3 from __future__
import unicode_literals
13 from .common
import InfoExtractor
, SearchInfoExtractor
14 from ..compat
import (
20 compat_urllib_parse_unquote_plus
,
21 compat_urllib_parse_urlencode
,
22 compat_urllib_parse_urlparse
,
25 from ..jsinterp
import JSInterpreter
51 class YoutubeBaseInfoExtractor(InfoExtractor
):
52 """Provide base functions for Youtube extractors"""
53 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
54 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
56 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
57 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
58 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
61 r
'embed|e|watch_popup|channel|c|user|playlist|watch|w|v|movies|results|shared|'
62 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout|'
63 r
'feed/(?:watch_later|history|subscriptions|library|trending|recommended)')
65 _NETRC_MACHINE
= 'youtube'
66 # If True it will raise an error if no login info is provided
67 _LOGIN_REQUIRED
= False
69 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
71 def _ids_to_results(self
, ids
):
73 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
78 Attempt to log in to YouTube.
79 True is returned if successful or skipped.
80 False is returned if login failed.
82 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
84 username
, password
= self
._get
_login
_info
()
85 # No authentication to be performed
87 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
88 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
89 # if self._downloader.params.get('cookiefile'): # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
90 # self.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
93 login_page
= self
._download
_webpage
(
94 self
._LOGIN
_URL
, None,
95 note
='Downloading login page',
96 errnote
='unable to fetch login page', fatal
=False)
97 if login_page
is False:
100 login_form
= self
._hidden
_inputs
(login_page
)
102 def req(url
, f_req
, note
, errnote
):
103 data
= login_form
.copy()
106 'checkConnection': 'youtube',
107 'checkedDomains': 'youtube',
109 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
110 'f.req': json
.dumps(f_req
),
111 'flowName': 'GlifWebSignIn',
112 'flowEntry': 'ServiceLogin',
113 # TODO: reverse actual botguard identifier generation algo
114 'bgRequest': '["identifier",""]',
116 return self
._download
_json
(
117 url
, None, note
=note
, errnote
=errnote
,
118 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
120 data
=urlencode_postdata(data
), headers
={
121 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
122 'Google-Accounts-XSRF': 1,
126 self
._downloader
.report_warning(message
)
130 None, [], None, 'US', None, None, 2, False, True,
134 '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',
136 1, [None, None, []], None, None, None, True
141 lookup_results
= req(
142 self
._LOOKUP
_URL
, lookup_req
,
143 'Looking up account info', 'Unable to look up account info')
145 if lookup_results
is False:
148 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
150 warn('Unable to extract user hash')
155 None, 1, None, [1, None, None, None, [password
, None, True]],
157 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],
158 1, [None, None, []], None, None, None, True
161 challenge_results
= req(
162 self
._CHALLENGE
_URL
, challenge_req
,
163 'Logging in', 'Unable to log in')
165 if challenge_results
is False:
168 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
170 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
172 'Unable to login: %s' % 'Invalid password'
173 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
176 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
178 warn('Unable to extract result entry')
181 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
183 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
184 if challenge_str
== 'TWO_STEP_VERIFICATION':
185 # SEND_SUCCESS - TFA code has been successfully sent to phone
186 # QUOTA_EXCEEDED - reached the limit of TFA codes
187 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
188 if status
== 'QUOTA_EXCEEDED':
189 warn('Exceeded the limit of TFA codes, try later')
192 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
194 warn('Unable to extract TL')
197 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
201 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
202 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
205 tfa_code
= remove_start(tfa_code
, 'G-')
208 user_hash
, None, 2, None,
210 9, None, None, None, None, None, None, None,
211 [None, tfa_code
, True, 2]
215 self
._TFA
_URL
.format(tl
), tfa_req
,
216 'Submitting TFA code', 'Unable to submit TFA code')
218 if tfa_results
is False:
221 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
223 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
225 'Unable to finish TFA: %s' % 'Invalid TFA code'
226 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
229 check_cookie_url
= try_get(
230 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
233 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
234 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
235 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
237 challenge
= CHALLENGES
.get(
239 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
240 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
243 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
245 if not check_cookie_url
:
246 warn('Unable to extract CheckCookie URL')
249 check_cookie_results
= self
._download
_webpage
(
250 check_cookie_url
, None, 'Checking cookie', fatal
=False)
252 if check_cookie_results
is False:
255 if 'https://myaccount.google.com/' not in check_cookie_results
:
256 warn('Unable to log in')
261 def _download_webpage_handle(self
, *args
, **kwargs
):
262 query
= kwargs
.get('query', {}).copy()
263 kwargs
['query'] = query
264 return super(YoutubeBaseInfoExtractor
, self
)._download
_webpage
_handle
(
265 *args
, **compat_kwargs(kwargs
))
267 def _real_initialize(self
):
268 if self
._downloader
is None:
270 if not self
._login
():
273 _DEFAULT_API_DATA
= {
277 'clientVersion': '2.20201021.03.00',
282 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
283 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
284 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
286 def _call_api(self, ep, query, video_id, fatal=True):
287 data = self._DEFAULT_API_DATA.copy()
290 return self._download_json(
291 'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id,
292 note='Downloading API JSON', errnote='Unable to download API page',
293 data=json.dumps(data).encode('utf8'), fatal=fatal,
294 headers={'content-type': 'application/json'},
295 query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'})
297 def _extract_yt_initial_data(self, video_id, webpage):
298 return self._parse_json(
300 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
301 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
304 def _extract_ytcfg(self, video_id, webpage):
305 return self._parse_json(
307 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
308 default='{}'), video_id, fatal=False)
310 def _extract_video(self, renderer):
311 video_id = renderer.get('videoId')
314 (lambda x: x['title']['runs'][0]['text'],
315 lambda x: x['title']['simpleText']), compat_str)
316 description = try_get(
317 renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
319 duration = parse_duration(try_get(
320 renderer, lambda x: x['lengthText']['simpleText'], compat_str))
321 view_count_text = try_get(
322 renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
323 view_count = str_to_int(self._search_regex(
324 r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
325 'view count', default=None))
327 renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
329 '_type': 'url_transparent',
330 'ie_key': YoutubeIE.ie_key(),
334 'description': description,
335 'duration': duration,
336 'view_count': view_count,
337 'uploader': uploader,
341 class YoutubeIE(YoutubeBaseInfoExtractor):
342 IE_DESC = 'YouTube.com'
343 _VALID_URL = r"""(?x)^
345 (?:https?://|//) # http(s):// or protocol-independent URL
346 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
347 (?:www\.)?deturl\.com/www\.youtube\.com/|
348 (?:www\.)?pwnyoutube\.com/|
349 (?:www\.)?hooktube\.com/|
350 (?:www\.)?yourepeat\.com/|
351 tube\.majestyc\.net/|
352 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
353 (?:(?:www|dev)\.)?invidio\.us/|
354 (?:(?:www|no)\.)?invidiou\.sh/|
355 (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
356 (?:www\.)?invidious\.kabi\.tk/|
357 (?:www\.)?invidious\.13ad\.de/|
358 (?:www\.)?invidious\.mastodon\.host/|
359 (?:www\.)?invidious\.zapashcanon\.fr/|
360 (?:www\.)?invidious\.kavin\.rocks/|
361 (?:www\.)?invidious\.tube/|
362 (?:www\.)?invidiou\.site/|
363 (?:www\.)?invidious\.site/|
364 (?:www\.)?invidious\.xyz/|
365 (?:www\.)?invidious\.nixnet\.xyz/|
366 (?:www\.)?invidious\.drycat\.fr/|
367 (?:www\.)?tube\.poal\.co/|
368 (?:www\.)?tube\.connect\.cafe/|
369 (?:www\.)?vid\.wxzm\.sx/|
370 (?:www\.)?vid\.mint\.lgbt/|
371 (?:www\.)?yewtu\.be/|
372 (?:www\.)?yt\.elukerio\.org/|
373 (?:www\.)?yt\.lelux\.fi/|
374 (?:www\.)?invidious\.ggc-project\.de/|
375 (?:www\.)?yt\.maisputain\.ovh/|
376 (?:www\.)?invidious\.13ad\.de/|
377 (?:www\.)?invidious\.toot\.koeln/|
378 (?:www\.)?invidious\.fdn\.fr/|
379 (?:www\.)?watch\.nettohikari\.com/|
380 (?:www\.)?kgg2m7yk5aybusll\.onion/|
381 (?:www\.)?qklhadlycap4cnod\.onion/|
382 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
383 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
384 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
385 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
386 (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
387 (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
388 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
389 (?:.*?\#/)? # handle anchor (#/) redirect urls
390 (?: # the various things that can precede the ID:
391 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
392 |(?: # or the v= param in all its forms
393 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
394 (?:\?|\#!?) # the params delimiter ? or # or #!
395 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
400 youtu\.be| # just youtu.be/xxxx
401 vid\.plus| # or vid.plus/xxxx
402 zwearz\.com/watch| # or zwearz.com/watch/xxxx
404 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
406 )? # all until now is optional -> you can pass the naked ID
407 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
410 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
411 WL # WL are handled by the watch later IE
414 (?(1).+)? # if we found the ID, everything can follow
415 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
417 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.js$',
418 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.js$',
421 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
422 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
423 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
424 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
425 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
426 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
427 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
428 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
429 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
430 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
431 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
432 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
433 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
434 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
435 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
436 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
437 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
438 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
442 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
443 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
444 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
445 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
446 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
447 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
448 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
450 # Apple HTTP Live Streaming
451 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
452 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
453 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
454 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
455 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
456 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
457 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
458 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
461 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
462 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
463 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
464 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
465 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
466 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
467 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
468 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
469 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
470 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
471 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
472 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
475 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
476 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
477 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
478 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
479 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
480 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
481 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
484 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
485 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
486 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
487 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
488 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
489 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
490 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
491 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
492 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
493 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
494 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
495 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
496 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
497 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
498 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
499 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
500 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
501 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
502 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
503 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
504 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
505 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
508 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
509 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
511 # Dash webm audio with opus inside
512 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
513 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
514 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
517 '_rtmp': {'protocol': 'rtmp'},
519 # av01 video only formats sometimes served with "unknown
" codecs
520 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
521 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
522 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
523 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
525 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
532 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
536 'title': 'youtube-dl test video "\'/\\ä↭𝕐
',
537 'uploader
': 'Philipp Hagemeister
',
538 'uploader_id
': 'phihag
',
539 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/user
/phihag
',
540 'channel_id
': 'UCLqxVugv74EIW3VWh2NOa3Q
',
541 'channel_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/channel
/UCLqxVugv74EIW3VWh2NOa3Q
',
542 'upload_date
': '20121002',
543 '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 .',
544 'categories': ['Science & Technology'],
545 'tags': ['youtube-dl'],
549 'dislike_count': int,
555 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
556 'note': 'Embed-only video (#1746)',
560 'upload_date': '20120608',
561 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
562 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
563 'uploader': 'SET India',
564 'uploader_id': 'setindia',
565 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
568 'skip': 'Private video',
571 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
572 'note': 'Use the first video ID in the URL',
576 'title': 'youtube-dl test video "\'/\\ä↭𝕐
',
577 'uploader
': 'Philipp Hagemeister
',
578 'uploader_id
': 'phihag
',
579 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/user
/phihag
',
580 'upload_date
': '20121002',
581 '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 .',
582 'categories': ['Science & Technology'],
583 'tags': ['youtube-dl'],
587 'dislike_count': int,
590 'skip_download': True,
594 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
595 'note': '256k DASH audio (format 141) via DASH manifest',
599 'upload_date': '20121002',
600 'uploader_id': '8KVIDEO',
601 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
603 'uploader': '8KVIDEO',
604 'title': 'UHDTV TEST 8K VIDEO.mp4'
607 'youtube_include_dash_manifest': True,
610 'skip': 'format 141 not served anymore',
612 # DASH manifest with encrypted signature
614 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
618 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
619 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
621 'uploader': 'AfrojackVEVO',
622 'uploader_id': 'AfrojackVEVO',
623 'upload_date': '20131011',
626 'youtube_include_dash_manifest': True,
627 'format': '141/bestaudio[ext=m4a]',
632 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
637 'upload_date': '20100909',
638 'uploader': 'Amazing Atheist',
639 'uploader_id': 'TheAmazingAtheist',
640 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
641 'title': 'Burning Everyone\'s Koran',
642 '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',
645 # Normal age-gate video (embed allowed)
647 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
651 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
652 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
654 'uploader': 'The Witcher',
655 'uploader_id': 'WitcherGame',
656 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
657 'upload_date': '20140605',
661 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
662 # YouTube Red ad is not captured for creator
664 'url': '__2ABJjxzNo',
669 'upload_date': '20100430',
670 'uploader_id': 'deadmau5',
671 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
672 'creator': 'deadmau5',
673 'description': 'md5:6cbcd3a92ce1bc676fc4d6ab4ace2336',
674 'uploader': 'deadmau5',
675 'title': 'Deadmau5 - Some Chords (HD)',
676 'alt_title': 'Some Chords',
678 'expected_warnings': [
679 'DASH manifest missing',
682 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
684 'url': 'lqQg6PlCWgI',
689 'upload_date': '20150827',
690 'uploader_id': 'olympic',
691 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
692 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
693 'uploader': 'Olympic',
694 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
697 'skip_download': 'requires avconv',
702 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
706 'stretched_ratio': 16 / 9.,
708 'upload_date': '20110310',
709 'uploader_id': 'AllenMeow',
710 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
711 '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',
713 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
716 # url_encoded_fmt_stream_map is empty string
718 'url': 'qEJwOuvDf7I',
722 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
724 'upload_date': '20150404',
725 'uploader_id': 'spbelect',
726 'uploader': 'Наблюдатели Петербурга',
729 'skip_download': 'requires avconv',
731 'skip': 'This live event has ended.',
733 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
735 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
739 'title': 'md5:7b81415841e02ecd4313668cde88737a',
740 'description': 'md5:116377fd2963b81ec4ce64b542173306',
742 'upload_date': '20150625',
743 'uploader_id': 'dorappi2000',
744 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
745 'uploader': 'dorappi2000',
746 'formats': 'mincount:31',
748 'skip': 'not actual anymore',
750 # DASH manifest with segment_list
752 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
753 'md5': '8ce563a1d667b599d21064e982ab9e31',
757 'upload_date': '20150501', # According to '<meta itemprop="datePublished
"', but in other places it's 20150510
758 'uploader': 'Airtek',
759 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
760 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
761 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
764 'youtube_include_dash_manifest': True,
765 'format': '135', # bestvideo
767 'skip': 'This live event has ended.',
770 # Multifeed videos (multiple cameras), URL is for Main Camera
771 'url': 'https://www.youtube.com/watch?v=jvGDaLqkpTg',
774 'title': 'Tom Clancy Free Weekend Rainbow Whatever',
775 'description': 'md5:e03b909557865076822aa169218d6a5d',
781 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Main Camera)',
782 'description': 'md5:e03b909557865076822aa169218d6a5d',
784 'upload_date': '20161111',
785 'uploader': 'Team PGP',
786 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
787 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
793 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 2)',
794 'description': 'md5:e03b909557865076822aa169218d6a5d',
796 'upload_date': '20161111',
797 'uploader': 'Team PGP',
798 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
805 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 3)',
806 'description': 'md5:e03b909557865076822aa169218d6a5d',
808 'upload_date': '20161111',
809 'uploader': 'Team PGP',
810 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
811 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
817 'title': 'Tom Clancy Free Weekend Rainbow Whatever (Camera 4)',
818 'description': 'md5:e03b909557865076822aa169218d6a5d',
820 'upload_date': '20161111',
821 'uploader': 'Team PGP',
822 'uploader_id': 'UChORY56LMMETTuGjXaJXvLg',
823 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UChORY56LMMETTuGjXaJXvLg',
827 'skip_download': True,
831 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
832 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
835 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
838 'skip': 'Not multifeed anymore',
841 'url': 'https://vid.plus/FlRa-iH7PGw',
842 'only_matching': True,
845 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
846 'only_matching': True,
849 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
850 # Also tests cut-off URL expansion in video description (see
851 # https://github.com/ytdl-org/youtube-dl/issues/1892,
852 # https://github.com/ytdl-org/youtube-dl/issues/8164)
853 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
857 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
858 'alt_title': 'Dark Walk - Position Music',
859 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
861 'upload_date': '20151119',
862 'uploader_id': 'IronSoulElf',
863 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
864 'uploader': 'IronSoulElf',
865 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
866 'track': 'Dark Walk - Position Music',
867 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
868 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
871 'skip_download': True,
875 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
876 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
877 'only_matching': True,
880 # Video with yt:stretch=17:0
881 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
885 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
886 'description': 'md5:ee18a25c350637c8faff806845bddee9',
887 'upload_date': '20151107',
888 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
889 'uploader': 'CH GAMER DROID',
892 'skip_download': True,
894 'skip': 'This video does not exist.',
897 # Video licensed under Creative Commons
898 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
902 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
903 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
905 'upload_date': '20150127',
906 'uploader_id': 'BerkmanCenter',
907 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
908 'uploader': 'The Berkman Klein Center for Internet & Society',
909 'license': 'Creative Commons Attribution license (reuse allowed)',
912 'skip_download': True,
916 # Channel-like uploader_url
917 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
921 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
922 'description': 'md5:13a2503d7b5904ef4b223aa101628f39',
924 'upload_date': '20151119',
925 'uploader': 'Bernie Sanders',
926 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
927 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
928 'license': 'Creative Commons Attribution license (reuse allowed)',
931 'skip_download': True,
935 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
936 'only_matching': True,
939 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
940 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
941 'only_matching': True,
944 # Rental video preview
945 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
949 'title': 'Piku - Trailer',
950 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
951 'upload_date': '20150811',
952 'uploader': 'FlixMatrix',
953 'uploader_id': 'FlixMatrixKaravan',
954 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
955 'license': 'Standard YouTube License',
958 'skip_download': True,
960 'skip': 'This video is not available.',
963 # YouTube Red video with episode data
964 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
968 'title': 'Isolation - Mind Field (Ep 1)',
969 'description': 'md5:f540112edec5d09fc8cc752d3d4ba3cd',
971 'upload_date': '20170118',
972 'uploader': 'Vsauce',
973 'uploader_id': 'Vsauce',
974 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
975 'series': 'Mind Field',
980 'skip_download': True,
982 'expected_warnings': [
983 'Skipping DASH manifest',
987 # The following content has been identified by the YouTube community
988 # as inappropriate or offensive to some audiences.
989 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
993 'title': 'Race Differences in Intelligence',
994 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
996 'upload_date': '20140124',
997 'uploader': 'New Century Foundation',
998 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
999 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1002 'skip_download': True,
1004 'skip': 'This video has been removed for violating YouTube\'s policy on hate speech.',
1008 'url': '1t24XAntNCY',
1009 'only_matching': True,
1012 # geo restricted to JP
1013 'url': 'sJL6WA-aGkQ',
1014 'only_matching': True,
1017 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1018 'only_matching': True,
1022 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1023 'only_matching': True,
1026 # Video with unsupported adaptive stream type formats
1027 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1029 'id': 'Z4Vy8R84T1U',
1031 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1032 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1034 'upload_date': '20130923',
1035 'uploader': 'Amelia Putri Harwita',
1036 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1037 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1038 'formats': 'maxcount:10',
1041 'skip_download': True,
1042 'youtube_include_dash_manifest': False,
1044 'skip': 'not actual anymore',
1047 # Youtube Music Auto-generated description
1048 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1050 'id': 'MgNrAu2pzNs',
1052 'title': 'Voyeur Girl',
1053 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1054 'upload_date': '20190312',
1055 'uploader': 'Stephen - Topic',
1056 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1057 'artist': 'Stephen',
1058 'track': 'Voyeur Girl',
1059 'album': 'it\'s too much love to know my dear',
1060 'release_date': '20190313',
1061 'release_year': 2019,
1064 'skip_download': True,
1068 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1069 'only_matching': True,
1072 # invalid -> valid video id redirection
1073 'url': 'DJztXj2GPfl',
1075 'id': 'DJztXj2GPfk',
1077 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1078 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1079 'upload_date': '20090125',
1080 'uploader': 'Prochorowka',
1081 'uploader_id': 'Prochorowka',
1082 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1083 'artist': 'Panjabi MC',
1084 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1085 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1088 'skip_download': True,
1090 'skip': 'Video unavailable',
1093 # empty description results in an empty string
1094 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1096 'id': 'x41yOUIvK2k',
1098 'title': 'IMG 3456',
1100 'upload_date': '20170613',
1101 'uploader_id': 'ElevageOrVert',
1102 'uploader': 'ElevageOrVert',
1105 'skip_download': True,
1109 # with '};' inside yt initial data (see [1])
1110 # see [2] for an example with '};' inside ytInitialPlayerResponse
1111 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1112 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1113 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1115 'id': 'CHqg6qOn4no',
1117 'title': 'Part 77 Sort a list of simple types in c#',
1118 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1119 'upload_date': '20130831',
1120 'uploader_id': 'kudvenkat',
1121 'uploader': 'kudvenkat',
1124 'skip_download': True,
1128 # another example of '};' in ytInitialData
1129 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1130 'only_matching': True,
1133 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1134 'only_matching': True,
1137 # Age-gated video only available with authentication (unavailable
1138 # via embed page workaround)
1139 'url': 'XgnwCQzjau8',
1140 'only_matching': True,
1144 def __init__(self, *args, **kwargs):
1145 super(YoutubeIE, self).__init__(*args, **kwargs)
1146 self._code_cache = {}
1147 self._player_cache = {}
1149 def _signature_cache_id(self, example_sig):
1150 """ Return a string representation of a signature """
1151 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1154 def _extract_player_info(cls, player_url):
1155 for player_re in cls._PLAYER_INFO_RE:
1156 id_m = re.search(player_re, player_url)
1160 raise ExtractorError('Cannot identify player %r' % player_url)
1161 return id_m.group('id')
1163 def _extract_signature_function(self, video_id, player_url, example_sig):
1164 player_id = self._extract_player_info(player_url)
1166 # Read from filesystem cache
1167 func_id = 'js_%s_%s' % (
1168 player_id, self._signature_cache_id(example_sig))
1169 assert os.path.basename(func_id) == func_id
1171 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1172 if cache_spec is not None:
1173 return lambda s: ''.join(s[i] for i in cache_spec)
1175 if player_id not in self._code_cache:
1176 self._code_cache[player_id] = self._download_webpage(
1177 player_url, video_id,
1178 note='Downloading player ' + player_id,
1179 errnote='Download of %s failed' % player_url)
1180 code = self._code_cache[player_id]
1181 res = self._parse_sig_js(code)
1183 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1184 cache_res = res(test_string)
1185 cache_spec = [ord(c) for c in cache_res]
1187 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1190 def _print_sig_code(self, func, example_sig):
1191 def gen_sig_code(idxs):
1192 def _genslice(start, end, step):
1193 starts = '' if start == 0 else str(start)
1194 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1195 steps = '' if step == 1 else (':%d' % step)
1196 return 's[%s%s%s]' % (starts, ends, steps)
1199 # Quelch pyflakes warnings - start will be set when step is set
1200 start = '(Never used)'
1201 for i, prev in zip(idxs[1:], idxs[:-1]):
1202 if step is not None:
1203 if i - prev == step:
1205 yield _genslice(start, prev, step)
1208 if i - prev in [-1, 1]:
1213 yield 's[%d]' % prev
1217 yield _genslice(start, i, step)
1219 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1220 cache_res = func(test_string)
1221 cache_spec = [ord(c) for c in cache_res]
1222 expr_code = ' + '.join(gen_sig_code(cache_spec))
1223 signature_id_tuple = '(%s)' % (
1224 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1225 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1226 ' return %s\n') % (signature_id_tuple, expr_code)
1227 self.to_screen('Extracted signature function:\n' + code)
1229 def _parse_sig_js(self, jscode):
1230 funcname = self._search_regex(
1231 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1232 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1233 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\(\s*""\s*\)',
1234 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1236 r'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1237 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1238 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1239 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1240 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1241 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1242 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1243 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1244 jscode, 'Initial JS player signature function name
', group='sig
')
1246 jsi = JSInterpreter(jscode)
1247 initial_function = jsi.extract_function(funcname)
1248 return lambda s: initial_function([s])
1250 def _decrypt_signature(self, s, video_id, player_url):
1251 """Turn the encrypted s field into a working signature"""
1253 if player_url is None:
1254 raise ExtractorError('Cannot decrypt signature without player_url
')
1256 if player_url.startswith('//'):
1257 player_url = 'https
:' + player_url
1258 elif not re.match(r'https?
://', player_url):
1259 player_url = compat_urlparse.urljoin(
1260 'https
://www
.youtube
.com
', player_url)
1262 player_id = (player_url, self._signature_cache_id(s))
1263 if player_id not in self._player_cache:
1264 func = self._extract_signature_function(
1265 video_id, player_url, s
1267 self._player_cache[player_id] = func
1268 func = self._player_cache[player_id]
1269 if self._downloader.params.get('youtube_print_sig_code
'):
1270 self._print_sig_code(func, s)
1272 except Exception as e:
1273 tb = traceback.format_exc()
1274 raise ExtractorError(
1275 'Signature extraction failed
: ' + tb, cause=e)
1277 def _mark_watched(self, video_id, player_response):
1278 playback_url = url_or_none(try_get(
1280 lambda x: x['playbackTracking
']['videostatsPlaybackUrl
']['baseUrl
']))
1281 if not playback_url:
1283 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1284 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1286 # cpn generation algorithm is reverse engineered from base.js.
1287 # In fact it works even with dummy cpn.
1288 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789
-_
'
1289 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1295 playback_url = compat_urlparse.urlunparse(
1296 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1298 self._download_webpage(
1299 playback_url, video_id, 'Marking watched
',
1300 'Unable to mark watched
', fatal=False)
1303 def _extract_urls(webpage):
1304 # Embedded YouTube player
1306 unescapeHTML(mobj.group('url
'))
1307 for mobj in re.finditer(r'''(?x)
1317 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1318 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1321 # lazyYT YouTube embed
1322 entries.extend(list(map(
1324 re.findall(r'class="lazyYT" data
-youtube
-id="([^"]+)"', webpage))))
1326 # Wordpress "YouTube Video Importer
" plugin
1327 matches = re.findall(r'''(?x)<div[^>]+
1328 class=(?P<q1>[\'"])[^
\'"]*\byvii_single_video_player\b[^\'"]*(?P
=q1
)[^
>]+
1329 data
-video_id
=(?P
<q2
>[\'"])([^\'"]+)(?P
=q2
)''', webpage)
1330 entries.extend(m[-1] for m in matches)
1335 def _extract_url(webpage):
1336 urls = YoutubeIE._extract_urls(webpage)
1337 return urls[0] if urls else None
1340 def extract_id(cls, url):
1341 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1343 raise ExtractorError('Invalid URL: %s' % url)
1344 video_id = mobj.group(2)
1347 def _extract_chapters_from_json(self, data, video_id, duration):
1348 chapters_list = try_get(
1350 lambda x: x['playerOverlays']
1351 ['playerOverlayRenderer']
1352 ['decoratedPlayerBarRenderer']
1353 ['decoratedPlayerBarRenderer']
1355 ['chapteredPlayerBarRenderer']
1358 if not chapters_list:
1361 def chapter_time(chapter):
1362 return float_or_none(
1365 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1369 for next_num, chapter in enumerate(chapters_list, start=1):
1370 start_time = chapter_time(chapter)
1371 if start_time is None:
1373 end_time = (chapter_time(chapters_list[next_num])
1374 if next_num < len(chapters_list) else duration)
1375 if end_time is None:
1378 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1381 'start_time': start_time,
1382 'end_time': end_time,
1387 def _extract_yt_initial_variable(self, webpage, regex, video_id, name):
1388 return self._parse_json(self._search_regex(
1389 (r'%s\s*%s' % (regex, self._YT_INITIAL_BOUNDARY_RE),
1390 regex), webpage, name, default='{}'), video_id, fatal=False)
1392 def _real_extract(self, url):
1393 url, smuggled_data = unsmuggle_url(url, {})
1394 video_id = self._match_id(url)
1395 base_url = self.http_scheme() + '//www.youtube.com/'
1396 webpage_url = base_url + 'watch?v=' + video_id
1397 webpage = self._download_webpage(webpage_url, video_id, fatal=False)
1399 player_response = None
1401 player_response = self._extract_yt_initial_variable(
1402 webpage, self._YT_INITIAL_PLAYER_RESPONSE_RE,
1403 video_id, 'initial player response')
1404 if not player_response:
1405 player_response = self._call_api(
1406 'player', {'videoId': video_id}, video_id)
1408 playability_status = player_response.get('playabilityStatus') or {}
1409 if playability_status.get('reason') == 'Sign in to confirm your age':
1410 pr = self._parse_json(try_get(compat_parse_qs(
1411 self._download_webpage(
1412 base_url + 'get_video_info', video_id,
1413 'Refetching age-gated info webpage',
1414 'unable to download video info webpage', query={
1415 'video_id': video_id,
1416 'eurl': 'https://www.youtube.com/embed/' + video_id,
1418 lambda x: x['player_response'][0],
1419 compat_str) or '{}', video_id)
1421 player_response = pr
1423 trailer_video_id = try_get(
1425 lambda x: x['errorScreen']['playerLegacyDesktopYpcTrailerRenderer']['trailerVideoId'],
1427 if trailer_video_id:
1428 return self.url_result(
1429 trailer_video_id, self.ie_key(), trailer_video_id)
1434 return x.get('simpleText') or ''.join([r['text'] for r in x['runs']])
1437 lambda x: self._html_search_meta(x, webpage, default=None)) \
1438 if webpage else lambda x: None
1440 video_details = player_response.get('videoDetails') or {}
1441 microformat = try_get(
1443 lambda x: x['microformat']['playerMicroformatRenderer'],
1445 video_title = video_details.get('title') \
1446 or get_text(microformat.get('title')) \
1447 or search_meta(['og:title', 'twitter:title', 'title'])
1448 video_description = video_details.get('shortDescription')
1450 if not smuggled_data.get('force_singlefeed', False):
1451 if not self._downloader.params.get('noplaylist'):
1452 multifeed_metadata_list = try_get(
1454 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1456 if multifeed_metadata_list:
1459 for feed in multifeed_metadata_list.split(','):
1460 # Unquote should take place before split on comma (,) since textual
1461 # fields may contain comma as well (see
1462 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1463 feed_data = compat_parse_qs(
1464 compat_urllib_parse_unquote_plus(feed))
1466 def feed_entry(name):
1468 feed_data, lambda x: x[name][0], compat_str)
1470 feed_id = feed_entry('id')
1473 feed_title = feed_entry('title')
1476 title += ' (%s)' % feed_title
1478 '_type': 'url_transparent',
1479 'ie_key': 'Youtube',
1481 base_url + 'watch?v=' + feed_data['id'][0],
1482 {'force_singlefeed': True}),
1485 feed_ids.append(feed_id)
1487 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1488 % (', '.join(feed_ids), video_id))
1489 return self.playlist_result(
1490 entries, video_id, video_title, video_description)
1492 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1497 # q = qualities(['tiny', 'small', 'medium', 'large', 'hd720', 'hd1080', 'hd1440', 'hd2160', 'hd2880', 'highres'])
1498 streaming_data = player_response.get('streamingData') or {}
1499 streaming_formats = streaming_data.get('formats') or []
1500 streaming_formats.extend(streaming_data.get('adaptiveFormats') or [])
1501 for fmt in streaming_formats:
1502 if fmt.get('targetDurationSec') or fmt.get('drmFamilies'):
1505 fmt_url = fmt.get('url')
1507 sc = compat_parse_qs(fmt.get('signatureCipher'))
1508 fmt_url = url_or_none(try_get(sc, lambda x: x['url'][0]))
1509 encrypted_sig = try_get(sc, lambda x: x['s'][0])
1510 if not (sc and fmt_url and encrypted_sig):
1515 player_url = self._search_regex(
1516 r'"(?:PLAYER_JS_URL|jsUrl)"\s*:\s*"([^"]+)"',
1517 webpage, 'player URL', fatal=False)
1520 signature = self._decrypt_signature(sc['s'][0], video_id, player_url)
1521 sp = try_get(sc, lambda x: x['sp'][0]) or 'signature'
1522 fmt_url += '&' + sp + '=' + signature
1524 itag = str_or_none(fmt.get('itag'))
1527 quality = fmt.get('quality')
1529 'asr': int_or_none(fmt.get('audioSampleRate')),
1530 'filesize': int_or_none(fmt.get('contentLength')),
1532 'format_note': fmt.get('qualityLabel') or quality,
1533 'fps': int_or_none(fmt.get('fps')),
1534 'height': int_or_none(fmt.get('height')),
1535 # 'quality': q(quality), # This does not correctly reflect the overall quality of the format
1536 'tbr': float_or_none(fmt.get(
1537 'averageBitrate') or fmt.get('bitrate'), 1000),
1539 'width': fmt.get('width'),
1541 mimetype = fmt.get('mimeType')
1544 r'((?:[^/]+)/(?:[^;]+))(?:;\s*codecs="([^"]+)")?', mimetype)
1546 dct['ext'] = mimetype2ext(mobj.group(1))
1547 dct.update(parse_codecs(mobj.group(2)))
1548 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
1549 dct['downloader_options'] = {
1550 # Youtube throttles chunks >~10M
1551 'http_chunk_size': 10485760,
1555 hls_manifest_url = streaming_data.get('hlsManifestUrl')
1556 if hls_manifest_url:
1557 for f in self._extract_m3u8_formats(
1558 hls_manifest_url, video_id, 'mp4', fatal=False):
1559 itag = self._search_regex(
1560 r'/itag/(\d+)', f['url'], 'itag', default=None)
1562 f['format_id'] = itag
1565 if self._downloader.params.get('youtube_include_dash_manifest'):
1566 dash_manifest_url = streaming_data.get('dashManifestUrl')
1567 if dash_manifest_url:
1569 for f in self._extract_mpd_formats(
1570 dash_manifest_url, video_id, fatal=False):
1571 filesize = int_or_none(self._search_regex(
1572 r'/clen/(\d+)', f.get('fragment_base_url')
1573 or f['url'], 'file size', default=None))
1575 f['filesize'] = filesize
1576 dash_formats.append(f)
1577 # Until further investigation prefer DASH formats as non-DASH
1578 # may not be available (see [1])
1579 # 1. https://github.com/ytdl-org/youtube-dl/issues/28070
1581 dash_formats_keys = [f['format_id'] for f in dash_formats]
1582 formats = [f for f in formats if f['format_id'] not in dash_formats_keys]
1583 formats.extend(dash_formats)
1586 if streaming_data.get('licenseInfos'):
1587 raise ExtractorError(
1588 'This video is DRM protected.', expected=True)
1591 lambda x: x['errorScreen']['playerErrorMessageRenderer'],
1593 reason = get_text(pemr.get('reason')) or playability_status.get('reason')
1594 subreason = pemr.get('subreason')
1596 subreason = clean_html(get_text(subreason))
1597 if subreason == 'The uploader has not made this video available in your country.':
1598 countries = microformat.get('availableCountries')
1600 regions_allowed = search_meta('regionsAllowed')
1601 countries = regions_allowed.split(',') if regions_allowed else None
1602 self.raise_geo_restricted(
1603 subreason, countries)
1604 reason += '\n' + subreason
1606 raise ExtractorError(reason, expected=True)
1608 self._sort_formats(formats)
1610 keywords = video_details.get('keywords') or []
1611 if not keywords and webpage:
1613 unescapeHTML(m.group('content'))
1614 for m in re.finditer(self._meta_regex('og:video:tag'), webpage)]
1615 for keyword in keywords:
1616 if keyword.startswith('yt:stretch='):
1617 w, h = keyword.split('=')[1].split(':')
1618 w, h = int(w), int(h)
1622 if f.get('vcodec') != 'none':
1623 f['stretched_ratio'] = ratio
1626 for container in (video_details, microformat):
1627 for thumbnail in (try_get(
1629 lambda x: x['thumbnail']['thumbnails'], list) or []):
1630 thumbnail_url = thumbnail.get('url')
1631 if not thumbnail_url:
1634 'height': int_or_none(thumbnail.get('height')),
1635 'url': thumbnail_url,
1636 'width': int_or_none(thumbnail.get('width')),
1641 thumbnail = search_meta(['og:image', 'twitter:image'])
1643 thumbnails = [{'url': thumbnail}]
1645 category = microformat.get('category') or search_meta('genre')
1646 channel_id = video_details.get('channelId') \
1647 or microformat.get('externalChannelId') \
1648 or search_meta('channelId')
1649 duration = int_or_none(
1650 video_details.get('lengthSeconds')
1651 or microformat.get('lengthSeconds')) \
1652 or parse_duration(search_meta('duration'))
1653 is_live = video_details.get('isLive')
1654 owner_profile_url = microformat.get('ownerProfileUrl')
1658 'title': self._live_title(video_title) if is_live else video_title,
1660 'thumbnails': thumbnails,
1661 'description': video_description,
1662 'upload_date': unified_strdate(
1663 microformat.get('uploadDate')
1664 or search_meta('uploadDate')),
1665 'uploader': video_details['author'],
1666 'uploader_id': self._search_regex(r'/(?:channel|user)/([^/?&#]+)', owner_profile_url, 'uploader id') if owner_profile_url else None,
1667 'uploader_url': owner_profile_url,
1668 'channel_id': channel_id,
1669 'channel_url': 'https://www.youtube.com/channel/' + channel_id if channel_id else None,
1670 'duration': duration,
1671 'view_count': int_or_none(
1672 video_details.get('viewCount')
1673 or microformat.get('viewCount')
1674 or search_meta('interactionCount')),
1675 'average_rating': float_or_none(video_details.get('averageRating')),
1676 'age_limit': 18 if (
1677 microformat.get('isFamilySafe') is False
1678 or search_meta('isFamilyFriendly') == 'false'
1679 or search_meta('og:restrictions:age') == '18+') else 0,
1680 'webpage_url': webpage_url,
1681 'categories': [category] if category else None,
1684 'playable_in_embed': playability_status.get('playableInEmbed'),
1689 lambda x: x['captions']['playerCaptionsTracklistRenderer'], dict)
1692 def process_language(container, base_url, lang_code, query):
1694 for fmt in self._SUBTITLE_FORMATS:
1700 'url': update_url_query(base_url, query),
1702 container[lang_code] = lang_subs
1704 for caption_track in (pctr.get('captionTracks') or []):
1705 base_url = caption_track.get('baseUrl')
1708 if caption_track.get('kind') != 'asr':
1709 lang_code = caption_track.get('languageCode')
1713 subtitles, base_url, lang_code, {})
1715 automatic_captions = {}
1716 for translation_language in (pctr.get('translationLanguages') or []):
1717 translation_language_code = translation_language.get('languageCode')
1718 if not translation_language_code:
1721 automatic_captions, base_url, translation_language_code,
1722 {'tlang': translation_language_code})
1723 info['automatic_captions'] = automatic_captions
1724 info['subtitles'] = subtitles
1726 parsed_url = compat_urllib_parse_urlparse(url)
1727 for component in [parsed_url.fragment, parsed_url.query]:
1728 query = compat_parse_qs(component)
1729 for k, v in query.items():
1730 for d_k, s_ks in [('start', ('start', 't')), ('end', ('end',))]:
1732 if d_k not in info and k in s_ks:
1733 info[d_k] = parse_duration(query[k][0])
1735 # Youtube Music Auto-generated description
1736 if video_description:
1737 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)
1739 release_year = mobj.group('release_year')
1740 release_date = mobj.group('release_date')
1742 release_date = release_date.replace('-', '')
1743 if not release_year:
1744 release_year = release_date[:4]
1746 'album': mobj.group('album'.strip()),
1747 'artist': mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·')),
1748 'track': mobj.group('track').strip(),
1749 'release_date': release_date,
1750 'release_year': int(release_year),
1755 initial_data = self._extract_yt_initial_variable(
1756 webpage, self._YT_INITIAL_DATA_RE, video_id,
1758 if not initial_data:
1759 initial_data = self._call_api(
1760 'next', {'videoId': video_id}, video_id, fatal=False)
1764 # This will error if there is no livechat
1765 initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
1766 info['subtitles']['live_chat'] = [{
1767 'video_id': video_id,
1769 'protocol': 'youtube_live_chat_replay',
1771 except (KeyError, IndexError, TypeError):
1775 chapters = self._extract_chapters_from_json(
1776 initial_data, video_id, duration)
1778 for engagment_pannel in (initial_data.get('engagementPanels') or []):
1780 engagment_pannel, lambda x: x['engagementPanelSectionListRenderer']['content']['macroMarkersListRenderer']['contents'],
1785 def chapter_time(mmlir):
1786 return parse_duration(
1787 get_text(mmlir.get('timeDescription')))
1790 for next_num, content in enumerate(contents, start=1):
1791 mmlir = content.get('macroMarkersListItemRenderer') or {}
1792 start_time = chapter_time(mmlir)
1793 end_time = chapter_time(try_get(
1794 contents, lambda x: x[next_num]['macroMarkersListItemRenderer'])) \
1795 if next_num < len(contents) else duration
1796 if start_time is None or end_time is None:
1799 'start_time': start_time,
1800 'end_time': end_time,
1801 'title': get_text(mmlir.get('title')),
1806 info['chapters'] = chapters
1810 lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'],
1812 for content in contents:
1813 vpir = content.get('videoPrimaryInfoRenderer')
1815 stl = vpir.get('superTitleLink')
1820 lambda x: x['superTitleIcon']['iconType']) == 'LOCATION_PIN':
1821 info['location'] = stl
1823 mobj = re.search(r'(.+?)\s*S(\d+)\s*•\s*E(\d+)', stl)
1826 'series': mobj.group(1),
1827 'season_number': int(mobj.group(2)),
1828 'episode_number': int(mobj.group(3)),
1830 for tlb in (try_get(
1832 lambda x: x['videoActions']['menuRenderer']['topLevelButtons'],
1834 tbr = tlb.get('toggleButtonRenderer') or {}
1835 for getter, regex in [(
1836 lambda x: x['defaultText']['accessibility']['accessibilityData'],
1837 r'(?P<count>[\d,]+)\s*(?P<type>(?:dis)?like)'), ([
1838 lambda x: x['accessibility'],
1839 lambda x: x['accessibilityData']['accessibilityData'],
1840 ], r'(?P<type>(?:dis)?like) this video along with (?P<count>[\d,]+) other people')]:
1841 label = (try_get(tbr, getter, dict) or {}).get('label')
1843 mobj = re.match(regex, label)
1845 info[mobj.group('type') + '_count'] = str_to_int(mobj.group('count'))
1847 sbr_tooltip = try_get(
1848 vpir, lambda x: x['sentimentBar']['sentimentBarRenderer']['tooltip'])
1850 like_count, dislike_count = sbr_tooltip.split(' / ')
1852 'like_count': str_to_int(like_count),
1853 'dislike_count': str_to_int(dislike_count),
1855 vsir = content.get('videoSecondaryInfoRenderer')
1857 info['channel'] = get_text(try_get(
1859 lambda x: x['owner']['videoOwnerRenderer']['title'],
1863 lambda x: x['metadataRowContainer']['metadataRowContainerRenderer']['rows'],
1865 multiple_songs = False
1867 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
1868 multiple_songs = True
1871 mrr = row.get('metadataRowRenderer') or {}
1872 mrr_title = mrr.get('title')
1875 mrr_title = get_text(mrr['title'])
1876 mrr_contents_text = get_text(mrr['contents'][0])
1877 if mrr_title == 'License':
1878 info['license'] = mrr_contents_text
1879 elif not multiple_songs:
1880 if mrr_title == 'Album':
1881 info['album'] = mrr_contents_text
1882 elif mrr_title == 'Artist':
1883 info['artist'] = mrr_contents_text
1884 elif mrr_title == 'Song':
1885 info['track'] = mrr_contents_text
1888 'channel': 'uploader',
1889 'channel_id': 'uploader_id',
1890 'channel_url': 'uploader_url',
1892 for to, frm in fallbacks.items():
1893 if not info.get(to):
1894 info[to] = info.get(frm)
1896 for s_k, d_k in [('artist', 'creator'), ('track', 'alt_title')]:
1901 # get xsrf for annotations or comments
1902 get_annotations = self._downloader.params.get('writeannotations', False)
1903 get_comments = self._downloader.params.get('getcomments', False)
1904 if get_annotations or get_comments:
1906 ytcfg = self._extract_ytcfg(video_id, webpage)
1908 xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
1910 xsrf_token = self._search_regex(
1911 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
1912 webpage, 'xsrf token', group='xsrf_token', fatal=False)
1916 invideo_url = try_get(
1917 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
1918 if xsrf_token and invideo_url:
1919 xsrf_field_name = None
1921 xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
1922 if not xsrf_field_name:
1923 xsrf_field_name = self._search_regex(
1924 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
1925 webpage, 'xsrf field name',
1926 group='xsrf_field_name', default='session_token')
1927 info['annotations'] = self._download_webpage(
1928 self._proto_relative_url(invideo_url),
1929 video_id, note='Downloading annotations',
1930 errnote='Unable to download video annotations', fatal=False,
1931 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
1934 # TODO: Refactor and move to seperate function
1936 expected_video_comment_count = 0
1939 def find_value(html, key, num_chars=2, separator='"'):
1940 pos_begin = html.find(key) + len(key) + num_chars
1941 pos_end = html.find(separator, pos_begin)
1942 return html[pos_begin: pos_end]
1944 def search_dict(partial, key):
1945 if isinstance(partial, dict):
1946 for k, v in partial.items():
1950 for o in search_dict(v, key):
1952 elif isinstance(partial, list):
1954 for o in search_dict(i, key):
1960 ncd = next(search_dict(initial_data, 'nextContinuationData'))
1961 continuations = [ncd['continuation']]
1962 # Handle videos where comments have been disabled entirely
1963 except StopIteration:
1966 def get_continuation(continuation, session_token, replies=False):
1969 'ctoken': continuation,
1972 query['action_get_comment_replies'] = 1
1974 query['action_get_comments'] = 1
1977 content, handle = self._download_webpage_handle(
1978 'https://www.youtube.com/comment_service_ajax',
1981 expected_status=[413],
1982 data=urlencode_postdata({
1983 'session_token': session_token
1988 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0',
1989 'X-YouTube-Client-Name': '1',
1990 'X-YouTube-Client-Version': '2.20201202.06.01'
1994 response_code = handle.getcode()
1995 if (response_code == 200):
1996 return self._parse_json(content, video_id)
1997 if (response_code == 413):
1999 raise ExtractorError('Unexpected HTTP error code: %s' % response_code)
2001 first_continuation = True
2003 self.to_screen('Downloading comments')
2004 while continuations:
2005 continuation = continuations.pop()
2006 comment_response = get_continuation(continuation, xsrf_token)
2007 if not comment_response:
2009 if list(search_dict(comment_response, 'externalErrorMessage')):
2010 raise ExtractorError('Error returned from server: ' + next(search_dict(comment_response, 'externalErrorMessage')))
2012 if 'continuationContents' not in comment_response['response']:
2013 # Something is wrong here. Youtube won't accept this continuation token for some reason and responds with a user satisfaction dialog (error?)
2015 # not sure if this actually helps
2016 if 'xsrf_token' in comment_response:
2017 xsrf_token = comment_response['xsrf_token']
2019 item_section = comment_response['response']['continuationContents']['itemSectionContinuation']
2020 if first_continuation:
2021 expected_video_comment_count = int(item_section['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'].replace(' Comments', '').replace('1 Comment', '1').replace(',', ''))
2022 first_continuation = False
2023 if 'contents' not in item_section:
2024 # continuation returned no comments?
2025 # set an empty array as to not break the for loop
2026 item_section['contents'] = []
2028 for meta_comment in item_section['contents']:
2029 comment = meta_comment['commentThreadRenderer']['comment']['commentRenderer']
2030 video_comments.append({
2031 'id': comment['commentId'],
2032 'text': ''.join([c['text'] for c in comment['contentText']['runs']]),
2033 'time_text': ''.join([c['text'] for c in comment['publishedTimeText']['runs']]),
2034 'author': comment.get('authorText', {}).get('simpleText', ''),
2035 'votes': comment.get('voteCount', {}).get('simpleText', '0'),
2036 'author_thumbnail': comment['authorThumbnail']['thumbnails'][-1]['url'],
2039 if 'replies' not in meta_comment['commentThreadRenderer']:
2042 reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']]
2043 while reply_continuations:
2045 continuation = reply_continuations.pop()
2046 replies_data = get_continuation(continuation, xsrf_token, True)
2047 if not replies_data or 'continuationContents' not in replies_data[1]['response']:
2050 if self._downloader.params.get('verbose', False):
2051 chain_msg = ' (chain %s)' % comment['commentId']
2052 self.to_screen('Comments downloaded: %d of ~%d%s' % (len(video_comments), expected_video_comment_count, chain_msg))
2053 reply_comment_meta = replies_data[1]['response']['continuationContents']['commentRepliesContinuation']
2054 for reply_meta in reply_comment_meta.get('contents', {}):
2055 reply_comment = reply_meta['commentRenderer']
2056 video_comments.append({
2057 'id': reply_comment['commentId'],
2058 'text': ''.join([c['text'] for c in reply_comment['contentText']['runs']]),
2059 'time_text': ''.join([c['text'] for c in reply_comment['publishedTimeText']['runs']]),
2060 'author': reply_comment.get('authorText', {}).get('simpleText', ''),
2061 'votes': reply_comment.get('voteCount', {}).get('simpleText', '0'),
2062 'author_thumbnail': reply_comment['authorThumbnail']['thumbnails'][-1]['url'],
2063 'parent': comment['commentId']
2065 if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0:
2067 reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']]
2069 self.to_screen('Comments downloaded: %d of ~%d' % (len(video_comments), expected_video_comment_count))
2070 if 'continuations' in item_section:
2071 continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']]
2074 self.to_screen('Total comments downloaded: %d of ~%d' % (len(video_comments), expected_video_comment_count))
2076 'comments': video_comments,
2077 'comment_count': expected_video_comment_count
2080 self.mark_watched(video_id, player_response)
2085 class YoutubeTabIE(YoutubeBaseInfoExtractor):
2086 IE_DESC = 'YouTube.com tab'
2087 _VALID_URL = r'''(?x
)
2091 youtube(?
:kids
)?\
.com|
2095 (?
:channel|c|user
)/|
2098 (?
:playlist|watch
)\?.*?
\blist
=
2100 (?
!(?
:%s)\b) # Direct URLs
2103 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
2104 IE_NAME = 'youtube:tab'
2107 # playlists, multipage
2108 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
2109 'playlist_mincount': 94,
2111 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2112 'title': 'Игорь Клейнер - Playlists',
2113 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2116 # playlists, multipage, different order
2117 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2118 'playlist_mincount': 94,
2120 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2121 'title': 'Игорь Клейнер - Playlists',
2122 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2125 # playlists, singlepage
2126 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2127 'playlist_mincount': 4,
2129 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
2130 'title': 'ThirstForScience - Playlists',
2131 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
2134 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
2135 'only_matching': True,
2137 # basic, single video playlist
2138 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2140 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2141 'uploader': 'Sergey M.',
2142 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2143 'title': 'youtube-dl public playlist',
2145 'playlist_count': 1,
2148 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2150 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2151 'uploader': 'Sergey M.',
2152 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2153 'title': 'youtube-dl empty playlist',
2155 'playlist_count': 0,
2158 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
2160 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2161 'title': 'lex will - Home',
2162 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2164 'playlist_mincount': 2,
2167 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
2169 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2170 'title': 'lex will - Videos',
2171 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2173 'playlist_mincount': 975,
2175 # Videos tab, sorted by popular
2176 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
2178 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2179 'title': 'lex will - Videos',
2180 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2182 'playlist_mincount': 199,
2185 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
2187 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2188 'title': 'lex will - Playlists',
2189 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2191 'playlist_mincount': 17,
2194 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
2196 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2197 'title': 'lex will - Community',
2198 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2200 'playlist_mincount': 18,
2203 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
2205 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2206 'title': 'lex will - Channels',
2207 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2209 'playlist_mincount': 138,
2211 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2212 'only_matching': True,
2214 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2215 'only_matching': True,
2217 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2218 'only_matching': True,
2220 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2221 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2223 'title': '29C3: Not my department',
2224 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2225 'uploader': 'Christiaan008',
2226 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
2228 'playlist_count': 96,
2230 'note': 'Large playlist',
2231 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2233 'title': 'Uploads from Cauchemar',
2234 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2235 'uploader': 'Cauchemar',
2236 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
2238 'playlist_mincount': 1123,
2240 # even larger playlist, 8832 videos
2241 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
2242 'only_matching': True,
2244 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2245 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2247 'title': 'Uploads from Interstellar Movie',
2248 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2249 'uploader': 'Interstellar Movie',
2250 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
2252 'playlist_mincount': 21,
2254 # https://github.com/ytdl-org/youtube-dl/issues/21844
2255 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2257 'title': 'Data Analysis with Dr Mike Pound',
2258 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2259 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
2260 'uploader': 'Computerphile',
2262 'playlist_mincount': 11,
2264 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2265 'only_matching': True,
2267 # Playlist URL that does not actually serve a playlist
2268 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2270 'id': 'FqZTN594JQw',
2272 'title': "Smiley's People 01 detective, Adventure Series, Action",
2273 'uploader': 'STREEM',
2274 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2275 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2276 'upload_date': '20150526',
2277 'license': 'Standard YouTube License',
2278 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2279 'categories': ['People & Blogs'],
2283 'dislike_count': int,
2286 'skip_download': True,
2288 'skip': 'This video is not available.',
2289 'add_ie': [YoutubeIE.ie_key()],
2291 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2292 'only_matching': True,
2294 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
2295 'only_matching': True,
2297 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
2299 'id': '9Auq9mYxFEE',
2301 'title': 'Watch Sky News live',
2302 'uploader': 'Sky News',
2303 'uploader_id': 'skynews',
2304 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
2305 'upload_date': '20191102',
2306 'description': 'md5:78de4e1c2359d0ea3ed829678e38b662',
2307 'categories': ['News & Politics'],
2310 'dislike_count': int,
2313 'skip_download': True,
2316 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2318 'id': 'a48o2S1cPoo',
2320 'title': 'The Young Turks - Live Main Show',
2321 'uploader': 'The Young Turks',
2322 'uploader_id': 'TheYoungTurks',
2323 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2324 'upload_date': '20150715',
2325 'license': 'Standard YouTube License',
2326 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2327 'categories': ['News & Politics'],
2328 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2330 'dislike_count': int,
2333 'skip_download': True,
2335 'only_matching': True,
2337 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2338 'only_matching': True,
2340 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2341 'only_matching': True,
2343 'url': 'https://www.youtube.com/feed/trending',
2344 'only_matching': True,
2347 'url': 'https://www.youtube.com/feed/library',
2348 'only_matching': True,
2351 'url': 'https://www.youtube.com/feed/history',
2352 'only_matching': True,
2355 'url': 'https://www.youtube.com/feed/subscriptions',
2356 'only_matching': True,
2359 'url': 'https://www.youtube.com/feed/watch_later',
2360 'only_matching': True,
2362 # no longer available?
2363 'url': 'https://www.youtube.com/feed/recommended',
2364 'only_matching': True,
2366 # inline playlist with not always working continuations
2367 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
2368 'only_matching': True,
2370 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
2371 'only_matching': True,
2373 'url': 'https://www.youtube.com/course',
2374 'only_matching': True,
2376 'url': 'https://www.youtube.com/zsecurity',
2377 'only_matching': True,
2379 'url': 'http://www.youtube.com/NASAgovVideo/videos',
2380 'only_matching': True,
2382 'url': 'https://www.youtube.com/TheYoungTurks/live',
2383 'only_matching': True,
2387 def suitable(cls, url):
2388 return False if YoutubeIE.suitable(url) else super(
2389 YoutubeTabIE, cls).suitable(url)
2391 def _extract_channel_id(self, webpage):
2392 channel_id = self._html_search_meta(
2393 'channelId', webpage, 'channel id', default=None)
2396 channel_url = self._html_search_meta(
2397 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
2398 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
2399 'twitter:app:url:googleplay'), webpage, 'channel url')
2400 return self._search_regex(
2401 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
2402 channel_url, 'channel id')
2405 def _extract_grid_item_renderer(item):
2406 for item_kind in ('Playlist', 'Video', 'Channel'):
2407 renderer = item.get('grid%sRenderer' % item_kind)
2411 def _grid_entries(self, grid_renderer):
2412 for item in grid_renderer['items']:
2413 if not isinstance(item, dict):
2415 renderer = self._extract_grid_item_renderer(item)
2416 if not isinstance(renderer, dict):
2419 renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
2421 playlist_id = renderer.get('playlistId')
2423 yield self.url_result(
2424 'https://www.youtube.com/playlist?list=%s' % playlist_id,
2425 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
2428 video_id = renderer.get('videoId')
2430 yield self._extract_video(renderer)
2432 channel_id = renderer.get('channelId')
2435 renderer, lambda x: x['title']['simpleText'], compat_str)
2436 yield self.url_result(
2437 'https://www.youtube.com/channel/%s' % channel_id,
2438 ie=YoutubeTabIE.ie_key(), video_title=title)
2440 def _shelf_entries_from_content(self, shelf_renderer):
2441 content = shelf_renderer.get('content')
2442 if not isinstance(content, dict):
2444 renderer = content.get('gridRenderer')
2446 # TODO: add support for nested playlists so each shelf is processed
2447 # as separate playlist
2448 # TODO: this includes only first N items
2449 for entry in self._grid_entries(renderer):
2451 renderer = content.get('horizontalListRenderer')
2456 def _shelf_entries(self, shelf_renderer, skip_channels=False):
2458 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
2460 shelf_url = urljoin('https://www.youtube.com', ep)
2462 # Skipping links to another channels, note that checking for
2463 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
2465 if skip_channels and '/channels?' in shelf_url:
2468 shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
2469 yield self.url_result(shelf_url, video_title=title)
2470 # Shelf may not contain shelf URL, fallback to extraction from content
2471 for entry in self._shelf_entries_from_content(shelf_renderer):
2474 def _playlist_entries(self, video_list_renderer):
2475 for content in video_list_renderer['contents']:
2476 if not isinstance(content, dict):
2478 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
2479 if not isinstance(renderer, dict):
2481 video_id = renderer.get('videoId')
2484 yield self._extract_video(renderer)
2486 r""" # Not needed in the new implementation
2487 def _itemSection_entries(self, item_sect_renderer):
2488 for content in item_sect_renderer['contents']:
2489 if not isinstance(content, dict):
2491 renderer = content.get('videoRenderer', {})
2492 if not isinstance(renderer, dict):
2494 video_id = renderer.get('videoId')
2497 yield self._extract_video(renderer)
2500 def _rich_entries(self, rich_grid_renderer):
2502 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
2503 video_id = renderer.get('videoId')
2506 yield self._extract_video(renderer)
2508 def _video_entry(self, video_renderer):
2509 video_id = video_renderer.get('videoId')
2511 return self._extract_video(video_renderer)
2513 def _post_thread_entries(self, post_thread_renderer):
2514 post_renderer = try_get(
2515 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
2516 if not post_renderer:
2519 video_renderer = try_get(
2520 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict)
2523 entry = self._video_entry(video_renderer)
2526 # inline video links
2527 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
2529 if not isinstance(run, dict):
2532 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
2535 if not YoutubeIE.suitable(ep_url):
2537 ep_video_id = YoutubeIE._match_id(ep_url)
2538 if video_id == ep_video_id:
2540 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id)
2542 def _post_thread_continuation_entries(self, post_thread_continuation):
2543 contents = post_thread_continuation.get('contents')
2544 if not isinstance(contents, list):
2546 for content in contents:
2547 renderer = content.get('backstagePostThreadRenderer')
2548 if not isinstance(renderer, dict):
2550 for entry in self._post_thread_entries(renderer):
2554 def _build_continuation_query(continuation, ctp=None):
2556 'ctoken': continuation,
2557 'continuation': continuation,
2564 def _extract_next_continuation_data(renderer):
2565 next_continuation = try_get(
2566 renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict)
2567 if not next_continuation:
2569 continuation = next_continuation.get('continuation')
2570 if not continuation:
2572 ctp = next_continuation.get('clickTrackingParams')
2573 return YoutubeTabIE._build_continuation_query(continuation, ctp)
2576 def _extract_continuation(cls, renderer):
2577 next_continuation = cls._extract_next_continuation_data(renderer)
2578 if next_continuation:
2579 return next_continuation
2580 contents = renderer.get('contents') or renderer.get('items')
2581 if not isinstance(contents, list):
2583 for content in contents:
2584 if not isinstance(content, dict):
2586 continuation_ep = try_get(
2587 content, lambda x: x['continuationItemRenderer']['continuationEndpoint'],
2589 if not continuation_ep:
2591 continuation = try_get(
2592 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
2593 if not continuation:
2595 ctp = continuation_ep.get('clickTrackingParams')
2596 return YoutubeTabIE._build_continuation_query(continuation, ctp)
2598 def _entries(self, tab, identity_token):
2600 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
2601 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
2602 for content in contents:
2603 if not isinstance(content, dict):
2605 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
2607 renderer = content.get('richItemRenderer')
2609 for entry in self._rich_entries(renderer):
2611 continuation_list[0] = self._extract_continuation(parent_renderer)
2613 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
2614 for isr_content in isr_contents:
2615 if not isinstance(isr_content, dict):
2617 renderer = isr_content.get('playlistVideoListRenderer')
2619 for entry in self._playlist_entries(renderer):
2621 continuation_list[0] = self._extract_continuation(renderer)
2623 renderer = isr_content.get('gridRenderer')
2625 for entry in self._grid_entries(renderer):
2627 continuation_list[0] = self._extract_continuation(renderer)
2629 renderer = isr_content.get('shelfRenderer')
2631 is_channels_tab = tab.get('title') == 'Channels'
2632 for entry in self._shelf_entries(renderer, not is_channels_tab):
2635 renderer = isr_content.get('backstagePostThreadRenderer')
2637 for entry in self._post_thread_entries(renderer):
2639 continuation_list[0] = self._extract_continuation(renderer)
2641 renderer = isr_content.get('videoRenderer')
2643 entry = self._video_entry(renderer)
2647 if not continuation_list[0]:
2648 continuation_list[0] = self._extract_continuation(is_renderer)
2650 if not continuation_list[0]:
2651 continuation_list[0] = self._extract_continuation(parent_renderer)
2653 continuation_list = [None] # Python 2 doesnot support nonlocal
2654 tab_content = try_get(tab, lambda x: x['content'], dict)
2658 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
2659 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
2660 for entry in extract_entries(parent_renderer):
2662 continuation = continuation_list[0]
2665 'x-youtube-client-name': '1',
2666 'x-youtube-client-version': '2.20201112.04.01',
2669 headers['x-youtube-identity-token'] = identity_token
2671 for page_num in itertools.count(1):
2672 if not continuation:
2676 while count <= retries:
2678 # Downloading page may result in intermittent 5xx HTTP error
2679 # that is usually worked around with a retry
2680 browse = self._download_json(
2681 'https://www.youtube.com/browse_ajax', None,
2682 'Downloading page %d%s'
2683 % (page_num, ' (retry #%d)' % count if count else ''),
2684 headers=headers, query=continuation)
2686 except ExtractorError as e:
2687 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
2689 if count <= retries:
2694 response = try_get(browse, lambda x: x[1]['response'], dict)
2698 continuation_contents = try_get(
2699 response, lambda x: x['continuationContents'], dict)
2700 if continuation_contents:
2701 continuation_renderer = continuation_contents.get('playlistVideoListContinuation')
2702 if continuation_renderer:
2703 for entry in self._playlist_entries(continuation_renderer):
2705 continuation = self._extract_continuation(continuation_renderer)
2707 continuation_renderer = continuation_contents.get('gridContinuation')
2708 if continuation_renderer:
2709 for entry in self._grid_entries(continuation_renderer):
2711 continuation = self._extract_continuation(continuation_renderer)
2713 continuation_renderer = continuation_contents.get('itemSectionContinuation')
2714 if continuation_renderer:
2715 for entry in self._post_thread_continuation_entries(continuation_renderer):
2717 continuation = self._extract_continuation(continuation_renderer)
2719 continuation_renderer = continuation_contents.get('sectionListContinuation') # for feeds
2720 if continuation_renderer:
2721 continuation_list = [None]
2722 for entry in extract_entries(continuation_renderer):
2724 continuation = continuation_list[0]
2728 'gridPlaylistRenderer': (self._grid_entries, 'items'),
2729 'gridVideoRenderer': (self._grid_entries, 'items'),
2730 'playlistVideoRenderer': (self._playlist_entries, 'contents'),
2731 'itemSectionRenderer': (self._playlist_entries, 'contents'),
2733 continuation_items = try_get(
2734 response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list)
2735 continuation_item = try_get(continuation_items, lambda x: x[0], dict) or {}
2736 video_items_renderer = None
2737 for key, value in continuation_item.items():
2738 if key not in known_renderers:
2740 video_items_renderer = {known_renderers[key][1]: continuation_items}
2741 for entry in known_renderers[key][0](video_items_renderer):
2743 continuation = self._extract_continuation(video_items_renderer)
2745 if video_items_renderer:
2750 def _extract_selected_tab(tabs):
2752 if try_get(tab, lambda x: x['tabRenderer']['selected'], bool):
2753 return tab['tabRenderer']
2755 raise ExtractorError('Unable to find selected tab')
2758 def _extract_uploader(data):
2760 sidebar_renderer = try_get(
2761 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
2762 if sidebar_renderer:
2763 for item in sidebar_renderer:
2764 if not isinstance(item, dict):
2766 renderer = item.get('playlistSidebarSecondaryInfoRenderer')
2767 if not isinstance(renderer, dict):
2770 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
2772 uploader['uploader'] = owner.get('text')
2773 uploader['uploader_id'] = try_get(
2774 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
2775 uploader['uploader_url'] = urljoin(
2776 'https://www.youtube.com/',
2777 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
2778 return {k: v for k, v in uploader.items() if v is not None}
2780 def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
2781 playlist_id = title = description = channel_url = channel_name = channel_id = None
2782 thumbnails_list = tags = []
2784 selected_tab = self._extract_selected_tab(tabs)
2786 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
2788 channel_name = renderer.get('title')
2789 channel_url = renderer.get('channelUrl')
2790 channel_id = renderer.get('externalId')
2794 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
2796 title = renderer.get('title')
2797 description = renderer.get('description', '')
2798 playlist_id = channel_id
2799 tags = renderer.get('keywords', '').split()
2801 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
2804 lambda x: x['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails'],
2809 for t in thumbnails_list:
2810 if not isinstance(t, dict):
2812 thumbnail_url = url_or_none(t.get('url'))
2813 if not thumbnail_url:
2816 'url': thumbnail_url,
2817 'width': int_or_none(t.get('width')),
2818 'height': int_or_none(t.get('height')),
2821 if playlist_id is None:
2822 playlist_id = item_id
2825 title += format_field(selected_tab, 'title', ' - %s')
2828 'playlist_id': playlist_id,
2829 'playlist_title': title,
2830 'playlist_description': description,
2831 'uploader': channel_name,
2832 'uploader_id': channel_id,
2833 'uploader_url': channel_url,
2834 'thumbnails': thumbnails,
2838 metadata.update(self._extract_uploader(data))
2840 'channel': metadata['uploader'],
2841 'channel_id': metadata['uploader_id'],
2842 'channel_url': metadata['uploader_url']})
2843 return self.playlist_result(
2844 self._entries(selected_tab, identity_token),
2847 def _extract_from_playlist(self, item_id, url, data, playlist):
2848 title = playlist.get('title') or try_get(
2849 data, lambda x: x['titleText']['simpleText'], compat_str)
2850 playlist_id = playlist.get('playlistId') or item_id
2851 # Inline playlist rendition continuation does not always work
2852 # at Youtube side, so delegating regular tab-based playlist URL
2853 # processing whenever possible.
2854 playlist_url = urljoin(url, try_get(
2855 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
2857 if playlist_url and playlist_url != url:
2858 return self.url_result(
2859 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
2861 return self.playlist_result(
2862 self._playlist_entries(playlist), playlist_id=playlist_id,
2863 playlist_title=title)
2866 def _extract_alerts(data):
2867 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
2868 if not isinstance(alert_dict, dict):
2870 for renderer in alert_dict:
2871 alert = alert_dict[renderer]
2872 alert_type = alert.get('type')
2875 message = try_get(alert, lambda x: x['text']['simpleText'], compat_str)
2877 yield alert_type, message
2878 for run in try_get(alert, lambda x: x['text']['runs'], list) or []:
2879 message = try_get(run, lambda x: x['text'], compat_str)
2881 yield alert_type, message
2883 def _extract_identity_token(self, webpage, item_id):
2884 ytcfg = self._extract_ytcfg(item_id, webpage)
2886 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
2889 return self._search_regex(
2890 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
2891 'identity token', default=None)
2893 def _real_extract(self, url):
2894 item_id = self._match_id(url)
2895 url = compat_urlparse.urlunparse(
2896 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
2897 is_home = re.match(r'(?P<pre>%s)(?P<post>/?(?![^#?]).*$)' % self._VALID_URL, url)
2898 if is_home is not None and is_home.group('not_channel') is None and item_id != 'feed':
2899 self._downloader.report_warning(
2900 'A channel/user page was given. All the channel\'s videos will be downloaded. '
2901 'To download only the videos in the home page, add a "/featured" to the URL')
2902 url = '%s/videos%s' % (is_home.group('pre'), is_home.group('post') or '')
2904 # Handle both video/playlist URLs
2905 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2906 video_id = qs.get('v', [None])[0]
2907 playlist_id = qs.get('list', [None])[0]
2909 if is_home is not None and is_home.group('not_channel') is not None and is_home.group('not_channel').startswith('watch') and not video_id:
2911 self._downloader.report_warning('%s is not a valid Youtube URL. Trying to download playlist %s' % (url, playlist_id))
2912 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
2913 # return self.url_result(playlist_id, ie=YoutubePlaylistIE.ie_key())
2915 raise ExtractorError('Unable to recognize tab page')
2916 if video_id and playlist_id:
2917 if self._downloader.params.get('noplaylist'):
2918 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2919 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
2920 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2922 webpage = self._download_webpage(url, item_id)
2923 identity_token = self._extract_identity_token(webpage, item_id)
2924 data = self._extract_yt_initial_data(item_id, webpage)
2926 for alert_type, alert_message in self._extract_alerts(data):
2927 if alert_type.lower() == 'error':
2929 self._downloader.report_warning('YouTube said: %s - %s' % ('ERROR', err_msg))
2930 err_msg = alert_message
2932 self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
2934 raise ExtractorError('YouTube said: %s' % err_msg, expected=True)
2936 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
2938 return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token)
2940 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
2942 return self._extract_from_playlist(item_id, url, data, playlist)
2943 # Fallback to video extraction if no playlist alike page is recognized.
2944 # First check for the current video then try the v attribute of URL query.
2946 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
2947 compat_str) or video_id
2949 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
2950 # Failed to recognize
2951 raise ExtractorError('Unable to recognize tab page')
2954 class YoutubePlaylistIE(InfoExtractor):
2955 IE_DESC = 'YouTube.com playlists'
2956 _VALID_URL = r'''(?x
)(?
:
2961 youtube(?
:kids
)?\
.com|
2966 (?P
<id>%(playlist_id)s)
2967 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2968 IE_NAME = 'youtube:playlist'
2970 'note': 'issue #673',
2971 'url': 'PLBB231211A4F62143',
2973 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2974 'id': 'PLBB231211A4F62143',
2975 'uploader': 'Wickydoo',
2976 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
2978 'playlist_mincount': 29,
2980 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2982 'title': 'YDL_safe_search',
2983 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2985 'playlist_count': 2,
2986 'skip': 'This playlist is private',
2989 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2990 'playlist_count': 4,
2993 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2994 'uploader': 'milan',
2995 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2998 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2999 'playlist_mincount': 982,
3001 'title': '2018 Chinese New Singles (11/6 updated)',
3002 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
3004 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
3007 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
3008 'only_matching': True,
3010 # music album playlist
3011 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
3012 'only_matching': True,
3016 def suitable(cls, url):
3017 return False if YoutubeTabIE.suitable(url) else super(
3018 YoutubePlaylistIE, cls).suitable(url)
3020 def _real_extract(self, url):
3021 playlist_id = self._match_id(url)
3022 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
3024 qs = {'list': playlist_id}
3025 return self.url_result(
3026 update_url_query('https://www.youtube.com/playlist', qs),
3027 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3030 class YoutubeYtBeIE(InfoExtractor):
3031 IE_DESC = 'youtu.be'
3032 _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}
3034 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
3036 'id': 'yeWKywCrFtk',
3038 'title': 'Small Scale Baler and Braiding Rugs',
3039 'uploader': 'Backus-Page House Museum',
3040 'uploader_id': 'backuspagemuseum',
3041 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
3042 'upload_date': '20161008',
3043 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
3044 'categories': ['Nonprofits & Activism'],
3047 'dislike_count': int,
3051 'skip_download': True,
3054 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
3055 'only_matching': True,
3058 def _real_extract(self, url):
3059 mobj = re.match(self._VALID_URL, url)
3060 video_id = mobj.group('id')
3061 playlist_id = mobj.group('playlist_id')
3062 return self.url_result(
3063 update_url_query('https://www.youtube.com/watch', {
3065 'list': playlist_id,
3066 'feature': 'youtu.be',
3067 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3070 class YoutubeYtUserIE(InfoExtractor):
3071 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
3072 _VALID_URL = r'ytuser:(?P<id>.+)'
3074 'url': 'ytuser:phihag',
3075 'only_matching': True,
3078 def _real_extract(self, url):
3079 user_id = self._match_id(url)
3080 return self.url_result(
3081 'https://www.youtube.com/user/%s' % user_id,
3082 ie=YoutubeTabIE.ie_key(), video_id=user_id)
3085 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3086 IE_NAME = 'youtube:favorites'
3087 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
3088 _VALID_URL = r':ytfav(?:ou?rite)?s?'
3089 _LOGIN_REQUIRED = True
3092 'only_matching': True,
3094 'url': ':ytfavorites',
3095 'only_matching': True,
3098 def _real_extract(self, url):
3099 return self.url_result(
3100 'https://www.youtube.com/playlist?list=LL',
3101 ie=YoutubeTabIE.ie_key())
3104 class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
3105 IE_DESC = 'YouTube.com searches'
3106 # there doesn't appear to be a real limit, for example if you search for
3107 # 'python' you get more than 8.000.000 results
3108 _MAX_RESULTS = float('inf')
3109 IE_NAME = 'youtube:search'
3110 _SEARCH_KEY = 'ytsearch'
3111 _SEARCH_PARAMS = None
3114 def _entries(self, query, n):
3118 'clientName': 'WEB',
3119 'clientVersion': '2.20201021.03.00',
3124 if self._SEARCH_PARAMS:
3125 data['params'] = self._SEARCH_PARAMS
3127 for page_num in itertools.count(1):
3128 search = self._download_json(
3129 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
3130 video_id='query "%s"' % query,
3131 note='Downloading page %s' % page_num,
3132 errnote='Unable to download API page', fatal=False,
3133 data=json.dumps(data).encode('utf8'),
3134 headers={'content-type': 'application/json'})
3137 slr_contents = try_get(
3139 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
3140 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
3142 if not slr_contents:
3145 # Youtube sometimes adds promoted content to searches,
3146 # changing the index location of videos and token.
3147 # So we search through all entries till we find them.
3148 continuation_token = None
3149 for slr_content in slr_contents:
3150 isr_contents = try_get(
3152 lambda x: x['itemSectionRenderer']['contents'],
3154 if not isr_contents:
3156 for content in isr_contents:
3157 if not isinstance(content, dict):
3159 video = content.get('videoRenderer')
3160 if not isinstance(video, dict):
3162 video_id = video.get('videoId')
3166 yield self._extract_video(video)
3171 if continuation_token is None:
3172 continuation_token = try_get(
3174 lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
3177 if not continuation_token:
3179 data['continuation'] = continuation_token
3181 def _get_n_results(self, query, n):
3182 """Get a specified number of results for a query"""
3183 return self.playlist_result(self._entries(query, n), query)
3186 class YoutubeSearchDateIE(YoutubeSearchIE):
3187 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3188 _SEARCH_KEY = 'ytsearchdate'
3189 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
3190 _SEARCH_PARAMS = 'CAI%3D'
3193 class YoutubeSearchURLIE(YoutubeSearchIE):
3194 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
3195 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
3196 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3197 # _MAX_RESULTS = 100
3199 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3200 'playlist_mincount': 5,
3202 'title': 'youtube-dl test video',
3205 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3206 'only_matching': True,
3210 def _make_valid_url(cls):
3211 return cls._VALID_URL
3213 def _real_extract(self, url):
3214 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
3215 query = (qs.get('search_query') or qs.get('q'))[0]
3216 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
3217 return self._get_n_results(query, self._MAX_RESULTS)
3220 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
3222 Base class for feed extractors
3223 Subclasses must define the _FEED_NAME property.
3225 _LOGIN_REQUIRED = True
3231 return 'youtube:%s' % self._FEED_NAME
3233 def _real_initialize(self):
3236 def _real_extract(self, url):
3237 return self.url_result(
3238 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3239 ie=YoutubeTabIE.ie_key())
3242 class YoutubeWatchLaterIE(InfoExtractor):
3243 IE_NAME = 'youtube:watchlater'
3244 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3245 _VALID_URL = r':ytwatchlater'
3247 'url': ':ytwatchlater',
3248 'only_matching': True,
3251 def _real_extract(self, url):
3252 return self.url_result(
3253 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3256 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3257 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3258 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
3259 _FEED_NAME = 'recommended'
3262 'only_matching': True,
3264 'url': ':ytrecommended',
3265 'only_matching': True,
3267 'url': 'https://youtube.com',
3268 'only_matching': True,
3272 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3273 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
3274 _VALID_URL = r':ytsub(?:scription)?s?'
3275 _FEED_NAME = 'subscriptions'
3278 'only_matching': True,
3280 'url': ':ytsubscriptions',
3281 'only_matching': True,
3285 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3286 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3287 _VALID_URL = r':ythistory'
3288 _FEED_NAME = 'history'
3290 'url': ':ythistory',
3291 'only_matching': True,
3295 class YoutubeTruncatedURLIE(InfoExtractor):
3296 IE_NAME = 'youtube:truncated_url'
3297 IE_DESC = False # Do not list
3298 _VALID_URL = r'''(?x
)
3300 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3303 annotation_id
=annotation_
[^
&]+|
3309 attribution_link
\?a
=[^
&]+
3315 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3316 'only_matching': True,
3318 'url': 'https://www.youtube.com/watch?',
3319 'only_matching': True,
3321 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3322 'only_matching': True,
3324 'url': 'https://www.youtube.com/watch?feature=foo',
3325 'only_matching': True,
3327 'url': 'https://www.youtube.com/watch?hl=en-GB',
3328 'only_matching': True,
3330 'url': 'https://www.youtube.com/watch?t=2372',
3331 'only_matching': True,
3334 def _real_extract(self, url):
3335 raise ExtractorError(
3336 'Did you forget to quote the URL? Remember that & is a meta '
3337 'character in most shells, so you want to put the URL in quotes, '
3339 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3340 ' or simply youtube-dl BaW_jenozKc .',
3344 class YoutubeTruncatedIDIE(InfoExtractor):
3345 IE_NAME = 'youtube:truncated_id'
3346 IE_DESC = False # Do not list
3347 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3350 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3351 'only_matching': True,
3354 def _real_extract(self, url):
3355 video_id = self._match_id(url)
3356 raise ExtractorError(
3357 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),