3 from __future__
import unicode_literals
14 from .common
import InfoExtractor
, SearchInfoExtractor
15 from ..jsinterp
import JSInterpreter
16 from ..swfinterp
import SWFInterpreter
17 from ..compat
import (
22 compat_urllib_parse_unquote
,
23 compat_urllib_parse_unquote_plus
,
24 compat_urllib_parse_urlencode
,
25 compat_urllib_parse_urlparse
,
59 class YoutubeBaseInfoExtractor(InfoExtractor
):
60 """Provide base functions for Youtube extractors"""
61 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
62 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
64 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
65 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
66 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
69 r
'embed|e|watch_popup|channel|c|user|playlist|watch|w|v|movies|results|shared|'
70 r
'storefront|oops|index|account|reporthistory|t/terms|about|upload|signin|logout|'
71 r
'feed/(?:watch_later|history|subscriptions|library|trending|recommended)')
73 _NETRC_MACHINE
= 'youtube'
74 # If True it will raise an error if no login info is provided
75 _LOGIN_REQUIRED
= False
77 _PLAYLIST_ID_RE
= r
'(?:(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}|RDMM|WL|LL|LM)'
79 def _set_language(self
):
81 '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
82 # YouTube sets the expire time to about two months
83 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
85 def _ids_to_results(self
, ids
):
87 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
92 Attempt to log in to YouTube.
93 True is returned if successful or skipped.
94 False is returned if login failed.
96 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
98 username
, password
= self
._get
_login
_info
()
99 # No authentication to be performed
101 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
102 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
103 if self
._downloader
.params
.get('cookiefile') and False: # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
104 self
.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
107 login_page
= self
._download
_webpage
(
108 self
._LOGIN
_URL
, None,
109 note
='Downloading login page',
110 errnote
='unable to fetch login page', fatal
=False)
111 if login_page
is False:
114 login_form
= self
._hidden
_inputs
(login_page
)
116 def req(url
, f_req
, note
, errnote
):
117 data
= login_form
.copy()
120 'checkConnection': 'youtube',
121 'checkedDomains': 'youtube',
123 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
124 'f.req': json
.dumps(f_req
),
125 'flowName': 'GlifWebSignIn',
126 'flowEntry': 'ServiceLogin',
127 # TODO: reverse actual botguard identifier generation algo
128 'bgRequest': '["identifier",""]',
130 return self
._download
_json
(
131 url
, None, note
=note
, errnote
=errnote
,
132 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
134 data
=urlencode_postdata(data
), headers
={
135 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
136 'Google-Accounts-XSRF': 1,
140 self
._downloader
.report_warning(message
)
144 None, [], None, 'US', None, None, 2, False, True,
148 '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',
150 1, [None, None, []], None, None, None, True
155 lookup_results
= req(
156 self
._LOOKUP
_URL
, lookup_req
,
157 'Looking up account info', 'Unable to look up account info')
159 if lookup_results
is False:
162 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
164 warn('Unable to extract user hash')
169 None, 1, None, [1, None, None, None, [password
, None, True]],
171 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],
172 1, [None, None, []], None, None, None, True
175 challenge_results
= req(
176 self
._CHALLENGE
_URL
, challenge_req
,
177 'Logging in', 'Unable to log in')
179 if challenge_results
is False:
182 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
184 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
186 'Unable to login: %s' % 'Invalid password'
187 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
190 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
192 warn('Unable to extract result entry')
195 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
197 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
198 if challenge_str
== 'TWO_STEP_VERIFICATION':
199 # SEND_SUCCESS - TFA code has been successfully sent to phone
200 # QUOTA_EXCEEDED - reached the limit of TFA codes
201 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
202 if status
== 'QUOTA_EXCEEDED':
203 warn('Exceeded the limit of TFA codes, try later')
206 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
208 warn('Unable to extract TL')
211 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
215 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
216 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
219 tfa_code
= remove_start(tfa_code
, 'G-')
222 user_hash
, None, 2, None,
224 9, None, None, None, None, None, None, None,
225 [None, tfa_code
, True, 2]
229 self
._TFA
_URL
.format(tl
), tfa_req
,
230 'Submitting TFA code', 'Unable to submit TFA code')
232 if tfa_results
is False:
235 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
237 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
239 'Unable to finish TFA: %s' % 'Invalid TFA code'
240 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
243 check_cookie_url
= try_get(
244 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
247 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
248 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
249 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
251 challenge
= CHALLENGES
.get(
253 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
254 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
257 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
259 if not check_cookie_url
:
260 warn('Unable to extract CheckCookie URL')
263 check_cookie_results
= self
._download
_webpage
(
264 check_cookie_url
, None, 'Checking cookie', fatal
=False)
266 if check_cookie_results
is False:
269 if 'https://myaccount.google.com/' not in check_cookie_results
:
270 warn('Unable to log in')
275 def _download_webpage_handle(self
, *args
, **kwargs
):
276 query
= kwargs
.get('query', {}).copy()
277 kwargs
['query'] = query
278 return super(YoutubeBaseInfoExtractor
, self
)._download
_webpage
_handle
(
279 *args
, **compat_kwargs(kwargs
))
281 def _real_initialize(self
):
282 if self
._downloader
is None:
285 if not self
._login
():
288 _DEFAULT_API_DATA
= {
292 'clientVersion': '2.20201021.03.00',
297 _YT_INITIAL_DATA_RE
= r
'(?:window\s*\[\s*["\']ytInitialData
["\']\s*\]|ytInitialData)\s*=\s*({.+?})\s*;'
298 _YT_INITIAL_PLAYER_RESPONSE_RE = r'ytInitialPlayerResponse\s*=\s*({.+?})\s*;'
299 _YT_INITIAL_BOUNDARY_RE = r'(?:var\s+meta|</script|\n)'
301 def _call_api(self, ep, query, video_id):
302 data = self._DEFAULT_API_DATA.copy()
305 response = self._download_json(
306 'https://www.youtube.com/youtubei/v1/%s' % ep, video_id=video_id,
307 note='Downloading API JSON', errnote='Unable to download API page',
308 data=json.dumps(data).encode('utf8'),
309 headers={'content-type': 'application/json'},
310 query={'key': 'AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8'})
314 def _extract_yt_initial_data(self, video_id, webpage):
315 return self._parse_json(
317 (r'%s\s*%s' % (self._YT_INITIAL_DATA_RE, self._YT_INITIAL_BOUNDARY_RE),
318 self._YT_INITIAL_DATA_RE), webpage, 'yt initial data'),
321 def _extract_ytcfg(self, video_id, webpage):
322 return self._parse_json(
324 r'ytcfg\.set\s*\(\s*({.+?})\s*\)\s*;', webpage, 'ytcfg',
325 default='{}'), video_id, fatal=False)
327 def _extract_video(self, renderer):
328 video_id = renderer.get('videoId')
331 (lambda x: x['title']['runs'][0]['text'],
332 lambda x: x['title']['simpleText']), compat_str)
333 description = try_get(
334 renderer, lambda x: x['descriptionSnippet']['runs'][0]['text'],
336 duration = parse_duration(try_get(
337 renderer, lambda x: x['lengthText']['simpleText'], compat_str))
338 view_count_text = try_get(
339 renderer, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
340 view_count = str_to_int(self._search_regex(
341 r'^([\d,]+)', re.sub(r'\s', '', view_count_text),
342 'view count', default=None))
344 renderer, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
346 '_type': 'url_transparent',
347 'ie_key': YoutubeIE.ie_key(),
351 'description': description,
352 'duration': duration,
353 'view_count': view_count,
354 'uploader': uploader,
358 class YoutubeIE(YoutubeBaseInfoExtractor):
359 IE_DESC = 'YouTube.com'
360 _VALID_URL = r"""(?x)^
362 (?:https?://|//) # http(s):// or protocol-independent URL
363 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
364 (?:www\.)?deturl\.com/www\.youtube\.com/|
365 (?:www\.)?pwnyoutube\.com/|
366 (?:www\.)?hooktube\.com/|
367 (?:www\.)?yourepeat\.com/|
368 tube\.majestyc\.net/|
369 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
370 (?:(?:www|dev)\.)?invidio\.us/|
371 (?:(?:www|no)\.)?invidiou\.sh/|
372 (?:(?:www|fi)\.)?invidious\.snopyta\.org/|
373 (?:www\.)?invidious\.kabi\.tk/|
374 (?:www\.)?invidious\.13ad\.de/|
375 (?:www\.)?invidious\.mastodon\.host/|
376 (?:www\.)?invidious\.zapashcanon\.fr/|
377 (?:www\.)?invidious\.kavin\.rocks/|
378 (?:www\.)?invidious\.tube/|
379 (?:www\.)?invidiou\.site/|
380 (?:www\.)?invidious\.site/|
381 (?:www\.)?invidious\.xyz/|
382 (?:www\.)?invidious\.nixnet\.xyz/|
383 (?:www\.)?invidious\.drycat\.fr/|
384 (?:www\.)?tube\.poal\.co/|
385 (?:www\.)?tube\.connect\.cafe/|
386 (?:www\.)?vid\.wxzm\.sx/|
387 (?:www\.)?vid\.mint\.lgbt/|
388 (?:www\.)?yewtu\.be/|
389 (?:www\.)?yt\.elukerio\.org/|
390 (?:www\.)?yt\.lelux\.fi/|
391 (?:www\.)?invidious\.ggc-project\.de/|
392 (?:www\.)?yt\.maisputain\.ovh/|
393 (?:www\.)?invidious\.13ad\.de/|
394 (?:www\.)?invidious\.toot\.koeln/|
395 (?:www\.)?invidious\.fdn\.fr/|
396 (?:www\.)?watch\.nettohikari\.com/|
397 (?:www\.)?kgg2m7yk5aybusll\.onion/|
398 (?:www\.)?qklhadlycap4cnod\.onion/|
399 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
400 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
401 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
402 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
403 (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
404 (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
405 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
406 (?:.*?\#/)? # handle anchor (#/) redirect urls
407 (?: # the various things that can precede the ID:
408 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
409 |(?: # or the v= param in all its forms
410 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
411 (?:\?|\#!?) # the params delimiter ? or # or #!
412 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
417 youtu\.be| # just youtu.be/xxxx
418 vid\.plus| # or vid.plus/xxxx
419 zwearz\.com/watch| # or zwearz.com/watch/xxxx
421 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
423 )? # all until now is optional -> you can pass the naked ID
424 (?P<id>[0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
427 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
428 WL # WL are handled by the watch later IE
431 (?(1).+)? # if we found the ID, everything can follow
432 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
433 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
435 r'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$',
436 r'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$',
439 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
440 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
441 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
442 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
443 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
444 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
445 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
446 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
447 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
448 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
449 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
450 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
451 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
452 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
453 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
454 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
455 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
456 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
460 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
461 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
462 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
463 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
464 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
465 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
466 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
468 # Apple HTTP Live Streaming
469 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
470 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
471 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
472 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
473 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
474 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
475 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
476 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
479 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
480 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
481 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
482 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
483 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
484 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
485 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
486 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
487 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
488 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
489 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
490 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
493 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
494 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
495 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
496 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
497 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
498 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
499 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
502 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
503 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
504 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
505 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
506 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
507 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
508 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
509 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
510 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
511 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
512 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
513 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
514 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
515 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
516 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
517 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
518 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
519 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
520 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
521 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
522 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
523 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
526 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
527 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
529 # Dash webm audio with opus inside
530 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
531 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
532 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
535 '_rtmp': {'protocol': 'rtmp'},
537 # av01 video only formats sometimes served with "unknown
" codecs
538 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
539 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
540 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
541 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
543 _SUBTITLE_FORMATS = ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
550 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
554 'title': 'youtube-dl test video "\'/\\ä↭𝕐
',
555 'uploader
': 'Philipp Hagemeister
',
556 'uploader_id
': 'phihag
',
557 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/user
/phihag
',
558 'channel_id
': 'UCLqxVugv74EIW3VWh2NOa3Q
',
559 'channel_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/channel
/UCLqxVugv74EIW3VWh2NOa3Q
',
560 'upload_date
': '20121002',
561 '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 .',
562 'categories': ['Science & Technology'],
563 'tags': ['youtube-dl'],
567 'dislike_count': int,
573 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
574 'note': 'Embed-only video (#1746)',
578 'upload_date': '20120608',
579 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
580 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
581 'uploader': 'SET India',
582 'uploader_id': 'setindia',
583 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
588 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=yZIXLfi8CZQ',
589 'note': 'Use the first video ID in the URL',
593 'title': 'youtube-dl test video "\'/\\ä↭𝕐
',
594 'uploader
': 'Philipp Hagemeister
',
595 'uploader_id
': 'phihag
',
596 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/user
/phihag
',
597 'upload_date
': '20121002',
598 '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 .',
599 'categories': ['Science & Technology'],
600 'tags': ['youtube-dl'],
604 'dislike_count': int,
607 'skip_download': True,
611 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
612 'note': '256k DASH audio (format 141) via DASH manifest',
616 'upload_date': '20121002',
617 'uploader_id': '8KVIDEO',
618 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
620 'uploader': '8KVIDEO',
621 'title': 'UHDTV TEST 8K VIDEO.mp4'
624 'youtube_include_dash_manifest': True,
627 'skip': 'format 141 not served anymore',
629 # DASH manifest with encrypted signature
631 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
635 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
636 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
638 'uploader': 'AfrojackVEVO',
639 'uploader_id': 'AfrojackVEVO',
640 'upload_date': '20131011',
643 'youtube_include_dash_manifest': True,
644 'format': '141/bestaudio[ext=m4a]',
649 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
654 'upload_date': '20100909',
655 'uploader': 'Amazing Atheist',
656 'uploader_id': 'TheAmazingAtheist',
657 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
658 'title': 'Burning Everyone\'s Koran',
659 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\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',
662 # Normal age-gate video (embed allowed)
664 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
668 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
669 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
671 'uploader': 'The Witcher',
672 'uploader_id': 'WitcherGame',
673 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
674 'upload_date': '20140605',
678 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
679 # YouTube Red ad is not captured for creator
681 'url': '__2ABJjxzNo',
686 'upload_date': '20100430',
687 'uploader_id': 'deadmau5',
688 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
689 'creator': 'Dada Life, deadmau5',
690 'description': 'md5:12c56784b8032162bb936a5f76d55360',
691 'uploader': 'deadmau5',
692 'title': 'Deadmau5 - Some Chords (HD)',
693 'alt_title': 'This Machine Kills Some Chords',
695 'expected_warnings': [
696 'DASH manifest missing',
699 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
701 'url': 'lqQg6PlCWgI',
706 'upload_date': '20150827',
707 'uploader_id': 'olympic',
708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
709 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
710 'uploader': 'Olympic',
711 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
714 'skip_download': 'requires avconv',
719 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
723 'stretched_ratio': 16 / 9.,
725 'upload_date': '20110310',
726 'uploader_id': 'AllenMeow',
727 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
728 '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',
730 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
733 # url_encoded_fmt_stream_map is empty string
735 'url': 'qEJwOuvDf7I',
739 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
741 'upload_date': '20150404',
742 'uploader_id': 'spbelect',
743 'uploader': 'Наблюдатели Петербурга',
746 'skip_download': 'requires avconv',
748 'skip': 'This live event has ended.',
750 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
752 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
756 'title': 'md5:7b81415841e02ecd4313668cde88737a',
757 'description': 'md5:116377fd2963b81ec4ce64b542173306',
759 'upload_date': '20150625',
760 'uploader_id': 'dorappi2000',
761 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
762 'uploader': 'dorappi2000',
763 'formats': 'mincount:31',
765 'skip': 'not actual anymore',
767 # DASH manifest with segment_list
769 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
770 'md5': '8ce563a1d667b599d21064e982ab9e31',
774 'upload_date': '20150501', # According to '<meta itemprop="datePublished
"', but in other places it's 20150510
775 'uploader': 'Airtek',
776 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
777 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
778 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
781 'youtube_include_dash_manifest': True,
782 'format': '135', # bestvideo
784 'skip': 'This live event has ended.',
787 # Multifeed videos (multiple cameras), URL is for Main Camera
788 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
791 'title': 'teamPGP: Rocket League Noob Stream',
792 'description': 'md5:dc7872fb300e143831327f1bae3af010',
798 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
799 'description': 'md5:dc7872fb300e143831327f1bae3af010',
801 'upload_date': '20150721',
802 'uploader': 'Beer Games Beer',
803 'uploader_id': 'beergamesbeer',
804 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
805 'license': 'Standard YouTube License',
811 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
812 'description': 'md5:dc7872fb300e143831327f1bae3af010',
814 'upload_date': '20150721',
815 'uploader': 'Beer Games Beer',
816 'uploader_id': 'beergamesbeer',
817 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
818 'license': 'Standard YouTube License',
824 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
825 'description': 'md5:dc7872fb300e143831327f1bae3af010',
827 'upload_date': '20150721',
828 'uploader': 'Beer Games Beer',
829 'uploader_id': 'beergamesbeer',
830 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
831 'license': 'Standard YouTube License',
837 'title': 'teamPGP: Rocket League Noob Stream (zim)',
838 'description': 'md5:dc7872fb300e143831327f1bae3af010',
840 'upload_date': '20150721',
841 'uploader': 'Beer Games Beer',
842 'uploader_id': 'beergamesbeer',
843 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
844 'license': 'Standard YouTube License',
848 'skip_download': True,
850 'skip': 'This video is not available.',
853 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
854 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
857 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
860 'skip': 'Not multifeed anymore',
863 'url': 'https://vid.plus/FlRa-iH7PGw',
864 'only_matching': True,
867 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
868 'only_matching': True,
871 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
872 # Also tests cut-off URL expansion in video description (see
873 # https://github.com/ytdl-org/youtube-dl/issues/1892,
874 # https://github.com/ytdl-org/youtube-dl/issues/8164)
875 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
879 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
880 'alt_title': 'Dark Walk - Position Music',
881 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
883 'upload_date': '20151119',
884 'uploader_id': 'IronSoulElf',
885 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
886 'uploader': 'IronSoulElf',
887 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
888 'track': 'Dark Walk - Position Music',
889 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
890 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
893 'skip_download': True,
897 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
898 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
899 'only_matching': True,
902 # Video with yt:stretch=17:0
903 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
907 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
908 'description': 'md5:ee18a25c350637c8faff806845bddee9',
909 'upload_date': '20151107',
910 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
911 'uploader': 'CH GAMER DROID',
914 'skip_download': True,
916 'skip': 'This video does not exist.',
919 # Video licensed under Creative Commons
920 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
924 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
925 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
927 'upload_date': '20150127',
928 'uploader_id': 'BerkmanCenter',
929 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
930 'uploader': 'The Berkman Klein Center for Internet & Society',
931 'license': 'Creative Commons Attribution license (reuse allowed)',
934 'skip_download': True,
938 # Channel-like uploader_url
939 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
943 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
944 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
946 'upload_date': '20151119',
947 'uploader': 'Bernie Sanders',
948 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
949 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
950 'license': 'Creative Commons Attribution license (reuse allowed)',
953 'skip_download': True,
957 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
958 'only_matching': True,
961 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
962 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
963 'only_matching': True,
966 # Rental video preview
967 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
971 'title': 'Piku - Trailer',
972 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
973 'upload_date': '20150811',
974 'uploader': 'FlixMatrix',
975 'uploader_id': 'FlixMatrixKaravan',
976 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
977 'license': 'Standard YouTube License',
980 'skip_download': True,
982 'skip': 'This video is not available.',
985 # YouTube Red video with episode data
986 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
990 'title': 'Isolation - Mind Field (Ep 1)',
991 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
993 'upload_date': '20170118',
994 'uploader': 'Vsauce',
995 'uploader_id': 'Vsauce',
996 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
997 'series': 'Mind Field',
1002 'skip_download': True,
1004 'expected_warnings': [
1005 'Skipping DASH manifest',
1009 # The following content has been identified by the YouTube community
1010 # as inappropriate or offensive to some audiences.
1011 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1013 'id': '6SJNVb0GnPI',
1015 'title': 'Race Differences in Intelligence',
1016 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1018 'upload_date': '20140124',
1019 'uploader': 'New Century Foundation',
1020 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1021 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1024 'skip_download': True,
1029 'url': '1t24XAntNCY',
1030 'only_matching': True,
1033 # geo restricted to JP
1034 'url': 'sJL6WA-aGkQ',
1035 'only_matching': True,
1038 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1039 'only_matching': True,
1043 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1044 'only_matching': True,
1047 # Video with unsupported adaptive stream type formats
1048 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1050 'id': 'Z4Vy8R84T1U',
1052 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1053 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1055 'upload_date': '20130923',
1056 'uploader': 'Amelia Putri Harwita',
1057 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1058 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1059 'formats': 'maxcount:10',
1062 'skip_download': True,
1063 'youtube_include_dash_manifest': False,
1065 'skip': 'not actual anymore',
1068 # Youtube Music Auto-generated description
1069 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1071 'id': 'MgNrAu2pzNs',
1073 'title': 'Voyeur Girl',
1074 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1075 'upload_date': '20190312',
1076 'uploader': 'Stephen - Topic',
1077 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1078 'artist': 'Stephen',
1079 'track': 'Voyeur Girl',
1080 'album': 'it\'s too much love to know my dear',
1081 'release_date': '20190313',
1082 'release_year': 2019,
1085 'skip_download': True,
1089 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1090 'only_matching': True,
1093 # invalid -> valid video id redirection
1094 'url': 'DJztXj2GPfl',
1096 'id': 'DJztXj2GPfk',
1098 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1099 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1100 'upload_date': '20090125',
1101 'uploader': 'Prochorowka',
1102 'uploader_id': 'Prochorowka',
1103 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1104 'artist': 'Panjabi MC',
1105 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1106 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1109 'skip_download': True,
1113 # empty description results in an empty string
1114 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1116 'id': 'x41yOUIvK2k',
1118 'title': 'IMG 3456',
1120 'upload_date': '20170613',
1121 'uploader_id': 'ElevageOrVert',
1122 'uploader': 'ElevageOrVert',
1125 'skip_download': True,
1129 # with '};' inside yt initial data (see [1])
1130 # see [2] for an example with '};' inside ytInitialPlayerResponse
1131 # 1. https://github.com/ytdl-org/youtube-dl/issues/27093
1132 # 2. https://github.com/ytdl-org/youtube-dl/issues/27216
1133 'url': 'https://www.youtube.com/watch?v=CHqg6qOn4no',
1135 'id': 'CHqg6qOn4no',
1137 'title': 'Part 77 Sort a list of simple types in c#',
1138 'description': 'md5:b8746fa52e10cdbf47997903f13b20dc',
1139 'upload_date': '20130831',
1140 'uploader_id': 'kudvenkat',
1141 'uploader': 'kudvenkat',
1144 'skip_download': True,
1148 # another example of '};' in ytInitialData
1149 'url': 'https://www.youtube.com/watch?v=gVfgbahppCY',
1150 'only_matching': True,
1153 'url': 'https://www.youtube.com/watch_popup?v=63RmMXCd_bQ',
1154 'only_matching': True,
1158 def __init__(self, *args, **kwargs):
1159 super(YoutubeIE, self).__init__(*args, **kwargs)
1160 self._player_cache = {}
1162 def report_video_info_webpage_download(self, video_id):
1163 """Report attempt to download video info webpage."""
1164 self.to_screen('%s: Downloading video info webpage' % video_id)
1166 def report_information_extraction(self, video_id):
1167 """Report attempt to extract video information."""
1168 self.to_screen('%s: Extracting video information' % video_id)
1170 def report_unavailable_format(self, video_id, format):
1171 """Report extracted video URL."""
1172 self.to_screen('%s: Format %s not available' % (video_id, format))
1174 def report_rtmp_download(self):
1175 """Indicate the download will use the RTMP protocol."""
1176 self.to_screen('RTMP download detected')
1178 def _signature_cache_id(self, example_sig):
1179 """ Return a string representation of a signature """
1180 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1183 def _extract_player_info(cls, player_url):
1184 for player_re in cls._PLAYER_INFO_RE:
1185 id_m = re.search(player_re, player_url)
1189 raise ExtractorError('Cannot identify player %r' % player_url)
1190 return id_m.group('ext'), id_m.group('id')
1192 def _extract_signature_function(self, video_id, player_url, example_sig):
1193 player_type, player_id = self._extract_player_info(player_url)
1195 # Read from filesystem cache
1196 func_id = '%s_%s_%s' % (
1197 player_type, player_id, self._signature_cache_id(example_sig))
1198 assert os.path.basename(func_id) == func_id
1200 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1201 if cache_spec is not None:
1202 return lambda s: ''.join(s[i] for i in cache_spec)
1205 'Downloading player %s' % player_url
1206 if self._downloader.params.get('verbose') else
1207 'Downloading %s player %s' % (player_type, player_id)
1209 if player_type == 'js':
1210 code = self._download_webpage(
1211 player_url, video_id,
1213 errnote='Download of %s failed' % player_url)
1214 res = self._parse_sig_js(code)
1215 elif player_type == 'swf':
1216 urlh = self._request_webpage(
1217 player_url, video_id,
1219 errnote='Download of %s failed' % player_url)
1221 res = self._parse_sig_swf(code)
1223 assert False, 'Invalid player type %r' % player_type
1225 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1226 cache_res = res(test_string)
1227 cache_spec = [ord(c) for c in cache_res]
1229 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1232 def _print_sig_code(self, func, example_sig):
1233 def gen_sig_code(idxs):
1234 def _genslice(start, end, step):
1235 starts = '' if start == 0 else str(start)
1236 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1237 steps = '' if step == 1 else (':%d' % step)
1238 return 's[%s%s%s]' % (starts, ends, steps)
1241 # Quelch pyflakes warnings - start will be set when step is set
1242 start = '(Never used)'
1243 for i, prev in zip(idxs[1:], idxs[:-1]):
1244 if step is not None:
1245 if i - prev == step:
1247 yield _genslice(start, prev, step)
1250 if i - prev in [-1, 1]:
1255 yield 's[%d]' % prev
1259 yield _genslice(start, i, step)
1261 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1262 cache_res = func(test_string)
1263 cache_spec = [ord(c) for c in cache_res]
1264 expr_code = ' + '.join(gen_sig_code(cache_spec))
1265 signature_id_tuple = '(%s)' % (
1266 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1267 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1268 ' return %s\n') % (signature_id_tuple, expr_code)
1269 self.to_screen('Extracted signature function:\n' + code)
1271 def _parse_sig_js(self, jscode):
1272 funcname = self._search_regex(
1273 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1274 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1275 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\(\s*""\s*\)',
1276 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1278 r'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1279 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1280 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1281 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1282 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1283 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1284 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1285 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1286 jscode, 'Initial JS player signature function name
', group='sig
')
1288 jsi = JSInterpreter(jscode)
1289 initial_function = jsi.extract_function(funcname)
1290 return lambda s: initial_function([s])
1292 def _parse_sig_swf(self, file_contents):
1293 swfi = SWFInterpreter(file_contents)
1294 TARGET_CLASSNAME = 'SignatureDecipher
'
1295 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1296 initial_function = swfi.extract_function(searched_class, 'decipher
')
1297 return lambda s: initial_function([s])
1299 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1300 """Turn the encrypted s field into a working signature"""
1302 if player_url is None:
1303 raise ExtractorError('Cannot decrypt signature without player_url
')
1305 if player_url.startswith('//'):
1306 player_url = 'https
:' + player_url
1307 elif not re.match(r'https?
://', player_url):
1308 player_url = compat_urlparse.urljoin(
1309 'https
://www
.youtube
.com
', player_url)
1311 player_id = (player_url, self._signature_cache_id(s))
1312 if player_id not in self._player_cache:
1313 func = self._extract_signature_function(
1314 video_id, player_url, s
1316 self._player_cache[player_id] = func
1317 func = self._player_cache[player_id]
1318 if self._downloader.params.get('youtube_print_sig_code
'):
1319 self._print_sig_code(func, s)
1321 except Exception as e:
1322 tb = traceback.format_exc()
1323 raise ExtractorError(
1324 'Signature extraction failed
: ' + tb, cause=e)
1326 def _get_subtitles(self, video_id, webpage, has_live_chat_replay):
1328 subs_doc = self._download_xml(
1329 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1330 video_id, note=False)
1331 except ExtractorError as err:
1332 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1336 for track in subs_doc.findall('track
'):
1337 lang = track.attrib['lang_code
']
1338 if lang in sub_lang_list:
1341 for ext in self._SUBTITLE_FORMATS:
1342 params = compat_urllib_parse_urlencode({
1346 'name
': track.attrib['name
'].encode('utf
-8'),
1348 sub_formats.append({
1349 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1352 sub_lang_list[lang] = sub_formats
1353 if has_live_chat_replay:
1354 sub_lang_list['live_chat
'] = [
1356 'video_id
': video_id,
1358 'protocol
': 'youtube_live_chat_replay
',
1361 if not sub_lang_list:
1362 self._downloader.report_warning('video doesn
\'t have subtitles
')
1364 return sub_lang_list
1366 def _get_ytplayer_config(self, video_id, webpage):
1368 # User data may contain arbitrary character sequences that may affect
1369 # JSON extraction with regex, e.g. when '};' is contained the second
1370 # regex won't capture the whole JSON
. Yet working around by trying more
1371 # concrete regex first keeping in mind proper quoted string handling
1372 # to be implemented in future that will replace this workaround (see
1373 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1374 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1375 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1376 r
';ytplayer\.config\s*=\s*({.+?});',
1378 config
= self
._search
_regex
(
1379 patterns
, webpage
, 'ytplayer.config', default
=None)
1381 return self
._parse
_json
(
1382 uppercase_escape(config
), video_id
, fatal
=False)
1384 def _get_automatic_captions(self
, video_id
, player_response
, player_config
):
1385 """We need the webpage for getting the captions url, pass it as an
1386 argument to speed up the process."""
1387 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1388 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1389 if not (player_response
or player_config
):
1390 self
._downloader
.report_warning(err_msg
)
1393 args
= player_config
.get('args') if player_config
else {}
1394 caption_url
= args
.get('ttsurl')
1396 timestamp
= args
['timestamp']
1397 # We get the available subtitles
1398 list_params
= compat_urllib_parse_urlencode({
1403 list_url
= caption_url
+ '&' + list_params
1404 caption_list
= self
._download
_xml
(list_url
, video_id
)
1405 original_lang_node
= caption_list
.find('track')
1406 if original_lang_node
is None:
1407 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1409 original_lang
= original_lang_node
.attrib
['lang_code']
1410 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1413 for lang_node
in caption_list
.findall('target'):
1414 sub_lang
= lang_node
.attrib
['lang_code']
1416 for ext
in self
._SUBTITLE
_FORMATS
:
1417 params
= compat_urllib_parse_urlencode({
1418 'lang': original_lang
,
1422 'kind': caption_kind
,
1424 sub_formats
.append({
1425 'url': caption_url
+ '&' + params
,
1428 sub_lang_list
[sub_lang
] = sub_formats
1429 return sub_lang_list
1431 def make_captions(sub_url
, sub_langs
):
1432 parsed_sub_url
= compat_urllib_parse_urlparse(sub_url
)
1433 caption_qs
= compat_parse_qs(parsed_sub_url
.query
)
1435 for sub_lang
in sub_langs
:
1437 for ext
in self
._SUBTITLE
_FORMATS
:
1439 'tlang': [sub_lang
],
1442 sub_url
= compat_urlparse
.urlunparse(parsed_sub_url
._replace
(
1443 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1444 sub_formats
.append({
1448 captions
[sub_lang
] = sub_formats
1451 # New captions format as of 22.06.2017
1453 renderer
= player_response
['captions']['playerCaptionsTracklistRenderer']
1454 base_url
= renderer
['captionTracks'][0]['baseUrl']
1456 for lang
in renderer
['translationLanguages']:
1457 lang_code
= lang
.get('languageCode')
1459 sub_lang_list
.append(lang_code
)
1460 return make_captions(base_url
, sub_lang_list
)
1462 # Some videos don't provide ttsurl but rather caption_tracks and
1463 # caption_translation_languages (e.g. 20LmZk1hakA)
1464 # Does not used anymore as of 22.06.2017
1465 caption_tracks
= args
['caption_tracks']
1466 caption_translation_languages
= args
['caption_translation_languages']
1467 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1469 for lang
in caption_translation_languages
.split(','):
1470 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1471 sub_lang
= lang_qs
.get('lc', [None])[0]
1473 sub_lang_list
.append(sub_lang
)
1474 return make_captions(caption_url
, sub_lang_list
)
1475 # An extractor error can be raise by the download process if there are
1476 # no automatic captions but there are subtitles
1477 except (KeyError, IndexError, ExtractorError
):
1478 self
._downloader
.report_warning(err_msg
)
1481 def _mark_watched(self
, video_id
, video_info
, player_response
):
1482 playback_url
= url_or_none(try_get(
1484 lambda x
: x
['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1485 video_info
, lambda x
: x
['videostats_playback_base_url'][0]))
1486 if not playback_url
:
1488 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1489 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1491 # cpn generation algorithm is reverse engineered from base.js.
1492 # In fact it works even with dummy cpn.
1493 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1494 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1500 playback_url
= compat_urlparse
.urlunparse(
1501 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1503 self
._download
_webpage
(
1504 playback_url
, video_id
, 'Marking watched',
1505 'Unable to mark watched', fatal
=False)
1508 def _extract_urls(webpage
):
1509 # Embedded YouTube player
1511 unescapeHTML(mobj
.group('url'))
1512 for mobj
in re
.finditer(r
'''(?x)
1522 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1523 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1526 # lazyYT YouTube embed
1527 entries.extend(list(map(
1529 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1531 # Wordpress "YouTube Video Importer" plugin
1532 matches = re.findall(r'''(?x
)<div
[^
>]+
1533 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1534 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1535 entries.extend(m[-1] for m in matches)
1540 def _extract_url(webpage):
1541 urls = YoutubeIE._extract_urls(webpage)
1542 return urls[0] if urls else None
1545 def extract_id(cls, url):
1546 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1548 raise ExtractorError('Invalid URL: %s' % url)
1549 video_id = mobj.group(2)
1552 def _extract_chapters_from_json(self, webpage, video_id, duration):
1555 data = self._extract_yt_initial_data(video_id, webpage)
1556 if not data or not isinstance(data, dict):
1558 chapters_list = try_get(
1560 lambda x: x['playerOverlays']
1561 ['playerOverlayRenderer']
1562 ['decoratedPlayerBarRenderer']
1563 ['decoratedPlayerBarRenderer']
1565 ['chapteredPlayerBarRenderer']
1568 if not chapters_list:
1571 def chapter_time(chapter):
1572 return float_or_none(
1575 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1579 for next_num, chapter in enumerate(chapters_list, start=1):
1580 start_time = chapter_time(chapter)
1581 if start_time is None:
1583 end_time = (chapter_time(chapters_list[next_num])
1584 if next_num < len(chapters_list) else duration)
1585 if end_time is None:
1588 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1591 'start_time': start_time,
1592 'end_time': end_time,
1598 def _extract_chapters_from_description(description, duration):
1601 chapter_lines = re.findall(
1602 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\
.www\
.watch\
.player\
.seekTo
[^
>]+>(\d{1,2}
:\d{1,2}
(?
::\d{1,2}
)?
)</a
>[^
>]*)(?
=$|
<br\s
*/>)',
1604 if not chapter_lines:
1607 for next_num, (chapter_line, time_point) in enumerate(
1608 chapter_lines, start=1):
1609 start_time = parse_duration(time_point)
1610 if start_time is None:
1612 if start_time > duration:
1614 end_time = (duration if next_num == len(chapter_lines)
1615 else parse_duration(chapter_lines[next_num][1]))
1616 if end_time is None:
1618 if end_time > duration:
1620 if start_time > end_time:
1622 chapter_title = re.sub(
1623 r'<a
[^
>]+>[^
<]+</a
>', '', chapter_line).strip(' \t-')
1624 chapter_title = re.sub(r'\s
+', ' ', chapter_title)
1626 'start_time
': start_time,
1627 'end_time
': end_time,
1628 'title
': chapter_title,
1632 def _extract_chapters(self, webpage, description, video_id, duration):
1633 return (self._extract_chapters_from_json(webpage, video_id, duration)
1634 or self._extract_chapters_from_description(description, duration))
1636 def _real_extract(self, url):
1637 url, smuggled_data = unsmuggle_url(url, {})
1640 'http
' if self._downloader.params.get('prefer_insecure
', False)
1645 parsed_url = compat_urllib_parse_urlparse(url)
1646 for component in [parsed_url.fragment, parsed_url.query]:
1647 query = compat_parse_qs(component)
1648 if start_time is None and 't
' in query:
1649 start_time = parse_duration(query['t
'][0])
1650 if start_time is None and 'start
' in query:
1651 start_time = parse_duration(query['start
'][0])
1652 if end_time is None and 'end
' in query:
1653 end_time = parse_duration(query['end
'][0])
1655 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1656 mobj = re.search(self._NEXT_URL_RE, url)
1658 url = proto + '://www
.youtube
.com
/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1659 video_id = self.extract_id(url)
1662 url = proto + '://www
.youtube
.com
/watch?v
=%s&gl
=US
&hl
=en
&has_verified
=1&bpctr
=9999999999' % video_id
1663 video_webpage, urlh = self._download_webpage_handle(url, video_id)
1665 qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query)
1666 video_id = qs.get('v
', [None])[0] or video_id
1668 # Attempt to extract SWF player URL
1669 mobj = re.search(r'swfConfig
.*?
"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1670 if mobj is not None:
1671 player_url = re.sub(r'\\(.)', r'\
1', mobj.group(1))
1677 def add_dash_mpd(video_info):
1678 dash_mpd = video_info.get('dashmpd
')
1679 if dash_mpd and dash_mpd[0] not in dash_mpds:
1680 dash_mpds.append(dash_mpd[0])
1682 def add_dash_mpd_pr(pl_response):
1683 dash_mpd = url_or_none(try_get(
1684 pl_response, lambda x: x['streamingData
']['dashManifestUrl
'],
1686 if dash_mpd and dash_mpd not in dash_mpds:
1687 dash_mpds.append(dash_mpd)
1692 def extract_view_count(v_info):
1693 return int_or_none(try_get(v_info, lambda x: x['view_count
'][0]))
1695 def extract_player_response(player_response, video_id):
1696 pl_response = str_or_none(player_response)
1699 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1700 if isinstance(pl_response, dict):
1701 add_dash_mpd_pr(pl_response)
1704 def extract_embedded_config(embed_webpage, video_id):
1705 embedded_config = self._search_regex(
1706 r'setConfig\
(({.*}
)\
);',
1707 embed_webpage, 'ytInitialData
', default=None)
1709 return embedded_config
1712 player_response = {}
1713 ytplayer_config = None
1714 embed_webpage = None
1717 if (self._og_search_property('restrictions
:age
', video_webpage, default=None) == '18+'
1718 or re.search(r'player
-age
-gate
-content
">', video_webpage) is not None):
1719 cookie_keys = self._get_cookies('https://www.youtube.com').keys()
1721 # We simulate the access to the video from www.youtube.com/v/{video_id}
1722 # this can be viewed without login into Youtube
1723 url = proto + '://www.youtube.com/embed/%s' % video_id
1724 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1725 ext = extract_embedded_config(embed_webpage, video_id)
1726 # playabilityStatus = re.search(r'{\\\"status\\\":\\\"(?P<playabilityStatus>[^\"]+)\\\"', ext)
1727 playable_in_embed = re.search(r'{\\\"playableInEmbed\\\":(?P<playableinEmbed>[^\,]+)', ext)
1728 if not playable_in_embed:
1729 self.to_screen('Could not determine whether playabale in embed for video %s' % video_id)
1730 playable_in_embed = ''
1732 playable_in_embed = playable_in_embed.group('playableinEmbed')
1733 # check if video is only playable on youtube in other words not playable in embed - if so it requires auth (cookies)
1734 # if re.search(r'player-unavailable">', embed_webpage) is not None:
1735 if playable_in_embed == 'false
':
1737 # TODO apply this patch when Support for Python 2.6(!) and above drops
1738 if ({'VISITOR_INFO1_LIVE', 'HSID', 'SSID', 'SID'} <= cookie_keys
1739 or {'VISITOR_INFO1_LIVE', '__Secure-3PSID', 'LOGIN_INFO'} <= cookie_keys):
1741 if (set(('VISITOR_INFO1_LIVE
', 'HSID
', 'SSID
', 'SID
')) <= set(cookie_keys)
1742 or set(('VISITOR_INFO1_LIVE
', '__Secure
-3PSID
', 'LOGIN_INFO
')) <= set(cookie_keys)):
1744 # Try looking directly into the video webpage
1745 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1747 args = ytplayer_config.get("args")
1748 if args is not None:
1749 if args.get('url_encoded_fmt_stream_map
') or args.get('hlsvp
'):
1750 # Convert to the same format returned by compat_parse_qs
1751 video_info = dict((k, [v]) for k, v in args.items())
1752 add_dash_mpd(video_info)
1753 # Rental video is not rented but preview is available (e.g.
1754 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1755 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1756 if not video_info and args.get('ypc_vid
'):
1757 return self.url_result(
1758 args['ypc_vid
'], YoutubeIE.ie_key(), video_id=args['ypc_vid
'])
1759 if args.get('livestream
') == '1' or args.get('live_playback
') == 1:
1761 if not player_response:
1762 player_response = extract_player_response(args.get('player_response
'), video_id)
1763 elif not player_response:
1764 player_response = ytplayer_config
1765 if not video_info or self._downloader.params.get('youtube_include_dash_manifest
', True):
1766 add_dash_mpd_pr(player_response)
1768 raise ExtractorError('Video
is age restricted
and only playable on Youtube
. Requires cookies
!', expected=True)
1770 data = compat_urllib_parse_urlencode({
1771 'video_id
': video_id,
1772 'eurl
': 'https
://youtube
.googleapis
.com
/v
/' + video_id,
1773 'sts
': self._search_regex(
1774 r'"sts"\s
*:\s
*(\d
+)', embed_webpage, 'sts
', default=''),
1776 video_info_url = proto + '://www
.youtube
.com
/get_video_info?
' + data
1778 video_info_webpage = self._download_webpage(
1779 video_info_url, video_id,
1780 note='Refetching age
-gated info webpage
',
1781 errnote='unable to download video info webpage
')
1782 except ExtractorError:
1783 video_info_webpage = None
1784 if video_info_webpage:
1785 video_info = compat_parse_qs(video_info_webpage)
1786 pl_response = video_info.get('player_response
', [None])[0]
1787 player_response = extract_player_response(pl_response, video_id)
1788 add_dash_mpd(video_info)
1789 view_count = extract_view_count(video_info)
1792 # Try looking directly into the video webpage
1793 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1795 args = ytplayer_config.get('args
', {})
1796 if args.get('url_encoded_fmt_stream_map
') or args.get('hlsvp
'):
1797 # Convert to the same format returned by compat_parse_qs
1798 video_info = dict((k, [v]) for k, v in args.items())
1799 add_dash_mpd(video_info)
1800 # Rental video is not rented but preview is available (e.g.
1801 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1802 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1803 if not video_info and args.get('ypc_vid
'):
1804 return self.url_result(
1805 args['ypc_vid
'], YoutubeIE.ie_key(), video_id=args['ypc_vid
'])
1806 if args.get('livestream
') == '1' or args.get('live_playback
') == 1:
1808 if not player_response:
1809 player_response = extract_player_response(args.get('player_response
'), video_id)
1810 if not video_info or self._downloader.params.get('youtube_include_dash_manifest
', True):
1811 add_dash_mpd_pr(player_response)
1813 if not video_info and not player_response:
1814 player_response = extract_player_response(
1816 (r'%s\s
*%s' % (self._YT_INITIAL_PLAYER_RESPONSE_RE, self._YT_INITIAL_BOUNDARY_RE),
1817 self._YT_INITIAL_PLAYER_RESPONSE_RE), video_webpage,
1818 'initial player response
', default='{}'),
1821 def extract_unavailable_message():
1823 for tag, kind in (('h1
', 'message
'), ('div
', 'submessage
')):
1824 msg = self._html_search_regex(
1825 r'(?s
)<{tag}
[^
>]+id=["\']unavailable-{kind}["\'][^
>]*>(.+?
)</{tag}
>'.format(tag=tag, kind=kind),
1826 video_webpage, 'unavailable
%s' % kind, default=None)
1828 messages.append(msg)
1830 return '\n'.join(messages)
1832 if not video_info and not player_response:
1833 unavailable_message = extract_unavailable_message()
1834 if not unavailable_message:
1835 unavailable_message = 'Unable to extract video data
'
1836 raise ExtractorError(
1837 'YouTube said
: %s' % unavailable_message, expected=True, video_id=video_id)
1839 if not isinstance(video_info, dict):
1842 playable_in_embed = try_get(
1843 player_response, lambda x: x['playabilityStatus
']['playableInEmbed
'])
1845 video_details = try_get(
1846 player_response, lambda x: x['videoDetails
'], dict) or {}
1848 microformat = try_get(
1849 player_response, lambda x: x['microformat
']['playerMicroformatRenderer
'], dict) or {}
1851 video_title = video_info.get('title
', [None])[0] or video_details.get('title
')
1853 self._downloader.report_warning('Unable to extract video title
')
1856 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1857 if video_description:
1860 redir_url = compat_urlparse.urljoin(url, m.group(1))
1861 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1862 if re.search(r'^
(?
:www\
.)?
(?
:youtube(?
:-nocookie
)?\
.com|youtu\
.be
)$
', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect
':
1863 qs = compat_parse_qs(parsed_redir_url.query)
1869 description_original = video_description = re.sub(r'''(?x)
1871 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1872 (?:title|href)="([^"]+)"\s+
1873 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1877 ''', replace_url, video_description)
1878 video_description = clean_html(video_description)
1880 video_description = video_details.get('shortDescription
')
1881 if video_description is None:
1882 video_description = self._html_search_meta('description
', video_webpage)
1884 if not smuggled_data.get('force_singlefeed
', False):
1885 if not self._downloader.params.get('noplaylist
'):
1886 multifeed_metadata_list = try_get(
1888 lambda x: x['multicamera
']['playerLegacyMulticameraRenderer
']['metadataList
'],
1889 compat_str) or try_get(
1890 video_info, lambda x: x['multifeed_metadata_list
'][0], compat_str)
1891 if multifeed_metadata_list:
1894 for feed in multifeed_metadata_list.split(','):
1895 # Unquote should take place before split on comma (,) since textual
1896 # fields may contain comma as well (see
1897 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1898 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1900 def feed_entry(name):
1901 return try_get(feed_data, lambda x: x[name][0], compat_str)
1903 feed_id = feed_entry('id')
1906 feed_title = feed_entry('title
')
1909 title += ' (%s)' % feed_title
1911 '_type
': 'url_transparent
',
1912 'ie_key
': 'Youtube
',
1914 '%s://www
.youtube
.com
/watch?v
=%s' % (proto, feed_data['id'][0]),
1915 {'force_singlefeed': True}),
1918 feed_ids.append(feed_id)
1920 'Downloading multifeed
video (%s) - add
--no
-playlist to just download video
%s'
1921 % (', '.join(feed_ids), video_id))
1922 return self.playlist_result(entries, video_id, video_title, video_description)
1924 self.to_screen('Downloading just video
%s because of
--no
-playlist
' % video_id)
1926 if view_count is None:
1927 view_count = extract_view_count(video_info)
1928 if view_count is None and video_details:
1929 view_count = int_or_none(video_details.get('viewCount
'))
1930 if view_count is None and microformat:
1931 view_count = int_or_none(microformat.get('viewCount
'))
1934 is_live = bool_or_none(video_details.get('isLive
'))
1936 has_live_chat_replay = False
1938 yt_initial_data = self._extract_yt_initial_data(video_id, video_webpage)
1940 yt_initial_data['contents
']['twoColumnWatchNextResults
']['conversationBar
']['liveChatRenderer
']['continuations
'][0]['reloadContinuationData
']['continuation
']
1941 has_live_chat_replay = True
1942 except (KeyError, IndexError, TypeError):
1945 # Check for "rental" videos
1946 if 'ypc_video_rental_bar_text
' in video_info and 'author
' not in video_info:
1947 raise ExtractorError('"rental" videos
not supported
. See https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/359 for more information
.', expected=True)
1949 def _extract_filesize(media_url):
1950 return int_or_none(self._search_regex(
1951 r'\bclen
[=/](\d
+)', media_url, 'filesize
', default=None))
1953 streaming_formats = try_get(player_response, lambda x: x['streamingData
']['formats
'], list) or []
1954 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData
']['adaptiveFormats
'], list) or [])
1956 if 'conn
' in video_info and video_info['conn
'][0].startswith('rtmp
'):
1957 self.report_rtmp_download()
1959 'format_id
': '_rtmp
',
1961 'url
': video_info['conn
'][0],
1962 'player_url
': player_url,
1964 elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map
', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts
', [''])[0]) >= 1):
1965 encoded_url_map = video_info.get('url_encoded_fmt_stream_map
', [''])[0] + ',' + video_info.get('adaptive_fmts
', [''])[0]
1966 if 'rtmpe
%3Dyes
' in encoded_url_map:
1967 raise ExtractorError('rtmpe downloads are
not supported
, see https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/343 for more information
.', expected=True)
1970 fmt_list = video_info.get('fmt_list
', [''])[0]
1972 for fmt in fmt_list.split(','):
1973 spec = fmt.split('/')
1975 width_height = spec[1].split('x
')
1976 if len(width_height) == 2:
1977 formats_spec[spec[0]] = {
1978 'resolution
': spec[1],
1979 'width
': int_or_none(width_height[0]),
1980 'height
': int_or_none(width_height[1]),
1982 for fmt in streaming_formats:
1983 itag = str_or_none(fmt.get('itag
'))
1986 quality = fmt.get('quality
')
1987 quality_label = fmt.get('qualityLabel
') or quality
1988 formats_spec[itag] = {
1989 'asr
': int_or_none(fmt.get('audioSampleRate
')),
1990 'filesize
': int_or_none(fmt.get('contentLength
')),
1991 'format_note
': quality_label,
1992 'fps
': int_or_none(fmt.get('fps
')),
1993 'height
': int_or_none(fmt.get('height
')),
1994 # bitrate for itag 43 is always 2147483647
1995 'tbr
': float_or_none(fmt.get('averageBitrate
') or fmt.get('bitrate
'), 1000) if itag != '43' else None,
1996 'width
': int_or_none(fmt.get('width
')),
1999 for fmt in streaming_formats:
2000 if fmt.get('drmFamilies
') or fmt.get('drm_families
'):
2002 url = url_or_none(fmt.get('url
'))
2005 cipher = fmt.get('cipher
') or fmt.get('signatureCipher
')
2008 url_data = compat_parse_qs(cipher)
2009 url = url_or_none(try_get(url_data, lambda x: x['url
'][0], compat_str))
2014 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
2016 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type
'][0]))
2017 # Unsupported FORMAT_STREAM_TYPE_OTF
2018 if stream_type == 3:
2021 format_id = fmt.get('itag
') or url_data['itag
'][0]
2024 format_id = compat_str(format_id)
2027 if 's
' in url_data or self._downloader.params.get('youtube_include_dash_manifest
', True):
2029 r'<script
[^
>]+\bsrc
=("[^"]+")[^>]+\bname=["\']player_ias
/base
',
2030 r'"jsUrl"\s
*:\s
*("[^"]+")',
2031 r'"assets
":.+?"js
":\s*("[^
"]+")')
2032 jsplayer_url_json = self._search_regex(
2034 embed_webpage if age_gate else video_webpage,
2035 'JS player
URL (1)', default=None)
2036 if not jsplayer_url_json and not age_gate:
2037 # We need the embed website after all
2038 if embed_webpage is None:
2039 embed_url = proto + '://www
.youtube
.com
/embed
/%s' % video_id
2040 embed_webpage = self._download_webpage(
2041 embed_url, video_id, 'Downloading embed webpage
')
2042 jsplayer_url_json = self._search_regex(
2043 ASSETS_RE, embed_webpage, 'JS player URL
')
2045 player_url = json.loads(jsplayer_url_json)
2046 if player_url is None:
2047 player_url_json = self._search_regex(
2048 r'ytplayer\
.config
.*?
"url"\s
*:\s
*("[^"]+")',
2049 video_webpage, 'age gate player URL')
2050 player_url = json.loads(player_url_json)
2052 if 'sig' in url_data:
2053 url += '&signature=' + url_data['sig'][0]
2054 elif 's' in url_data:
2055 encrypted_sig = url_data['s'][0]
2057 if self._downloader.params.get('verbose'):
2058 if player_url is None:
2059 player_desc = 'unknown'
2061 player_type, player_version = self._extract_player_info(player_url)
2062 player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version)
2063 parts_sizes = self._signature_cache_id(encrypted_sig)
2064 self.to_screen('{%s} signature length %s, %s' %
2065 (format_id, parts_sizes, player_desc))
2067 signature = self._decrypt_signature(
2068 encrypted_sig, video_id, player_url, age_gate)
2069 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2070 url += '&%s=%s' % (sp, signature)
2071 if 'ratebypass' not in url:
2072 url += '&ratebypass=yes'
2075 'format_id': format_id,
2077 'player_url': player_url,
2079 if format_id in self._formats:
2080 dct.update(self._formats[format_id])
2081 if format_id in formats_spec:
2082 dct.update(formats_spec[format_id])
2084 # Some itags are not included in DASH manifest thus corresponding formats will
2085 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2086 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2087 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2088 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2091 width = int_or_none(fmt.get('width'))
2093 height = int_or_none(fmt.get('height'))
2095 filesize = int_or_none(url_data.get(
2096 'clen', [None])[0]) or _extract_filesize(url)
2098 quality = url_data.get('quality', [None])[0] or fmt.get('quality')
2099 quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
2101 tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
2102 or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
2103 fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
2106 'filesize': filesize,
2111 'format_note': quality_label or quality,
2113 for key, value in more_fields.items():
2116 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
2118 type_split = type_.split(';')
2119 kind_ext = type_split[0].split('/')
2120 if len(kind_ext) == 2:
2122 dct['ext'] = mimetype2ext(type_split[0])
2123 if kind in ('audio', 'video'):
2125 for mobj in re.finditer(
2126 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
2127 if mobj.group('key
') == 'codecs
':
2128 codecs = mobj.group('val
')
2131 dct.update(parse_codecs(codecs))
2132 if dct.get('acodec
') == 'none
' or dct.get('vcodec
') == 'none
':
2133 dct['downloader_options
'] = {
2134 # Youtube throttles chunks >~10M
2135 'http_chunk_size
': 10485760,
2140 url_or_none(try_get(
2142 lambda x: x['streamingData
']['hlsManifestUrl
'],
2144 or url_or_none(try_get(
2145 video_info, lambda x: x['hlsvp
'][0], compat_str)))
2148 m3u8_formats = self._extract_m3u8_formats(
2149 manifest_url, video_id, 'mp4
', fatal=False)
2150 for a_format in m3u8_formats:
2151 itag = self._search_regex(
2152 r'/itag
/(\d
+)/', a_format['url
'], 'itag
', default=None)
2154 a_format['format_id
'] = itag
2155 if itag in self._formats:
2156 dct = self._formats[itag].copy()
2157 dct.update(a_format)
2159 a_format['player_url
'] = player_url
2160 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2161 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
2162 if self._downloader.params.get('youtube_include_hls_manifest
', True):
2163 formats.append(a_format)
2165 error_message = extract_unavailable_message()
2166 if not error_message:
2167 reason_list = try_get(
2169 lambda x: x['playabilityStatus
']['errorScreen
']['playerErrorMessageRenderer
']['subreason
']['runs
'],
2171 for reason in reason_list:
2172 if not isinstance(reason, dict):
2174 reason_text = try_get(reason, lambda x: x['text
'], compat_str)
2176 if not error_message:
2178 error_message += reason_text
2180 error_message = clean_html(error_message)
2181 if not error_message:
2182 error_message = clean_html(try_get(
2183 player_response, lambda x: x['playabilityStatus
']['reason
'],
2185 if not error_message:
2186 error_message = clean_html(
2187 try_get(video_info, lambda x: x['reason
'][0], compat_str))
2189 raise ExtractorError(error_message, expected=True)
2190 raise ExtractorError('no conn
, hlsvp
, hlsManifestUrl
or url_encoded_fmt_stream_map information found
in video info
')
2193 video_uploader = try_get(
2194 video_info, lambda x: x['author
'][0],
2195 compat_str) or str_or_none(video_details.get('author
'))
2197 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2199 self._downloader.report_warning('unable to extract uploader name
')
2202 video_uploader_id = None
2203 video_uploader_url = None
2205 r'<link itemprop
="url" href
="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2207 if mobj is not None:
2208 video_uploader_id = mobj.group('uploader_id')
2209 video_uploader_url = mobj.group('uploader_url')
2211 owner_profile_url = url_or_none(microformat.get('ownerProfileUrl'))
2212 if owner_profile_url:
2213 video_uploader_id = self._search_regex(
2214 r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id',
2216 video_uploader_url = owner_profile_url
2219 str_or_none(video_details.get('channelId'))
2220 or self._html_search_meta(
2221 'channelId', video_webpage, 'channel id', default=None)
2222 or self._search_regex(
2223 r'data-channel-external-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
2224 video_webpage, 'channel
id', default=None, group='id'))
2225 channel_url = 'http
://www
.youtube
.com
/channel
/%s' % channel_id if channel_id else None
2228 thumbnails_list = try_get(
2229 video_details, lambda x: x['thumbnail
']['thumbnails
'], list) or []
2230 for t in thumbnails_list:
2231 if not isinstance(t, dict):
2233 thumbnail_url = url_or_none(t.get('url
'))
2234 if not thumbnail_url:
2237 'url
': thumbnail_url,
2238 'width
': int_or_none(t.get('width
')),
2239 'height
': int_or_none(t.get('height
')),
2243 video_thumbnail = None
2244 # We try first to get a high quality image:
2245 m_thumb = re.search(r'<span itemprop
="thumbnail".*?href
="(.*?)">',
2246 video_webpage, re.DOTALL)
2247 if m_thumb is not None:
2248 video_thumbnail = m_thumb.group(1)
2249 thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url
'][0], compat_str)
2251 video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
2253 thumbnails.append({'url': video_thumbnail})
2256 upload_date = self._html_search_meta(
2257 'datePublished
', video_webpage, 'upload date
', default=None)
2259 upload_date = self._search_regex(
2260 [r'(?s
)id="eow-date.*?>(.*?)</span>',
2261 r'(?:id="watch
-uploader
-info
".*?>.*?|["\']simpleText
["\']\s*:\s*["\'])(?
:Published|Uploaded|Streamed live|Started
) on (.+?
)[<"\']'],
2262 video_webpage, 'upload date', default=None)
2264 upload_date = microformat.get('publishDate') or microformat.get('uploadDate')
2265 upload_date = unified_strdate(upload_date)
2267 video_license = self._html_search_regex(
2268 r'<h4[^>]+class="title
"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2269 video_webpage, 'license', default=None)
2271 m_music = re.search(
2273 <h4[^>]+class="title
"[^>]*>\s*Music\s*</h4>\s*
2281 \bhref=["\']/red
[^
>]*>|
# drop possible
2282 >\s
*Listen ad
-free
with YouTube Red
# YouTube Red ad
2289 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2290 video_creator = clean_html(m_music.group('creator'))
2292 video_alt_title = video_creator = None
2294 def extract_meta(field):
2295 return self._html_search_regex(
2296 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2297 video_webpage, field, default=None)
2299 track = extract_meta('Song')
2300 artist = extract_meta('Artist')
2301 album = extract_meta('Album')
2303 # Youtube Music Auto-generated description
2304 release_date = release_year = None
2305 if video_description:
2306 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)
2309 track = mobj.group('track').strip()
2311 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2313 album = mobj.group('album'.strip())
2314 release_year = mobj.group('release_year')
2315 release_date = mobj.group('release_date')
2317 release_date = release_date.replace('-', '')
2318 if not release_year:
2319 release_year = int(release_date[:4])
2321 release_year = int(release_year)
2323 yt_initial_data = self._extract_yt_initial_data(video_id, video_webpage)
2324 contents = try_get(yt_initial_data, lambda x: x['contents']['twoColumnWatchNextResults']['results']['results']['contents'], list) or []
2325 for content in contents:
2326 rows = try_get(content, lambda x: x['videoSecondaryInfoRenderer']['metadataRowContainer']['metadataRowContainerRenderer']['rows'], list) or []
2327 multiple_songs = False
2329 if try_get(row, lambda x: x['metadataRowRenderer']['hasDividerLine']) is True:
2330 multiple_songs = True
2333 mrr = row.get('metadataRowRenderer') or {}
2334 mrr_title = try_get(
2335 mrr, lambda x: x['title']['simpleText'], compat_str)
2336 mrr_contents = try_get(
2337 mrr, lambda x: x['contents'][0], dict) or {}
2338 mrr_contents_text = try_get(mrr_contents, [lambda x: x['simpleText'], lambda x: x['runs'][0]['text']], compat_str)
2339 if not (mrr_title and mrr_contents_text):
2341 if mrr_title == 'License':
2342 video_license = mrr_contents_text
2343 elif not multiple_songs:
2344 if mrr_title == 'Album':
2345 album = mrr_contents_text
2346 elif mrr_title == 'Artist':
2347 artist = mrr_contents_text
2348 elif mrr_title == 'Song':
2349 track = mrr_contents_text
2351 m_episode = re.search(
2352 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2355 series = unescapeHTML(m_episode.group('series'))
2356 season_number = int(m_episode.group('season'))
2357 episode_number = int(m_episode.group('episode'))
2359 series = season_number = episode_number = None
2361 m_cat_container = self._search_regex(
2362 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2363 video_webpage, 'categories', default=None)
2366 category = self._html_search_regex(
2367 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2371 microformat, lambda x: x['category'], compat_str)
2372 video_categories = None if category is None else [category]
2375 unescapeHTML(m.group('content'))
2376 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2378 video_tags = try_get(video_details, lambda x: x['keywords'], list)
2380 def _extract_count(count_name):
2381 return str_to_int(self._search_regex(
2382 (r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>' % re.escape(count_name),
2383 r'["\']label["\']\s*:\s*["\']([\d,.]+)\s+%ss["\']' % re.escape(count_name)),
2384 video_webpage, count_name, default=None))
2386 like_count = _extract_count('like')
2387 dislike_count = _extract_count('dislike')
2389 if view_count is None:
2390 view_count = str_to_int(self._search_regex(
2391 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2392 'view count', default=None))
2395 float_or_none(video_details.get('averageRating'))
2396 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2399 video_subtitles = self.extract_subtitles(
2400 video_id, video_webpage, has_live_chat_replay)
2401 automatic_captions = self.extract_automatic_captions(video_id, player_response, ytplayer_config)
2403 video_duration = try_get(
2404 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2405 if not video_duration:
2406 video_duration = int_or_none(video_details.get('lengthSeconds'))
2407 if not video_duration:
2408 video_duration = parse_duration(self._html_search_meta(
2409 'duration', video_webpage, 'video duration'))
2411 # Get Subscriber Count of channel
2412 subscriber_count = parse_count(self._search_regex(
2413 r'"text":"([\d\.]+\w?) subscribers"',
2419 # get xsrf for annotations or comments
2420 get_annotations = self._downloader.params.get('writeannotations', False)
2421 get_comments = self._downloader.params.get('getcomments', False)
2422 if get_annotations or get_comments:
2424 ytcfg = self._extract_ytcfg(video_id, video_webpage)
2426 xsrf_token = try_get(ytcfg, lambda x: x['XSRF_TOKEN'], compat_str)
2428 xsrf_token = self._search_regex(
2429 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>(?:(?!\2).)+)\2',
2430 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2433 video_annotations = None
2435 invideo_url = try_get(
2436 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2437 if xsrf_token and invideo_url:
2438 xsrf_field_name = None
2440 xsrf_field_name = try_get(ytcfg, lambda x: x['XSRF_FIELD_NAME'], compat_str)
2441 if not xsrf_field_name:
2442 xsrf_field_name = self._search_regex(
2443 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2444 video_webpage, 'xsrf field name',
2445 group='xsrf_field_name', default='session_token')
2446 video_annotations = self._download_webpage(
2447 self._proto_relative_url(invideo_url),
2448 video_id, note='Downloading annotations',
2449 errnote='Unable to download video annotations', fatal=False,
2450 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2452 chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
2455 # TODO: Refactor and move to seperate function
2457 expected_video_comment_count = 0
2460 def find_value(html, key, num_chars=2, separator='"'):
2461 pos_begin = html.find(key) + len(key) + num_chars
2462 pos_end = html.find(separator, pos_begin)
2463 return html[pos_begin: pos_end]
2465 def search_dict(partial, key):
2466 if isinstance(partial, dict):
2467 for k, v in partial.items():
2471 for o in search_dict(v, key):
2473 elif isinstance(partial, list):
2475 for o in search_dict(i, key):
2479 ncd = next(search_dict(yt_initial_data, 'nextContinuationData'))
2480 continuations = [ncd['continuation']]
2481 # Handle videos where comments have been disabled entirely
2482 except StopIteration:
2485 def get_continuation(continuation, session_token, replies=False):
2488 'ctoken': continuation,
2491 query['action_get_comment_replies'] = 1
2493 query['action_get_comments'] = 1
2496 content, handle = self._download_webpage_handle(
2497 'https://www.youtube.com/comment_service_ajax',
2500 expected_status=[413],
2501 data=urlencode_postdata({
2502 'session_token': session_token
2507 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:76.0) Gecko/20100101 Firefox/76.0',
2508 'X-YouTube-Client-Name': '1',
2509 'X-YouTube-Client-Version': '2.20201202.06.01'
2513 response_code = handle.getcode()
2514 if (response_code == 200):
2515 return self._parse_json(content, video_id)
2516 if (response_code == 413):
2518 raise ExtractorError('Unexpected HTTP error code: %s' % response_code)
2520 first_continuation = True
2521 while continuations:
2522 continuation, itct = continuations.pop()
2523 comment_response = get_continuation(continuation, xsrf_token)
2524 if not comment_response:
2526 if list(search_dict(comment_response, 'externalErrorMessage')):
2527 raise ExtractorError('Error returned from server: ' + next(search_dict(comment_response, 'externalErrorMessage')))
2529 if 'continuationContents' not in comment_response['response']:
2530 # Something is wrong here. Youtube won't accept this continuation token for some reason and responds with a user satisfaction dialog (error?)
2532 # not sure if this actually helps
2533 if 'xsrf_token' in comment_response:
2534 xsrf_token = comment_response['xsrf_token']
2536 item_section = comment_response['response']['continuationContents']['itemSectionContinuation']
2537 if first_continuation:
2538 expected_video_comment_count = int(item_section['header']['commentsHeaderRenderer']['countText']['runs'][0]['text'].replace(' Comments', '').replace('1 Comment', '1').replace(',', ''))
2539 first_continuation = False
2540 if 'contents' not in item_section:
2541 # continuation returned no comments?
2542 # set an empty array as to not break the for loop
2543 item_section['contents'] = []
2545 for meta_comment in item_section['contents']:
2546 comment = meta_comment['commentThreadRenderer']['comment']['commentRenderer']
2547 video_comments.append({
2548 'id': comment['commentId'],
2549 'text': ''.join([c['text'] for c in comment['contentText']['runs']]),
2550 'time_text': ''.join([c['text'] for c in comment['publishedTimeText']['runs']]),
2551 'author': comment.get('authorText', {}).get('simpleText', ''),
2552 'votes': comment.get('voteCount', {}).get('simpleText', '0'),
2553 'author_thumbnail': comment['authorThumbnail']['thumbnails'][-1]['url'],
2556 if 'replies' not in meta_comment['commentThreadRenderer']:
2559 reply_continuations = [rcn['nextContinuationData']['continuation'] for rcn in meta_comment['commentThreadRenderer']['replies']['commentRepliesRenderer']['continuations']]
2560 while reply_continuations:
2562 continuation = reply_continuations.pop()
2563 replies_data = get_continuation(continuation, xsrf_token, True)
2564 if not replies_data or 'continuationContents' not in replies_data[1]['response']:
2567 if self._downloader.params.get('verbose', False):
2568 self.to_screen('[debug] Comments downloaded (chain %s) %s of ~%s' % (comment['commentId'], len(video_comments), expected_video_comment_count))
2569 reply_comment_meta = replies_data[1]['response']['continuationContents']['commentRepliesContinuation']
2570 for reply_meta in replies_data[1]['response']['continuationContents']['commentRepliesContinuation']['contents']:
2571 reply_comment = reply_meta['commentRenderer']
2572 video_comments.append({
2573 'id': reply_comment['commentId'],
2574 'text': ''.join([c['text'] for c in reply_comment['contentText']['runs']]),
2575 'time_text': ''.join([c['text'] for c in reply_comment['publishedTimeText']['runs']]),
2576 'author': reply_comment.get('authorText', {}).get('simpleText', ''),
2577 'votes': reply_comment.get('voteCount', {}).get('simpleText', '0'),
2578 'author_thumbnail': reply_comment['authorThumbnail']['thumbnails'][-1]['url'],
2579 'parent': comment['commentId']
2581 if 'continuations' not in reply_comment_meta or len(reply_comment_meta['continuations']) == 0:
2584 reply_continuations += [rcn['nextContinuationData']['continuation'] for rcn in reply_comment_meta['continuations']]
2586 self.to_screen('Comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count))
2588 if 'continuations' in item_section:
2589 continuations += [ncd['nextContinuationData']['continuation'] for ncd in item_section['continuations']]
2592 self.to_screen('Total comments downloaded %s of ~%s' % (len(video_comments), expected_video_comment_count))
2594 expected_video_comment_count = None
2595 video_comments = None
2597 # Look for the DASH manifest
2598 if self._downloader.params.get('youtube_include_dash_manifest', True):
2599 dash_mpd_fatal = True
2600 for mpd_url in dash_mpds:
2603 def decrypt_sig(mobj):
2605 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2606 return '/signature/%s' % dec_s
2608 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2610 for df in self._extract_mpd_formats(
2611 mpd_url, video_id, fatal=dash_mpd_fatal,
2612 formats_dict=self._formats):
2613 if not df.get('filesize'):
2614 df['filesize'] = _extract_filesize(df['url'])
2615 # Do not overwrite DASH format found in some previous DASH manifest
2616 if df['format_id'] not in dash_formats:
2617 dash_formats[df['format_id']] = df
2618 # Additional DASH manifests may end up in HTTP Error 403 therefore
2619 # allow them to fail without bug report message if we already have
2620 # some DASH manifest succeeded. This is temporary workaround to reduce
2621 # burst of bug reports until we figure out the reason and whether it
2622 # can be fixed at all.
2623 dash_mpd_fatal = False
2624 except (ExtractorError, KeyError) as e:
2625 self.report_warning(
2626 'Skipping DASH manifest: %r' % e, video_id)
2628 # Remove the formats we found through non-DASH, they
2629 # contain less info and it can be wrong, because we use
2630 # fixed values (for example the resolution). See
2631 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2633 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2634 formats.extend(dash_formats.values())
2636 # Check for malformed aspect ratio
2637 stretched_m = re.search(
2638 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2641 w = float(stretched_m.group('w'))
2642 h = float(stretched_m.group('h'))
2643 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2644 # We will only process correct ratios.
2648 if f.get('vcodec') != 'none':
2649 f['stretched_ratio'] = ratio
2652 if 'reason' in video_info:
2653 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2654 regions_allowed = self._html_search_meta(
2655 'regionsAllowed', video_webpage, default=None)
2656 countries = regions_allowed.split(',') if regions_allowed else None
2657 self.raise_geo_restricted(
2658 msg=video_info['reason'][0], countries=countries)
2659 reason = video_info['reason'][0]
2660 if 'Invalid parameters' in reason:
2661 unavailable_message = extract_unavailable_message()
2662 if unavailable_message:
2663 reason = unavailable_message
2664 raise ExtractorError(
2665 'YouTube said: %s' % reason,
2666 expected=True, video_id=video_id)
2667 if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
2668 raise ExtractorError('This video is DRM protected.', expected=True)
2670 self._sort_formats(formats)
2672 self.mark_watched(video_id, video_info, player_response)
2676 'uploader': video_uploader,
2677 'uploader_id': video_uploader_id,
2678 'uploader_url': video_uploader_url,
2679 'channel': video_uploader,
2680 'channel_id': channel_id,
2681 'channel_url': channel_url,
2682 'upload_date': upload_date,
2683 'license': video_license,
2684 'creator': video_creator or artist,
2685 'title': video_title,
2686 'alt_title': video_alt_title or track,
2687 'thumbnails': thumbnails,
2688 'description': video_description,
2689 'categories': video_categories,
2691 'subtitles': video_subtitles,
2692 'automatic_captions': automatic_captions,
2693 'duration': video_duration,
2694 'age_limit': 18 if age_gate else 0,
2695 'annotations': video_annotations,
2696 'chapters': chapters,
2697 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2698 'view_count': view_count,
2699 'like_count': like_count,
2700 'dislike_count': dislike_count,
2701 'average_rating': average_rating,
2704 'start_time': start_time,
2705 'end_time': end_time,
2707 'season_number': season_number,
2708 'episode_number': episode_number,
2712 'release_date': release_date,
2713 'release_year': release_year,
2714 'subscriber_count': subscriber_count,
2715 'playable_in_embed': playable_in_embed,
2716 'comments': video_comments,
2717 'comment_count': expected_video_comment_count,
2721 class YoutubeTabIE(YoutubeBaseInfoExtractor):
2722 IE_DESC = 'YouTube.com tab'
2723 _VALID_URL = r'''(?x
)
2727 youtube(?
:kids
)?\
.com|
2731 (?
:channel|c|user
)/|
2734 (?
:playlist|watch
)\?.*?
\blist
=
2736 (?
!(?
:%s)\b) # Direct URLs
2739 ''' % YoutubeBaseInfoExtractor._RESERVED_NAMES
2740 IE_NAME = 'youtube:tab'
2743 # playlists, multipage
2744 'url': 'https://www.youtube.com/c/ИгорьКлейнер/playlists?view=1&flow=grid',
2745 'playlist_mincount': 94,
2747 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2748 'title': 'Игорь Клейнер - Playlists',
2749 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2752 # playlists, multipage, different order
2753 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2754 'playlist_mincount': 94,
2756 'id': 'UCqj7Cz7revf5maW9g5pgNcg',
2757 'title': 'Игорь Клейнер - Playlists',
2758 'description': 'md5:be97ee0f14ee314f1f002cf187166ee2',
2761 # playlists, singlepage
2762 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2763 'playlist_mincount': 4,
2765 'id': 'UCAEtajcuhQ6an9WEzY9LEMQ',
2766 'title': 'ThirstForScience - Playlists',
2767 'description': 'md5:609399d937ea957b0f53cbffb747a14c',
2770 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
2771 'only_matching': True,
2773 # basic, single video playlist
2774 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2776 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2777 'uploader': 'Sergey M.',
2778 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2779 'title': 'youtube-dl public playlist',
2781 'playlist_count': 1,
2784 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2786 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2787 'uploader': 'Sergey M.',
2788 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2789 'title': 'youtube-dl empty playlist',
2791 'playlist_count': 0,
2794 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/featured',
2796 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2797 'title': 'lex will - Home',
2798 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2800 'playlist_mincount': 2,
2803 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos',
2805 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2806 'title': 'lex will - Videos',
2807 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2809 'playlist_mincount': 975,
2811 # Videos tab, sorted by popular
2812 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/videos?view=0&sort=p&flow=grid',
2814 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2815 'title': 'lex will - Videos',
2816 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2818 'playlist_mincount': 199,
2821 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/playlists',
2823 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2824 'title': 'lex will - Playlists',
2825 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2827 'playlist_mincount': 17,
2830 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/community',
2832 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2833 'title': 'lex will - Community',
2834 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2836 'playlist_mincount': 18,
2839 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w/channels',
2841 'id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2842 'title': 'lex will - Channels',
2843 'description': 'md5:2163c5d0ff54ed5f598d6a7e6211e488',
2845 'playlist_mincount': 138,
2847 'url': 'https://invidio.us/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2848 'only_matching': True,
2850 'url': 'https://www.youtubekids.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2851 'only_matching': True,
2853 'url': 'https://music.youtube.com/channel/UCmlqkdCBesrv2Lak1mF_MxA',
2854 'only_matching': True,
2856 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2857 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2859 'title': '29C3: Not my department',
2860 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2861 'uploader': 'Christiaan008',
2862 'uploader_id': 'UCEPzS1rYsrkqzSLNp76nrcg',
2864 'playlist_count': 96,
2866 'note': 'Large playlist',
2867 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2869 'title': 'Uploads from Cauchemar',
2870 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2871 'uploader': 'Cauchemar',
2872 'uploader_id': 'UCBABnxM4Ar9ten8Mdjj1j0Q',
2874 'playlist_mincount': 1123,
2876 # even larger playlist, 8832 videos
2877 'url': 'http://www.youtube.com/user/NASAgovVideo/videos',
2878 'only_matching': True,
2880 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2881 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2883 'title': 'Uploads from Interstellar Movie',
2884 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2885 'uploader': 'Interstellar Movie',
2886 'uploader_id': 'UCXw-G3eDE9trcvY2sBMM_aA',
2888 'playlist_mincount': 21,
2890 # https://github.com/ytdl-org/youtube-dl/issues/21844
2891 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2893 'title': 'Data Analysis with Dr Mike Pound',
2894 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2895 'uploader_id': 'UC9-y-6csu5WGm29I7JiwpnA',
2896 'uploader': 'Computerphile',
2898 'playlist_mincount': 11,
2900 'url': 'https://invidio.us/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2901 'only_matching': True,
2903 # Playlist URL that does not actually serve a playlist
2904 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2906 'id': 'FqZTN594JQw',
2908 'title': "Smiley's People 01 detective, Adventure Series, Action",
2909 'uploader': 'STREEM',
2910 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2911 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2912 'upload_date': '20150526',
2913 'license': 'Standard YouTube License',
2914 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2915 'categories': ['People & Blogs'],
2919 'dislike_count': int,
2922 'skip_download': True,
2924 'skip': 'This video is not available.',
2925 'add_ie': [YoutubeIE.ie_key()],
2927 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2928 'only_matching': True,
2930 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
2931 'only_matching': True,
2933 'url': 'https://www.youtube.com/channel/UCoMdktPbSTixAyNGwb-UYkQ/live',
2935 'id': '9Auq9mYxFEE',
2937 'title': 'Watch Sky News live',
2938 'uploader': 'Sky News',
2939 'uploader_id': 'skynews',
2940 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/skynews',
2941 'upload_date': '20191102',
2942 'description': 'md5:78de4e1c2359d0ea3ed829678e38b662',
2943 'categories': ['News & Politics'],
2946 'dislike_count': int,
2949 'skip_download': True,
2952 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2954 'id': 'a48o2S1cPoo',
2956 'title': 'The Young Turks - Live Main Show',
2957 'uploader': 'The Young Turks',
2958 'uploader_id': 'TheYoungTurks',
2959 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2960 'upload_date': '20150715',
2961 'license': 'Standard YouTube License',
2962 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2963 'categories': ['News & Politics'],
2964 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2966 'dislike_count': int,
2969 'skip_download': True,
2971 'only_matching': True,
2973 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2974 'only_matching': True,
2976 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2977 'only_matching': True,
2979 'url': 'https://www.youtube.com/feed/trending',
2980 'only_matching': True,
2983 'url': 'https://www.youtube.com/feed/library',
2984 'only_matching': True,
2987 'url': 'https://www.youtube.com/feed/history',
2988 'only_matching': True,
2991 'url': 'https://www.youtube.com/feed/subscriptions',
2992 'only_matching': True,
2995 'url': 'https://www.youtube.com/feed/watch_later',
2996 'only_matching': True,
2998 # no longer available?
2999 'url': 'https://www.youtube.com/feed/recommended',
3000 'only_matching': True,
3002 # inline playlist with not always working continuations
3003 'url': 'https://www.youtube.com/watch?v=UC6u0Tct-Fo&list=PL36D642111D65BE7C',
3004 'only_matching': True,
3006 'url': 'https://www.youtube.com/course?list=ECUl4u3cNGP61MdtwGTqZA0MreSaDybji8',
3007 'only_matching': True,
3009 'url': 'https://www.youtube.com/course',
3010 'only_matching': True,
3012 'url': 'https://www.youtube.com/zsecurity',
3013 'only_matching': True,
3015 'url': 'http://www.youtube.com/NASAgovVideo/videos',
3016 'only_matching': True,
3018 'url': 'https://www.youtube.com/TheYoungTurks/live',
3019 'only_matching': True,
3023 def suitable(cls, url):
3024 return False if YoutubeIE.suitable(url) else super(
3025 YoutubeTabIE, cls).suitable(url)
3027 def _extract_channel_id(self, webpage):
3028 channel_id = self._html_search_meta(
3029 'channelId', webpage, 'channel id', default=None)
3032 channel_url = self._html_search_meta(
3033 ('og:url', 'al:ios:url', 'al:android:url', 'al:web:url',
3034 'twitter:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad',
3035 'twitter:app:url:googleplay'), webpage, 'channel url')
3036 return self._search_regex(
3037 r'https?://(?:www\.)?youtube\.com/channel/([^/?#&])+',
3038 channel_url, 'channel id')
3041 def _extract_grid_item_renderer(item):
3042 for item_kind in ('Playlist', 'Video', 'Channel'):
3043 renderer = item.get('grid%sRenderer' % item_kind)
3047 def _grid_entries(self, grid_renderer):
3048 for item in grid_renderer['items']:
3049 if not isinstance(item, dict):
3051 renderer = self._extract_grid_item_renderer(item)
3052 if not isinstance(renderer, dict):
3055 renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
3057 playlist_id = renderer.get('playlistId')
3059 yield self.url_result(
3060 'https://www.youtube.com/playlist?list=%s' % playlist_id,
3061 ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3064 video_id = renderer.get('videoId')
3066 yield self._extract_video(renderer)
3068 channel_id = renderer.get('channelId')
3071 renderer, lambda x: x['title']['simpleText'], compat_str)
3072 yield self.url_result(
3073 'https://www.youtube.com/channel/%s' % channel_id,
3074 ie=YoutubeTabIE.ie_key(), video_title=title)
3076 def _shelf_entries_from_content(self, shelf_renderer):
3077 content = shelf_renderer.get('content')
3078 if not isinstance(content, dict):
3080 renderer = content.get('gridRenderer')
3082 # TODO: add support for nested playlists so each shelf is processed
3083 # as separate playlist
3084 # TODO: this includes only first N items
3085 for entry in self._grid_entries(renderer):
3087 renderer = content.get('horizontalListRenderer')
3092 def _shelf_entries(self, shelf_renderer, skip_channels=False):
3094 shelf_renderer, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3096 shelf_url = urljoin('https://www.youtube.com', ep)
3098 # Skipping links to another channels, note that checking for
3099 # endpoint.commandMetadata.webCommandMetadata.webPageTypwebPageType == WEB_PAGE_TYPE_CHANNEL
3101 if skip_channels and '/channels?' in shelf_url:
3104 shelf_renderer, lambda x: x['title']['runs'][0]['text'], compat_str)
3105 yield self.url_result(shelf_url, video_title=title)
3106 # Shelf may not contain shelf URL, fallback to extraction from content
3107 for entry in self._shelf_entries_from_content(shelf_renderer):
3110 def _playlist_entries(self, video_list_renderer):
3111 for content in video_list_renderer['contents']:
3112 if not isinstance(content, dict):
3114 renderer = content.get('playlistVideoRenderer') or content.get('playlistPanelVideoRenderer')
3115 if not isinstance(renderer, dict):
3117 video_id = renderer.get('videoId')
3120 yield self._extract_video(renderer)
3122 r""" # Not needed in the new implementation
3123 def _itemSection_entries(self, item_sect_renderer):
3124 for content in item_sect_renderer['contents']:
3125 if not isinstance(content, dict):
3127 renderer = content.get('videoRenderer', {})
3128 if not isinstance(renderer, dict):
3130 video_id = renderer.get('videoId')
3133 yield self._extract_video(renderer)
3136 def _rich_entries(self, rich_grid_renderer):
3138 rich_grid_renderer, lambda x: x['content']['videoRenderer'], dict) or {}
3139 video_id = renderer.get('videoId')
3142 yield self._extract_video(renderer)
3144 def _video_entry(self, video_renderer):
3145 video_id = video_renderer.get('videoId')
3147 return self._extract_video(video_renderer)
3149 def _post_thread_entries(self, post_thread_renderer):
3150 post_renderer = try_get(
3151 post_thread_renderer, lambda x: x['post']['backstagePostRenderer'], dict)
3152 if not post_renderer:
3155 video_renderer = try_get(
3156 post_renderer, lambda x: x['backstageAttachment']['videoRenderer'], dict)
3159 entry = self._video_entry(video_renderer)
3162 # inline video links
3163 runs = try_get(post_renderer, lambda x: x['contentText']['runs'], list) or []
3165 if not isinstance(run, dict):
3168 run, lambda x: x['navigationEndpoint']['urlEndpoint']['url'], compat_str)
3171 if not YoutubeIE.suitable(ep_url):
3173 ep_video_id = YoutubeIE._match_id(ep_url)
3174 if video_id == ep_video_id:
3176 yield self.url_result(ep_url, ie=YoutubeIE.ie_key(), video_id=video_id)
3178 def _post_thread_continuation_entries(self, post_thread_continuation):
3179 contents = post_thread_continuation.get('contents')
3180 if not isinstance(contents, list):
3182 for content in contents:
3183 renderer = content.get('backstagePostThreadRenderer')
3184 if not isinstance(renderer, dict):
3186 for entry in self._post_thread_entries(renderer):
3190 def _build_continuation_query(continuation, ctp=None):
3192 'ctoken': continuation,
3193 'continuation': continuation,
3200 def _extract_next_continuation_data(renderer):
3201 next_continuation = try_get(
3202 renderer, lambda x: x['continuations'][0]['nextContinuationData'], dict)
3203 if not next_continuation:
3205 continuation = next_continuation.get('continuation')
3206 if not continuation:
3208 ctp = next_continuation.get('clickTrackingParams')
3209 return YoutubeTabIE._build_continuation_query(continuation, ctp)
3212 def _extract_continuation(cls, renderer):
3213 next_continuation = cls._extract_next_continuation_data(renderer)
3214 if next_continuation:
3215 return next_continuation
3216 contents = renderer.get('contents')
3217 if not isinstance(contents, list):
3219 for content in contents:
3220 if not isinstance(content, dict):
3222 continuation_ep = try_get(
3223 content, lambda x: x['continuationItemRenderer']['continuationEndpoint'],
3225 if not continuation_ep:
3227 continuation = try_get(
3228 continuation_ep, lambda x: x['continuationCommand']['token'], compat_str)
3229 if not continuation:
3231 ctp = continuation_ep.get('clickTrackingParams')
3232 return YoutubeTabIE._build_continuation_query(continuation, ctp)
3234 def _entries(self, tab, identity_token):
3236 def extract_entries(parent_renderer): # this needs to called again for continuation to work with feeds
3237 contents = try_get(parent_renderer, lambda x: x['contents'], list) or []
3238 for content in contents:
3239 if not isinstance(content, dict):
3241 is_renderer = try_get(content, lambda x: x['itemSectionRenderer'], dict)
3243 renderer = content.get('richItemRenderer')
3245 for entry in self._rich_entries(renderer):
3247 continuation_list[0] = self._extract_continuation(parent_renderer)
3249 isr_contents = try_get(is_renderer, lambda x: x['contents'], list) or []
3250 for isr_content in isr_contents:
3251 if not isinstance(isr_content, dict):
3253 renderer = isr_content.get('playlistVideoListRenderer')
3255 for entry in self._playlist_entries(renderer):
3257 continuation_list[0] = self._extract_continuation(renderer)
3259 renderer = isr_content.get('gridRenderer')
3261 for entry in self._grid_entries(renderer):
3263 continuation_list[0] = self._extract_continuation(renderer)
3265 renderer = isr_content.get('shelfRenderer')
3267 is_channels_tab = tab.get('title') == 'Channels'
3268 for entry in self._shelf_entries(renderer, not is_channels_tab):
3271 renderer = isr_content.get('backstagePostThreadRenderer')
3273 for entry in self._post_thread_entries(renderer):
3275 continuation_list[0] = self._extract_continuation(renderer)
3277 renderer = isr_content.get('videoRenderer')
3279 entry = self._video_entry(renderer)
3283 if not continuation_list[0]:
3284 continuation_list[0] = self._extract_continuation(is_renderer)
3286 if not continuation_list[0]:
3287 continuation_list[0] = self._extract_continuation(parent_renderer)
3289 continuation_list = [None] # Python 2 doesnot support nonlocal
3290 tab_content = try_get(tab, lambda x: x['content'], dict)
3294 try_get(tab_content, lambda x: x['sectionListRenderer'], dict)
3295 or try_get(tab_content, lambda x: x['richGridRenderer'], dict) or {})
3296 for entry in extract_entries(parent_renderer):
3298 continuation = continuation_list[0]
3301 'x-youtube-client-name': '1',
3302 'x-youtube-client-version': '2.20201112.04.01',
3305 headers['x-youtube-identity-token'] = identity_token
3307 for page_num in itertools.count(1):
3308 if not continuation:
3312 while count <= retries:
3314 # Downloading page may result in intermittent 5xx HTTP error
3315 # that is usually worked around with a retry
3316 browse = self._download_json(
3317 'https://www.youtube.com/browse_ajax', None,
3318 'Downloading page %d%s'
3319 % (page_num, ' (retry #%d)' % count if count else ''),
3320 headers=headers, query=continuation)
3322 except ExtractorError as e:
3323 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
3325 if count <= retries:
3330 response = try_get(browse, lambda x: x[1]['response'], dict)
3334 continuation_contents = try_get(
3335 response, lambda x: x['continuationContents'], dict)
3336 if continuation_contents:
3337 continuation_renderer = continuation_contents.get('playlistVideoListContinuation')
3338 if continuation_renderer:
3339 for entry in self._playlist_entries(continuation_renderer):
3341 continuation = self._extract_continuation(continuation_renderer)
3343 continuation_renderer = continuation_contents.get('gridContinuation')
3344 if continuation_renderer:
3345 for entry in self._grid_entries(continuation_renderer):
3347 continuation = self._extract_continuation(continuation_renderer)
3349 continuation_renderer = continuation_contents.get('itemSectionContinuation')
3350 if continuation_renderer:
3351 for entry in self._post_thread_continuation_entries(continuation_renderer):
3353 continuation = self._extract_continuation(continuation_renderer)
3355 continuation_renderer = continuation_contents.get('sectionListContinuation') # for feeds
3356 if continuation_renderer:
3357 continuation_list = [None]
3358 for entry in extract_entries(continuation_renderer):
3360 continuation = continuation_list[0]
3363 continuation_items = try_get(
3364 response, lambda x: x['onResponseReceivedActions'][0]['appendContinuationItemsAction']['continuationItems'], list)
3365 if continuation_items:
3366 continuation_item = continuation_items[0]
3367 if not isinstance(continuation_item, dict):
3369 renderer = continuation_item.get('playlistVideoRenderer') or continuation_item.get('itemSectionRenderer')
3371 video_list_renderer = {'contents': continuation_items}
3372 for entry in self._playlist_entries(video_list_renderer):
3374 continuation = self._extract_continuation(video_list_renderer)
3379 def _extract_selected_tab(tabs):
3381 if try_get(tab, lambda x: x['tabRenderer']['selected'], bool):
3382 return tab['tabRenderer']
3384 raise ExtractorError('Unable to find selected tab')
3387 def _extract_uploader(data):
3389 sidebar_renderer = try_get(
3390 data, lambda x: x['sidebar']['playlistSidebarRenderer']['items'], list)
3391 if sidebar_renderer:
3392 for item in sidebar_renderer:
3393 if not isinstance(item, dict):
3395 renderer = item.get('playlistSidebarSecondaryInfoRenderer')
3396 if not isinstance(renderer, dict):
3399 renderer, lambda x: x['videoOwner']['videoOwnerRenderer']['title']['runs'][0], dict)
3401 uploader['uploader'] = owner.get('text')
3402 uploader['uploader_id'] = try_get(
3403 owner, lambda x: x['navigationEndpoint']['browseEndpoint']['browseId'], compat_str)
3404 uploader['uploader_url'] = urljoin(
3405 'https://www.youtube.com/',
3406 try_get(owner, lambda x: x['navigationEndpoint']['browseEndpoint']['canonicalBaseUrl'], compat_str))
3407 return {k: v for k, v in uploader.items() if v is not None}
3409 def _extract_from_tabs(self, item_id, webpage, data, tabs, identity_token):
3410 playlist_id = title = description = channel_url = channel_name = channel_id = None
3411 thumbnails_list = tags = []
3413 selected_tab = self._extract_selected_tab(tabs)
3415 data, lambda x: x['metadata']['channelMetadataRenderer'], dict)
3417 channel_name = renderer.get('title')
3418 channel_url = renderer.get('channelUrl')
3419 channel_id = renderer.get('externalId')
3423 data, lambda x: x['metadata']['playlistMetadataRenderer'], dict)
3425 title = renderer.get('title')
3426 description = renderer.get('description')
3427 playlist_id = channel_id
3428 tags = renderer.get('keywords', '').split()
3430 try_get(renderer, lambda x: x['avatar']['thumbnails'], list)
3431 or data['sidebar']['playlistSidebarRenderer']['items'][0]['playlistSidebarPrimaryInfoRenderer']['thumbnailRenderer']['playlistVideoThumbnailRenderer']['thumbnail']['thumbnails']
3435 for t in thumbnails_list:
3436 if not isinstance(t, dict):
3438 thumbnail_url = url_or_none(t.get('url'))
3439 if not thumbnail_url:
3442 'url': thumbnail_url,
3443 'width': int_or_none(t.get('width')),
3444 'height': int_or_none(t.get('height')),
3447 if playlist_id is None:
3448 playlist_id = item_id
3451 title += format_field(selected_tab, 'title', ' - %s')
3454 'playlist_id': playlist_id,
3455 'playlist_title': title,
3456 'playlist_description': description,
3457 'uploader': channel_name,
3458 'uploader_id': channel_id,
3459 'uploader_url': channel_url,
3460 'thumbnails': thumbnails,
3464 metadata.update(self._extract_uploader(data))
3466 'channel': metadata['uploader'],
3467 'channel_id': metadata['uploader_id'],
3468 'channel_url': metadata['uploader_url']})
3469 return self.playlist_result(
3470 self._entries(selected_tab, identity_token),
3473 def _extract_from_playlist(self, item_id, url, data, playlist):
3474 title = playlist.get('title') or try_get(
3475 data, lambda x: x['titleText']['simpleText'], compat_str)
3476 playlist_id = playlist.get('playlistId') or item_id
3477 # Inline playlist rendition continuation does not always work
3478 # at Youtube side, so delegating regular tab-based playlist URL
3479 # processing whenever possible.
3480 playlist_url = urljoin(url, try_get(
3481 playlist, lambda x: x['endpoint']['commandMetadata']['webCommandMetadata']['url'],
3483 if playlist_url and playlist_url != url:
3484 return self.url_result(
3485 playlist_url, ie=YoutubeTabIE.ie_key(), video_id=playlist_id,
3487 return self.playlist_result(
3488 self._playlist_entries(playlist), playlist_id=playlist_id,
3489 playlist_title=title)
3492 def _extract_alerts(data):
3493 for alert_dict in try_get(data, lambda x: x['alerts'], list) or []:
3494 if not isinstance(alert_dict, dict):
3496 for renderer in alert_dict:
3497 alert = alert_dict[renderer]
3498 alert_type = alert.get('type')
3501 message = try_get(alert, lambda x: x['text']['simpleText'], compat_str)
3503 yield alert_type, message
3504 for run in try_get(alert, lambda x: x['text']['runs'], list) or []:
3505 message = try_get(run, lambda x: x['text'], compat_str)
3507 yield alert_type, message
3509 def _extract_identity_token(self, webpage, item_id):
3510 ytcfg = self._extract_ytcfg(item_id, webpage)
3512 token = try_get(ytcfg, lambda x: x['ID_TOKEN'], compat_str)
3515 return self._search_regex(
3516 r'\bID_TOKEN["\']\s*:\s*["\'](.+?)["\']', webpage,
3517 'identity token', default=None)
3519 def _real_extract(self, url):
3520 item_id = self._match_id(url)
3521 url = compat_urlparse.urlunparse(
3522 compat_urlparse.urlparse(url)._replace(netloc='www.youtube.com'))
3523 is_home = re.match(r'(?P<pre>%s)(?P<post>/?(?![^#?]).*$)' % self._VALID_URL, url)
3524 if is_home is not None and is_home.group('not_channel') is None and item_id != 'feed':
3525 self._downloader.report_warning(
3526 'A channel/user page was given. All the channel\'s videos will be downloaded. '
3527 'To download only the videos in the home page, add a "/featured" to the URL')
3528 url = '%s/videos%s' % (is_home.group('pre'), is_home.group('post') or '')
3530 # Handle both video/playlist URLs
3531 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
3532 video_id = qs.get('v', [None])[0]
3533 playlist_id = qs.get('list', [None])[0]
3535 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:
3537 self._downloader.report_warning('%s is not a valid Youtube URL. Trying to download playlist %s' % (url, playlist_id))
3538 url = 'https://www.youtube.com/playlist?list=%s' % playlist_id
3539 # return self.url_result(playlist_id, ie=YoutubePlaylistIE.ie_key())
3541 raise ExtractorError('Unable to recognize tab page')
3542 if video_id and playlist_id:
3543 if self._downloader.params.get('noplaylist'):
3544 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3545 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
3546 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
3548 webpage = self._download_webpage(url, item_id)
3549 identity_token = self._extract_identity_token(webpage, item_id)
3550 data = self._extract_yt_initial_data(item_id, webpage)
3552 for alert_type, alert_message in self._extract_alerts(data):
3553 if alert_type.lower() == 'error':
3555 self._downloader.report_warning('YouTube said: %s - %s' % ('ERROR', err_msg))
3556 err_msg = alert_message
3558 self._downloader.report_warning('YouTube said: %s - %s' % (alert_type, alert_message))
3560 raise ExtractorError('YouTube said: %s' % err_msg, expected=True)
3562 data, lambda x: x['contents']['twoColumnBrowseResultsRenderer']['tabs'], list)
3564 return self._extract_from_tabs(item_id, webpage, data, tabs, identity_token)
3566 data, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist'], dict)
3568 return self._extract_from_playlist(item_id, url, data, playlist)
3569 # Fallback to video extraction if no playlist alike page is recognized.
3570 # First check for the current video then try the v attribute of URL query.
3572 data, lambda x: x['currentVideoEndpoint']['watchEndpoint']['videoId'],
3573 compat_str) or video_id
3575 return self.url_result(video_id, ie=YoutubeIE.ie_key(), video_id=video_id)
3576 # Failed to recognize
3577 raise ExtractorError('Unable to recognize tab page')
3580 class YoutubePlaylistIE(InfoExtractor):
3581 IE_DESC = 'YouTube.com playlists'
3582 _VALID_URL = r'''(?x
)(?
:
3587 youtube(?
:kids
)?\
.com|
3592 (?P
<id>%(playlist_id)s)
3593 )''' % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
3594 IE_NAME = 'youtube:playlist'
3596 'note': 'issue #673',
3597 'url': 'PLBB231211A4F62143',
3599 'title': '[OLD]Team Fortress 2 (Class-based LP)',
3600 'id': 'PLBB231211A4F62143',
3601 'uploader': 'Wickydoo',
3602 'uploader_id': 'UCKSpbfbl5kRQpTdL7kMc-1Q',
3604 'playlist_mincount': 29,
3606 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
3608 'title': 'YDL_safe_search',
3609 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
3611 'playlist_count': 2,
3612 'skip': 'This playlist is private',
3615 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
3616 'playlist_count': 4,
3619 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
3620 'uploader': 'milan',
3621 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
3624 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
3625 'playlist_mincount': 982,
3627 'title': '2018 Chinese New Singles (11/6 updated)',
3628 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
3630 'uploader_id': 'UC21nz3_MesPLqtDqwdvnoxA',
3633 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
3634 'only_matching': True,
3636 # music album playlist
3637 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
3638 'only_matching': True,
3642 def suitable(cls, url):
3643 return False if YoutubeTabIE.suitable(url) else super(
3644 YoutubePlaylistIE, cls).suitable(url)
3646 def _real_extract(self, url):
3647 playlist_id = self._match_id(url)
3648 qs = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
3650 qs = {'list': playlist_id}
3651 return self.url_result(
3652 update_url_query('https://www.youtube.com/playlist', qs),
3653 ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3656 class YoutubeYtBeIE(InfoExtractor):
3657 IE_DESC = 'youtu.be'
3658 _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}
3660 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
3662 'id': 'yeWKywCrFtk',
3664 'title': 'Small Scale Baler and Braiding Rugs',
3665 'uploader': 'Backus-Page House Museum',
3666 'uploader_id': 'backuspagemuseum',
3667 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
3668 'upload_date': '20161008',
3669 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
3670 'categories': ['Nonprofits & Activism'],
3673 'dislike_count': int,
3677 'skip_download': True,
3680 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
3681 'only_matching': True,
3684 def _real_extract(self, url):
3685 mobj = re.match(self._VALID_URL, url)
3686 video_id = mobj.group('id')
3687 playlist_id = mobj.group('playlist_id')
3688 return self.url_result(
3689 update_url_query('https://www.youtube.com/watch', {
3691 'list': playlist_id,
3692 'feature': 'youtu.be',
3693 }), ie=YoutubeTabIE.ie_key(), video_id=playlist_id)
3696 class YoutubeYtUserIE(InfoExtractor):
3697 IE_DESC = 'YouTube.com user videos, URL or "ytuser" keyword'
3698 _VALID_URL = r'ytuser:(?P<id>.+)'
3700 'url': 'ytuser:phihag',
3701 'only_matching': True,
3704 def _real_extract(self, url):
3705 user_id = self._match_id(url)
3706 return self.url_result(
3707 'https://www.youtube.com/user/%s' % user_id,
3708 ie=YoutubeTabIE.ie_key(), video_id=user_id)
3711 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3712 IE_NAME = 'youtube:favorites'
3713 IE_DESC = 'YouTube.com liked videos, ":ytfav" for short (requires authentication)'
3714 _VALID_URL = r':ytfav(?:ou?rite)?s?'
3715 _LOGIN_REQUIRED = True
3718 'only_matching': True,
3720 'url': ':ytfavorites',
3721 'only_matching': True,
3724 def _real_extract(self, url):
3725 return self.url_result(
3726 'https://www.youtube.com/playlist?list=LL',
3727 ie=YoutubeTabIE.ie_key())
3730 class YoutubeSearchIE(SearchInfoExtractor, YoutubeBaseInfoExtractor):
3731 IE_DESC = 'YouTube.com searches'
3732 # there doesn't appear to be a real limit, for example if you search for
3733 # 'python' you get more than 8.000.000 results
3734 _MAX_RESULTS = float('inf')
3735 IE_NAME = 'youtube:search'
3736 _SEARCH_KEY = 'ytsearch'
3737 _SEARCH_PARAMS = None
3740 def _entries(self, query, n):
3744 'clientName': 'WEB',
3745 'clientVersion': '2.20201021.03.00',
3750 if self._SEARCH_PARAMS:
3751 data['params'] = self._SEARCH_PARAMS
3753 for page_num in itertools.count(1):
3754 search = self._download_json(
3755 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
3756 video_id='query "%s"' % query,
3757 note='Downloading page %s' % page_num,
3758 errnote='Unable to download API page', fatal=False,
3759 data=json.dumps(data).encode('utf8'),
3760 headers={'content-type': 'application/json'})
3763 slr_contents = try_get(
3765 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
3766 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
3768 if not slr_contents:
3771 # Youtube sometimes adds promoted content to searches,
3772 # changing the index location of videos and token.
3773 # So we search through all entries till we find them.
3774 continuation_token = None
3775 for slr_content in slr_contents:
3776 isr_contents = try_get(
3778 lambda x: x['itemSectionRenderer']['contents'],
3780 if not isr_contents:
3782 for content in isr_contents:
3783 if not isinstance(content, dict):
3785 video = content.get('videoRenderer')
3786 if not isinstance(video, dict):
3788 video_id = video.get('videoId')
3792 yield self._extract_video(video)
3797 if continuation_token is None:
3798 continuation_token = try_get(
3800 lambda x: x['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
3803 if not continuation_token:
3805 data['continuation'] = continuation_token
3807 def _get_n_results(self, query, n):
3808 """Get a specified number of results for a query"""
3809 return self.playlist_result(self._entries(query, n), query)
3812 class YoutubeSearchDateIE(YoutubeSearchIE):
3813 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3814 _SEARCH_KEY = 'ytsearchdate'
3815 IE_DESC = 'YouTube.com searches, newest videos first, "ytsearchdate" keyword'
3816 _SEARCH_PARAMS = 'CAI%3D'
3819 class YoutubeSearchURLIE(YoutubeSearchIE):
3820 IE_DESC = 'YouTube.com searches, "ytsearch" keyword'
3821 IE_NAME = YoutubeSearchIE.IE_NAME + '_url'
3822 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?:[^&]+)(?:[&]|$)'
3823 # _MAX_RESULTS = 100
3825 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3826 'playlist_mincount': 5,
3828 'title': 'youtube-dl test video',
3831 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3832 'only_matching': True,
3836 def _make_valid_url(cls):
3837 return cls._VALID_URL
3839 def _real_extract(self, url):
3840 qs = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
3841 query = (qs.get('search_query') or qs.get('q'))[0]
3842 self._SEARCH_PARAMS = qs.get('sp', ('',))[0]
3843 return self._get_n_results(query, self._MAX_RESULTS)
3846 class YoutubeFeedsInfoExtractor(YoutubeTabIE):
3848 Base class for feed extractors
3849 Subclasses must define the _FEED_NAME property.
3851 _LOGIN_REQUIRED = True
3857 return 'youtube:%s' % self._FEED_NAME
3859 def _real_initialize(self):
3862 def _real_extract(self, url):
3863 return self.url_result(
3864 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3865 ie=YoutubeTabIE.ie_key())
3868 class YoutubeWatchLaterIE(InfoExtractor):
3869 IE_NAME = 'youtube:watchlater'
3870 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3871 _VALID_URL = r':ytwatchlater'
3873 'url': ':ytwatchlater',
3874 'only_matching': True,
3877 def _real_extract(self, url):
3878 return self.url_result(
3879 'https://www.youtube.com/playlist?list=WL', ie=YoutubeTabIE.ie_key())
3882 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3883 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3884 _VALID_URL = r'https?://(?:www\.)?youtube\.com/?(?:[?#]|$)|:ytrec(?:ommended)?'
3885 _FEED_NAME = 'recommended'
3888 'only_matching': True,
3890 'url': ':ytrecommended',
3891 'only_matching': True,
3893 'url': 'https://youtube.com',
3894 'only_matching': True,
3898 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3899 IE_DESC = 'YouTube.com subscriptions feed, ":ytsubs" for short (requires authentication)'
3900 _VALID_URL = r':ytsub(?:scription)?s?'
3901 _FEED_NAME = 'subscriptions'
3904 'only_matching': True,
3906 'url': ':ytsubscriptions',
3907 'only_matching': True,
3911 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3912 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3913 _VALID_URL = r':ythistory'
3914 _FEED_NAME = 'history'
3916 'url': ':ythistory',
3917 'only_matching': True,
3921 class YoutubeTruncatedURLIE(InfoExtractor):
3922 IE_NAME = 'youtube:truncated_url'
3923 IE_DESC = False # Do not list
3924 _VALID_URL = r'''(?x
)
3926 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3929 annotation_id
=annotation_
[^
&]+|
3935 attribution_link
\?a
=[^
&]+
3941 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3942 'only_matching': True,
3944 'url': 'https://www.youtube.com/watch?',
3945 'only_matching': True,
3947 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3948 'only_matching': True,
3950 'url': 'https://www.youtube.com/watch?feature=foo',
3951 'only_matching': True,
3953 'url': 'https://www.youtube.com/watch?hl=en-GB',
3954 'only_matching': True,
3956 'url': 'https://www.youtube.com/watch?t=2372',
3957 'only_matching': True,
3960 def _real_extract(self, url):
3961 raise ExtractorError(
3962 'Did you forget to quote the URL? Remember that & is a meta '
3963 'character in most shells, so you want to put the URL in quotes, '
3965 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3966 ' or simply youtube-dl BaW_jenozKc .',
3970 class YoutubeTruncatedIDIE(InfoExtractor):
3971 IE_NAME = 'youtube:truncated_id'
3972 IE_DESC = False # Do not list
3973 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3976 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3977 'only_matching': True,
3980 def _real_extract(self, url):
3981 video_id = self._match_id(url)
3982 raise ExtractorError(
3983 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),
3987 # Do Youtube show urls even exist anymore? I couldn't find any
3989 class YoutubeShowIE(YoutubeTabIE
):
3990 IE_DESC
= 'YouTube.com (multi-season) shows'
3991 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3992 IE_NAME
= 'youtube:show'
3994 'url': 'https://www.youtube.com/show/airdisasters',
3995 'playlist_mincount': 5,
3997 'id': 'airdisasters',
3998 'title': 'Air Disasters',
4002 def _real_extract(self
, url
):
4003 playlist_id
= self
._match
_id
(url
)
4004 return super(YoutubeShowIE
, self
)._real
_extract
(
4005 'https://www.youtube.com/show/%s/playlists' % playlist_id
)