3 from __future__
import unicode_literals
15 from .common
import InfoExtractor
, SearchInfoExtractor
16 from ..compat
import (
21 compat_urllib_parse_unquote_plus
,
22 compat_urllib_parse_urlencode
,
23 compat_urllib_parse_urlparse
,
26 from ..jsinterp
import JSInterpreter
57 return compat_urlparse
.parse_qs(compat_urlparse
.urlparse(url
).query
)
60 class YoutubeBaseInfoExtractor(InfoExtractor
):
61 """Provide base functions for Youtube extractors"""
62 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
63 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
65 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
66 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
67 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
70 r
'channel|c|user|playlist|watch|w|v|embed|e|watch_popup|'
71 r
'movies|results|shared|hashtag|trending|feed|feeds|oembed|'
72 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout')
74 _NETRC_MACHINE
= 'youtube'
75 # If True it will raise an error if no login info is provided
76 _LOGIN_REQUIRED
= False
78 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
82 Attempt to log in to YouTube.
83 True is returned if successful or skipped.
84 False is returned if login failed.
86 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
88 username
, password
= self
._get
_login
_info
()
89 # No authentication to be performed
91 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
92 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
93 # if self._downloader.params.get('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
94 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
97 login_page
= self
._download
_webpage
(
98 self
._LOGIN
_URL
, None,
99 note
='Downloading login page',
100 errnote
='unable to fetch login page', fatal
=False)
101 if login_page
is False:
104 login_form
= self
._hidden
_inputs
(login_page
)
106 def req(url
, f_req
, note
, errnote
):
107 data
= login_form
.copy()
110 'checkConnection': 'youtube',
111 'checkedDomains': 'youtube',
113 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
114 'f.req': json
.dumps(f_req
),
115 'flowName': 'GlifWebSignIn',
116 'flowEntry': 'ServiceLogin',
117 # TODO: reverse actual botguard identifier generation algo
118 'bgRequest': '["identifier",""]',
120 return self
._download
_json
(
121 url
, None, note
=note
, errnote
=errnote
,
122 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
124 data
=urlencode_postdata(data
), headers
={
125 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
126 'Google-Accounts-XSRF': 1,
130 self
.report_warning(message
)
134 None, [], None, 'US', None, None, 2, False, True,
138 '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',
140 1, [None, None, []], None, None, None, True
145 lookup_results
= req(
146 self
._LOOKUP
_URL
, lookup_req
,
147 'Looking up account info', 'Unable to look up account info')
149 if lookup_results
is False:
152 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
154 warn('Unable to extract user hash')
159 None, 1, None, [1, None, None, None, [password
, None, True]],
161 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],
162 1, [None, None, []], None, None, None, True
165 challenge_results
= req(
166 self
._CHALLENGE
_URL
, challenge_req
,
167 'Logging in', 'Unable to log in')
169 if challenge_results
is False:
172 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
174 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
176 'Unable to login: %s' % 'Invalid password'
177 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
180 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
182 warn('Unable to extract result entry')
185 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
187 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
188 if challenge_str
== 'TWO_STEP_VERIFICATION':
189 # SEND_SUCCESS - TFA code has been successfully sent to phone
190 # QUOTA_EXCEEDED - reached the limit of TFA codes
191 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
192 if status
== 'QUOTA_EXCEEDED':
193 warn('Exceeded the limit of TFA codes, try later')
196 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
198 warn('Unable to extract TL')
201 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
205 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
206 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
209 tfa_code
= remove_start(tfa_code
, 'G-')
212 user_hash
, None, 2, None,
214 9, None, None, None, None, None, None, None,
215 [None, tfa_code
, True, 2]
219 self
._TFA
_URL
.format(tl
), tfa_req
,
220 'Submitting TFA code', 'Unable to submit TFA code')
222 if tfa_results
is False:
225 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
227 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
229 'Unable to finish TFA: %s' % 'Invalid TFA code'
230 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
233 check_cookie_url
= try_get(
234 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
237 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
238 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
239 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
241 challenge
= CHALLENGES
.get(
243 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
244 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
247 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
249 if not check_cookie_url
:
250 warn('Unable to extract CheckCookie URL')
253 check_cookie_results
= self
._download
_webpage
(
254 check_cookie_url
, None, 'Checking cookie', fatal
=False)
256 if check_cookie_results
is False:
259 if 'https://myaccount.google.com/' not in check_cookie_results
:
260 warn('Unable to log in')
265 def _initialize_consent(self
):
266 cookies
= self
._get
_cookies
('https://www.youtube.com/')
267 if cookies
.get('__Secure-3PSID'):
270 consent
= cookies
.get('CONSENT')
272 if 'YES' in consent
.value
:
274 consent_id
= self
._search
_regex
(
275 r
'PENDING\+(\d+)', consent
.value
, 'consent', default
=None)
277 consent_id
= random
.randint(100, 999)
278 self
._set
_cookie
('.youtube.com', 'CONSENT', 'YES+cb.20210328-17-p0.en+FX+%s' % consent_id
)
280 def _real_initialize(self
):
281 self
._initialize
_consent
()
282 if self
._downloader
is None:
284 if not self
._login
():
287 _YT_WEB_CLIENT_VERSION
= '2.20210407.08.00'
288 _YT_INNERTUBE_API_KEY
= 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'
289 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
290 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
291 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
293 def _generate_sapisidhash_header(self):
294 sapisid_cookie = self._get_cookies('https://www.youtube.com').get('SAPISID')
295 if sapisid_cookie is None:
297 time_now = round(time.time())
298 sapisidhash = hashlib.sha1((str(time_now) + " " + sapisid_cookie.value + " " + "https
://www
.youtube
.com
").encode("utf
-8")).hexdigest()
299 return "SAPISIDHASH
%s_%s" % (time_now, sapisidhash)
301 def _call_api(self, ep, query, video_id, fatal=True, headers=None,
302 note='Downloading API JSON', errnote='Unable to download API page',
303 context=None, api_key=None):
305 data = {'context': context} if context else {'context': self._extract_context()}
307 real_headers = self._generate_api_headers()
308 real_headers.update({'content-type': 'application/json'})
310 real_headers.update(headers)
311 return self._download_json(
312 'https://www.youtube.com/youtubei/v1/%s' % ep,
313 video_id=video_id, fatal=fatal, note=note, errnote=errnote,
314 data=json.dumps(data).encode('utf8'), headers=real_headers,
315 query={'key': api_key or self._extract_api_key()})
317 def _extract_api_key(self, ytcfg=None):
318 return try_get(ytcfg, lambda x: x['INNERTUBE_API_KEY'], compat_str) or self._YT_INNERTUBE_API_KEY
320 def _extract_yt_initial_data(self, video_id, webpage):
321 return self._parse_json(
323 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
324 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
327 def _extract_identity_token(self, webpage, item_id):
328 ytcfg = self._extract_ytcfg(item_id, webpage)
330 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
333 return self._search_regex(
334 r'\bID_TOKEN["\']\s
*:\s
*["\'](.+?)["\']', webpage,
335 'identity token
', default=None)
338 def _extract_account_syncid(data):
340 Extract syncId required to download private playlists of secondary channels
341 @param data Either response or ytcfg
344 data, (lambda x: x['responseContext
']['mainAppWebResponseContext
']['datasyncId
'],
345 lambda x: x['DATASYNC_ID
']), compat_str) or '').split("||")
346 if len(sync_ids) >= 2 and sync_ids[1]:
347 # datasyncid is of the form "channel_syncid||user_syncid" for secondary channel
348 # and just "user_syncid||" for primary channel. We only want the channel_syncid
350 # ytcfg includes channel_syncid if on secondary channel
351 return data.get('DELEGATED_SESSION_ID
')
353 def _extract_ytcfg(self, video_id, webpage):
356 return self._parse_json(
358 r'ytcfg\
.set\s
*\
(\s
*({.+?}
)\s
*\
)\s
*;', webpage, 'ytcfg
',
359 default='{}'), video_id, fatal=False) or {}
361 def __extract_client_version(self
, ytcfg
):
362 return try_get(ytcfg
, lambda x
: x
['INNERTUBE_CLIENT_VERSION'], compat_str
) or self
._YT
_WEB
_CLIENT
_VERSION
364 def _extract_context(self
, ytcfg
=None):
365 context
= try_get(ytcfg
, lambda x
: x
['INNERTUBE_CONTEXT'], dict)
369 # Recreate the client context (required)
370 client_version
= self
.__extract
_client
_version
(ytcfg
)
371 client_name
= try_get(ytcfg
, lambda x
: x
['INNERTUBE_CLIENT_NAME'], compat_str
) or 'WEB'
374 'clientName': client_name
,
375 'clientVersion': client_version
,
378 visitor_data
= try_get(ytcfg
, lambda x
: x
['VISITOR_DATA'], compat_str
)
380 context
['client']['visitorData'] = visitor_data
383 def _generate_api_headers(self
, ytcfg
=None, identity_token
=None, account_syncid
=None, visitor_data
=None):
385 'X-YouTube-Client-Name': '1',
386 'X-YouTube-Client-Version': self
.__extract
_client
_version
(ytcfg
),
389 headers
['x-youtube-identity-token'] = identity_token
391 headers
['X-Goog-PageId'] = account_syncid
392 headers
['X-Goog-AuthUser'] = 0
394 headers
['x-goog-visitor-id'] = visitor_data
395 auth
= self
._generate
_sapisidhash
_header
()
397 headers
['Authorization'] = auth
398 headers
['X-Origin'] = 'https://www.youtube.com'
401 def _extract_video(self
, renderer
):
402 video_id
= renderer
.get('videoId')
405 (lambda x
: x
['title']['runs'][0]['text'],
406 lambda x
: x
['title']['simpleText']), compat_str
)
407 description
= try_get(
408 renderer
, lambda x
: x
['descriptionSnippet']['runs'][0]['text'],
410 duration
= parse_duration(try_get(
411 renderer
, lambda x
: x
['lengthText']['simpleText'], compat_str
))
412 view_count_text
= try_get(
413 renderer
, lambda x
: x
['viewCountText']['simpleText'], compat_str
) or ''
414 view_count
= str_to_int(self
._search
_regex
(
415 r
'^([\d,]+)', re
.sub(r
'\s', '', view_count_text
),
416 'view count', default
=None))
419 (lambda x
: x
['ownerText']['runs'][0]['text'],
420 lambda x
: x
['shortBylineText']['runs'][0]['text']), compat_str
)
423 'ie_key': YoutubeIE
.ie_key(),
427 'description': description
,
428 'duration': duration
,
429 'view_count': view_count
,
430 'uploader': uploader
,
434 class YoutubeIE(YoutubeBaseInfoExtractor
):
435 IE_DESC
= 'YouTube.com'
437 # invidious-redirect websites
438 r
'(?:www\.)?redirect\.invidious\.io',
439 r
'(?:(?:www|dev)\.)?invidio\.us',
440 # Invidious instances taken from https://github.com/iv-org/documentation/blob/master/Invidious-Instances.md
441 r
'(?:www\.)?invidious\.pussthecat\.org',
442 r
'(?:www\.)?invidious\.zee\.li',
443 r
'(?:(?:www|au)\.)?ytprivate\.com',
444 r
'(?:www\.)?invidious\.namazso\.eu',
445 r
'(?:www\.)?invidious\.ethibox\.fr',
446 r
'(?:www\.)?w6ijuptxiku4xpnnaetxvnkc5vqcdu7mgns2u77qefoixi63vbvnpnqd\.onion',
447 r
'(?:www\.)?kbjggqkzv65ivcqj6bumvp337z6264huv5kpkwuv6gu5yjiskvan7fad\.onion',
448 r
'(?:www\.)?invidious\.3o7z6yfxhbw7n3za4rss6l434kmv55cgw2vuziwuigpwegswvwzqipyd\.onion',
449 r
'(?:www\.)?grwp24hodrefzvjjuccrkw3mjq4tzhaaq32amf33dzpmuxe7ilepcmad\.onion',
450 # youtube-dl invidious instances list
451 r
'(?:(?:www|no)\.)?invidiou\.sh',
452 r
'(?:(?:www|fi)\.)?invidious\.snopyta\.org',
453 r
'(?:www\.)?invidious\.kabi\.tk',
454 r
'(?:www\.)?invidious\.mastodon\.host',
455 r
'(?:www\.)?invidious\.zapashcanon\.fr',
456 r
'(?:www\.)?invidious\.kavin\.rocks',
457 r
'(?:www\.)?invidious\.tinfoil-hat\.net',
458 r
'(?:www\.)?invidious\.himiko\.cloud',
459 r
'(?:www\.)?invidious\.reallyancient\.tech',
460 r
'(?:www\.)?invidious\.tube',
461 r
'(?:www\.)?invidiou\.site',
462 r
'(?:www\.)?invidious\.site',
463 r
'(?:www\.)?invidious\.xyz',
464 r
'(?:www\.)?invidious\.nixnet\.xyz',
465 r
'(?:www\.)?invidious\.048596\.xyz',
466 r
'(?:www\.)?invidious\.drycat\.fr',
467 r
'(?:www\.)?inv\.skyn3t\.in',
468 r
'(?:www\.)?tube\.poal\.co',
469 r
'(?:www\.)?tube\.connect\.cafe',
470 r
'(?:www\.)?vid\.wxzm\.sx',
471 r
'(?:www\.)?vid\.mint\.lgbt',
472 r
'(?:www\.)?vid\.puffyan\.us',
473 r
'(?:www\.)?yewtu\.be',
474 r
'(?:www\.)?yt\.elukerio\.org',
475 r
'(?:www\.)?yt\.lelux\.fi',
476 r
'(?:www\.)?invidious\.ggc-project\.de',
477 r
'(?:www\.)?yt\.maisputain\.ovh',
478 r
'(?:www\.)?ytprivate\.com',
479 r
'(?:www\.)?invidious\.13ad\.de',
480 r
'(?:www\.)?invidious\.toot\.koeln',
481 r
'(?:www\.)?invidious\.fdn\.fr',
482 r
'(?:www\.)?watch\.nettohikari\.com',
483 r
'(?:www\.)?kgg2m7yk5aybusll\.onion',
484 r
'(?:www\.)?qklhadlycap4cnod\.onion',
485 r
'(?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion',
486 r
'(?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion',
487 r
'(?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion',
488 r
'(?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion',
489 r
'(?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p',
490 r
'(?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion',
492 _VALID_URL
= r
"""(?x)^
494 (?:https?://|//) # http(s):// or protocol-independent URL
495 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com|
496 (?:www\.)?deturl\.com/www\.youtube\.com|
497 (?:www\.)?pwnyoutube\.com|
498 (?:www\.)?hooktube\.com|
499 (?:www\.)?yourepeat\.com|
502 youtube\.googleapis\.com)/ # the various hostnames, with wildcard subdomains
503 (?:.*?\#/)? # handle anchor (#/) redirect urls
504 (?: # the various things that can precede the ID:
505 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
506 |(?: # or the v= param in all its forms
507 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
508 (?:\?|\#!?) # the params delimiter ? or # or #!
509 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
514 youtu\.be| # just youtu.be/xxxx
515 vid\.plus| # or vid.plus/xxxx
516 zwearz\.com/watch| # or zwearz.com/watch/xxxx
519 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
521 )? # all until now is optional -> you can pass the naked ID
522 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
523 (?(1).+)? # if we found the ID, everything can follow
525 'invidious': '|'.join(_INVIDIOUS_SITES
),
528 r
'/s/player/(?P<id>[a-zA-Z0-9_-]{8,})/player',
529 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$',
530 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
533 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
534 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
535 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
536 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
537 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
538 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
539 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
540 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
541 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
542 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
543 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
544 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
545 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
546 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
547 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
548 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
549 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
550 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
554 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
555 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
556 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
557 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
558 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
559 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
560 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
562 # Apple HTTP Live Streaming
563 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
564 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
565 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
566 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
567 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
568 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
569 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
570 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
573 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
574 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
575 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
576 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
577 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
578 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
579 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
580 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
581 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
582 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
583 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
584 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
587 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
588 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
589 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
590 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
591 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
592 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
593 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
596 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
597 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
598 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
599 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
600 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
601 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
602 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
603 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
604 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
605 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
606 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
607 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
608 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
609 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
610 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
611 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
612 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
613 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
614 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
615 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
616 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
617 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
620 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
621 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
623 # Dash webm audio with opus inside
624 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
625 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
626 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
629 '_rtmp': {'protocol': 'rtmp'}
,
631 # av01 video only formats sometimes served with "unknown" codecs
632 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
633 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
634 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
635 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
637 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
644 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
648 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
649 'uploader': 'Philipp Hagemeister',
650 'uploader_id': 'phihag',
651 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
652 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
653 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
654 'upload_date': '20121002',
655 '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 .',
656 'categories': ['Science & Technology'],
657 'tags': ['youtube-dl'],
661 'dislike_count': int,
667 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
668 'note': 'Embed-only video (#1746)',
672 'upload_date': '20120608',
673 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
674 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
675 'uploader': 'SET India',
676 'uploader_id': 'setindia',
677 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
680 'skip': 'Private video',
683 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
684 'note': 'Use the first video ID in the URL',
688 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
689 'uploader': 'Philipp Hagemeister',
690 'uploader_id': 'phihag',
691 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
692 'upload_date': '20121002',
693 '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 .',
694 'categories': ['Science & Technology'],
695 'tags': ['youtube-dl'],
699 'dislike_count': int,
702 'skip_download': True,
706 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
707 'note': '256k DASH audio (format 141) via DASH manifest',
711 'upload_date': '20121002',
712 'uploader_id': '8KVIDEO',
713 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
715 'uploader': '8KVIDEO',
716 'title': 'UHDTV TEST 8K VIDEO.mp4'
719 'youtube_include_dash_manifest': True,
722 'skip': 'format 141 not served anymore',
724 # DASH manifest with encrypted signature
726 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
730 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
731 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
733 'uploader': 'AfrojackVEVO',
734 'uploader_id': 'AfrojackVEVO',
735 'upload_date': '20131011',
739 'youtube_include_dash_manifest': True,
740 'format': '141/bestaudio[ext=m4a]',
745 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
750 'upload_date': '20100909',
751 'uploader': 'Amazing Atheist',
752 'uploader_id': 'TheAmazingAtheist',
753 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
754 'title': 'Burning Everyone\'s Koran',
755 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms \r\n\r\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
758 # Normal age-gate video (embed allowed)
760 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
764 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
765 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
767 'uploader': 'The Witcher',
768 'uploader_id': 'WitcherGame',
769 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
770 'upload_date': '20140605',
774 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
775 # YouTube Red ad is not captured for creator
777 'url': '__2ABJjxzNo',
782 'upload_date': '20100430',
783 'uploader_id': 'deadmau5',
784 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
785 'creator': 'deadmau5',
786 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
787 'uploader': 'deadmau5',
788 'title': 'Deadmau5 - Some Chords (HD)',
789 'alt_title': 'Some Chords',
791 'expected_warnings': [
792 'DASH manifest missing',
795 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
797 'url': 'lqQg6PlCWgI',
802 'upload_date': '20150827',
803 'uploader_id': 'olympic',
804 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
805 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
806 'uploader': 'Olympic',
807 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
810 'skip_download': 'requires avconv',
815 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
819 'stretched_ratio': 16 / 9.,
821 'upload_date': '20110310',
822 'uploader_id': 'AllenMeow',
823 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
824 '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',
826 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
829 # url_encoded_fmt_stream_map is empty string
831 'url': 'qEJwOuvDf7I',
835 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
837 'upload_date': '20150404',
838 'uploader_id': 'spbelect',
839 'uploader': 'Наблюдатели Петербурга',
842 'skip_download': 'requires avconv',
844 'skip': 'This live event has ended.',
846 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
848 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
852 'title': 'md5:7b81415841e02ecd4313668cde88737a',
853 'description': 'md5:116377fd2963b81ec4ce64b542173306',
855 'upload_date': '20150625',
856 'uploader_id': 'dorappi2000',
857 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
858 'uploader': 'dorappi2000',
859 'formats': 'mincount:31',
861 'skip': 'not actual anymore',
863 # DASH manifest with segment_list
865 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
866 'md5': '8ce563a1d667b599d21064e982ab9e31',
870 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
871 'uploader': 'Airtek',
872 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
873 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
874 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
877 'youtube_include_dash_manifest': True,
878 'format': '135', # bestvideo
880 'skip': 'This live event has ended.',
883 # Multifeed videos (multiple cameras), URL is for Main Camera
884 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
887 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
888 'description': 'md5:e03b909557865076822aa169218d6a5d',
894 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
895 'description': 'md5:e03b909557865076822aa169218d6a5d',
897 'upload_date': '20161111',
898 'uploader': 'Team PGP',
899 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
900 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
906 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
907 'description': 'md5:e03b909557865076822aa169218d6a5d',
909 'upload_date': '20161111',
910 'uploader': 'Team PGP',
911 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
912 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
918 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
919 'description': 'md5:e03b909557865076822aa169218d6a5d',
921 'upload_date': '20161111',
922 'uploader': 'Team PGP',
923 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
924 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
930 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
931 'description': 'md5:e03b909557865076822aa169218d6a5d',
933 'upload_date': '20161111',
934 'uploader': 'Team PGP',
935 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
936 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
940 'skip_download': True,
944 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
945 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
948 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
951 'skip': 'Not multifeed anymore',
954 'url': 'https://vid.plus/FlRa-iH7PGw',
955 'only_matching': True,
958 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
959 'only_matching': True,
962 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
963 # Also tests cut-off URL expansion in video description (see
964 # https://github.com/ytdl-org/youtube-dl/issues/1892,
965 # https://github.com/ytdl-org/youtube-dl/issues/8164)
966 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
970 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
971 'alt_title': 'Dark Walk - Position Music',
972 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
974 'upload_date': '20151119',
975 'uploader_id': 'IronSoulElf',
976 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
977 'uploader': 'IronSoulElf',
978 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
979 'track': 'Dark Walk - Position Music',
980 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
981 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
984 'skip_download': True,
988 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
989 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
990 'only_matching': True,
993 # Video with yt:stretch=17:0
994 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
998 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
999 'description': 'md5:ee18a25c350637c8faff806845bddee9',
1000 'upload_date': '20151107',
1001 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
1002 'uploader': 'CH GAMER DROID',
1005 'skip_download': True,
1007 'skip': 'This video does not exist.',
1010 # Video with incomplete 'yt:stretch=16:'
1011 'url': 'https://www.youtube.com/watch?v=FRhJzUSJbGI',
1012 'only_matching': True,
1015 # Video licensed under Creative Commons
1016 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1018 'id': 'M4gD1WSo5mA',
1020 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1021 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1023 'upload_date': '20150127',
1024 'uploader_id': 'BerkmanCenter',
1025 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1026 'uploader': 'The Berkman Klein Center for Internet & Society',
1027 'license': 'Creative Commons Attribution license (reuse allowed)',
1030 'skip_download': True,
1034 # Channel-like uploader_url
1035 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1037 'id': 'eQcmzGIKrzg',
1039 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1040 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
1042 'upload_date': '20151119',
1043 'uploader': 'Bernie Sanders',
1044 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1045 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1046 'license': 'Creative Commons Attribution license (reuse allowed)',
1049 'skip_download': True,
1053 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1054 'only_matching': True,
1057 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1058 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1059 'only_matching': True,
1062 # Rental video preview
1063 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1065 'id': 'uGpuVWrhIzE',
1067 'title': 'Piku - Trailer',
1068 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1069 'upload_date': '20150811',
1070 'uploader': 'FlixMatrix',
1071 'uploader_id': 'FlixMatrixKaravan',
1072 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1073 'license': 'Standard YouTube License',
1076 'skip_download': True,
1078 'skip': 'This video is not available.',
1081 # YouTube Red video with episode data
1082 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1084 'id': 'iqKdEhx-dD4',
1086 'title': 'Isolation - Mind Field (Ep 1)',
1087 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
1089 'upload_date': '20170118',
1090 'uploader': 'Vsauce',
1091 'uploader_id': 'Vsauce',
1092 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1093 'series': 'Mind Field',
1095 'episode_number': 1,
1098 'skip_download': True,
1100 'expected_warnings': [
1101 'Skipping DASH manifest',
1105 # The following content has been identified by the YouTube community
1106 # as inappropriate or offensive to some audiences.
1107 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1109 'id': '6SJNVb0GnPI',
1111 'title': 'Race Differences in Intelligence',
1112 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1114 'upload_date': '20140124',
1115 'uploader': 'New Century Foundation',
1116 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1117 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1120 'skip_download': True,
1122 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1126 'url': '1t24XAntNCY',
1127 'only_matching': True,
1130 # geo restricted to JP
1131 'url': 'sJL6WA-aGkQ',
1132 'only_matching': True,
1135 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1136 'only_matching': True,
1139 'url': 'https://redirect.invidious.io/watch?v=BaW_jenozKc',
1140 'only_matching': True,
1143 # from https://nitter.pussthecat.org/YouTube/status/1360363141947944964#m
1144 'url': 'https://redirect.invidious.io/Yh0AhrY9GjA',
1145 'only_matching': True,
1149 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1150 'only_matching': True,
1153 # Video with unsupported adaptive stream type formats
1154 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1156 'id': 'Z4Vy8R84T1U',
1158 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1159 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1161 'upload_date': '20130923',
1162 'uploader': 'Amelia Putri Harwita',
1163 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1164 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1165 'formats': 'maxcount:10',
1168 'skip_download': True,
1169 'youtube_include_dash_manifest': False,
1171 'skip': 'not actual anymore',
1174 # Youtube Music Auto-generated description
1175 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1177 'id': 'MgNrAu2pzNs',
1179 'title': 'Voyeur Girl',
1180 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1181 'upload_date': '20190312',
1182 'uploader': 'Stephen - Topic',
1183 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1184 'artist': 'Stephen',
1185 'track': 'Voyeur Girl',
1186 'album': 'it\'s too much love to know my dear',
1187 'release_date': '20190313',
1188 'release_year': 2019,
1191 'skip_download': True,
1195 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1196 'only_matching': True,
1199 # invalid -> valid video id redirection
1200 'url': 'DJztXj2GPfl',
1202 'id': 'DJztXj2GPfk',
1204 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1205 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1206 'upload_date': '20090125',
1207 'uploader': 'Prochorowka',
1208 'uploader_id': 'Prochorowka',
1209 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1210 'artist': 'Panjabi MC',
1211 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1212 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1215 'skip_download': True,
1217 'skip': 'Video unavailable',
1220 # empty description results in an empty string
1221 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1223 'id': 'x41yOUIvK2k',
1225 'title': 'IMG 3456',
1227 'upload_date': '20170613',
1228 'uploader_id': 'ElevageOrVert',
1229 'uploader': 'ElevageOrVert',
1232 'skip_download': True,
1236 # with '};' inside yt initial data (see [1])
1237 # see [2] for an example with '};' inside ytInitialPlayerResponse
1238 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1239 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1240 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1242 'id': 'CHqg6qOn4no',
1244 'title': 'Part 77 Sort a list of simple types in c#',
1245 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1246 'upload_date': '20130831',
1247 'uploader_id': 'kudvenkat',
1248 'uploader': 'kudvenkat',
1251 'skip_download': True,
1255 # another example of '};' in ytInitialData
1256 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1257 'only_matching': True,
1260 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1261 'only_matching': True,
1264 # https://github.com/ytdl-org/youtube-dl/pull/28094
1265 'url': 'OtqTfy26tG0',
1267 'id': 'OtqTfy26tG0',
1269 'title': 'Burn Out',
1270 'description': 'md5:8d07b84dcbcbfb34bc12a56d968b6131',
1271 'upload_date': '20141120',
1272 'uploader': 'The Cinematic Orchestra - Topic',
1273 'uploader_id': 'UCIzsJBIyo8hhpFm1NK0uLgw',
1274 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCIzsJBIyo8hhpFm1NK0uLgw',
1275 'artist': 'The Cinematic Orchestra',
1276 'track': 'Burn Out',
1277 'album': 'Every Day',
1278 'release_data': None,
1279 'release_year': None,
1282 'skip_download': True,
1286 # controversial video, only works with bpctr when authenticated with cookies
1287 'url': 'https://www.youtube.com/watch?v=nGC3D_FkCmg',
1288 'only_matching': True,
1291 # restricted location, https://github.com/ytdl-org/youtube-dl/issues/28685
1292 'url': 'cBvYw8_A0vQ',
1294 'id': 'cBvYw8_A0vQ',
1296 'title': '4K Ueno Okachimachi Street Scenes 上野御徒町歩き',
1297 'description': 'md5:ea770e474b7cd6722b4c95b833c03630',
1298 'upload_date': '20201120',
1299 'uploader': 'Walk around Japan',
1300 'uploader_id': 'UC3o_t8PzBmXf5S9b7GLx1Mw',
1301 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UC3o_t8PzBmXf5S9b7GLx1Mw',
1304 'skip_download': True,
1307 # Has multiple audio streams
1308 'url': 'WaOKSUlf4TM',
1309 'only_matching': True
1312 # multiple subtitles with same lang_code
1313 'url': 'https://www.youtube.com/watch?v=wsQiKKfKxug',
1314 'only_matching': True,
1319 def suitable(cls
, url
):
1320 # Hack for lazy extractors until more generic solution is implemented
1322 from .youtube
import parse_qs
1324 if qs
.get('list', [None])[0]:
1326 return super(YoutubeIE
, cls
).suitable(url
)
1328 def __init__(self
, *args
, **kwargs
):
1329 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1330 self
._code
_cache
= {}
1331 self
._player
_cache
= {}
1333 def _signature_cache_id(self
, example_sig
):
1334 """ Return a string representation of a signature """
1335 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1338 def _extract_player_info(cls
, player_url
):
1339 for player_re
in cls
._PLAYER
_INFO
_RE
:
1340 id_m
= re
.search(player_re
, player_url
)
1344 raise ExtractorError('Cannot identify player %r' % player_url
)
1345 return id_m
.group('id')
1347 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1348 player_id
= self
._extract
_player
_info
(player_url
)
1350 # Read from filesystem cache
1351 func_id
= 'js_%s_%s' % (
1352 player_id
, self
._signature
_cache
_id
(example_sig
))
1353 assert os
.path
.basename(func_id
) == func_id
1355 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1356 if cache_spec
is not None:
1357 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1359 if player_id
not in self
._code
_cache
:
1360 self
._code
_cache
[player_id
] = self
._download
_webpage
(
1361 player_url
, video_id
,
1362 note
='Downloading player ' + player_id
,
1363 errnote
='Download of %s failed' % player_url
)
1364 code
= self
._code
_cache
[player_id
]
1365 res
= self
._parse
_sig
_js
(code
)
1367 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1368 cache_res
= res(test_string
)
1369 cache_spec
= [ord(c
) for c
in cache_res
]
1371 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1374 def _print_sig_code(self
, func
, example_sig
):
1375 def gen_sig_code(idxs
):
1376 def _genslice(start
, end
, step
):
1377 starts
= '' if start
== 0 else str(start
)
1378 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1379 steps
= '' if step
== 1 else (':%d' % step
)
1380 return 's[%s%s%s]' % (starts
, ends
, steps
)
1383 # Quelch pyflakes warnings - start will be set when step is set
1384 start
= '(Never used)'
1385 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1386 if step
is not None:
1387 if i
- prev
== step
:
1389 yield _genslice(start
, prev
, step
)
1392 if i
- prev
in [-1, 1]:
1397 yield 's[%d]' % prev
1401 yield _genslice(start
, i
, step
)
1403 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1404 cache_res
= func(test_string
)
1405 cache_spec
= [ord(c
) for c
in cache_res
]
1406 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1407 signature_id_tuple
= '(%s)' % (
1408 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1409 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1410 ' return %s\n') % (signature_id_tuple
, expr_code
)
1411 self
.to_screen('Extracted signature function:\n' + code
)
1413 def _parse_sig_js(self
, jscode
):
1414 funcname
= self
._search
_regex
(
1415 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1416 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1417 r
'\bm=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(h\.s\)\)',
1418 r
'\bc&&\(c=(?P<sig>[a-zA-Z0-9$]{2})\(decodeURIComponent\(c\)\)',
1419 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}\(a,\d+\)',
1420 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\(\s*""\s*\)',
1421 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1423 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1424 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1425 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1426 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1427 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1428 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1429 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1430 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1431 jscode, 'Initial JS player signature function name
', group='sig
')
1433 jsi = JSInterpreter(jscode)
1434 initial_function = jsi.extract_function(funcname)
1435 return lambda s: initial_function([s])
1437 def _decrypt_signature(self, s, video_id, player_url):
1438 """Turn the encrypted s field into a working signature"""
1440 if player_url is None:
1441 raise ExtractorError('Cannot decrypt signature without player_url
')
1443 if player_url.startswith('//'):
1444 player_url = 'https
:' + player_url
1445 elif not re.match(r'https?
://', player_url):
1446 player_url = compat_urlparse.urljoin(
1447 'https
://www
.youtube
.com
', player_url)
1449 player_id = (player_url, self._signature_cache_id(s))
1450 if player_id not in self._player_cache:
1451 func = self._extract_signature_function(
1452 video_id, player_url, s
1454 self._player_cache[player_id] = func
1455 func = self._player_cache[player_id]
1456 if self._downloader.params.get('youtube_print_sig_code
'):
1457 self._print_sig_code(func, s)
1459 except Exception as e:
1460 tb = traceback.format_exc()
1461 raise ExtractorError(
1462 'Signature extraction failed
: ' + tb, cause=e)
1464 def _mark_watched(self, video_id, player_response):
1465 playback_url = url_or_none(try_get(
1467 lambda x: x['playbackTracking
']['videostatsPlaybackUrl
']['baseUrl
']))
1468 if not playback_url:
1470 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1471 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1473 # cpn generation algorithm is reverse engineered from base.js.
1474 # In fact it works even with dummy cpn.
1475 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
1476 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1482 playback_url = compat_urlparse.urlunparse(
1483 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1485 self._download_webpage(
1486 playback_url, video_id, 'Marking watched
',
1487 'Unable to mark watched
', fatal=False)
1490 def _extract_urls(webpage):
1491 # Embedded YouTube player
1493 unescapeHTML(mobj.group('url
'))
1494 for mobj in re.finditer(r'''(?x)
1504 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1505 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1508 # lazyYT YouTube embed
1509 entries.extend(list(map(
1511 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
1513 # Wordpress "YouTube Video Importer
" plugin
1514 matches = re.findall(r'''(?x)<div[^>]+
1515 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
1516 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
1517 entries.extend(m[-1] for m in matches)
1522 def _extract_url(webpage):
1523 urls = YoutubeIE._extract_urls(webpage)
1524 return urls[0] if urls else None
1527 def extract_id(cls, url):
1528 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1530 raise ExtractorError('Invalid URL: %s' % url)
1531 video_id = mobj.group(2)
1534 def _extract_chapters_from_json(self, data, video_id, duration):
1535 chapters_list = try_get(
1537 lambda x: x['playerOverlays']
1538 ['playerOverlayRenderer']
1539 ['decoratedPlayerBarRenderer']
1540 ['decoratedPlayerBarRenderer']
1542 ['chapteredPlayerBarRenderer']
1545 if not chapters_list:
1548 def chapter_time(chapter):
1549 return float_or_none(
1552 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1556 for next_num, chapter in enumerate(chapters_list, start=1):
1557 start_time = chapter_time(chapter)
1558 if start_time is None:
1560 end_time = (chapter_time(chapters_list[next_num])
1561 if next_num < len(chapters_list) else duration)
1562 if end_time is None:
1565 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1568 'start_time': start_time,
1569 'end_time': end_time,
1574 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
1575 return self._parse_json(self._search_regex(
1576 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
1577 regex), webpage, name, default='{}'), video_id, fatal=False)
1580 def parse_time_text(time_text):
1582 Parse the comment time text
1583 time_text is in the format 'X units ago (edited)'
1585 time_text_split = time_text.split(' ')
1586 if len(time_text_split) >= 3:
1587 return datetime_from_str('now-%s%s' % (time_text_split[0], time_text_split[1]), precision='auto')
1590 def _join_text_entries(runs):
1593 if not isinstance(run, dict):
1595 sub_text = try_get(run, lambda x: x['text'], compat_str)
1603 def _extract_comment(self, comment_renderer, parent=None):
1604 comment_id = comment_renderer.get('commentId')
1607 comment_text_runs = try_get(comment_renderer, lambda x: x['contentText']['runs']) or []
1608 text = self._join_text_entries(comment_text_runs) or ''
1609 comment_time_text = try_get(comment_renderer, lambda x: x['publishedTimeText']['runs']) or []
1610 time_text = self._join_text_entries(comment_time_text)
1611 timestamp = calendar.timegm(self.parse_time_text(time_text).timetuple())
1612 author = try_get(comment_renderer, lambda x: x['authorText']['simpleText'], compat_str)
1613 author_id = try_get(comment_renderer,
1614 lambda x: x['authorEndpoint']['browseEndpoint']['browseId'], compat_str)
1615 votes = str_to_int(try_get(comment_renderer, (lambda x: x['voteCount']['simpleText'],
1616 lambda x: x['likeCount']), compat_str)) or 0
1617 author_thumbnail = try_get(comment_renderer,
1618 lambda x: x['authorThumbnail']['thumbnails'][-1]['url'], compat_str)
1620 author_is_uploader = try_get(comment_renderer, lambda x: x['authorIsChannelOwner'], bool)
1621 is_liked = try_get(comment_renderer, lambda x: x['isLiked'], bool)
1625 'timestamp': timestamp,
1626 'time_text': time_text,
1627 'like_count': votes,
1628 'is_favorited': is_liked,
1630 'author_id': author_id,
1631 'author_thumbnail': author_thumbnail,
1632 'author_is_uploader': author_is_uploader,
1633 'parent': parent or 'root'
1636 def _comment_entries(self, root_continuation_data, identity_token, account_syncid,
1637 ytcfg, session_token_list, parent=None, comment_counts=None):
1639 def extract_thread(parent_renderer):
1640 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
1642 comment_counts[2] = 0
1643 for content in contents:
1644 comment_thread_renderer = try_get(content, lambda x: x['commentThreadRenderer'])
1645 comment_renderer = try_get(
1646 comment_thread_renderer, (lambda x: x['comment']['commentRenderer'], dict)) or try_get(
1647 content, (lambda x: x['commentRenderer'], dict))
1649 if not comment_renderer:
1651 comment = self._extract_comment(comment_renderer, parent)
1654 comment_counts[0] += 1
1656 # Attempt to get the replies
1657 comment_replies_renderer = try_get(
1658 comment_thread_renderer, lambda x: x['replies']['commentRepliesRenderer'], dict)
1660 if comment_replies_renderer:
1661 comment_counts[2] += 1
1662 comment_entries_iter = self._comment_entries(
1663 comment_replies_renderer, identity_token, account_syncid, ytcfg,
1664 parent=comment.get('id'), session_token_list=session_token_list,
1665 comment_counts=comment_counts)
1667 for reply_comment in comment_entries_iter:
1670 if not comment_counts:
1671 # comment so far, est. total comments, current comment thread #
1672 comment_counts = [0, 0, 0]
1674 # TODO: Generalize the download code with TabIE
1675 context = self._extract_context(ytcfg)
1676 visitor_data = try_get(context, lambda x: x['client']['visitorData'], compat_str)
1677 continuation = YoutubeTabIE._extract_continuation(root_continuation_data) # TODO
1678 first_continuation = False
1680 first_continuation = True
1682 for page_num in itertools.count(0):
1683 if not continuation:
1685 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
1686 retries = self._downloader.params.get('extractor_retries', 3)
1690 while count < retries:
1693 self.report_warning('%s. Retrying ...' % last_error)
1696 'ctoken': continuation['ctoken'],
1701 query['action_get_comment_replies'] = 1
1703 query['action_get_comments'] = 1
1705 comment_prog_str = '(%d/%d)' % (comment_counts[0], comment_counts[1])
1707 if first_continuation:
1708 note_prefix = 'Downloading initial comment continuation page'
1710 note_prefix = ' Downloading comment reply thread %d %s' % (comment_counts[2], comment_prog_str)
1712 note_prefix = '%sDownloading comment%s page %d %s' % (
1713 ' ' if parent else '',
1714 ' replies' if parent else '',
1718 browse = self._download_json(
1719 'https://www.youtube.com/comment_service_ajax', None,
1720 '%s %s' % (note_prefix, '(retry #%d)' % count if count else ''),
1721 headers=headers, query=query,
1722 data=urlencode_postdata({
1723 'session_token': session_token_list[0]
1725 except ExtractorError as e:
1726 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503, 404, 413):
1727 if e.cause.code == 413:
1728 self.report_warning('Assumed end of comments (received HTTP Error 413)')
1730 # Downloading page may result in intermittent 5xx HTTP error
1731 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
1732 last_error = 'HTTP Error %s' % e.cause.code
1733 if e.cause.code == 404:
1734 last_error = last_error + ' (this API is probably deprecated)'
1739 session_token = try_get(browse, lambda x: x['xsrf_token'], compat_str)
1741 session_token_list[0] = session_token
1743 response = try_get(browse,
1744 (lambda x: x['response'],
1745 lambda x: x[1]['response'])) or {}
1747 if response.get('continuationContents'):
1750 # YouTube sometimes gives reload: now json if something went wrong (e.g. bad auth)
1751 if browse.get('reload'):
1752 raise ExtractorError('Invalid or missing params in continuation request', expected=False)
1754 # TODO: not tested, merged from old extractor
1755 err_msg = browse.get('externalErrorMessage')
1757 raise ExtractorError('YouTube said: %s' % err_msg, expected=False)
1759 # Youtube sometimes sends incomplete data
1760 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
1761 last_error = 'Incomplete data received'
1762 if count >= retries:
1763 raise ExtractorError(last_error)
1767 visitor_data = try_get(
1769 lambda x: x['responseContext']['webResponseContextExtensionData']['ytConfigData']['visitorData'],
1770 compat_str) or visitor_data
1772 known_continuation_renderers = {
1773 'itemSectionContinuation': extract_thread,
1774 'commentRepliesContinuation': extract_thread
1777 # extract next root continuation from the results
1778 continuation_contents = try_get(
1779 response, lambda x: x['continuationContents'], dict) or {}
1781 for key, value in continuation_contents.items():
1782 if key not in known_continuation_renderers:
1784 continuation_renderer = value
1786 if first_continuation:
1787 first_continuation = False
1788 expected_comment_count = try_get(
1789 continuation_renderer,
1790 (lambda x: x['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'],
1791 lambda x: x['header']['commentsHeaderRenderer']['commentsCount']['runs'][0]['text']),
1794 if expected_comment_count:
1795 comment_counts[1] = str_to_int(expected_comment_count)
1796 self.to_screen('Downloading ~%d comments' % str_to_int(expected_comment_count))
1797 yield comment_counts[1]
1800 # 1/True for newest, 0/False for popular (default)
1801 comment_sort_index = int(True)
1802 sort_continuation_renderer = try_get(
1803 continuation_renderer,
1804 lambda x: x['header']['commentsHeaderRenderer']['sortMenu']['sortFilterSubMenuRenderer']['subMenuItems']
1805 [comment_sort_index]['continuation']['reloadContinuationData'], dict)
1806 # If this fails, the initial continuation page
1807 # starts off with popular anyways.
1808 if sort_continuation_renderer:
1809 continuation = YoutubeTabIE._build_continuation_query(
1810 continuation=sort_continuation_renderer.get('continuation'),
1811 ctp=sort_continuation_renderer.get('clickTrackingParams'))
1812 self.to_screen('Sorting comments by %s' % ('popular' if comment_sort_index == 0 else 'newest'))
1815 for entry in known_continuation_renderers[key](continuation_renderer):
1818 continuation = YoutubeTabIE._extract_continuation(continuation_renderer) # TODO
1821 def _extract_comments(self, ytcfg, video_id, contents, webpage, xsrf_token):
1822 """Entry for comment extraction"""
1824 known_entry_comment_renderers = (
1825 'itemSectionRenderer',
1828 for entry in contents:
1829 for key, renderer in entry.items():
1830 if key not in known_entry_comment_renderers:
1833 comment_iter = self._comment_entries(
1835 identity_token=self._extract_identity_token(webpage, item_id=video_id),
1836 account_syncid=self._extract_account_syncid(ytcfg),
1838 session_token_list=[xsrf_token])
1840 for comment in comment_iter:
1841 if isinstance(comment, int):
1842 estimated_total = comment
1844 comments.append(comment)
1846 self.to_screen('Downloaded %d/%d comments' % (len(comments), estimated_total))
1848 'comments': comments,
1849 'comment_count': len(comments),
1852 def _real_extract(self, url):
1853 url, smuggled_data = unsmuggle_url(url, {})
1854 video_id = self._match_id(url)
1855 base_url = self.http_scheme() + '//www.youtube.com/'
1856 webpage_url = base_url + 'watch?v=' + video_id
1857 webpage = self._download_webpage(
1858 webpage_url + '&bpctr=9999999999&has_verified=1', video_id, fatal=False)
1860 player_response = None
1862 player_response = self._extract_yt_initial_variable(
1863 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
1864 video_id, 'initial player response')
1866 ytcfg = self._extract_ytcfg(video_id, webpage)
1867 if not player_response:
1868 player_response = self._call_api(
1869 'player', {'videoId': video_id}, video_id, api_key=self._extract_api_key(ytcfg))
1871 playability_status = player_response.get('playabilityStatus') or {}
1872 if playability_status.get('reason') == 'Sign in to confirm your age':
1873 pr = self._parse_json(try_get(compat_parse_qs(
1874 self._download_webpage(
1875 base_url + 'get_video_info', video_id,
1876 'Refetching age-gated info webpage',
1877 'unable to download video info webpage', query={
1878 'video_id': video_id,
1879 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1881 lambda x: x['player_response'][0],
1882 compat_str) or '{}', video_id)
1884 player_response = pr
1886 trailer_video_id = try_get(
1888 lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'],
1890 if trailer_video_id:
1891 return self.url_result(
1892 trailer_video_id, self.ie_key(), trailer_video_id)
1897 text = x.get('simpleText')
1898 if text and isinstance(text, compat_str):
1900 runs = x.get('runs')
1901 if not isinstance(runs, list):
1903 return ''.join([r['text'] for r in runs if isinstance(r.get('text'), compat_str)])
1906 lambda x: self._html_search_meta(x, webpage, default=None)) \
1907 if webpage else lambda x: None
1909 video_details = player_response.get('videoDetails') or {}
1910 microformat = try_get(
1912 lambda x: x['microformat']['playerMicroformatRenderer'],
1914 video_title = video_details.get('title') \
1915 or get_text(microformat.get('title')) \
1916 or search_meta(['og:title', 'twitter:title', 'title'])
1917 video_description = video_details.get('shortDescription')
1919 if not smuggled_data.get('force_singlefeed', False):
1920 if not self._downloader.params.get('noplaylist'):
1921 multifeed_metadata_list = try_get(
1923 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1925 if multifeed_metadata_list:
1928 for feed in multifeed_metadata_list.split(','):
1929 # Unquote should take place before split on comma (,) since textual
1930 # fields may contain comma as well (see
1931 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1932 feed_data = compat_parse_qs(
1933 compat_urllib_parse_unquote_plus(feed))
1935 def feed_entry(name):
1937 feed_data, lambda x: x[name][0], compat_str)
1939 feed_id = feed_entry('id')
1942 feed_title = feed_entry('title')
1945 title += ' (%s)' % feed_title
1947 '_type': 'url_transparent',
1948 'ie_key': 'Youtube',
1950 base_url + 'watch?v=' + feed_data['id'][0],
1951 {'force_singlefeed': True}),
1954 feed_ids.append(feed_id)
1956 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1957 % (', '.join(feed_ids), video_id))
1958 return self.playlist_result(
1959 entries, video_id, video_title, video_description)
1961 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1967 q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
1968 streaming_data = player_response.get('streamingData') or {}
1969 streaming_formats = streaming_data.get('formats') or []
1970 streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
1971 for fmt in streaming_formats:
1972 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
1975 itag = str_or_none(fmt.get('itag'))
1976 quality = fmt.get('quality')
1977 if itag and quality:
1978 itag_qualities[itag] = quality
1979 # FORMAT_STREAM_TYPE_OTF(otf=1) requires downloading the init fragment
1980 # (adding `&sq=0` to the URL) and parsing emsg box to determine the
1981 # number of fragment that would subsequently requested with (`&sq=N`)
1982 if fmt.get('type') == 'FORMAT_STREAM_TYPE_OTF':
1985 fmt_url = fmt.get('url')
1987 sc = compat_parse_qs(fmt.get('signatureCipher'))
1988 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
1989 encrypted_sig = try_get(sc, lambda x: x['s'][0])
1990 if not (sc and fmt_url and encrypted_sig):
1995 player_url = self._search_regex(
1996 r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1997 webpage, 'player URL', fatal=False)
2000 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
2001 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
2002 fmt_url += '&' + sp + '=' + signature
2006 tbr = float_or_none(
2007 fmt.get('averageBitrate') or fmt.get('bitrate'), 1000)
2008 audio_track = fmt.get('audioTrack') or {}
2010 'asr': int_or_none(fmt.get('audioSampleRate')),
2011 'filesize': int_or_none(fmt.get('contentLength')),
2013 'format_note': audio_track.get('displayName') or fmt.get('qualityLabel') or quality,
2014 'fps': int_or_none(fmt.get('fps')),
2015 'height': int_or_none(fmt.get('height')),
2016 'quality': q(quality),
2019 'width': fmt.get('width'),
2020 'language': audio_track.get('id', '').split('.')[0],
2022 mimetype = fmt.get('mimeType')
2025 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', mimetype)
2027 dct['ext'] = mimetype2ext(mobj.group(1))
2028 dct.update(parse_codecs(mobj.group(2)))
2029 no_audio = dct.get('acodec') == 'none'
2030 no_video = dct.get('vcodec') == 'none'
2035 if no_audio or no_video:
2036 dct['downloader_options'] = {
2037 # Youtube throttles chunks >~10M
2038 'http_chunk_size': 10485760,
2041 dct['container'] = dct['ext'] + '_dash'
2044 hls_manifest_url = streaming_data.get('hlsManifestUrl')
2045 if hls_manifest_url:
2046 for f in self._extract_m3u8_formats(
2047 hls_manifest_url, video_id, 'mp4', fatal=False):
2048 itag = self._search_regex(
2049 r'/itag/(\d+)', f['url'], 'itag', default=None)
2051 f['format_id'] = itag
2054 if self._downloader.params.get('youtube_include_dash_manifest', True):
2055 dash_manifest_url = streaming_data.get('dashManifestUrl')
2056 if dash_manifest_url:
2057 for f in self._extract_mpd_formats(
2058 dash_manifest_url, video_id, fatal=False):
2059 itag = f['format_id']
2062 if itag in itag_qualities:
2063 # Not actually usefull since the sorting is already done with "quality,res,fps,codec"
2064 # but kept to maintain feature parity (and code similarity) with youtube-dl
2065 # Remove if this causes any issues with sorting in future
2066 f['quality'] = q(itag_qualities[itag])
2067 filesize = int_or_none(self._search_regex(
2068 r'/clen/(\d+)', f.get('fragment_base_url')
2069 or f['url'], 'file size', default=None))
2071 f['filesize'] = filesize
2075 if not self._downloader.params.get('allow_unplayable_formats') and streaming_data.get('licenseInfos'):
2076 self.raise_no_formats(
2077 'This video is DRM protected.', expected=True)
2080 lambda x: x['errorScreen']['playerErrorMessageRenderer'],
2082 reason = get_text(pemr.get('reason')) or playability_status.get('reason')
2083 subreason = pemr.get('subreason')
2085 subreason = clean_html(get_text(subreason))
2086 if subreason == 'The uploader has not made this video available in your country.':
2087 countries = microformat.get('availableCountries')
2089 regions_allowed = search_meta('regionsAllowed')
2090 countries = regions_allowed.split(',') if regions_allowed else None
2091 self.raise_geo_restricted(subreason, countries, metadata_available=True)
2092 reason += '\n' + subreason
2094 self.raise_no_formats(reason, expected=True)
2096 self._sort_formats(formats)
2098 keywords = video_details.get('keywords') or []
2099 if not keywords and webpage:
2101 unescapeHTML(m.group('content'))
2102 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
2103 for keyword in keywords:
2104 if keyword.startswith('yt:stretch='):
2105 mobj = re.search(r'(\d+)\s*:\s*(\d+)', keyword)
2107 # NB: float is intentional for forcing float division
2108 w, h = (float(v) for v in mobj.groups())
2112 if f.get('vcodec') != 'none':
2113 f['stretched_ratio'] = ratio
2117 for container in (video_details, microformat):
2118 for thumbnail in (try_get(
2120 lambda x: x['thumbnail']['thumbnails'], list) or []):
2121 thumbnail_url = thumbnail.get('url')
2122 if not thumbnail_url:
2124 # Sometimes youtube gives a wrong thumbnail URL. See:
2125 # https://github.com/yt-dlp/yt-dlp/issues/233
2126 # https://github.com/ytdl-org/youtube-dl/issues/28023
2127 if 'maxresdefault' in thumbnail_url:
2128 thumbnail_url = thumbnail_url.split('?')[0]
2130 'height': int_or_none(thumbnail.get('height')),
2131 'url': thumbnail_url,
2132 'width': int_or_none(thumbnail.get('width')),
2137 thumbnail = search_meta(['og:image', 'twitter:image'])
2139 thumbnails = [{'url': thumbnail}]
2141 category = microformat.get('category') or search_meta('genre')
2142 channel_id = video_details.get('channelId') \
2143 or microformat.get('externalChannelId') \
2144 or search_meta('channelId')
2145 duration = int_or_none(
2146 video_details.get('lengthSeconds')
2147 or microformat.get('lengthSeconds')) \
2148 or parse_duration(search_meta('duration'))
2149 is_live = video_details.get('isLive')
2150 owner_profile_url = microformat.get('ownerProfileUrl')
2154 'title': self._live_title(video_title) if is_live else video_title,
2156 'thumbnails': thumbnails,
2157 'description': video_description,
2158 'upload_date': unified_strdate(
2159 microformat.get('uploadDate')
2160 or search_meta('uploadDate')),
2161 'uploader': video_details['author'],
2162 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
2163 'uploader_url': owner_profile_url,
2164 'channel_id': channel_id,
2165 'channel_url': 'https://www.youtube.com/channel/' + channel_id if channel_id else None,
2166 'duration': duration,
2167 'view_count': int_or_none(
2168 video_details.get('viewCount')
2169 or microformat.get('viewCount')
2170 or search_meta('interactionCount')),
2171 'average_rating': float_or_none(video_details.get('averageRating')),
2172 'age_limit': 18 if (
2173 microformat.get('isFamilySafe') is False
2174 or search_meta('isFamilyFriendly') == 'false'
2175 or search_meta('og:restrictions:age') == '18+') else 0,
2176 'webpage_url': webpage_url,
2177 'categories': [category] if category else None,
2180 'playable_in_embed': playability_status.get('playableInEmbed'),
2181 'was_live': video_details.get('isLiveContent'),
2186 lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
2189 def process_language(container, base_url, lang_code, query):
2190 lang_subs = container.setdefault(lang_code, [])
2191 for fmt in self._SUBTITLE_FORMATS:
2197 'url': update_url_query(base_url, query),
2200 for caption_track in (pctr.get('captionTracks') or []):
2201 base_url = caption_track.get('baseUrl')
2204 if caption_track.get('kind') != 'asr':
2206 remove_start(caption_track.get('vssId') or '', '.').replace('.', '-')
2207 or caption_track.get('languageCode'))
2211 subtitles, base_url, lang_code, {})
2213 automatic_captions = {}
2214 for translation_language in (pctr.get('translationLanguages') or []):
2215 translation_language_code = translation_language.get('languageCode')
2216 if not translation_language_code:
2219 automatic_captions, base_url, translation_language_code,
2220 {'tlang': translation_language_code})
2221 info['automatic_captions'] = automatic_captions
2222 info['subtitles'] = subtitles
2224 parsed_url = compat_urllib_parse_urlparse(url)
2225 for component in [parsed_url.fragment, parsed_url.query]:
2226 query = compat_parse_qs(component)
2227 for k, v in query.items():
2228 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
2230 if d_k not in info and k in s_ks:
2231 info[d_k] = parse_duration(query[k][0])
2233 # Youtube Music Auto-generated description
2234 if video_description:
2235 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)
2237 release_year = mobj.group('release_year')
2238 release_date = mobj.group('release_date')
2240 release_date = release_date.replace('-', '')
2241 if not release_year:
2242 release_year = release_date[:4]
2244 'album': mobj.group('album'.strip()),
2245 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
2246 'track': mobj.group('track').strip(),
2247 'release_date': release_date,
2248 'release_year': int_or_none(release_year),
2253 initial_data = self._extract_yt_initial_variable(
2254 webpage, self._YT_INITIAL_DATA_RE, video_id,
2256 if not initial_data:
2257 initial_data = self._call_api(
2258 'next', {'videoId': video_id}, video_id, fatal=False, api_key=self._extract_api_key(ytcfg))
2262 # This will error if there is no livechat
2263 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2264 info['subtitles']['live_chat'] = [{
2265 'url': 'https://www.youtube.com/watch?v=%s' % video_id, # url is needed to set cookies
2266 'video_id': video_id,
2268 'protocol': 'youtube_live_chat_replay',
2270 except (KeyError, IndexError, TypeError):
2274 chapters = self._extract_chapters_from_json(
2275 initial_data, video_id, duration)
2277 for engagment_pannel in (initial_data.get('engagementPanels') or []):
2279 engagment_pannel, lambda x: x['engagementPanelSectionListRenderer']['content']['macroMarkersListRenderer']['contents'],
2284 def chapter_time(mmlir):
2285 return parse_duration(
2286 get_text(mmlir.get('timeDescription')))
2289 for next_num, content in enumerate(contents, start=1):
2290 mmlir = content.get('macroMarkersListItemRenderer') or {}
2291 start_time = chapter_time(mmlir)
2292 end_time = chapter_time(try_get(
2293 contents, lambda x: x[next_num]['macroMarkersListItemRenderer'])) \
2294 if next_num < len(contents) else duration
2295 if start_time is None or end_time is None:
2298 'start_time': start_time,
2299 'end_time': end_time,
2300 'title': get_text(mmlir.get('title')),
2305 info['chapters'] = chapters
2309 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
2311 for content in contents:
2312 vpir = content.get('videoPrimaryInfoRenderer')
2314 stl = vpir.get('superTitleLink')
2319 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
2320 info['location'] = stl
2322 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
2325 'series': mobj.group(1),
2326 'season_number': int(mobj.group(2)),
2327 'episode_number': int(mobj.group(3)),
2329 for tlb in (try_get(
2331 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
2333 tbr = tlb.get('toggleButtonRenderer') or {}
2334 for getter, regex in [(
2335 lambda x: x['defaultText']['accessibility']['accessibilityData'],
2336 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
2337 lambda x: x['accessibility'],
2338 lambda x: x['accessibilityData']['accessibilityData'],
2339 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
2340 label = (try_get(tbr, getter, dict) or {}).get('label')
2342 mobj = re.match(regex, label)
2344 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
2346 sbr_tooltip = try_get(
2347 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
2349 like_count, dislike_count = sbr_tooltip.split(' / ')
2351 'like_count': str_to_int(like_count),
2352 'dislike_count': str_to_int(dislike_count),
2354 vsir = content.get('videoSecondaryInfoRenderer')
2356 info['channel'] = get_text(try_get(
2358 lambda x: x['owner']['videoOwnerRenderer']['title'],
2362 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
2364 multiple_songs = False
2366 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
2367 multiple_songs = True
2370 mrr = row.get('metadataRowRenderer') or {}
2371 mrr_title = mrr.get('title')
2374 mrr_title = get_text(mrr['title'])
2375 mrr_contents_text = get_text(mrr['contents'][0])
2376 if mrr_title == 'License':
2377 info['license'] = mrr_contents_text
2378 elif not multiple_songs:
2379 if mrr_title == 'Album':
2380 info['album'] = mrr_contents_text
2381 elif mrr_title == 'Artist':
2382 info['artist'] = mrr_contents_text
2383 elif mrr_title == 'Song':
2384 info['track'] = mrr_contents_text
2387 'channel': 'uploader',
2388 'channel_id': 'uploader_id',
2389 'channel_url': 'uploader_url',
2391 for to, frm in fallbacks.items():
2392 if not info.get(to):
2393 info[to] = info.get(frm)
2395 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
2400 is_private = bool_or_none(video_details.get('isPrivate'))
2401 is_unlisted = bool_or_none(microformat.get('isUnlisted'))
2402 is_membersonly = None
2404 if initial_data and is_private is not None:
2405 is_membersonly = False
2407 contents = try_get(initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list)
2408 for content in contents or []:
2409 badges = try_get(content, lambda x: x['videoPrimaryInfoRenderer']['badges'], list)
2410 for badge in badges or []:
2411 label = try_get(badge, lambda x: x['metadataBadgeRenderer']['label']) or ''
2412 if label.lower() == 'members only':
2413 is_membersonly = True
2415 elif label.lower() == 'premium':
2418 if is_membersonly or is_premium:
2421 # TODO: Add this for playlists
2422 info['availability'] = self._availability(
2423 is_private=is_private,
2424 needs_premium=is_premium,
2425 needs_subscription=is_membersonly,
2426 needs_auth=info['age_limit'] >= 18,
2427 is_unlisted=None if is_private is None else is_unlisted)
2429 # get xsrf for annotations or comments
2430 get_annotations = self._downloader.params.get('writeannotations', False)
2431 get_comments = self._downloader.params.get('getcomments', False)
2432 if get_annotations or get_comments:
2434 ytcfg = self._extract_ytcfg(video_id, webpage)
2436 xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
2438 xsrf_token = self._search_regex(
2439 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
2440 webpage, 'xsrf token', group='xsrf_token', fatal=False)
2444 invideo_url = try_get(
2445 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2446 if xsrf_token and invideo_url:
2447 xsrf_field_name = None
2449 xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
2450 if not xsrf_field_name:
2451 xsrf_field_name = self._search_regex(
2452 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2453 webpage, 'xsrf field name',
2454 group='xsrf_field_name', default='session_token')
2455 info['annotations'] = self._download_webpage(
2456 self._proto_relative_url(invideo_url),
2457 video_id, note='Downloading annotations',
2458 errnote='Unable to download video annotations', fatal=False,
2459 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2462 info['__post_extractor'] = lambda: self._extract_comments(ytcfg, video_id, contents, webpage, xsrf_token)
2464 self.mark_watched(video_id, player_response)
2469 class YoutubeTabIE(YoutubeBaseInfoExtractor):
2470 IE_DESC = 'YouTube.com tab'
2471 _VALID_URL = r'''(?x
)
2475 youtube(?
:kids
)?\
.com|
2479 (?
:channel|c|user
)/|
2482 (?
:playlist|watch
)\?.*?
\blist
=
2484 (?
!(?
:%s)\b) # Direct URLs
2487 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
2488 IE_NAME = 'youtube:tab'
2491 # playlists, multipage
2492 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
2493 'playlist_mincount': 94,
2495 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2496 'title': 'Игорь Клейнер - Playlists',
2497 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2498 'uploader': 'Игорь Клейнер',
2499 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
2502 # playlists, multipage, different order
2503 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2504 'playlist_mincount': 94,
2506 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2507 'title': 'Игорь Клейнер - Playlists',
2508 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2509 'uploader_id': 'UCqj7Cz7revf5maW9g5pgNcg',
2510 'uploader': 'Игорь Клейнер',
2514 'url': 'https://www.youtube.com/c/3blue1brown/playlists?view=50&sort=dd&shelf_id=3',
2515 'playlist_mincount': 5,
2517 'id': 'UCYO_jab_esuFRV4b17AJtAw',
2518 'title': '3Blue1Brown - Playlists',
2519 'description': 'md5:e1384e8a133307dd10edee76e875d62f',
2522 # playlists, singlepage
2523 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2524 'playlist_mincount': 4,
2526 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
2527 'title': 'ThirstForScience - Playlists',
2528 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
2529 'uploader': 'ThirstForScience',
2530 'uploader_id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
2533 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
2534 'only_matching': True,
2536 # basic, single video playlist
2537 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2539 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2540 'uploader': 'Sergey M.',
2541 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2542 'title': 'youtube-dl public playlist',
2544 'playlist_count': 1,
2547 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2549 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2550 'uploader': 'Sergey M.',
2551 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2552 'title': 'youtube-dl empty playlist',
2554 'playlist_count': 0,
2557 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
2559 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2560 'title': 'lex will - Home',
2561 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2562 'uploader': 'lex will',
2563 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2565 'playlist_mincount': 2,
2568 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
2570 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2571 'title': 'lex will - Videos',
2572 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2573 'uploader': 'lex will',
2574 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2576 'playlist_mincount': 975,
2578 # Videos tab, sorted by popular
2579 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
2581 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2582 'title': 'lex will - Videos',
2583 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2584 'uploader': 'lex will',
2585 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2587 'playlist_mincount': 199,
2590 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
2592 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2593 'title': 'lex will - Playlists',
2594 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2595 'uploader': 'lex will',
2596 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2598 'playlist_mincount': 17,
2601 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
2603 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2604 'title': 'lex will - Community',
2605 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2606 'uploader': 'lex will',
2607 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2609 'playlist_mincount': 18,
2612 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
2614 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2615 'title': 'lex will - Channels',
2616 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2617 'uploader': 'lex will',
2618 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2620 'playlist_mincount': 12,
2622 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2623 'only_matching': True,
2625 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2626 'only_matching': True,
2628 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2629 'only_matching': True,
2631 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2632 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2634 'title': '29C3: Not my department',
2635 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2636 'uploader': 'Christiaan008',
2637 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
2638 'description': 'md5:a14dc1a8ef8307a9807fe136a0660268',
2640 'playlist_count': 96,
2642 'note': 'Large playlist',
2643 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2645 'title': 'Uploads from Cauchemar',
2646 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2647 'uploader': 'Cauchemar',
2648 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
2650 'playlist_mincount': 1123,
2652 # even larger playlist, 8832 videos
2653 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
2654 'only_matching': True,
2656 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2657 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2659 'title': 'Uploads from Interstellar Movie',
2660 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2661 'uploader': 'Interstellar Movie',
2662 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
2664 'playlist_mincount': 21,
2666 'note': 'Playlist with "show unavailable videos" button',
2667 'url': 'https://www.youtube.com/playlist?list=UUTYLiWFZy8xtPwxFwX9rV7Q',
2669 'title': 'Uploads from Phim Siêu Nhân Nhật Bản',
2670 'id': 'UUTYLiWFZy8xtPwxFwX9rV7Q',
2671 'uploader': 'Phim Siêu Nhân Nhật Bản',
2672 'uploader_id': 'UCTYLiWFZy8xtPwxFwX9rV7Q',
2674 'playlist_mincount': 1400,
2675 'expected_warnings': [
2676 'YouTube said: INFO - Unavailable videos are hidden',
2679 'note': 'Playlist with unavailable videos in a later page',
2680 'url': 'https://www.youtube.com/playlist?list=UU8l9frL61Yl5KFOl87nIm2w',
2682 'title': 'Uploads from BlankTV',
2683 'id': 'UU8l9frL61Yl5KFOl87nIm2w',
2684 'uploader': 'BlankTV',
2685 'uploader_id': 'UC8l9frL61Yl5KFOl87nIm2w',
2687 'playlist_mincount': 20000,
2689 # https://github.com/ytdl-org/youtube-dl/issues/21844
2690 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2692 'title': 'Data Analysis with Dr Mike Pound',
2693 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2694 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
2695 'uploader': 'Computerphile',
2696 'description': 'md5:7f567c574d13d3f8c0954d9ffee4e487',
2698 'playlist_mincount': 11,
2700 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2701 'only_matching': True,
2703 # Playlist URL that does not actually serve a playlist
2704 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2706 'id': 'FqZTN594JQw',
2708 'title': "Smiley's People 01 detective, Adventure Series, Action",
2709 'uploader': 'STREEM',
2710 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2711 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2712 'upload_date': '20150526',
2713 'license': 'Standard YouTube License',
2714 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2715 'categories': ['People & Blogs'],
2719 'dislike_count': int,
2722 'skip_download': True,
2724 'skip': 'This video is not available.',
2725 'add_ie': [YoutubeIE.ie_key()],
2727 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2728 'only_matching': True,
2730 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
2731 'only_matching': True,
2733 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
2735 'id': '9Auq9mYxFEE',
2737 'title': compat_str,
2738 'uploader': 'Sky News',
2739 'uploader_id': 'skynews',
2740 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
2741 'upload_date': '20191102',
2742 'description': 'md5:85ddd75d888674631aaf9599a9a0b0ae',
2743 'categories': ['News & Politics'],
2746 'dislike_count': int,
2749 'skip_download': True,
2752 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2754 'id': 'a48o2S1cPoo',
2756 'title': 'The Young Turks - Live Main Show',
2757 'uploader': 'The Young Turks',
2758 'uploader_id': 'TheYoungTurks',
2759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2760 'upload_date': '20150715',
2761 'license': 'Standard YouTube License',
2762 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2763 'categories': ['News & Politics'],
2764 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2766 'dislike_count': int,
2769 'skip_download': True,
2771 'only_matching': True,
2773 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2774 'only_matching': True,
2776 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2777 'only_matching': True,
2779 'url': 'https://www.youtube.com/feed/trending',
2780 'only_matching': True,
2783 'url': 'https://www.youtube.com/feed/library',
2784 'only_matching': True,
2787 'url': 'https://www.youtube.com/feed/history',
2788 'only_matching': True,
2791 'url': 'https://www.youtube.com/feed/subscriptions',
2792 'only_matching': True,
2795 'url': 'https://www.youtube.com/feed/watch_later',
2796 'only_matching': True,
2798 # no longer available?
2799 'url': 'https://www.youtube.com/feed/recommended',
2800 'only_matching': True,
2802 # inline playlist with not always working continuations
2803 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
2804 'only_matching': True,
2806 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
2807 'only_matching': True,
2809 'url': 'https://www.youtube.com/course',
2810 'only_matching': True,
2812 'url': 'https://www.youtube.com/zsecurity',
2813 'only_matching': True,
2815 'url': 'http://www.youtube.com/NASAgovVideo/videos',
2816 'only_matching': True,
2818 'url': 'https://www.youtube.com/TheYoungTurks/live',
2819 'only_matching': True,
2821 'url': 'https://www.youtube.com/hashtag/cctv9',
2826 'playlist_mincount': 350,
2828 'url': 'https://www.youtube.com/watch?list=PLW4dVinRY435CBE_JD3t-0SRXKfnZHS1P&feature=youtu.be&v=M9cJMXmQ_ZU',
2829 'only_matching': True,
2833 def suitable(cls, url):
2834 return False if YoutubeIE.suitable(url) else super(
2835 YoutubeTabIE, cls).suitable(url)
2837 def _extract_channel_id(self, webpage):
2838 channel_id = self._html_search_meta(
2839 'channelId', webpage, 'channel id', default=None)
2842 channel_url = self._html_search_meta(
2843 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
2844 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
2845 'twitter:app:url:googleplay'), webpage, 'channel url')
2846 return self._search_regex(
2847 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
2848 channel_url, 'channel id')
2851 def _extract_basic_item_renderer(item):
2852 # Modified from _extract_grid_item_renderer
2853 known_basic_renderers = (
2854 'playlistRenderer', 'videoRenderer', 'channelRenderer', 'showRenderer'
2856 for key, renderer in item.items():
2857 if not isinstance(renderer, dict):
2859 elif key in known_basic_renderers:
2861 elif key.startswith('grid') and key.endswith('Renderer'):
2864 def _grid_entries(self, grid_renderer):
2865 for item in grid_renderer['items']:
2866 if not isinstance(item, dict):
2868 renderer = self._extract_basic_item_renderer(item)
2869 if not isinstance(renderer, dict):
2872 renderer, (lambda x: x['title']['runs'][0]['text'],
2873 lambda x: x['title']['simpleText']), compat_str)
2875 playlist_id = renderer.get('playlistId')
2877 yield self.url_result(
2878 'https://www.youtube.com/playlist?list=%s' % playlist_id,
2879 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
2883 video_id = renderer.get('videoId')
2885 yield self._extract_video(renderer)
2888 channel_id = renderer.get('channelId')
2891 renderer, lambda x: x['title']['simpleText'], compat_str)
2892 yield self.url_result(
2893 'https://www.youtube.com/channel/%s' % channel_id,
2894 ie=YoutubeTabIE.ie_key(), video_title=title)
2896 # generic endpoint URL support
2897 ep_url = urljoin('https://www.youtube.com/', try_get(
2898 renderer, lambda x: x['navigationEndpoint']['commandMetadata']['webCommandMetadata']['url'],
2901 for ie in (YoutubeTabIE, YoutubePlaylistIE, YoutubeIE):
2902 if ie.suitable(ep_url):
2903 yield self.url_result(
2904 ep_url, ie=ie.ie_key(), video_id=ie._match_id(ep_url), video_title=title)
2907 def _shelf_entries_from_content(self, shelf_renderer):
2908 content = shelf_renderer.get('content')
2909 if not isinstance(content, dict):
2911 renderer = content.get('gridRenderer') or content.get('expandedShelfContentsRenderer')
2913 # TODO: add support for nested playlists so each shelf is processed
2914 # as separate playlist
2915 # TODO: this includes only first N items
2916 for entry in self._grid_entries(renderer):
2918 renderer = content.get('horizontalListRenderer')
2923 def _shelf_entries(self, shelf_renderer, skip_channels=False):
2925 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
2927 shelf_url = urljoin('https://www.youtube.com', ep)
2929 # Skipping links to another channels, note that checking for
2930 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
2932 if skip_channels and '/channels?' in shelf_url:
2935 shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
2936 yield self.url_result(shelf_url, video_title=title)
2937 # Shelf may not contain shelf URL, fallback to extraction from content
2938 for entry in self._shelf_entries_from_content(shelf_renderer):
2941 def _playlist_entries(self, video_list_renderer):
2942 for content in video_list_renderer['contents']:
2943 if not isinstance(content, dict):
2945 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
2946 if not isinstance(renderer, dict):
2948 video_id = renderer.get('videoId')
2951 yield self._extract_video(renderer)
2953 def _rich_entries(self, rich_grid_renderer):
2955 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
2956 video_id = renderer.get('videoId')
2959 yield self._extract_video(renderer)
2961 def _video_entry(self, video_renderer):
2962 video_id = video_renderer.get('videoId')
2964 return self._extract_video(video_renderer)
2966 def _post_thread_entries(self, post_thread_renderer):
2967 post_renderer = try_get(
2968 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
2969 if not post_renderer:
2972 video_renderer = try_get(
2973 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict) or {}
2974 video_id = video_renderer.get('videoId')
2976 entry = self._extract_video(video_renderer)
2979 # playlist attachment
2980 playlist_id = try_get(
2981 post_renderer, lambda x: x['backstageAttachment']['playlistRenderer']['playlistId'], compat_str)
2983 yield self.url_result(
2984 'https://www.youtube.com/playlist?list=%s' % playlist_id,
2985 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
2986 # inline video links
2987 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
2989 if not isinstance(run, dict):
2992 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
2995 if not YoutubeIE.suitable(ep_url):
2997 ep_video_id = YoutubeIE._match_id(ep_url)
2998 if video_id == ep_video_id:
3000 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=ep_video_id)
3002 def _post_thread_continuation_entries(self, post_thread_continuation):
3003 contents = post_thread_continuation.get('contents')
3004 if not isinstance(contents, list):
3006 for content in contents:
3007 renderer = content.get('backstagePostThreadRenderer')
3008 if not isinstance(renderer, dict):
3010 for entry in self._post_thread_entries(renderer):
3014 def _rich_grid_entries(self
, contents
):
3015 for content
in contents
:
3016 video_renderer
= try_get(content
, lambda x
: x
['richItemRenderer']['content']['videoRenderer'], dict)
3018 entry
= self
._video
_entry
(video_renderer
)
3024 def _build_continuation_query(continuation, ctp=None):
3026 'ctoken': continuation,
3027 'continuation': continuation,
3034 def _extract_next_continuation_data(renderer):
3035 next_continuation = try_get(
3036 renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict)
3037 if not next_continuation:
3039 continuation = next_continuation.get('continuation')
3040 if not continuation:
3042 ctp = next_continuation.get('clickTrackingParams')
3043 return YoutubeTabIE._build_continuation_query(continuation, ctp)
3046 def _extract_continuation(cls, renderer):
3047 next_continuation = cls._extract_next_continuation_data(renderer)
3048 if next_continuation:
3049 return next_continuation
3051 for key in ('contents', 'items'):
3052 contents.extend(try_get(renderer, lambda x: x[key], list) or [])
3053 for content in contents:
3054 if not isinstance(content, dict):
3056 continuation_ep = try_get(
3057 content, lambda x: x['continuationItemRenderer']['continuationEndpoint'],
3059 if not continuation_ep:
3061 continuation = try_get(
3062 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
3063 if not continuation:
3065 ctp = continuation_ep.get('clickTrackingParams')
3066 return YoutubeTabIE._build_continuation_query(continuation, ctp)
3068 def _entries(self, tab, item_id, identity_token, account_syncid, ytcfg):
3070 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3071 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3072 for content in contents:
3073 if not isinstance(content, dict):
3075 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3077 renderer = content.get('richItemRenderer')
3079 for entry in self._rich_entries(renderer):
3081 continuation_list[0] = self._extract_continuation(parent_renderer)
3083 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3084 for isr_content in isr_contents:
3085 if not isinstance(isr_content, dict):
3089 'playlistVideoListRenderer': self._playlist_entries,
3090 'gridRenderer': self._grid_entries,
3091 'shelfRenderer': lambda x: self._shelf_entries(x, tab.get('title') != 'Channels'),
3092 'backstagePostThreadRenderer': self._post_thread_entries,
3093 'videoRenderer': lambda x: [self._video_entry(x)],
3095 for key, renderer in isr_content.items():
3096 if key not in known_renderers:
3098 for entry in known_renderers[key](renderer):
3101 continuation_list[0] = self._extract_continuation(renderer)
3104 if not continuation_list[0]:
3105 continuation_list[0] = self._extract_continuation(is_renderer)
3107 if not continuation_list[0]:
3108 continuation_list[0] = self._extract_continuation(parent_renderer)
3110 continuation_list = [None] # Python 2 doesnot support nonlocal
3111 tab_content = try_get(tab, lambda x: x['content'], dict)
3115 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3116 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3117 for entry in extract_entries(parent_renderer):
3119 continuation = continuation_list[0]
3120 context = self._extract_context(ytcfg)
3121 visitor_data = try_get(context, lambda x: x['client']['visitorData'], compat_str)
3123 for page_num in itertools.count(1):
3124 if not continuation:
3127 'continuation': continuation['continuation'],
3128 'clickTracking': {'clickTrackingParams': continuation['itct']}
3130 headers = self._generate_api_headers(ytcfg, identity_token, account_syncid, visitor_data)
3131 response = self._extract_response(
3132 item_id='%s page %s' % (item_id, page_num),
3133 query=query, headers=headers, ytcfg=ytcfg,
3134 check_get_keys=('continuationContents', 'onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3138 visitor_data = try_get(
3139 response, lambda x: x['responseContext']['visitorData'], compat_str) or visitor_data
3141 known_continuation_renderers = {
3142 'playlistVideoListContinuation': self._playlist_entries,
3143 'gridContinuation': self._grid_entries,
3144 'itemSectionContinuation': self._post_thread_continuation_entries,
3145 'sectionListContinuation': extract_entries, # for feeds
3147 continuation_contents = try_get(
3148 response, lambda x: x['continuationContents'], dict) or {}
3149 continuation_renderer = None
3150 for key, value in continuation_contents.items():
3151 if key not in known_continuation_renderers:
3153 continuation_renderer = value
3154 continuation_list = [None]
3155 for entry in known_continuation_renderers[key](continuation_renderer):
3157 continuation = continuation_list[0] or self._extract_continuation(continuation_renderer)
3159 if continuation_renderer:
3163 'gridPlaylistRenderer': (self._grid_entries, 'items'),
3164 'gridVideoRenderer': (self._grid_entries, 'items'),
3165 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
3166 'itemSectionRenderer': (extract_entries, 'contents'), # for feeds
3167 'richItemRenderer': (extract_entries, 'contents'), # for hashtag
3168 'backstagePostThreadRenderer': (self._post_thread_continuation_entries, 'contents')
3170 on_response_received = dict_get(response, ('onResponseReceivedActions', 'onResponseReceivedEndpoints'))
3171 continuation_items = try_get(
3172 on_response_received, lambda x: x[0]['appendContinuationItemsAction']['continuationItems'], list)
3173 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
3174 video_items_renderer = None
3175 for key, value in continuation_item.items():
3176 if key not in known_renderers:
3178 video_items_renderer = {known_renderers[key][1]: continuation_items}
3179 continuation_list = [None]
3180 for entry in known_renderers[key][0](video_items_renderer):
3182 continuation = continuation_list[0] or self._extract_continuation(video_items_renderer)
3184 if video_items_renderer:
3189 def _extract_selected_tab(tabs):
3191 if try_get(tab, lambda x: x['tabRenderer']['selected'], bool):
3192 return tab['tabRenderer']
3194 raise ExtractorError('Unable to find selected tab')
3197 def _extract_uploader(data):
3199 sidebar_renderer = try_get(
3200 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
3201 if sidebar_renderer:
3202 for item in sidebar_renderer:
3203 if not isinstance(item, dict):
3205 renderer = item.get('playlistSidebarSecondaryInfoRenderer')
3206 if not isinstance(renderer, dict):
3209 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3211 uploader['uploader'] = owner.get('text')
3212 uploader['uploader_id'] = try_get(
3213 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3214 uploader['uploader_url'] = urljoin(
3215 'https://www.youtube.com/',
3216 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3217 return {k: v for k, v in uploader.items() if v is not None}
3219 def _extract_from_tabs(self, item_id, webpage, data, tabs):
3220 playlist_id = title = description = channel_url = channel_name = channel_id = None
3221 thumbnails_list = tags = []
3223 selected_tab = self._extract_selected_tab(tabs)
3225 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3227 channel_name = renderer.get('title')
3228 channel_url = renderer.get('channelUrl')
3229 channel_id = renderer.get('externalId')
3232 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3235 title = renderer.get('title')
3236 description = renderer.get('description', '')
3237 playlist_id = channel_id
3238 tags = renderer.get('keywords', '').split()
3240 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
3243 lambda x: x['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
3248 for t in thumbnails_list:
3249 if not isinstance(t, dict):
3251 thumbnail_url = url_or_none(t.get('url'))
3252 if not thumbnail_url:
3255 'url': thumbnail_url,
3256 'width': int_or_none(t.get('width')),
3257 'height': int_or_none(t.get('height')),
3259 if playlist_id is None:
3260 playlist_id = item_id
3263 try_get(data, lambda x: x['header']['hashtagHeaderRenderer']['hashtag']['simpleText'])
3265 title += format_field(selected_tab, 'title', ' - %s')
3268 'playlist_id': playlist_id,
3269 'playlist_title': title,
3270 'playlist_description': description,
3271 'uploader': channel_name,
3272 'uploader_id': channel_id,
3273 'uploader_url': channel_url,
3274 'thumbnails': thumbnails,
3278 metadata.update(self._extract_uploader(data))
3280 'channel': metadata['uploader'],
3281 'channel_id': metadata['uploader_id'],
3282 'channel_url': metadata['uploader_url']})
3283 return self.playlist_result(
3285 selected_tab, playlist_id,
3286 self._extract_identity_token(webpage, item_id),
3287 self._extract_account_syncid(data),
3288 self._extract_ytcfg(item_id, webpage)),
3291 def _extract_mix_playlist(self, playlist, playlist_id, data, webpage):
3292 first_id = last_id = None
3293 ytcfg = self._extract_ytcfg(playlist_id, webpage)
3294 headers = self._generate_api_headers(
3295 ytcfg, account_syncid=self._extract_account_syncid(data),
3296 identity_token=self._extract_identity_token(webpage, item_id=playlist_id),
3297 visitor_data=try_get(self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
3298 for page_num in itertools.count(1):
3299 videos = list(self._playlist_entries(playlist))
3302 start = next((i for i, v in enumerate(videos) if v['id'] == last_id), -1) + 1
3303 if start >= len(videos):
3305 for video in videos[start:]:
3306 if video['id'] == first_id:
3307 self.to_screen('First video %s found again; Assuming end of Mix' % first_id)
3310 first_id = first_id or videos[0]['id']
3311 last_id = videos[-1]['id']
3312 watch_endpoint = try_get(
3313 playlist, lambda x: x['contents'][-1]['playlistPanelVideoRenderer']['navigationEndpoint']['watchEndpoint'])
3315 'playlistId': playlist_id,
3316 'videoId': watch_endpoint.get('videoId') or last_id,
3317 'index': watch_endpoint.get('index') or len(videos),
3318 'params': watch_endpoint.get('params') or 'OAE%3D'
3320 response = self._extract_response(
3321 item_id='%s page %d' % (playlist_id, page_num),
3325 check_get_keys='contents'
3328 response, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
3330 def _extract_from_playlist(self, item_id, url, data, playlist, webpage):
3331 title = playlist.get('title') or try_get(
3332 data, lambda x: x['titleText']['simpleText'], compat_str)
3333 playlist_id = playlist.get('playlistId') or item_id
3335 # Delegating everything except mix playlists to regular tab-based playlist URL
3336 playlist_url = urljoin(url, try_get(
3337 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3339 if playlist_url and playlist_url != url:
3340 return self.url_result(
3341 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3344 return self.playlist_result(
3345 self._extract_mix_playlist(playlist, playlist_id, data, webpage),
3346 playlist_id=playlist_id, playlist_title=title)
3348 def _extract_alerts(self, data, expected=False):
3350 def _real_extract_alerts():
3351 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
3352 if not isinstance(alert_dict, dict):
3354 for alert in alert_dict.values():
3355 alert_type = alert.get('type')
3358 message = try_get(alert, lambda x: x['text']['simpleText'], compat_str) or ''
3360 yield alert_type, message
3361 for run in try_get(alert, lambda x: x['text']['runs'], list) or []:
3362 message += try_get(run, lambda x: x['text'], compat_str)
3364 yield alert_type, message
3368 for alert_type, alert_message in _real_extract_alerts():
3369 if alert_type.lower() == 'error':
3370 errors.append([alert_type, alert_message])
3372 warnings.append([alert_type, alert_message])
3374 for alert_type, alert_message in (warnings + errors[:-1]):
3375 self.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
3377 raise ExtractorError('YouTube said: %s' % errors[-1][1], expected=expected)
3379 def _reload_with_unavailable_videos(self, item_id, data, webpage):
3381 Get playlist with unavailable videos if the 'show unavailable videos' button exists.
3383 sidebar_renderer = try_get(
3384 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
3385 if not sidebar_renderer:
3387 browse_id = params = None
3388 for item in sidebar_renderer:
3389 if not isinstance(item, dict):
3391 renderer = item.get('playlistSidebarPrimaryInfoRenderer')
3392 menu_renderer = try_get(
3393 renderer, lambda x: x['menu']['menuRenderer']['items'], list) or []
3394 for menu_item in menu_renderer:
3395 if not isinstance(menu_item, dict):
3397 nav_item_renderer = menu_item.get('menuNavigationItemRenderer')
3399 nav_item_renderer, lambda x: x['text']['simpleText'], compat_str)
3400 if not text or text.lower() != 'show unavailable videos':
3402 browse_endpoint = try_get(
3403 nav_item_renderer, lambda x: x['navigationEndpoint']['browseEndpoint'], dict) or {}
3404 browse_id = browse_endpoint.get('browseId')
3405 params = browse_endpoint.get('params')
3408 ytcfg = self._extract_ytcfg(item_id, webpage)
3409 headers = self._generate_api_headers(
3410 ytcfg, account_syncid=self._extract_account_syncid(ytcfg),
3411 identity_token=self._extract_identity_token(webpage, item_id=item_id),
3412 visitor_data=try_get(
3413 self._extract_context(ytcfg), lambda x: x['client']['visitorData'], compat_str))
3415 'params': params or 'wgYCCAA=',
3416 'browseId': browse_id or 'VL%s' % item_id
3418 return self._extract_response(
3419 item_id=item_id, headers=headers, query=query,
3420 check_get_keys='contents', fatal=False,
3421 note='Downloading API JSON with unavailable videos')
3423 def _extract_response(self, item_id, query, note='Downloading API JSON', headers=None,
3424 ytcfg=None, check_get_keys=None, ep='browse', fatal=True):
3428 retries = self._downloader.params.get('extractor_retries', 3)
3429 if check_get_keys is None:
3431 while count < retries:
3434 self.report_warning('%s. Retrying ...' % last_error)
3436 response = self._call_api(
3437 ep=ep, fatal=True, headers=headers,
3438 video_id=item_id, query=query,
3439 context=self._extract_context(ytcfg),
3440 api_key=self._extract_api_key(ytcfg),
3441 note='%s%s' % (note, ' (retry #%d)' % count if count else ''))
3442 except ExtractorError as e:
3443 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503, 404):
3444 # Downloading page may result in intermittent 5xx HTTP error
3445 # Sometimes a 404 is also recieved. See: https://github.com/ytdl-org/youtube-dl/issues/28289
3446 last_error = 'HTTP Error %s' % e.cause.code
3452 self.report_warning(error_to_compat_str(e))
3456 # Youtube may send alerts if there was an issue with the continuation page
3457 self._extract_alerts(response, expected=False)
3458 if not check_get_keys or dict_get(response, check_get_keys):
3460 # Youtube sometimes sends incomplete data
3461 # See: https://github.com/ytdl-org/youtube-dl/issues/28194
3462 last_error = 'Incomplete data received'
3463 if count >= retries:
3465 raise ExtractorError(last_error)
3467 self.report_warning(last_error)
3471 def _extract_webpage(self, url, item_id):
3472 retries = self._downloader.params.get('extractor_retries', 3)
3474 last_error = 'Incomplete yt initial data recieved'
3475 while count < retries:
3477 # Sometimes youtube returns a webpage with incomplete ytInitialData
3478 # See: https://github.com/yt-dlp/yt-dlp/issues/116
3480 self.report_warning('%s. Retrying ...' % last_error)
3481 webpage = self._download_webpage(
3483 'Downloading webpage%s' % (' (retry #%d)' % count if count else ''))
3484 data = self._extract_yt_initial_data(item_id, webpage)
3485 self._extract_alerts(data, expected=True)
3486 if data.get('contents') or data.get('currentVideoEndpoint'):
3488 if count >= retries:
3489 raise ExtractorError(last_error)
3490 return webpage, data
3492 def _real_extract(self, url):
3493 item_id = self._match_id(url)
3494 url = compat_urlparse.urlunparse(
3495 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
3496 compat_opts = self._downloader.params.get('compat_opts', [])
3498 # This is not matched in a channel page with a tab selected
3499 mobj = re.match(r'(?P<pre>%s)(?P<post>/?(?![^#?]).*$)' % self._VALID_URL, url)
3500 mobj = mobj.groupdict() if mobj else {}
3501 if mobj and not mobj.get('not_channel') and 'no-youtube-channel-redirect' not in compat_opts:
3502 self.report_warning(
3503 'A channel/user page was given. All the channel\'s videos will be downloaded. '
3504 'To download only the videos in the home page, add a "/featured" to the URL')
3505 url = '%s/videos%s' % (mobj.get('pre'), mobj.get('post') or '')
3507 # Handle both video/playlist URLs
3509 video_id = qs.get('v', [None])[0]
3510 playlist_id = qs.get('list', [None])[0]
3512 if not video_id and (mobj.get('not_channel') or '').startswith('watch'):
3514 # If there is neither video or playlist ids,
3515 # youtube redirects to home page, which is undesirable
3516 raise ExtractorError('Unable to recognize tab page')
3517 self.report_warning('A video URL was given without video ID. Trying to download playlist %s' % playlist_id)
3518 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
3520 if video_id and playlist_id:
3521 if self._downloader.params.get('noplaylist'):
3522 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3523 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
3524 self.to_screen('Downloading playlist %s; add --no-playlist to just download video %s' % (playlist_id, video_id))
3526 webpage, data = self._extract_webpage(url, item_id)
3528 # YouTube sometimes provides a button to reload playlist with unavailable videos.
3529 if 'no-youtube-unavailable-videos' not in compat_opts:
3530 data = self._reload_with_unavailable_videos(item_id, data, webpage) or data
3533 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
3535 return self._extract_from_tabs(item_id, webpage, data, tabs)
3538 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
3540 return self._extract_from_playlist(item_id, url, data, playlist, webpage)
3543 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
3544 compat_str) or video_id
3546 self.report_warning('Unable to recognize playlist. Downloading just video %s' % video_id)
3547 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
3549 raise ExtractorError('Unable to recognize tab page')
3552 class YoutubePlaylistIE(InfoExtractor):
3553 IE_DESC = 'YouTube.com playlists'
3554 _VALID_URL = r'''(?x
)(?
:
3559 youtube(?
:kids
)?\
.com|
3564 (?P
<id>%(playlist_id)s)
3565 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
3566 IE_NAME = 'youtube:playlist'
3568 'note': 'issue #673',
3569 'url': 'PLBB231211A4F62143',
3571 'title': '[OLD]Team Fortress 2 (Class-based LP)',
3572 'id': 'PLBB231211A4F62143',
3573 'uploader': 'Wickydoo',
3574 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
3576 'playlist_mincount': 29,
3578 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
3580 'title': 'YDL_safe_search',
3581 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
3583 'playlist_count': 2,
3584 'skip': 'This playlist is private',
3587 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
3588 'playlist_count': 4,
3591 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
3592 'uploader': 'milan',
3593 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
3596 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
3597 'playlist_mincount': 982,
3599 'title': '2018 Chinese New Singles (11/6 updated)',
3600 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
3602 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
3605 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
3606 'only_matching': True,
3608 # music album playlist
3609 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
3610 'only_matching': True,
3614 def suitable(cls, url):
3615 if YoutubeTabIE.suitable(url):
3617 # Hack for lazy extractors until more generic solution is implemented
3619 from .youtube import parse_qs
3621 if qs.get('v', [None])[0]:
3623 return super(YoutubePlaylistIE, cls).suitable(url)
3625 def _real_extract(self, url):
3626 playlist_id = self._match_id(url)
3629 qs = {'list': playlist_id}
3630 return self.url_result(
3631 update_url_query('https://www.youtube.com/playlist', qs),
3632 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3635 class YoutubeYtBeIE(InfoExtractor):
3636 IE_DESC = 'youtu.be'
3637 _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}
3639 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
3641 'id': 'yeWKywCrFtk',
3643 'title': 'Small Scale Baler and Braiding Rugs',
3644 'uploader': 'Backus-Page House Museum',
3645 'uploader_id': 'backuspagemuseum',
3646 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
3647 'upload_date': '20161008',
3648 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
3649 'categories': ['Nonprofits & Activism'],
3652 'dislike_count': int,
3656 'skip_download': True,
3659 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
3660 'only_matching': True,
3663 def _real_extract(self, url):
3664 mobj = re.match(self._VALID_URL, url)
3665 video_id = mobj.group('id')
3666 playlist_id = mobj.group('playlist_id')
3667 return self.url_result(
3668 update_url_query('https://www.youtube.com/watch', {
3670 'list': playlist_id,
3671 'feature': 'youtu.be',
3672 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3675 class YoutubeYtUserIE(InfoExtractor):
3676 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
3677 _VALID_URL = r'ytuser:(?P<id>.+)'
3679 'url': 'ytuser:phihag',
3680 'only_matching': True,
3683 def _real_extract(self, url):
3684 user_id = self._match_id(url)
3685 return self.url_result(
3686 'https://www.youtube.com/user/%s' % user_id,
3687 ie=YoutubeTabIE.ie_key(), video_id=user_id)
3690 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3691 IE_NAME = 'youtube:favorites'
3692 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
3693 _VALID_URL = r':ytfav(?:ou?rite)?s?'
3694 _LOGIN_REQUIRED = True
3697 'only_matching': True,
3699 'url': ':ytfavorites',
3700 'only_matching': True,
3703 def _real_extract(self, url):
3704 return self.url_result(
3705 'https://www.youtube.com/playlist?list=LL',
3706 ie=YoutubeTabIE.ie_key())
3709 class YoutubeSearchIE(SearchInfoExtractor, YoutubeTabIE):
3710 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
3711 # there doesn't appear to be a real limit, for example if you search for
3712 # 'python' you get more than 8.000.000 results
3713 _MAX_RESULTS = float('inf')
3714 IE_NAME = 'youtube:search'
3715 _SEARCH_KEY = 'ytsearch'
3716 _SEARCH_PARAMS = None
3719 def _entries(self, query, n):
3720 data = {'query': query}
3721 if self._SEARCH_PARAMS:
3722 data['params'] = self._SEARCH_PARAMS
3724 for page_num in itertools.count(1):
3725 search = self._extract_response(
3726 item_id='query "%s" page %s' % (query, page_num), ep='search', query=data,
3727 check_get_keys=('contents', 'onResponseReceivedCommands')
3731 slr_contents = try_get(
3733 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
3734 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
3736 if not slr_contents:
3739 # Youtube sometimes adds promoted content to searches,
3740 # changing the index location of videos and token.
3741 # So we search through all entries till we find them.
3742 continuation_token = None
3743 for slr_content in slr_contents:
3744 if continuation_token is None:
3745 continuation_token = try_get(
3747 lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
3750 isr_contents = try_get(
3752 lambda x: x['itemSectionRenderer']['contents'],
3754 if not isr_contents:
3756 for content in isr_contents:
3757 if not isinstance(content, dict):
3759 video = content.get('videoRenderer')
3760 if not isinstance(video, dict):
3762 video_id = video.get('videoId')
3766 yield self._extract_video(video)
3771 if not continuation_token:
3773 data['continuation'] = continuation_token
3775 def _get_n_results(self, query, n):
3776 """Get a specified number of results for a query"""
3777 return self.playlist_result(self._entries(query, n), query)
3780 class YoutubeSearchDateIE(YoutubeSearchIE):
3781 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3782 _SEARCH_KEY = 'ytsearchdate'
3783 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
3784 _SEARCH_PARAMS = 'CAI%3D'
3787 class YoutubeSearchURLIE(YoutubeSearchIE):
3788 IE_DESC = 'YouTube.com search URLs'
3789 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
3790 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3791 # _MAX_RESULTS = 100
3793 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3794 'playlist_mincount': 5,
3796 'title': 'youtube-dl test video',
3799 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3800 'only_matching': True,
3804 def _make_valid_url(cls):
3805 return cls._VALID_URL
3807 def _real_extract(self, url):
3808 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
3809 query = (qs.get('search_query') or qs.get('q'))[0]
3810 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
3811 return self._get_n_results(query, self._MAX_RESULTS)
3814 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
3816 Base class for feed extractors
3817 Subclasses must define the _FEED_NAME property.
3819 _LOGIN_REQUIRED = True
3824 return 'youtube:%s' % self._FEED_NAME
3826 def _real_initialize(self):
3829 def _real_extract(self, url):
3830 return self.url_result(
3831 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3832 ie=YoutubeTabIE.ie_key())
3835 class YoutubeWatchLaterIE(InfoExtractor):
3836 IE_NAME = 'youtube:watchlater'
3837 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3838 _VALID_URL = r':ytwatchlater'
3840 'url': ':ytwatchlater',
3841 'only_matching': True,
3844 def _real_extract(self, url):
3845 return self.url_result(
3846 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3849 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3850 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3851 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
3852 _FEED_NAME = 'recommended'
3855 'only_matching': True,
3857 'url': ':ytrecommended',
3858 'only_matching': True,
3860 'url': 'https://youtube.com',
3861 'only_matching': True,
3865 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3866 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
3867 _VALID_URL = r':ytsub(?:scription)?s?'
3868 _FEED_NAME = 'subscriptions'
3871 'only_matching': True,
3873 'url': ':ytsubscriptions',
3874 'only_matching': True,
3878 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3879 IE_DESC = 'Youtube watch history, ":ythis" for short (requires authentication)'
3880 _VALID_URL = r':ythis(?:tory)?'
3881 _FEED_NAME = 'history'
3883 'url': ':ythistory',
3884 'only_matching': True,
3888 class YoutubeTruncatedURLIE(InfoExtractor):
3889 IE_NAME = 'youtube:truncated_url'
3890 IE_DESC = False # Do not list
3891 _VALID_URL = r'''(?x
)
3893 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3896 annotation_id
=annotation_
[^
&]+|
3902 attribution_link
\?a
=[^
&]+
3908 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3909 'only_matching': True,
3911 'url': 'https://www.youtube.com/watch?',
3912 'only_matching': True,
3914 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3915 'only_matching': True,
3917 'url': 'https://www.youtube.com/watch?feature=foo',
3918 'only_matching': True,
3920 'url': 'https://www.youtube.com/watch?hl=en-GB',
3921 'only_matching': True,
3923 'url': 'https://www.youtube.com/watch?t=2372',
3924 'only_matching': True,
3927 def _real_extract(self, url):
3928 raise ExtractorError(
3929 'Did you forget to quote the URL? Remember that & is a meta '
3930 'character in most shells, so you want to put the URL in quotes, '
3932 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3933 ' or simply youtube-dl BaW_jenozKc .',
3937 class YoutubeTruncatedIDIE(InfoExtractor):
3938 IE_NAME = 'youtube:truncated_id'
3939 IE_DESC = False # Do not list
3940 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3943 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3944 'only_matching': True,
3947 def _real_extract(self, url):
3948 video_id = self._match_id(url)
3949 raise ExtractorError(
3950 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),