218 new_continuation_intlist = list(itertools.chain.from_iterable(
2219 [bytes_to_intlist(base64.b64decode(part)) for part in parts]))
2220 return base64.b64encode(intlist_to_bytes(new_continuation_intlist)).decode('utf-8')
2222 def _extract_comments(self, ytcfg, video_id, contents, webpage):
2223 """Entry for comment extraction"""
2224 def _real_comment_extract(contents):
2225 if isinstance(contents, list):
2226 for entry in contents:
2227 for key, renderer in entry.items():
2228 if key not in known_entry_comment_renderers:
2230 yield from self._comment_entries(
2231 renderer, video_id=video_id, ytcfg=ytcfg,
2232 identity_token=self._extract_identity_token(webpage, item_id=video_id),
2233 account_syncid=self._extract_account_syncid(ytcfg))
2236 known_entry_comment_renderers = ('itemSectionRenderer',)
2238 max_comments = int_or_none(self._configuration_arg('max_comments', [''])[0]) or float('inf')
2241 for comment in _real_comment_extract(contents):
2242 if len(comments) >= max_comments:
2244 if isinstance(comment, int):
2245 estimated_total = comment
2247 comments.append(comment)
2248 except KeyboardInterrupt:
2249 self.to_screen('Interrupted by user')
2250 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
2252 'comments': comments,
2253 'comment_count': len(comments),
2257 def _generate_player_context(sts=None):
2259 'html5Preference': 'HTML5_PREF_WANTS',
2262 context['signatureTimestamp'] = sts
2264 'playbackContext': {
2265 'contentPlaybackContext': context
2267 'contentCheckOk': True
2271 def _get_video_info_params(video_id, client='TVHTML5'):
2279 'cver': '6.20180913',
2283 'video_id': video_id,
2284 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
2287 query.update(GVI_CLIENTS.get(client))
2290 def _real_extract(self, url):
2291 url, smuggled_data = unsmuggle_url(url, {})
2292 video_id = self._match_id(url)
2294 is_music_url = smuggled_data.get('is_music_url') or self.is_music_url(url)
2296 base_url = self.http_scheme() + '//www.youtube.com/'
2297 webpage_url = base_url + 'watch?v=' + video_id
2298 webpage = self._download_webpage(
2299 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
2301 ytcfg = self._extract_ytcfg(video_id, webpage) or self._get_default_ytcfg()
2302 identity_token = self._extract_identity_token(webpage, video_id)
2303 session_index = self._extract_session_index(ytcfg)
2304 player_url = self._extract_player_url(ytcfg, webpage)
2306 player_client = self._configuration_arg('player_client', [''])[0]
2307 if player_client not in ('web', 'android', ''):
2308 self.report_warning(f'Invalid player_client {player_client} given. Falling back to android client.')
2309 force_mobile_client = player_client != 'web'
2310 player_skip = self._configuration_arg('player_skip')
2311 player_response = None
2313 player_response = self._extract_yt_initial_variable(
2314 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
2315 video_id, 'initial player response')
2317 syncid = self._extract_account_syncid(ytcfg, player_response)
2318 headers = self._generate_api_headers(ytcfg, identity_token, syncid, session_index=session_index)
2320 ytm_streaming_data = {}
2323 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2324 if sts and not force_mobile_client and 'configs' not in player_skip:
2325 ytm_webpage = self._download_webpage(
2326 'https://music.youtube.com',
2327 video_id, fatal=False, note='Downloading remix client config')
2329 ytm_cfg = self._extract_ytcfg(video_id, ytm_webpage) or {}
2330 ytm_client = 'WEB_REMIX'
2331 if not sts or force_mobile_client:
2332 # Android client already has signature descrambled
2333 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2335 self.report_warning('Falling back to android remix client for player API.')
2336 ytm_client = 'ANDROID_MUSIC'
2339 ytm_headers = self._generate_api_headers(
2340 ytm_cfg, identity_token, syncid,
2341 client=ytm_client, session_index=session_index)
2342 ytm_query = {'videoId': video_id}
2343 ytm_query.update(self._generate_player_context(sts))
2345 ytm_player_response = self._extract_response(
2346 item_id=video_id, ep='player', query=ytm_query,
2347 ytcfg=ytm_cfg, headers=ytm_headers, fatal=False,
2348 default_client=ytm_client,
2349 note='Downloading %sremix player API JSON' % ('android ' if force_mobile_client else ''))
2350 ytm_streaming_data = try_get(ytm_player_response, lambda x: x['streamingData'], dict) or {}
2352 if not player_response or force_mobile_client:
2353 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2356 ytp_headers = headers
2357 if not sts or force_mobile_client:
2358 # Android client already has signature descrambled
2359 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2361 self.report_warning('Falling back to android client for player API.')
2362 yt_client = 'ANDROID'
2364 ytp_headers = self._generate_api_headers(ytpcfg, identity_token, syncid,
2365 client=yt_client, session_index=session_index)
2367 yt_query = {'videoId': video_id}
2368 yt_query.update(self._generate_player_context(sts))
2369 player_response = self._extract_response(
2370 item_id=video_id, ep='player', query=yt_query,
2371 ytcfg=ytpcfg, headers=ytp_headers, fatal=False,
2372 default_client=yt_client,
2373 note='Downloading %splayer API JSON' % ('android ' if force_mobile_client else '')
2374 ) or player_response
2376 # Age-gate workarounds
2377 playability_status = player_response.get('playabilityStatus') or {}
2378 if playability_status.get('reason') in self._AGE_GATE_REASONS:
2379 gvi_clients = ('ANDROID', 'TVHTML5') if force_mobile_client else ('TVHTML5', 'ANDROID')
2380 for gvi_client in gvi_clients:
2381 pr = self._parse_json(try_get(compat_parse_qs(
2382 self._download_webpage(
2383 base_url + 'get_video_info', video_id,
2384 'Refetching age-gated %s info webpage' % gvi_client.lower(),
2385 'unable to download video info webpage', fatal=False,
2386 query=self._get_video_info_params(video_id, client=gvi_client))),
2387 lambda x: x['player_response'][0],
2388 compat_str) or '{}', video_id)
2392 self.report_warning('Falling back to embedded-only age-gate workaround.')
2393 embed_webpage = None
2394 sts = self._extract_signature_timestamp(video_id, player_url, ytcfg, fatal=False)
2395 if sts and not force_mobile_client and 'configs' not in player_skip:
2396 embed_webpage = self._download_webpage(
2397 'https://www.youtube.com/embed/%s?html5=1' % video_id,
2398 video_id=video_id, note='Downloading age-gated embed config')
2400 ytcfg_age = self._extract_ytcfg(video_id, embed_webpage) or {}
2401 # If we extracted the embed webpage, it'll tell us if we can view the video
2402 embedded_pr = self._parse_json(
2403 try_get(ytcfg_age, lambda x: x['PLAYER_VARS']['embedded_player_response'], str) or '{}',
2405 embedded_ps_reason = try_get(embedded_pr, lambda x: x['playabilityStatus']['reason'], str) or ''
2406 if embedded_ps_reason not in self._AGE_GATE_REASONS:
2407 yt_client = 'WEB_EMBEDDED_PLAYER'
2408 if not sts or force_mobile_client:
2409 # Android client already has signature descrambled
2410 # See: https://github.com/TeamNewPipe/NewPipeExtractor/issues/562
2412 self.report_warning(
2413 'Falling back to android embedded client for player API (note: some formats may be missing).')
2414 yt_client = 'ANDROID_EMBEDDED_PLAYER'
2417 ytage_headers = self._generate_api_headers(
2418 ytcfg_age, identity_token, syncid,
2419 client=yt_client, session_index=session_index)
2420 yt_age_query = {'videoId': video_id}
2421 yt_age_query.update(self._generate_player_context(sts))
2422 pr = self._extract_response(
2423 item_id=video_id, ep='player', query=yt_age_query,
2424 ytcfg=ytcfg_age, headers=ytage_headers, fatal=False,
2425 default_client=yt_client,
2426 note='Downloading %sage-gated player API JSON' % ('android ' if force_mobile_client else '')
2430 player_response = pr
2432 trailer_video_id = try_get(
2434 lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'],
2436 if trailer_video_id:
2437 return self.url_result(
2438 trailer_video_id, self.ie_key(), trailer_video_id)
2441 lambda x: self._html_search_meta(x, webpage, default=None)) \
2442 if webpage else lambda x: None
2444 video_details = player_response.get('videoDetails') or {}
2445 microformat = try_get(
2447 lambda x: x['microformat']['playerMicroformatRenderer'],
2449 video_title = video_details.get('title') \
2450 or self._get_text(microformat.get('title')) \
2451 or search_meta(['og:title', 'twitter:title', 'title'])
2452 video_description = video_details.get('shortDescription')
2454 if not smuggled_data.get('force_singlefeed', False):
2455 if not self.get_param('noplaylist'):
2456 multifeed_metadata_list = try_get(
2458 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
2460 if multifeed_metadata_list:
2463 for feed in multifeed_metadata_list.split(','):
2464 # Unquote should take place before split on comma (,) since textual
2465 # fields may contain comma as well (see
2466 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2467 feed_data = compat_parse_qs(
2468 compat_urllib_parse_unquote_plus(feed))
2470 def feed_entry(name):
2472 feed_data, lambda x: x[name][0], compat_str)
2474 feed_id = feed_entry('id')
2477 feed_title = feed_entry('title')
2480 title += ' (%s)' % feed_title
2482 '_type': 'url_transparent',
2483 'ie_key': 'Youtube',
2485 base_url + 'watch?v=' + feed_data['id'][0],
2486 {'force_singlefeed': True}),
2489 feed_ids.append(feed_id)
2491 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
2492 % (', '.join(feed_ids), video_id))
2493 return self.playlist_result(
2494 entries, video_id, video_title, video_description)
2496 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2498 formats, itags, stream_ids = [], [], []
2501 # "tiny" is the smallest video-only format. But some audio-only formats
2502 # was also labeled "tiny". It is not clear if such formats still exist
2503 'tiny', 'audio_quality_low', 'audio_quality_medium', 'audio_quality_high', # Audio only formats
2504 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'
2507 streaming_data = player_response.get('streamingData') or {}
2508 streaming_formats = streaming_data.get('formats') or []
2509 streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
2510 streaming_formats.extend(ytm_streaming_data.get('formats') or [])
2511 streaming_formats.extend(ytm_streaming_data.get('adaptiveFormats') or [])
2513 for fmt in streaming_formats:
2514 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
2517 itag = str_or_none(fmt.get('itag'))
2518 audio_track = fmt.get('audioTrack') or {}
2519 stream_id = '%s.%s' % (itag or '', audio_track.get('id', ''))
2520 if stream_id in stream_ids:
2523 quality = fmt.get('quality')
2524 if quality == 'tiny' or not quality:
2525 quality = fmt.get('audioQuality', '').lower() or quality
2526 if itag and quality:
2527 itag_qualities[itag] = quality
2528 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
2529 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
2530 # number of fragment that would subsequently requested with (`&sq=N`)
2531 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
2534 fmt_url = fmt.get('url')
2536 sc = compat_parse_qs(fmt.get('signatureCipher'))
2537 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
2538 encrypted_sig = try_get(sc, lambda x: x['s'][0])
2539 if not (sc and fmt_url and encrypted_sig):
2543 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2544 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2545 fmt_url += '&' + sp + '=' + signature
2549 stream_ids.append(stream_id)
2551 tbr = float_or_none(
2552 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
2554 'asr': int_or_none(fmt.get('audioSampleRate')),
2555 'filesize': int_or_none(fmt.get('contentLength')),
2557 'format_note': audio_track.get('displayName') or fmt.get('qualityLabel') or quality,
2558 'fps': int_or_none(fmt.get('fps')),
2559 'height': int_or_none(fmt.get('height')),
2560 'quality': q(quality),
2563 'width': fmt.get('width'),
2564 'language': audio_track.get('id', '').split('.')[0],
2566 mime_mobj = re.match(
2567 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', fmt.get('mimeType') or '')
2569 dct['ext'] = mimetype2ext(mime_mobj.group(1))
2570 dct.update(parse_codecs(mime_mobj.group(2)))
2571 # The 3gp format in android client has a quality of "small",
2572 # but is actually worse than all other formats
2573 if dct['ext'] == '3gp':
2574 dct['quality'] = q('tiny')
2575 no_audio = dct.get('acodec') == 'none'
2576 no_video = dct.get('vcodec') == 'none'
2581 if no_audio or no_video:
2582 dct['downloader_options'] = {
2583 # Youtube throttles chunks >~10M
2584 'http_chunk_size': 10485760,
2587 dct['container'] = dct['ext'] + '_dash'
2590 skip_manifests = self._configuration_arg('skip')
2591 get_dash = 'dash' not in skip_manifests and self.get_param('youtube_include_dash_manifest', True)
2592 get_hls = 'hls' not in skip_manifests and self.get_param('youtube_include_hls_manifest', True)
2594 for sd in (streaming_data, ytm_streaming_data):
2595 hls_manifest_url = get_hls and sd.get('hlsManifestUrl')
2596 if hls_manifest_url:
2597 for f in self._extract_m3u8_formats(
2598 hls_manifest_url, video_id, 'mp4', fatal=False):
2599 itag = self._search_regex(
2600 r'/itag/(\d+)', f['url'], 'itag', default=None)
2602 f['format_id'] = itag
2605 dash_manifest_url = get_dash and sd.get('dashManifestUrl')
2606 if dash_manifest_url:
2607 for f in self._extract_mpd_formats(
2608 dash_manifest_url, video_id, fatal=False):
2609 itag = f['format_id']
2612 if itag in itag_qualities:
2613 f['quality'] = q(itag_qualities[itag])
2614 filesize = int_or_none(self._search_regex(
2615 r'/clen/(\d+)', f.get('fragment_base_url')
2616 or f['url'], 'file size', default=None))
2618 f['filesize'] = filesize
2622 if not self.get_param('allow_unplayable_formats') and streaming_data.get('licenseInfos'):
2623 self.raise_no_formats(
2624 'This video is DRM protected.', expected=True)
2627 lambda x: x['errorScreen']['playerErrorMessageRenderer'],
2629 reason = self._get_text(pemr.get('reason')) or playability_status.get('reason')
2630 subreason = pemr.get('subreason')
2632 subreason = clean_html(self._get_text(subreason))
2633 if subreason == 'The uploader has not made this video available in your country.':
2634 countries = microformat.get('availableCountries')
2636 regions_allowed = search_meta('regionsAllowed')
2637 countries = regions_allowed.split(',') if regions_allowed else None
2638 self.raise_geo_restricted(subreason, countries, metadata_available=True)
2639 reason += '\n' + subreason
2641 self.raise_no_formats(reason, expected=True)
2643 self._sort_formats(formats)
2645 keywords = video_details.get('keywords') or []
2646 if not keywords and webpage:
2648 unescapeHTML(m.group('content'))
2649 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2650 for keyword in keywords:
2651 if keyword.startswith('yt:stretch='):
2652 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2654 # NB: float is intentional for forcing float division
2655 w, h = (float(v) for v in mobj.groups())
2659 if f.get('vcodec') != 'none':
2660 f['stretched_ratio'] = ratio
2663 category = microformat.get('category') or search_meta('genre')
2664 channel_id = video_details.get('channelId') \
2665 or microformat.get('externalChannelId') \
2666 or search_meta('channelId')
2667 duration = int_or_none(
2668 video_details.get('lengthSeconds')
2669 or microformat.get('lengthSeconds')) \
2670 or parse_duration(search_meta('duration'))
2671 is_live = video_details.get('isLive')
2672 is_upcoming = video_details.get('isUpcoming')
2673 owner_profile_url = microformat.get('ownerProfileUrl')
2676 for container in (video_details, microformat):
2677 for thumbnail in (try_get(
2679 lambda x: x['thumbnail']['thumbnails'], list) or []):
2680 thumbnail_url = thumbnail.get('url')
2681 if not thumbnail_url:
2683 # Sometimes youtube gives a wrong thumbnail URL. See:
2684 # https://github.com/yt-dlp/yt-dlp/issues/233
2685 # https://github.com/ytdl-org/youtube-dl/issues/28023
2686 if 'maxresdefault' in thumbnail_url:
2687 thumbnail_url = thumbnail_url.split('?')[0]
2689 'url': thumbnail_url,
2690 'height': int_or_none(thumbnail.get('height')),
2691 'width': int_or_none(thumbnail.get('width')),
2693 thumbnail_url = search_meta(['og:image', 'twitter:image'])
2696 'url': thumbnail_url,
2698 # The best resolution thumbnails sometimes does not appear in the webpage
2699 # See: https://github.com/ytdl-org/youtube-dl/issues/29049, https://github.com/yt-dlp/yt-dlp/issues/340
2700 # List of possible thumbnails - Ref: <https://stackoverflow.com/a/20542029>
2701 hq_thumbnail_names = ['maxresdefault', 'hq720', 'sddefault', 'sd1', 'sd2', 'sd3']
2702 guaranteed_thumbnail_names = [
2703 'hqdefault', 'hq1', 'hq2', 'hq3', '0',
2704 'mqdefault', 'mq1', 'mq2', 'mq3',
2705 'default', '1', '2', '3'
2707 thumbnail_names = hq_thumbnail_names + guaranteed_thumbnail_names
2708 n_thumbnail_names = len(thumbnail_names)
2711 'url': 'https://i.ytimg.com/vi{webp}/{video_id}/{name}{live}.{ext}'.format(
2712 video_id=video_id, name=name, ext=ext,
2713 webp='_webp' if ext == 'webp' else '', live='_live' if is_live else ''),
2714 '_test_url': name in hq_thumbnail_names,
2715 } for name in thumbnail_names for ext in ('webp', 'jpg'))
2716 for thumb in thumbnails:
2717 i = next((i for i, t in enumerate(thumbnail_names) if f'/{video_id}/{t}' in thumb['url']), n_thumbnail_names)
2718 thumb['preference'] = (0 if '.webp' in thumb['url'] else -1) - (2 * i)
2719 self._remove_duplicate_formats(thumbnails)
2723 'title': self._live_title(video_title) if is_live else video_title,
2725 'thumbnails': thumbnails,
2726 'description': video_description,
2727 'upload_date': unified_strdate(
2728 microformat.get('uploadDate')
2729 or search_meta('uploadDate')),
2730 'uploader': video_details['author'],
2731 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2732 'uploader_url': owner_profile_url,
2733 'channel_id': channel_id,
2734 'channel_url': 'https://www.youtube.com/channel/' + channel_id if channel_id else None,
2735 'duration': duration,
2736 'view_count': int_or_none(
2737 video_details.get('viewCount')
2738 or microformat.get('viewCount')
2739 or search_meta('interactionCount')),
2740 'average_rating': float_or_none(video_details.get('averageRating')),
2741 'age_limit': 18 if (
2742 microformat.get('isFamilySafe') is False
2743 or search_meta('isFamilyFriendly') == 'false'
2744 or search_meta('og:restrictions:age') == '18+') else 0,
2745 'webpage_url': webpage_url,
2746 'categories': [category] if category else None,
2749 'playable_in_embed': playability_status.get('playableInEmbed'),
2750 'was_live': video_details.get('isLiveContent'),
2755 lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
2758 def process_language(container, base_url, lang_code, sub_name, query):
2759 lang_subs = container.setdefault(lang_code, [])
2760 for fmt in self._SUBTITLE_FORMATS:
2766 'url': update_url_query(base_url, query),
2770 for caption_track in (pctr.get('captionTracks') or []):
2771 base_url = caption_track.get('baseUrl')
2774 if caption_track.get('kind') != 'asr':
2776 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2777 or caption_track.get('languageCode'))
2781 subtitles, base_url, lang_code,
2782 try_get(caption_track, lambda x: x['name']['simpleText']),
2785 automatic_captions = {}
2786 for translation_language in (pctr.get('translationLanguages') or []):
2787 translation_language_code = translation_language.get('languageCode')
2788 if not translation_language_code:
2791 automatic_captions, base_url, translation_language_code,
2792 self._get_text(translation_language.get('languageName'), max_runs=1),
2793 {'tlang': translation_language_code})
2794 info['automatic_captions'] = automatic_captions
2795 info['subtitles'] = subtitles
2797 parsed_url = compat_urllib_parse_urlparse(url)
2798 for component in [parsed_url.fragment, parsed_url.query]:
2799 query = compat_parse_qs(component)
2800 for k, v in query.items():
2801 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2803 if d_k not in info and k in s_ks:
2804 info[d_k] = parse_duration(query[k][0])
2806 # Youtube Music Auto-generated description
2807 if video_description:
2808 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)
2810 release_year = mobj.group('release_year')
2811 release_date = mobj.group('release_date')
2813 release_date = release_date.replace('-', '')
2814 if not release_year:
2815 release_year = release_date[:4]
2817 'album': mobj.group('album'.strip()),
2818 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2819 'track': mobj.group('track').strip(),
2820 'release_date': release_date,
2821 'release_year': int_or_none(release_year),
2826 initial_data = self._extract_yt_initial_variable(
2827 webpage, self._YT_INITIAL_DATA_RE, video_id,
2829 if not initial_data:
2830 initial_data = self._extract_response(
2831 item_id=video_id, ep='next', fatal=False,
2832 ytcfg=ytcfg, headers=headers, query={'videoId': video_id},
2833 note='Downloading initial data API JSON')
2836 # This will error if there is no livechat
2837 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2838 info['subtitles']['live_chat'] = [{
2839 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2840 'video_id': video_id,
2842 'protocol': 'youtube_live_chat' if is_live or is_upcoming else 'youtube_live_chat_replay',
2844 except (KeyError, IndexError, TypeError):
2848 info['chapters'] = (
2849 self._extract_chapters_from_json(initial_data, duration)
2850 or self._extract_chapters_from_engagement_panel(initial_data, duration)
2855 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2857 for content in contents:
2858 vpir = content.get('videoPrimaryInfoRenderer')
2860 stl = vpir.get('superTitleLink')
2862 stl = self._get_text(stl)
2865 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2866 info['location'] = stl
2868 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2871 'series': mobj.group(1),
2872 'season_number': int(mobj.group(2)),
2873 'episode_number': int(mobj.group(3)),
2875 for tlb in (try_get(
2877 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
2879 tbr = tlb.get('toggleButtonRenderer') or {}
2880 for getter, regex in [(
2881 lambda x: x['defaultText']['accessibility']['accessibilityData'],
2882 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
2883 lambda x: x['accessibility'],
2884 lambda x: x['accessibilityData']['accessibilityData'],
2885 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
2886 label = (try_get(tbr, getter, dict) or {}).get('label')
2888 mobj = re.match(regex, label)
2890 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
2892 sbr_tooltip = try_get(
2893 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
2895 like_count, dislike_count = sbr_tooltip.split(' / ')
2897 'like_count': str_to_int(like_count),
2898 'dislike_count': str_to_int(dislike_count),
2900 vsir = content.get('videoSecondaryInfoRenderer')
2902 info['channel'] = self._get_text(try_get(
2904 lambda x: x['owner']['videoOwnerRenderer']['title'],
2908 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
2910 multiple_songs = False
2912 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
2913 multiple_songs = True
2916 mrr = row.get('metadataRowRenderer') or {}
2917 mrr_title = mrr.get('title')
2920 mrr_title = self._get_text(mrr['title'])
2921 mrr_contents_text = self._get_text(mrr['contents'][0])
2922 if mrr_title == 'License':
2923 info['license'] = mrr_contents_text
2924 elif not multiple_songs:
2925 if mrr_title == 'Album':
2926 info['album'] = mrr_contents_text
2927 elif mrr_title == 'Artist':
2928 info['artist'] = mrr_contents_text
2929 elif mrr_title == 'Song':
2930 info['track'] = mrr_contents_text
2933 'channel': 'uploader',
2934 'channel_id': 'uploader_id',
2935 'channel_url': 'uploader_url',
2937 for to, frm in fallbacks.items():
2938 if not info.get(to):
2939 info[to] = info.get(frm)
2941 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
2946 is_private = bool_or_none(video_details.get('isPrivate'))
2947 is_unlisted = bool_or_none(microformat.get('isUnlisted'))
2948 is_membersonly = None
2950 if initial_data and is_private is not None:
2951 is_membersonly = False
2953 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
2954 badge_labels = set()
2955 for content in contents:
2956 if not isinstance(content, dict):
2958 badge_labels.update(self._extract_badges(content.get('videoPrimaryInfoRenderer')))
2959 for badge_label in badge_labels:
2960 if badge_label.lower() == 'members only':
2961 is_membersonly = True
2962 elif badge_label.lower() == 'premium':
2964 elif badge_label.lower() == 'unlisted':
2967 info['availability'] = self._availability(
2968 is_private=is_private,
2969 needs_premium=is_premium,
2970 needs_subscription=is_membersonly,
2971 needs_auth=info['age_limit'] >= 18,
2972 is_unlisted=None if is_private is None else is_unlisted)
2974 # get xsrf for annotations or comments
2975 get_annotations = self.get_param('writeannotations', False)
2976 get_comments = self.get_param('getcomments', False)
2977 if get_annotations or get_comments:
2979 ytcfg = self._extract_ytcfg(video_id, webpage)
2981 xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
2983 xsrf_token = self._search_regex(
2984 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
2985 webpage, 'xsrf token', group='xsrf_token', fatal=False)
2989 invideo_url = try_get(
2990 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2991 if xsrf_token and invideo_url:
2992 xsrf_field_name = None
2994 xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
2995 if not xsrf_field_name:
2996 xsrf_field_name = self._search_regex(
2997 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2998 webpage, 'xsrf field name',
2999 group='xsrf_field_name', default='session_token')
3000 info['annotations'] = self._download_webpage(
3001 self._proto_relative_url(invideo_url),
3002 video_id, note='Downloading annotations',
3003 errnote='Unable to download video annotations', fatal=False,
3004 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
3007 info['__post_extractor'] = lambda: self._extract_comments(ytcfg, video_id, contents, webpage)
3009 self.mark_watched(video_id, player_response)
3014 class YoutubeTabIE(YoutubeBaseInfoExtractor):
3015 IE_DESC = 'YouTube.com tab'
3016 _VALID_URL = r'''(?x
)
3020 youtube(?
:kids
)?\
.com|
3024 (?P
<channel_type
>channel|c|user|browse
)/|
3027 (?
:playlist|watch
)\?.*?
\blist
=
3029 (?
!(?
:%s)\b) # Direct URLs
3032 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
3033 IE_NAME = 'youtube:tab'
3036 'note': 'playlists, multipage',
3037 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
3038 'playlist_mincount': 94,
3040 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3041 'title': 'Игорь Клейнер - Playlists',
3042 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3043 'uploader': 'Игорь Клейнер',
3044 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3047 'note': 'playlists, multipage, different order',
3048 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3049 'playlist_mincount': 94,
3051 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
3052 'title': 'Игорь Клейнер - Playlists',
3053 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
3054 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
3055 'uploader': 'Игорь Клейнер',
3058 'note': 'playlists, series',
3059 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
3060 'playlist_mincount': 5,
3062 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3063 'title': '3Blue1Brown - Playlists',
3064 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3065 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3066 'uploader': '3Blue1Brown',
3069 'note': 'playlists, singlepage',
3070 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3071 'playlist_mincount': 4,
3073 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3074 'title': 'ThirstForScience - Playlists',
3075 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
3076 'uploader': 'ThirstForScience',
3077 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
3080 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3081 'only_matching': True,
3083 'note': 'basic, single video playlist',
3084 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3086 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3087 'uploader': 'Sergey M.',
3088 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3089 'title': 'youtube-dl public playlist',
3091 'playlist_count': 1,
3093 'note': 'empty playlist',
3094 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3096 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
3097 'uploader': 'Sergey M.',
3098 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
3099 'title': 'youtube-dl empty playlist',
3101 'playlist_count': 0,
3104 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
3106 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3107 'title': 'lex will - Home',
3108 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3109 'uploader': 'lex will',
3110 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3112 'playlist_mincount': 2,
3114 'note': 'Videos tab',
3115 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
3117 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3118 'title': 'lex will - Videos',
3119 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3120 'uploader': 'lex will',
3121 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3123 'playlist_mincount': 975,
3125 'note': 'Videos tab, sorted by popular',
3126 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
3128 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3129 'title': 'lex will - Videos',
3130 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3131 'uploader': 'lex will',
3132 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3134 'playlist_mincount': 199,
3136 'note': 'Playlists tab',
3137 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
3139 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3140 'title': 'lex will - Playlists',
3141 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3142 'uploader': 'lex will',
3143 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3145 'playlist_mincount': 17,
3147 'note': 'Community tab',
3148 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
3150 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3151 'title': 'lex will - Community',
3152 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3153 'uploader': 'lex will',
3154 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3156 'playlist_mincount': 18,
3158 'note': 'Channels tab',
3159 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
3161 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3162 'title': 'lex will - Channels',
3163 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
3164 'uploader': 'lex will',
3165 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3167 'playlist_mincount': 12,
3169 'note': 'Search tab',
3170 'url': 'https://www.youtube.com/c/3blue1brown/search?query=linear%20algebra',
3171 'playlist_mincount': 40,
3173 'id': 'UCYO_jab_esuFRV4b17AJtAw',
3174 'title': '3Blue1Brown - Search - linear algebra',
3175 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
3176 'uploader': '3Blue1Brown',
3177 'uploader_id': 'UCYO_jab_esuFRV4b17AJtAw',
3180 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3181 'only_matching': True,
3183 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3184 'only_matching': True,
3186 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
3187 'only_matching': True,
3189 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
3190 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3192 'title': '29C3: Not my department',
3193 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
3194 'uploader': 'Christiaan008',
3195 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
3196 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
3198 'playlist_count': 96,
3200 'note': 'Large playlist',
3201 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
3203 'title': 'Uploads from Cauchemar',
3204 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
3205 'uploader': 'Cauchemar',
3206 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
3208 'playlist_mincount': 1123,
3210 'note': 'even larger playlist, 8832 videos',
3211 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
3212 'only_matching': True,
3214 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
3215 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
3217 'title': 'Uploads from Interstellar Movie',
3218 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
3219 'uploader': 'Interstellar Movie',
3220 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
3222 'playlist_mincount': 21,
3224 'note': 'Playlist with "show unavailable videos" button',
3225 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
3227 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
3228 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
3229 'uploader': 'Phim Siêu Nhân Nhật Bản',
3230 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
3232 'playlist_mincount': 200,
3234 'note': 'Playlist with unavailable videos in page 7',
3235 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
3237 'title': 'Uploads from BlankTV',
3238 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
3239 'uploader': 'BlankTV',
3240 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
3242 'playlist_mincount': 1000,
3244 'note': 'https://github.com/ytdl-org/youtube-dl/issues/21844',
3245 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3247 'title': 'Data Analysis with Dr Mike Pound',
3248 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
3249 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
3250 'uploader': 'Computerphile',
3251 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
3253 'playlist_mincount': 11,
3255 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
3256 'only_matching': True,
3258 'note': 'Playlist URL that does not actually serve a playlist',
3259 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
3261 'id': 'FqZTN594JQw',
3263 'title': "Smiley's People 01 detective, Adventure Series, Action",
3264 'uploader': 'STREEM',
3265 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
3266 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
3267 'upload_date': '20150526',
3268 'license': 'Standard YouTube License',
3269 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
3270 'categories': ['People & Blogs'],
3274 'dislike_count': int,
3277 'skip_download': True,
3279 'skip': 'This video is not available.',
3280 'add_ie': [YoutubeIE.ie_key()],
3282 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
3283 'only_matching': True,
3285 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
3286 'only_matching': True,
3288 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
3290 'id': 'X1whbWASnNQ', # This will keep changing
3292 'title': compat_str,
3293 'uploader': 'Sky News',
3294 'uploader_id': 'skynews',
3295 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
3296 'upload_date': r're:\d{8}',
3297 'description': compat_str,
3298 'categories': ['News & Politics'],
3301 'dislike_count': int,
3304 'skip_download': True,
3306 'expected_warnings': ['Downloading just video ', 'Ignoring subtitle tracks found in '],
3308 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3310 'id': 'a48o2S1cPoo',
3312 'title': 'The Young Turks - Live Main Show',
3313 'uploader': 'The Young Turks',
3314 'uploader_id': 'TheYoungTurks',
3315 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3316 'upload_date': '20150715',
3317 'license': 'Standard YouTube License',
3318 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3319 'categories': ['News & Politics'],
3320 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3322 'dislike_count': int,
3325 'skip_download': True,
3327 'only_matching': True,
3329 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3330 'only_matching': True,
3332 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3333 'only_matching': True,
3335 'note': 'A channel that is not live. Should raise error',
3336 'url': 'https://www.youtube.com/user/numberphile/live',
3337 'only_matching': True,
3339 'url': 'https://www.youtube.com/feed/trending',
3340 'only_matching': True,
3342 'url': 'https://www.youtube.com/feed/library',
3343 'only_matching': True,
3345 'url': 'https://www.youtube.com/feed/history',
3346 'only_matching': True,
3348 'url': 'https://www.youtube.com/feed/subscriptions',
3349 'only_matching': True,
3351 'url': 'https://www.youtube.com/feed/watch_later',
3352 'only_matching': True,
3354 'note': 'Recommended - redirects to home page',
3355 'url': 'https://www.youtube.com/feed/recommended',
3356 'only_matching': True,
3358 'note': 'inline playlist with not always working continuations',
3359 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3360 'only_matching': True,
3362 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3363 'only_matching': True,
3365 'url': 'https://www.youtube.com/course',
3366 'only_matching': True,
3368 'url': 'https://www.youtube.com/zsecurity',
3369 'only_matching': True,
3371 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3372 'only_matching': True,
3374 'url': 'https://www.youtube.com/TheYoungTurks/live',
3375 'only_matching': True,
3377 'url': 'https://www.youtube.com/hashtag/cctv9',
3382 'playlist_mincount': 350,
3384 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
3385 'only_matching': True,
3387 'note': 'Requires Premium: should request additional YTM-info webpage (and have format 141) for videos in playlist',
3388 'url': 'https://music.youtube.com/playlist?list=PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3389 'only_matching': True
3391 'note': '/browse/ should redirect to /channel/',
3392 'url': 'https://music.youtube.com/browse/UC1a8OFewdjuLq6KlF8M_8Ng',
3393 'only_matching': True
3395 'note': 'VLPL, should redirect to playlist?list=PL...',
3396 'url': 'https://music.youtube.com/browse/VLPLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3398 'id': 'PLRBp0Fe2GpgmgoscNFLxNyBVSFVdYmFkq',
3399 'uploader': 'NoCopyrightSounds',
3400 'description': 'Providing you with copyright free / safe music for gaming, live streaming, studying and more!',
3401 'uploader_id': 'UC_aEa8K-EOJ3D6gOs7HcyNg',
3402 'title': 'NCS Releases',
3404 'playlist_mincount': 166,
3406 'note': 'Topic, should redirect to playlist?list=UU...',
3407 'url': 'https://music.youtube.com/browse/UC9ALqqC4aIeG5iDs7i90Bfw',
3409 'id': 'UU9ALqqC4aIeG5iDs7i90Bfw',
3410 'uploader_id': 'UC9ALqqC4aIeG5iDs7i90Bfw',
3411 'title': 'Uploads from Royalty Free Music - Topic',
3412 'uploader': 'Royalty Free Music - Topic',
3414 'expected_warnings': [
3415 'A channel/user page was given',
3416 'The URL does not have a videos tab',
3418 'playlist_mincount': 101,
3420 'note': 'Topic without a UU playlist',
3421 'url': 'https://www.youtube.com/channel/UCtFRv9O2AHqOZjjynzrv-xg',
3423 'id': 'UCtFRv9O2AHqOZjjynzrv-xg',
3424 'title': 'UCtFRv9O2AHqOZjjynzrv-xg',
3426 'expected_warnings': [
3427 'A channel/user page was given',
3428 'The URL does not have a videos tab',
3429 'Falling back to channel URL',
3431 'playlist_mincount': 9,
3433 'note': 'Youtube music Album',
3434 'url': 'https://music.youtube.com/browse/MPREb_gTAcphH99wE',
3436 'id': 'OLAK5uy_l1m0thk3g31NmIIz_vMIbWtyv7eZixlH0',
3437 'title': 'Album - Royalty Free Music Library V2 (50 Songs)',
3439 'playlist_count': 50,
3441 'note': 'unlisted single video playlist',
3442 'url': 'https://www.youtube.com/playlist?list=PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3444 'uploader_id': 'UC9zHu_mHU96r19o-wV5Qs1Q',
3445 'uploader': 'colethedj',
3446 'id': 'PLwL24UFy54GrB3s2KMMfjZscDi1x5Dajf',
3447 'title': 'yt-dlp unlisted playlist test',
3448 'availability': 'unlisted'
3450 'playlist_count': 1,
3454 def suitable(cls, url):
3455 return False if YoutubeIE.suitable(url) else super(
3456 YoutubeTabIE, cls).suitable(url)
3458 def _extract_channel_id(self, webpage):
3459 channel_id = self._html_search_meta(
3460 'channelId', webpage, 'channel id', default=None)
3463 channel_url = self._html_search_meta(
3464 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3465 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3466 'twitter:app:url:googleplay'), webpage, 'channel url')
3467 return self._search_regex(
3468 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3469 channel_url, 'channel id')
3472 def _extract_basic_item_renderer(item):
3473 # Modified from _extract_grid_item_renderer
3474 known_basic_renderers = (
3475 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
3477 for key, renderer in item.items():
3478 if not isinstance(renderer, dict):
3480 elif key in known_basic_renderers:
3482 elif key.startswith('grid') and key.endswith('Renderer'):
3485 def _grid_entries(self, grid_renderer):
3486 for item in grid_renderer['items']:
3487 if not isinstance(item, dict):
3489 renderer = self._extract_basic_item_renderer(item)
3490 if not isinstance(renderer, dict):
3492 title = self._get_text(renderer.get('title'))
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')
3510 yield self.url_result(
3511 'https://www.youtube.com/channel/%s' % channel_id,
3512 ie=YoutubeTabIE.ie_key(), video_title=title)
3514 # generic endpoint URL support
3515 ep_url = urljoin('https://www.youtube.com/', try_get(
3516 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
3519 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
3520 if ie.suitable(ep_url):
3521 yield self.url_result(
3522 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
3525 def _shelf_entries_from_content(self, shelf_renderer):
3526 content = shelf_renderer.get('content')
3527 if not isinstance(content, dict):
3529 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
3531 # TODO: add support for nested playlists so each shelf is processed
3532 # as separate playlist
3533 # TODO: this includes only first N items
3534 for entry in self._grid_entries(renderer):
3536 renderer = content.get('horizontalListRenderer')
3541 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3543 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3545 shelf_url = urljoin('https://www.youtube.com', ep)
3547 # Skipping links to another channels, note that checking for
3548 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3550 if skip_channels and '/channels?' in shelf_url:
3552 title = self._get_text(shelf_renderer, lambda x: x['title'])
3553 yield self.url_result(shelf_url, video_title=title)
3554 # Shelf may not contain shelf URL, fallback to extraction from content
3555 for entry in self._shelf_entries_from_content(shelf_renderer):
3558 def _playlist_entries(self, video_list_renderer):
3559 for content in video_list_renderer['contents']:
3560 if not isinstance(content, dict):
3562 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3563 if not isinstance(renderer, dict):
3565 video_id = renderer.get('videoId')
3568 yield self._extract_video(renderer)
3570 def _rich_entries(self, rich_grid_renderer):
3572 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3573 video_id = renderer.get('videoId')
3576 yield self._extract_video(renderer)
3578 def _video_entry(self, video_renderer):
3579 video_id = video_renderer.get('videoId')
3581 return self._extract_video(video_renderer)
3583 def _post_thread_entries(self, post_thread_renderer):
3584 post_renderer = try_get(
3585 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3586 if not post_renderer:
3589 video_renderer = try_get(
3590 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
3591 video_id = video_renderer.get('videoId')
3593 entry = self._extract_video(video_renderer)
3596 # playlist attachment
3597 playlist_id = try_get(
3598 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
3600 yield self.url_result(
3601 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3602 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3603 # inline video links
3604 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3606 if not isinstance(run, dict):
3609 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3612 if not YoutubeIE.suitable(ep_url):
3614 ep_video_id = YoutubeIE._match_id(ep_url)
3615 if video_id == ep_video_id:
3617 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3619 def _post_thread_continuation_entries(self, post_thread_continuation):
3620 contents = post_thread_continuation.get('contents')
3621 if not isinstance(contents, list):
3623 for content in contents:
3624 renderer = content.get('backstagePostThreadRenderer')
3625 if not isinstance(renderer, dict):
3627 for entry in self._post_thread_entries(renderer):
3631 def _rich_grid_entries(self
, contents
):
3632 for content
in contents
:
3633 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3635 entry
= self
._video
_entry
(video_renderer
)
3639 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3641 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3642 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3643 for content in contents:
3644 if not isinstance(content, dict):
3646 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3648 renderer = content.get('richItemRenderer')
3650 for entry in self._rich_entries(renderer):
3652 continuation_list[0] = self._extract_continuation(parent_renderer)
3654 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3655 for isr_content in isr_contents:
3656 if not isinstance(isr_content, dict):
3660 'playlistVideoListRenderer': self._playlist_entries,
3661 'gridRenderer': self._grid_entries,
3662 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3663 'backstagePostThreadRenderer': self._post_thread_entries,
3664 'videoRenderer': lambda x: [self._video_entry(x)],
3666 for key, renderer in isr_content.items():
3667 if key not in known_renderers:
3669 for entry in known_renderers[key](renderer):
3672 continuation_list[0] = self._extract_continuation(renderer)
3675 if not continuation_list[0]:
3676 continuation_list[0] = self._extract_continuation(is_renderer)
3678 if not continuation_list[0]:
3679 continuation_list[0] = self._extract_continuation(parent_renderer)
3681 continuation_list = [None] # Python 2 doesnot support nonlocal
3682 tab_content = try_get(tab, lambda x: x['content'], dict)
3686 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3687 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3688 for entry in extract_entries(parent_renderer):
3690 continuation = continuation_list[0]
3693 for page_num in itertools.count(1):
3694 if not continuation:
3696 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
3697 response = self._extract_response(
3698 item_id='%s page %s' % (item_id, page_num),
3699 query=continuation, headers=headers, ytcfg=ytcfg,
3700 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3704 visitor_data = try_get(
3705 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
3707 known_continuation_renderers = {
3708 'playlistVideoListContinuation': self._playlist_entries,
3709 'gridContinuation': self._grid_entries,
3710 'itemSectionContinuation': self._post_thread_continuation_entries,
3711 'sectionListContinuation': extract_entries, # for feeds
3713 continuation_contents = try_get(
3714 response, lambda x: x['continuationContents'], dict) or {}
3715 continuation_renderer = None
3716 for key, value in continuation_contents.items():
3717 if key not in known_continuation_renderers:
3719 continuation_renderer = value
3720 continuation_list = [None]
3721 for entry in known_continuation_renderers[key](continuation_renderer):
3723 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3725 if continuation_renderer:
3729 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3730 'gridVideoRenderer': (self._grid_entries, 'items'),
3731 'gridChannelRenderer': (self._grid_entries, 'items'),
3732 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3733 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3734 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3735 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3737 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3738 continuation_items = try_get(
3739 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3740 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3741 video_items_renderer = None
3742 for key, value in continuation_item.items():
3743 if key not in known_renderers:
3745 video_items_renderer = {known_renderers[key][1]: continuation_items}
3746 continuation_list = [None]
3747 for entry in known_renderers[key][0](video_items_renderer):
3749 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3751 if video_items_renderer:
3756 def _extract_selected_tab(tabs):
3758 renderer = dict_get(tab, ('tabRenderer', 'expandableTabRenderer')) or {}
3759 if renderer.get('selected') is True:
3762 raise ExtractorError('Unable to find selected tab')
3765 def _extract_uploader(cls, data):
3767 renderer = cls._extract_sidebar_info_renderer(data, 'playlistSidebarSecondaryInfoRenderer') or {}
3769 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3771 uploader['uploader'] = owner.get('text')
3772 uploader['uploader_id'] = try_get(
3773 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3774 uploader['uploader_url'] = urljoin(
3775 'https://www.youtube.com/',
3776 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3777 return {k: v for k, v in uploader.items() if v is not None}
3779 def _extract_from_tabs(self, item_id, webpage, data, tabs):
3780 playlist_id = title = description = channel_url = channel_name = channel_id = None
3781 thumbnails_list = tags = []
3783 selected_tab = self._extract_selected_tab(tabs)
3785 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3787 channel_name = renderer.get('title')
3788 channel_url = renderer.get('channelUrl')
3789 channel_id = renderer.get('externalId')
3792 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3795 title = renderer.get('title')
3796 description = renderer.get('description', '')
3797 playlist_id = channel_id
3798 tags = renderer.get('keywords', '').split()
3800 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
3802 self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer'),
3803 lambda x: x['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
3808 for t in thumbnails_list:
3809 if not isinstance(t, dict):
3811 thumbnail_url = url_or_none(t.get('url'))
3812 if not thumbnail_url:
3815 'url': thumbnail_url,
3816 'width': int_or_none(t.get('width')),
3817 'height': int_or_none(t.get('height')),
3819 if playlist_id is None:
3820 playlist_id = item_id
3823 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3825 title += format_field(selected_tab, 'title', ' - %s')
3826 title += format_field(selected_tab, 'expandedText', ' - %s')
3828 'playlist_id': playlist_id,
3829 'playlist_title': title,
3830 'playlist_description': description,
3831 'uploader': channel_name,
3832 'uploader_id': channel_id,
3833 'uploader_url': channel_url,
3834 'thumbnails': thumbnails,
3837 availability = self._extract_availability(data)
3839 metadata['availability'] = availability
3841 metadata.update(self._extract_uploader(data))
3843 'channel': metadata['uploader'],
3844 'channel_id': metadata['uploader_id'],
3845 'channel_url': metadata['uploader_url']})
3846 ytcfg = self._extract_ytcfg(item_id, webpage)
3847 return self.playlist_result(
3849 selected_tab, playlist_id,
3850 self._extract_identity_token(webpage, item_id),
3851 self._extract_account_syncid(ytcfg, data), ytcfg),
3854 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
3855 first_id = last_id = None
3856 ytcfg = self._extract_ytcfg(playlist_id, webpage)
3857 headers = self._generate_api_headers(
3858 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
3859 identity_token=self._extract_identity_token(webpage, item_id=playlist_id))
3860 for page_num in itertools.count(1):
3861 videos = list(self._playlist_entries(playlist))
3864 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3865 if start >= len(videos):
3867 for video in videos[start:]:
3868 if video['id'] == first_id:
3869 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3872 first_id = first_id or videos[0]['id']
3873 last_id = videos[-1]['id']
3874 watch_endpoint = try_get(
3875 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
3877 'playlistId': playlist_id,
3878 'videoId': watch_endpoint.get('videoId') or last_id,
3879 'index': watch_endpoint.get('index') or len(videos),
3880 'params': watch_endpoint.get('params') or 'OAE%3D'
3882 response = self._extract_response(
3883 item_id='%s page %d' % (playlist_id, page_num),
3884 query=query, ep='next', headers=headers, ytcfg=ytcfg,
3885 check_get_keys='contents'
3888 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
3890 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
3891 title = playlist.get('title') or try_get(
3892 data, lambda x: x['titleText']['simpleText'], compat_str)
3893 playlist_id = playlist.get('playlistId') or item_id
3895 # Delegating everything except mix playlists to regular tab-based playlist URL
3896 playlist_url = urljoin(url, try_get(
3897 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3899 if playlist_url and playlist_url != url:
3900 return self.url_result(
3901 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3904 return self.playlist_result(
3905 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
3906 playlist_id=playlist_id, playlist_title=title)
3908 def _extract_availability(self, data):
3910 Gets the availability of a given playlist/tab.
3911 Note: Unless YouTube tells us explicitly, we do not assume it is public
3912 @param data: response
3914 is_private = is_unlisted = None
3915 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer') or {}
3916 badge_labels = self._extract_badges(renderer)
3918 # Personal playlists, when authenticated, have a dropdown visibility selector instead of a badge
3919 privacy_dropdown_entries = try_get(
3920 renderer, lambda x: x['privacyForm']['dropdownFormFieldRenderer']['dropdown']['dropdownRenderer']['entries'], list) or []
3921 for renderer_dict in privacy_dropdown_entries:
3922 is_selected = try_get(
3923 renderer_dict, lambda x: x['privacyDropdownItemRenderer']['isSelected'], bool) or False
3926 label = self._get_text(
3927 try_get(renderer_dict, lambda x: x['privacyDropdownItemRenderer']['label'], dict) or [])
3929 badge_labels.add(label.lower())
3932 for badge_label in badge_labels:
3933 if badge_label == 'unlisted':
3935 elif badge_label == 'private':
3937 elif badge_label == 'public':
3938 is_unlisted = is_private = False
3939 return self._availability(is_private, False, False, False, is_unlisted)
3942 def _extract_sidebar_info_renderer(data, info_renderer, expected_type=dict):
3943 sidebar_renderer = try_get(
3944 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list) or []
3945 for item in sidebar_renderer:
3946 renderer = try_get(item, lambda x: x[info_renderer], expected_type)
3950 def _reload_with_unavailable_videos(self, item_id, data, webpage):
3952 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
3954 browse_id = params = None
3955 renderer = self._extract_sidebar_info_renderer(data, 'playlistSidebarPrimaryInfoRenderer')
3958 menu_renderer = try_get(
3959 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
3960 for menu_item in menu_renderer:
3961 if not isinstance(menu_item, dict):
3963 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
3965 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
3966 if not text or text.lower() != 'show unavailable videos':
3968 browse_endpoint = try_get(
3969 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
3970 browse_id = browse_endpoint.get('browseId')
3971 params = browse_endpoint.get('params')
3974 ytcfg = self._extract_ytcfg(item_id, webpage)
3975 headers = self._generate_api_headers(
3976 ytcfg, account_syncid=self._extract_account_syncid(ytcfg, data),
3977 identity_token=self._extract_identity_token(webpage, item_id=item_id),
3978 visitor_data=try_get(
3979 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
3981 'params': params or 'wgYCCAA=',
3982 'browseId': browse_id or 'VL%s' % item_id
3984 return self._extract_response(
3985 item_id=item_id, headers=headers, query=query,
3986 check_get_keys='contents', fatal=False, ytcfg=ytcfg,
3987 note='Downloading API JSON with unavailable videos')
3989 def _extract_webpage(self, url, item_id):
3990 retries = self.get_param('extractor_retries', 3)
3992 last_error = 'Incomplete yt initial data recieved'
3993 while count < retries:
3995 # Sometimes youtube returns a webpage with incomplete ytInitialData
3996 # See: https://github.com/yt-dlp/yt-dlp/issues/116
3998 self.report_warning('%s. Retrying ...' % last_error)
3999 webpage = self._download_webpage(
4001 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
4002 data = self._extract_yt_initial_data(item_id, webpage)
4003 if data.get('contents') or data.get('currentVideoEndpoint'):
4005 # Extract alerts here only when there is error
4006 self._extract_and_report_alerts(data)
4007 if count >= retries:
4008 raise ExtractorError(last_error)
4009 return webpage, data
4012 def _smuggle_data(entries, data):
4013 for entry in entries:
4015 entry['url'] = smuggle_url(entry['url'], data)
4018 def _real_extract(self, url):
4019 url, smuggled_data = unsmuggle_url(url, {})
4020 if self.is_music_url(url):
4021 smuggled_data['is_music_url'] = True
4022 info_dict = self.__real_extract(url, smuggled_data)
4023 if info_dict.get('entries'):
4024 info_dict['entries'] = self._smuggle_data(info_dict['entries'], smuggled_data)
4027 _url_re = re.compile(r'(?P<pre>%s)(?(channel_type)(?P<tab>/\w+))?(?P<post>.*)$' % _VALID_URL)
4029 def __real_extract(self, url, smuggled_data):
4030 item_id = self._match_id(url)
4031 url = compat_urlparse.urlunparse(
4032 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
4033 compat_opts = self.get_param('compat_opts', [])
4036 mobj = self._url_re.match(url).groupdict()
4037 mobj.update((k, '') for k, v in mobj.items() if v is None)
4040 mobj = get_mobj(url)
4041 # Youtube returns incomplete data if tabname is not lower case
4042 pre, tab, post, is_channel = mobj['pre'], mobj['tab'].lower(), mobj['post'], not mobj['not_channel']
4045 if smuggled_data.get('is_music_url'):
4046 if item_id[:2] == 'VL':
4047 # Youtube music VL channels have an equivalent playlist
4048 item_id = item_id[2:]
4049 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4050 elif item_id[:2] == 'MP':
4051 # Youtube music albums (/channel/MP...) have a OLAK playlist that can be extracted from the webpage
4052 item_id = self._search_regex(
4053 r'\\x22audioPlaylistId\\x22:\\x22([0-9A-Za-z_-]+)\\x22',
4054 self._download_webpage('https://music.youtube.com/channel/%s' % item_id, item_id),
4056 pre, tab, post, is_channel = 'https://www.youtube.com/playlist?list=%s' % item_id, '', '', False
4057 elif mobj['channel_type'] == 'browse':
4058 # Youtube music /browse/ should be changed to /channel/
4059 pre = 'https://www.youtube.com/channel/%s' % item_id
4060 if is_channel and not tab and 'no-youtube-channel-redirect' not in compat_opts:
4061 # Home URLs should redirect to /videos/
4062 self.report_warning(
4063 'A channel/user page was given. All the channel\'s videos will be downloaded. '
4064 'To download only the videos in the home page, add a "/featured" to the URL')
4067 url = ''.join((pre, tab, post))
4068 mobj = get_mobj(url)
4070 # Handle both video/playlist URLs
4072 video_id = qs.get('v', [None])[0]
4073 playlist_id = qs.get('list', [None])[0]
4075 if not video_id and mobj['not_channel'].startswith('watch'):
4077 # If there is neither video or playlist ids, youtube redirects to home page, which is undesirable
4078 raise ExtractorError('Unable to recognize tab page')
4079 # Common mistake: https://www.youtube.com/watch?list=playlist_id
4080 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
4081 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
4082 mobj = get_mobj(url)
4084 if video_id and playlist_id:
4085 if self.get_param('noplaylist'):
4086 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
4087 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4088 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
4090 webpage, data = self._extract_webpage(url, item_id)
4093 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4095 selected_tab = self._extract_selected_tab(tabs)
4096 tab_name = selected_tab.get('title', '')
4097 if 'no-youtube-channel-redirect' not in compat_opts:
4098 if mobj['tab'] == '/live':
4099 # Live tab should have redirected to the video
4100 raise ExtractorError('The channel is not currently live', expected=True)
4101 if mobj['tab'] == '/videos' and tab_name.lower() != mobj['tab'][1:]:
4102 if not mobj['not_channel'] and item_id[:2] == 'UC':
4103 # Topic channels don't have /videos. Use the equivalent playlist instead
4104 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:]))
4105 pl_id = 'UU%s' % item_id[2:]
4106 pl_url = 'https://www.youtube.com/playlist?list=%s%s' % (pl_id, mobj['post'])
4108 pl_webpage, pl_data = self._extract_webpage(pl_url, pl_id)
4109 for alert_type, alert_message in self._extract_alerts(pl_data):
4110 if alert_type == 'error':
4111 raise ExtractorError('Youtube said: %s' % alert_message)
4112 item_id, url, webpage, data = pl_id, pl_url, pl_webpage, pl_data
4113 except ExtractorError:
4114 self.report_warning('The playlist gave error. Falling back to channel URL')
4116 self.report_warning('The URL does not have a %s tab. %s is being downloaded instead' % (mobj['tab'][1:], tab_name))
4118 self.write_debug('Final URL: %s' % url)
4120 # YouTube sometimes provides a button to reload playlist with unavailable videos.
4121 if 'no-youtube-unavailable-videos' not in compat_opts:
4122 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
4123 self._extract_and_report_alerts(data)
4125 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
4127 return self._extract_from_tabs(item_id, webpage, data, tabs)
4130 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
4132 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
4135 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
4136 compat_str) or video_id
4138 if mobj['tab'] != '/live': # live tab is expected to redirect to video
4139 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
4140 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
4142 raise ExtractorError('Unable to recognize tab page')
4145 class YoutubePlaylistIE(InfoExtractor):
4146 IE_DESC = 'YouTube.com playlists'
4147 _VALID_URL = r'''(?x
)(?
:
4152 youtube(?
:kids
)?\
.com|
4157 (?P
<id>%(playlist_id)s)
4158 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
4159 IE_NAME = 'youtube:playlist'
4161 'note': 'issue #673',
4162 'url': 'PLBB231211A4F62143',
4164 'title': '[OLD]Team Fortress 2 (Class-based LP)',
4165 'id': 'PLBB231211A4F62143',
4166 'uploader': 'Wickydoo',
4167 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
4169 'playlist_mincount': 29,
4171 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4173 'title': 'YDL_safe_search',
4174 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
4176 'playlist_count': 2,
4177 'skip': 'This playlist is private',
4180 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4181 'playlist_count': 4,
4184 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
4185 'uploader': 'milan',
4186 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
4189 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4190 'playlist_mincount': 982,
4192 'title': '2018 Chinese New Singles (11/6 updated)',
4193 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
4195 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
4198 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
4199 'only_matching': True,
4201 # music album playlist
4202 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
4203 'only_matching': True,
4207 def suitable(cls, url):
4208 if YoutubeTabIE.suitable(url):
4210 # Hack for lazy extractors until more generic solution is implemented
4212 from .youtube import parse_qs
4214 if qs.get('v', [None])[0]:
4216 return super(YoutubePlaylistIE, cls).suitable(url)
4218 def _real_extract(self, url):
4219 playlist_id = self._match_id(url)
4220 is_music_url = YoutubeBaseInfoExtractor.is_music_url(url)
4221 url = update_url_query(
4222 'https://www.youtube.com/playlist',
4223 parse_qs(url) or {'list': playlist_id})
4225 url = smuggle_url(url, {'is_music_url': True})
4226 return self.url_result(url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4229 class YoutubeYtBeIE(InfoExtractor):
4230 IE_DESC = 'youtu.be'
4231 _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}
4233 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
4235 'id': 'yeWKywCrFtk',
4237 'title': 'Small Scale Baler and Braiding Rugs',
4238 'uploader': 'Backus-Page House Museum',
4239 'uploader_id': 'backuspagemuseum',
4240 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
4241 'upload_date': '20161008',
4242 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
4243 'categories': ['Nonprofits & Activism'],
4246 'dislike_count': int,
4250 'skip_download': True,
4253 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
4254 'only_matching': True,
4257 def _real_extract(self, url):
4258 mobj = re.match(self._VALID_URL, url)
4259 video_id = mobj.group('id')
4260 playlist_id = mobj.group('playlist_id')
4261 return self.url_result(
4262 update_url_query('https://www.youtube.com/watch', {
4264 'list': playlist_id,
4265 'feature': 'youtu.be',
4266 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
4269 class YoutubeYtUserIE(InfoExtractor):
4270 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
4271 _VALID_URL = r'ytuser:(?P<id>.+)'
4273 'url': 'ytuser:phihag',
4274 'only_matching': True,
4277 def _real_extract(self, url):
4278 user_id = self._match_id(url)
4279 return self.url_result(
4280 'https://www.youtube.com/user/%s' % user_id,
4281 ie=YoutubeTabIE.ie_key(), video_id=user_id)
4284 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
4285 IE_NAME = 'youtube:favorites'
4286 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
4287 _VALID_URL = r':ytfav(?:ou?rite)?s?'
4288 _LOGIN_REQUIRED = True
4291 'only_matching': True,
4293 'url': ':ytfavorites',
4294 'only_matching': True,
4297 def _real_extract(self, url):
4298 return self.url_result(
4299 'https://www.youtube.com/playlist?list=LL',
4300 ie=YoutubeTabIE.ie_key())
4303 class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
4304 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
4305 # there doesn't appear to be a real limit, for example if you search for
4306 # 'python' you get more than 8.000.000 results
4307 _MAX_RESULTS = float('inf')
4308 IE_NAME = 'youtube:search'
4309 _SEARCH_KEY = 'ytsearch'
4310 _SEARCH_PARAMS = None
4313 def _entries(self, query, n):
4314 data = {'query': query}
4315 if self._SEARCH_PARAMS:
4316 data['params'] = self._SEARCH_PARAMS
4319 for page_num in itertools.count(1):
4320 data.update(continuation)
4321 search = self._extract_response(
4322 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
4323 check_get_keys=('contents', 'onResponseReceivedCommands')
4327 slr_contents = try_get(
4329 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
4330 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
4332 if not slr_contents:
4335 # Youtube sometimes adds promoted content to searches,
4336 # changing the index location of videos and token.
4337 # So we search through all entries till we find them.
4339 for slr_content in slr_contents:
4340 if not continuation:
4341 continuation = self._extract_continuation({'contents': [slr_content]})
4343 isr_contents = try_get(
4345 lambda x: x['itemSectionRenderer']['contents'],
4347 if not isr_contents:
4349 for content in isr_contents:
4350 if not isinstance(content, dict):
4352 video = content.get('videoRenderer')
4353 if not isinstance(video, dict):
4355 video_id = video.get('videoId')
4359 yield self._extract_video(video)
4364 if not continuation:
4367 def _get_n_results(self, query, n):
4368 """Get a specified number of results for a query"""
4369 return self.playlist_result(self._entries(query, n), query)
4372 class YoutubeSearchDateIE(YoutubeSearchIE):
4373 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
4374 _SEARCH_KEY = 'ytsearchdate'
4375 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
4376 _SEARCH_PARAMS = 'CAI%3D'
4379 class YoutubeSearchURLIE(YoutubeSearchIE):
4380 IE_DESC = 'YouTube.com search URLs'
4381 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
4382 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
4383 # _MAX_RESULTS = 100
4385 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
4386 'playlist_mincount': 5,
4388 'title': 'youtube-dl test video',
4391 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
4392 'only_matching': True,
4396 def _make_valid_url(cls):
4397 return cls._VALID_URL
4399 def _real_extract(self, url):
4400 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
4401 query = (qs.get('search_query') or qs.get('q'))[0]
4402 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
4403 return self._get_n_results(query, self._MAX_RESULTS)
4406 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
4408 Base class for feed extractors
4409 Subclasses must define the _FEED_NAME property.
4411 _LOGIN_REQUIRED = True
4416 return 'youtube:%s' % self._FEED_NAME
4418 def _real_extract(self, url):
4419 return self.url_result(
4420 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
4421 ie=YoutubeTabIE.ie_key())
4424 class YoutubeWatchLaterIE(InfoExtractor):
4425 IE_NAME = 'youtube:watchlater'
4426 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
4427 _VALID_URL = r':ytwatchlater'
4429 'url': ':ytwatchlater',
4430 'only_matching': True,
4433 def _real_extract(self, url):
4434 return self.url_result(
4435 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
4438 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
4439 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
4440 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
4441 _FEED_NAME = 'recommended'
4442 _LOGIN_REQUIRED = False
4445 'only_matching': True,
4447 'url': ':ytrecommended',
4448 'only_matching': True,
4450 'url': 'https://youtube.com',
4451 'only_matching': True,
4455 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
4456 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
4457 _VALID_URL = r':ytsub(?:scription)?s?'
4458 _FEED_NAME = 'subscriptions'
4461 'only_matching': True,
4463 'url': ':ytsubscriptions',
4464 'only_matching': True,
4468 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
4469 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
4470 _VALID_URL = r':ythis(?:tory)?'
4471 _FEED_NAME = 'history'
4473 'url': ':ythistory',
4474 'only_matching': True,
4478 class YoutubeTruncatedURLIE(InfoExtractor):
4479 IE_NAME = 'youtube:truncated_url'
4480 IE_DESC = False # Do not list
4481 _VALID_URL = r'''(?x
)
4483 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
4486 annotation_id
=annotation_
[^
&]+|
4492 attribution_link
\?a
=[^
&]+
4498 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
4499 'only_matching': True,
4501 'url': 'https://www.youtube.com/watch?',
4502 'only_matching': True,
4504 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
4505 'only_matching': True,
4507 'url': 'https://www.youtube.com/watch?feature=foo',
4508 'only_matching': True,
4510 'url': 'https://www.youtube.com/watch?hl=en-GB',
4511 'only_matching': True,
4513 'url': 'https://www.youtube.com/watch?t=2372',
4514 'only_matching': True,
4517 def _real_extract(self, url):
4518 raise ExtractorError(
4519 'Did you forget to quote the URL? Remember that & is a meta '
4520 'character in most shells, so you want to put the URL in quotes, '
4522 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
4523 ' or simply youtube-dl BaW_jenozKc .',
4527 class YoutubeTruncatedIDIE(InfoExtractor):
4528 IE_NAME = 'youtube:truncated_id'
4529 IE_DESC = False # Do not list
4530 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
4533 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
4534 'only_matching': True,
4537 def _real_extract(self, url):
4538 video_id = self._match_id(url)
4539 raise ExtractorError(
4540 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),