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
,
36 get_element_by_attribute
,
60 class YoutubeBaseInfoExtractor(InfoExtractor
):
61 """Provide base functions for Youtube extractors"""
62 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
63 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
65 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
66 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
67 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
69 _NETRC_MACHINE
= 'youtube'
70 # If True it will raise an error if no login info is provided
71 _LOGIN_REQUIRED
= False
73 _PLAYLIST_ID_RE
= r
'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
74 _INITIAL_DATA_RE
= r
'(?:window\["ytInitialData"\]|ytInitialData)\W?=\W?({.*?});'
75 _YTCFG_DATA_RE
= r
"ytcfg.set\(({.*?})\)"
77 _YOUTUBE_CLIENT_HEADERS
= {
78 'x-youtube-client-name': '1',
79 'x-youtube-client-version': '1.20200609.04.02',
82 def _set_language(self
):
84 '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
85 # YouTube sets the expire time to about two months
86 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
88 def _ids_to_results(self
, ids
):
90 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
95 Attempt to log in to YouTube.
96 True is returned if successful or skipped.
97 False is returned if login failed.
99 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
101 username
, password
= self
._get
_login
_info
()
102 # No authentication to be performed
104 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
105 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
106 if self
._downloader
.params
.get('cookiefile') and False: # TODO remove 'and False' later - too many people using outdated cookies and open issues, remind them.
107 self
.to_screen('[Cookies] Reminder - Make sure to always use up to date cookies!')
110 login_page
= self
._download
_webpage
(
111 self
._LOGIN
_URL
, None,
112 note
='Downloading login page',
113 errnote
='unable to fetch login page', fatal
=False)
114 if login_page
is False:
117 login_form
= self
._hidden
_inputs
(login_page
)
119 def req(url
, f_req
, note
, errnote
):
120 data
= login_form
.copy()
123 'checkConnection': 'youtube',
124 'checkedDomains': 'youtube',
126 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
127 'f.req': json
.dumps(f_req
),
128 'flowName': 'GlifWebSignIn',
129 'flowEntry': 'ServiceLogin',
130 # TODO: reverse actual botguard identifier generation algo
131 'bgRequest': '["identifier",""]',
133 return self
._download
_json
(
134 url
, None, note
=note
, errnote
=errnote
,
135 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
137 data
=urlencode_postdata(data
), headers
={
138 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
139 'Google-Accounts-XSRF': 1,
143 self
._downloader
.report_warning(message
)
147 None, [], None, 'US', None, None, 2, False, True,
151 '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',
153 1, [None, None, []], None, None, None, True
158 lookup_results
= req(
159 self
._LOOKUP
_URL
, lookup_req
,
160 'Looking up account info', 'Unable to look up account info')
162 if lookup_results
is False:
165 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
167 warn('Unable to extract user hash')
172 None, 1, None, [1, None, None, None, [password
, None, True]],
174 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],
175 1, [None, None, []], None, None, None, True
178 challenge_results
= req(
179 self
._CHALLENGE
_URL
, challenge_req
,
180 'Logging in', 'Unable to log in')
182 if challenge_results
is False:
185 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
187 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
189 'Unable to login: %s' % 'Invalid password'
190 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
193 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
195 warn('Unable to extract result entry')
198 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
200 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
201 if challenge_str
== 'TWO_STEP_VERIFICATION':
202 # SEND_SUCCESS - TFA code has been successfully sent to phone
203 # QUOTA_EXCEEDED - reached the limit of TFA codes
204 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
205 if status
== 'QUOTA_EXCEEDED':
206 warn('Exceeded the limit of TFA codes, try later')
209 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
211 warn('Unable to extract TL')
214 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
218 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
219 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
222 tfa_code
= remove_start(tfa_code
, 'G-')
225 user_hash
, None, 2, None,
227 9, None, None, None, None, None, None, None,
228 [None, tfa_code
, True, 2]
232 self
._TFA
_URL
.format(tl
), tfa_req
,
233 'Submitting TFA code', 'Unable to submit TFA code')
235 if tfa_results
is False:
238 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
240 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
242 'Unable to finish TFA: %s' % 'Invalid TFA code'
243 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
246 check_cookie_url
= try_get(
247 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
250 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
251 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
252 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
254 challenge
= CHALLENGES
.get(
256 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
257 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
260 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
262 if not check_cookie_url
:
263 warn('Unable to extract CheckCookie URL')
266 check_cookie_results
= self
._download
_webpage
(
267 check_cookie_url
, None, 'Checking cookie', fatal
=False)
269 if check_cookie_results
is False:
272 if 'https://myaccount.google.com/' not in check_cookie_results
:
273 warn('Unable to log in')
278 def _download_webpage_handle(self
, *args
, **kwargs
):
279 query
= kwargs
.get('query', {}).copy()
280 kwargs
['query'] = query
281 return super(YoutubeBaseInfoExtractor
, self
)._download
_webpage
_handle
(
282 *args
, **compat_kwargs(kwargs
))
284 def _get_yt_initial_data(self
, video_id
, webpage
):
285 config
= self
._search
_regex
(
286 (r
'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});',
287 r
'var\s+ytInitialData\s*=\s*(.*?)(?<=});'),
288 webpage
, 'ytInitialData', default
=None)
290 return self
._parse
_json
(
291 uppercase_escape(config
), video_id
, fatal
=False)
293 def _real_initialize(self
):
294 if self
._downloader
is None:
297 if not self
._login
():
301 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
303 def _find_entries_in_json(self
, extracted
):
308 if obj
is None or isinstance(obj
, str):
311 if type(obj
) is list:
315 if type(obj
) is dict:
316 if self
._is
_entry
(obj
):
320 if 'continuationCommand' in obj
:
321 c
['continuation'] = obj
324 for _
, o
in obj
.items():
327 _real_find(extracted
)
329 return entries
, try_get(c
, lambda x
: x
["continuation"])
331 def _entries(self
, page
, playlist_id
, max_pages
=None):
335 for m
in re
.finditer(self
._YTCFG
_DATA
_RE
, page
):
336 parsed
= self
._parse
_json
(m
.group(1), playlist_id
,
337 transform_source
=js_to_json
, fatal
=False)
339 yt_conf
.update(parsed
)
341 data_json
= self
._parse
_json
(self
._search
_regex
(self
._INITIAL
_DATA
_RE
, page
, 'ytInitialData'), None)
343 for page_num
in range(1, max_pages
+ 1) if max_pages
is not None else itertools
.count(1):
344 entries
, continuation
= self
._find
_entries
_in
_json
(data_json
)
345 processed
= self
._process
_entries
(entries
, seen
)
349 for entry
in processed
:
352 if not continuation
or not yt_conf
:
354 continuation_token
= try_get(continuation
, lambda x
: x
['continuationCommand']['token'])
355 continuation_url
= try_get(continuation
, lambda x
: x
['commandMetadata']['webCommandMetadata']['apiUrl'])
356 if not continuation_token
or not continuation_url
:
361 while count
<= retries
:
363 # Downloading page may result in intermittent 5xx HTTP error
364 # that is usually worked around with a retry
365 data_json
= self
._download
_json
(
366 'https://www.youtube.com%s' % continuation_url
,
368 'Downloading continuation page #%s%s' % (page_num
, ' (retry #%d)' % count
if count
else ''),
370 transform_source
=uppercase_escape
,
372 'key': try_get(yt_conf
, lambda x
: x
['INNERTUBE_API_KEY'])
374 data
= str(json
.dumps({
375 'context': try_get(yt_conf
, lambda x
: x
['INNERTUBE_CONTEXT']),
376 'continuation': continuation_token
377 })).encode(encoding
='UTF-8',errors
='strict'),
379 'Content-Type': 'application/json'
383 except ExtractorError
as e
:
384 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (500, 503):
390 def _extract_title(self
, renderer
):
391 title
= try_get(renderer
, lambda x
: x
['title']['runs'][0]['text'], compat_str
)
394 return try_get(renderer
, lambda x
: x
['title']['simpleText'], compat_str
)
397 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
398 def _is_entry(self
, obj
):
399 return 'videoId' in obj
401 def _process_entries(self
, entries
, seen
):
404 for renderer
in entries
:
405 video_id
= try_get(renderer
, lambda x
: x
['videoId'])
406 video_title
= self
._extract
_title
(renderer
)
408 if video_id
is None or video_title
is None:
409 # we do not have a videoRenderer or title extraction broke
412 video_title
= video_title
.strip()
415 idx
= ids_in_page
.index(video_id
)
416 if video_title
and not titles_in_page
[idx
]:
417 titles_in_page
[idx
] = video_title
419 ids_in_page
.append(video_id
)
420 titles_in_page
.append(video_title
)
422 for video_id
, video_title
in zip(ids_in_page
, titles_in_page
):
423 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
426 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
427 def _is_entry(self
, obj
):
428 return 'playlistId' in obj
430 def _process_entries(self
, entries
, seen
):
431 for playlist_id
in orderedSet(try_get(r
, lambda x
: x
['playlistId']) for r
in entries
):
433 yield self
.url_result(
434 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
436 def _real_extract(self
, url
):
437 playlist_id
= self
._match
_id
(url
)
438 webpage
= self
._download
_webpage
(url
, playlist_id
)
439 title
= self
._og
_search
_title
(webpage
, fatal
=False)
440 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
443 class YoutubeIE(YoutubeBaseInfoExtractor
):
444 IE_DESC
= 'YouTube.com'
445 _VALID_URL
= r
"""(?x)^
447 (?:https?://|//) # http(s):// or protocol-independent URL
448 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
449 (?:www\.)?deturl\.com/www\.youtube\.com/|
450 (?:www\.)?pwnyoutube\.com/|
451 (?:www\.)?hooktube\.com/|
452 (?:www\.)?yourepeat\.com/|
453 tube\.majestyc\.net/|
454 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
455 (?:(?:www|dev)\.)?invidio\.us/|
456 (?:(?:www|no)\.)?invidiou\.sh/|
457 (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
458 (?:www\.)?invidious\.kabi\.tk/|
459 (?:www\.)?invidious\.13ad\.de/|
460 (?:www\.)?invidious\.mastodon\.host/|
461 (?:www\.)?invidious\.nixnet\.xyz/|
462 (?:www\.)?invidious\.drycat\.fr/|
463 (?:www\.)?tube\.poal\.co/|
464 (?:www\.)?vid\.wxzm\.sx/|
465 (?:www\.)?yewtu\.be/|
466 (?:www\.)?yt\.elukerio\.org/|
467 (?:www\.)?yt\.lelux\.fi/|
468 (?:www\.)?invidious\.ggc-project\.de/|
469 (?:www\.)?yt\.maisputain\.ovh/|
470 (?:www\.)?invidious\.13ad\.de/|
471 (?:www\.)?invidious\.toot\.koeln/|
472 (?:www\.)?invidious\.fdn\.fr/|
473 (?:www\.)?watch\.nettohikari\.com/|
474 (?:www\.)?kgg2m7yk5aybusll\.onion/|
475 (?:www\.)?qklhadlycap4cnod\.onion/|
476 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
477 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
478 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
479 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
480 (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
481 (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
482 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
483 (?:.*?\#/)? # handle anchor (#/) redirect urls
484 (?: # the various things that can precede the ID:
485 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
486 |(?: # or the v= param in all its forms
487 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
488 (?:\?|\#!?) # the params delimiter ? or # or #!
489 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
494 youtu\.be| # just youtu.be/xxxx
495 vid\.plus| # or vid.plus/xxxx
496 zwearz\.com/watch| # or zwearz.com/watch/xxxx
498 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
500 )? # all until now is optional -> you can pass the naked ID
501 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
504 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
505 WL # WL are handled by the watch later IE
508 (?(1).+)? # if we found the ID, everything can follow
509 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
510 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
512 r
'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$',
513 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$',
516 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
517 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
518 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
519 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
520 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
521 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
522 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
523 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
524 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
525 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
526 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
527 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
528 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
529 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
530 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
531 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
532 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
533 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
537 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
538 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
539 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
540 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
541 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
542 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
543 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
545 # Apple HTTP Live Streaming
546 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
547 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
548 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
549 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
550 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
551 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
552 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
553 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
556 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
557 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
558 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
559 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
560 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
561 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
562 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
563 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
564 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
565 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
566 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
567 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
570 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
571 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
572 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
573 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
574 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
575 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
576 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
579 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
580 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
581 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
582 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
583 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
584 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
585 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
586 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
587 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
588 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
589 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
590 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
591 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
592 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
593 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
594 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
595 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
596 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
597 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
598 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
599 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
600 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
603 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
604 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
606 # Dash webm audio with opus inside
607 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
608 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
609 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
612 '_rtmp': {'protocol': 'rtmp'}
,
614 # av01 video only formats sometimes served with "unknown" codecs
615 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
616 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
617 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
618 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
620 _SUBTITLE_FORMATS
= ('json3', 'srv1', 'srv2', 'srv3', 'ttml', 'vtt')
627 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
631 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
632 'uploader': 'Philipp Hagemeister',
633 'uploader_id': 'phihag',
634 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
635 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
636 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
637 'upload_date': '20121002',
638 '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 .',
639 'categories': ['Science & Technology'],
640 'tags': ['youtube-dl'],
644 'dislike_count': int,
650 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
651 'note': 'Embed-only video (#1746)',
655 'upload_date': '20120608',
656 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
657 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
658 'uploader': 'SET India',
659 'uploader_id': 'setindia',
660 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
665 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
666 'note': 'Use the first video ID in the URL',
670 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
671 'uploader': 'Philipp Hagemeister',
672 'uploader_id': 'phihag',
673 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
674 'upload_date': '20121002',
675 '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 .',
676 'categories': ['Science & Technology'],
677 'tags': ['youtube-dl'],
681 'dislike_count': int,
684 'skip_download': True,
688 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
689 'note': '256k DASH audio (format 141) via DASH manifest',
693 'upload_date': '20121002',
694 'uploader_id': '8KVIDEO',
695 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
697 'uploader': '8KVIDEO',
698 'title': 'UHDTV TEST 8K VIDEO.mp4'
701 'youtube_include_dash_manifest': True,
704 'skip': 'format 141 not served anymore',
708 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
713 'upload_date': '20100909',
714 'uploader': 'Amazing Atheist',
715 'uploader_id': 'TheAmazingAtheist',
716 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
717 'title': 'Burning Everyone\'s Koran',
718 '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',
721 # Normal age-gate video (embed allowed)
723 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
727 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
728 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
730 'uploader': 'The Witcher',
731 'uploader_id': 'WitcherGame',
732 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
733 'upload_date': '20140605',
737 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
739 'url': 'lqQg6PlCWgI',
744 'upload_date': '20150827',
745 'uploader_id': 'olympic',
746 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
747 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
748 'uploader': 'Olympic',
749 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
752 'skip_download': 'requires avconv',
757 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
761 'stretched_ratio': 16 / 9.,
763 'upload_date': '20110310',
764 'uploader_id': 'AllenMeow',
765 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
766 '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',
768 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
771 # url_encoded_fmt_stream_map is empty string
773 'url': 'qEJwOuvDf7I',
777 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
779 'upload_date': '20150404',
780 'uploader_id': 'spbelect',
781 'uploader': 'Наблюдатели Петербурга',
784 'skip_download': 'requires avconv',
786 'skip': 'This live event has ended.',
788 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
790 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
794 'title': 'md5:7b81415841e02ecd4313668cde88737a',
795 'description': 'md5:116377fd2963b81ec4ce64b542173306',
797 'upload_date': '20150625',
798 'uploader_id': 'dorappi2000',
799 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
800 'uploader': 'dorappi2000',
801 'formats': 'mincount:31',
803 'skip': 'not actual anymore',
805 # DASH manifest with segment_list
807 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
808 'md5': '8ce563a1d667b599d21064e982ab9e31',
812 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
813 'uploader': 'Airtek',
814 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
815 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
816 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
819 'youtube_include_dash_manifest': True,
820 'format': '135', # bestvideo
822 'skip': 'This live event has ended.',
825 # Multifeed videos (multiple cameras), URL is for Main Camera
826 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
829 'title': 'teamPGP: Rocket League Noob Stream',
830 'description': 'md5:dc7872fb300e143831327f1bae3af010',
836 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
837 'description': 'md5:dc7872fb300e143831327f1bae3af010',
839 'upload_date': '20150721',
840 'uploader': 'Beer Games Beer',
841 'uploader_id': 'beergamesbeer',
842 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
843 'license': 'Standard YouTube License',
849 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
850 'description': 'md5:dc7872fb300e143831327f1bae3af010',
852 'upload_date': '20150721',
853 'uploader': 'Beer Games Beer',
854 'uploader_id': 'beergamesbeer',
855 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
856 'license': 'Standard YouTube License',
862 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
863 'description': 'md5:dc7872fb300e143831327f1bae3af010',
865 'upload_date': '20150721',
866 'uploader': 'Beer Games Beer',
867 'uploader_id': 'beergamesbeer',
868 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
869 'license': 'Standard YouTube License',
875 'title': 'teamPGP: Rocket League Noob Stream (zim)',
876 'description': 'md5:dc7872fb300e143831327f1bae3af010',
878 'upload_date': '20150721',
879 'uploader': 'Beer Games Beer',
880 'uploader_id': 'beergamesbeer',
881 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
882 'license': 'Standard YouTube License',
886 'skip_download': True,
888 'skip': 'This video is not available.',
891 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
892 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
895 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
898 'skip': 'Not multifeed anymore',
901 'url': 'https://vid.plus/FlRa-iH7PGw',
902 'only_matching': True,
905 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
906 'only_matching': True,
909 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
910 # Also tests cut-off URL expansion in video description (see
911 # https://github.com/ytdl-org/youtube-dl/issues/1892,
912 # https://github.com/ytdl-org/youtube-dl/issues/8164)
913 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
917 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
918 'alt_title': 'Dark Walk - Position Music',
919 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
921 'upload_date': '20151119',
922 'uploader_id': 'IronSoulElf',
923 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
924 'uploader': 'IronSoulElf',
925 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
926 'track': 'Dark Walk - Position Music',
927 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
928 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
931 'skip_download': True,
935 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
936 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
937 'only_matching': True,
940 # Video with yt:stretch=17:0
941 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
945 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
946 'description': 'md5:ee18a25c350637c8faff806845bddee9',
947 'upload_date': '20151107',
948 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
949 'uploader': 'CH GAMER DROID',
952 'skip_download': True,
954 'skip': 'This video does not exist.',
957 # Video licensed under Creative Commons
958 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
962 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
963 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
965 'upload_date': '20150127',
966 'uploader_id': 'BerkmanCenter',
967 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
968 'uploader': 'The Berkman Klein Center for Internet & Society',
969 'license': 'Creative Commons Attribution license (reuse allowed)',
972 'skip_download': True,
976 # Channel-like uploader_url
977 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
981 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
982 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
984 'upload_date': '20151119',
985 'uploader': 'Bernie Sanders',
986 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
987 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
988 'license': 'Creative Commons Attribution license (reuse allowed)',
991 'skip_download': True,
995 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
996 'only_matching': True,
999 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1000 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1001 'only_matching': True,
1004 # Rental video preview
1005 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1007 'id': 'uGpuVWrhIzE',
1009 'title': 'Piku - Trailer',
1010 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1011 'upload_date': '20150811',
1012 'uploader': 'FlixMatrix',
1013 'uploader_id': 'FlixMatrixKaravan',
1014 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1015 'license': 'Standard YouTube License',
1018 'skip_download': True,
1020 'skip': 'This video is not available.',
1023 # YouTube Red video with episode data
1024 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1026 'id': 'iqKdEhx-dD4',
1028 'title': 'Isolation - Mind Field (Ep 1)',
1029 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1031 'upload_date': '20170118',
1032 'uploader': 'Vsauce',
1033 'uploader_id': 'Vsauce',
1034 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1035 'series': 'Mind Field',
1037 'episode_number': 1,
1040 'skip_download': True,
1042 'expected_warnings': [
1043 'Skipping DASH manifest',
1047 # The following content has been identified by the YouTube community
1048 # as inappropriate or offensive to some audiences.
1049 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1051 'id': '6SJNVb0GnPI',
1053 'title': 'Race Differences in Intelligence',
1054 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1056 'upload_date': '20140124',
1057 'uploader': 'New Century Foundation',
1058 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1059 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1062 'skip_download': True,
1067 'url': '1t24XAntNCY',
1068 'only_matching': True,
1071 # geo restricted to JP
1072 'url': 'sJL6WA-aGkQ',
1073 'only_matching': True,
1076 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1077 'only_matching': True,
1080 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1081 'only_matching': True,
1085 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1086 'only_matching': True,
1089 # Video with unsupported adaptive stream type formats
1090 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1092 'id': 'Z4Vy8R84T1U',
1094 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1095 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1097 'upload_date': '20130923',
1098 'uploader': 'Amelia Putri Harwita',
1099 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1100 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1101 'formats': 'maxcount:10',
1104 'skip_download': True,
1105 'youtube_include_dash_manifest': False,
1107 'skip': 'not actual anymore',
1110 # Youtube Music Auto-generated description
1111 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1113 'id': 'MgNrAu2pzNs',
1115 'title': 'Voyeur Girl',
1116 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1117 'upload_date': '20190312',
1118 'uploader': 'Stephen - Topic',
1119 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1120 'artist': 'Stephen',
1121 'track': 'Voyeur Girl',
1122 'album': 'it\'s too much love to know my dear',
1123 'release_date': '20190313',
1124 'release_year': 2019,
1127 'skip_download': True,
1131 # Youtube Music Auto-generated description
1132 # Retrieve 'artist' field from 'Artist:' in video description
1133 # when it is present on youtube music video
1134 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1136 'id': 'k0jLE7tTwjY',
1138 'title': 'Latch Feat. Sam Smith',
1139 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1140 'upload_date': '20150110',
1141 'uploader': 'Various Artists - Topic',
1142 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1143 'artist': 'Disclosure',
1144 'track': 'Latch Feat. Sam Smith',
1145 'album': 'Latch Featuring Sam Smith',
1146 'release_date': '20121008',
1147 'release_year': 2012,
1150 'skip_download': True,
1154 # Youtube Music Auto-generated description
1155 # handle multiple artists on youtube music video
1156 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1158 'id': '74qn0eJSjpA',
1160 'title': 'Eastside',
1161 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1162 'upload_date': '20180710',
1163 'uploader': 'Benny Blanco - Topic',
1164 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1165 'artist': 'benny blanco, Halsey, Khalid',
1166 'track': 'Eastside',
1167 'album': 'Eastside',
1168 'release_date': '20180713',
1169 'release_year': 2018,
1172 'skip_download': True,
1176 # Youtube Music Auto-generated description
1177 # handle youtube music video with release_year and no release_date
1178 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1180 'id': '-hcAI0g-f5M',
1182 'title': 'Put It On Me',
1183 'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
1184 'upload_date': '20180426',
1185 'uploader': 'Matt Maeson - Topic',
1186 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1187 'artist': 'Matt Maeson',
1188 'track': 'Put It On Me',
1189 'album': 'The Hearse',
1190 'release_date': None,
1191 'release_year': 2018,
1194 'skip_download': True,
1198 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1199 'only_matching': True,
1202 # invalid -> valid video id redirection
1203 'url': 'DJztXj2GPfl',
1205 'id': 'DJztXj2GPfk',
1207 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1208 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1209 'upload_date': '20090125',
1210 'uploader': 'Prochorowka',
1211 'uploader_id': 'Prochorowka',
1212 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1213 'artist': 'Panjabi MC',
1214 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1215 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1218 'skip_download': True,
1222 # empty description results in an empty string
1223 'url': 'https://www.youtube.com/watch?v=x41yOUIvK2k',
1225 'id': 'x41yOUIvK2k',
1227 'title': 'IMG 3456',
1229 'upload_date': '20170613',
1230 'uploader_id': 'ElevageOrVert',
1231 'uploader': 'ElevageOrVert',
1234 'skip_download': True,
1239 def __init__(self
, *args
, **kwargs
):
1240 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1241 self
._player
_cache
= {}
1243 def report_video_info_webpage_download(self
, video_id
):
1244 """Report attempt to download video info webpage."""
1245 self
.to_screen('%s: Downloading video info webpage' % video_id
)
1247 def report_information_extraction(self
, video_id
):
1248 """Report attempt to extract video information."""
1249 self
.to_screen('%s: Extracting video information' % video_id
)
1251 def report_unavailable_format(self
, video_id
, format
):
1252 """Report extracted video URL."""
1253 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
1255 def report_rtmp_download(self
):
1256 """Indicate the download will use the RTMP protocol."""
1257 self
.to_screen('RTMP download detected')
1259 def _signature_cache_id(self
, example_sig
):
1260 """ Return a string representation of a signature """
1261 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1264 def _extract_player_info(cls
, player_url
):
1265 for player_re
in cls
._PLAYER
_INFO
_RE
:
1266 id_m
= re
.search(player_re
, player_url
)
1270 raise ExtractorError('Cannot identify player %r' % player_url
)
1271 return id_m
.group('ext'), id_m
.group('id')
1273 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1274 player_type
, player_id
= self
._extract
_player
_info
(player_url
)
1276 # Read from filesystem cache
1277 func_id
= '%s_%s_%s' % (
1278 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
1279 assert os
.path
.basename(func_id
) == func_id
1281 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1282 if cache_spec
is not None:
1283 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1286 'Downloading player %s' % player_url
1287 if self
._downloader
.params
.get('verbose') else
1288 'Downloading %s player %s' % (player_type
, player_id
)
1290 if player_type
== 'js':
1291 code
= self
._download
_webpage
(
1292 player_url
, video_id
,
1294 errnote
='Download of %s failed' % player_url
)
1295 res
= self
._parse
_sig
_js
(code
)
1296 elif player_type
== 'swf':
1297 urlh
= self
._request
_webpage
(
1298 player_url
, video_id
,
1300 errnote
='Download of %s failed' % player_url
)
1302 res
= self
._parse
_sig
_swf
(code
)
1304 assert False, 'Invalid player type %r' % player_type
1306 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1307 cache_res
= res(test_string
)
1308 cache_spec
= [ord(c
) for c
in cache_res
]
1310 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1313 def _print_sig_code(self
, func
, example_sig
):
1314 def gen_sig_code(idxs
):
1315 def _genslice(start
, end
, step
):
1316 starts
= '' if start
== 0 else str(start
)
1317 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1318 steps
= '' if step
== 1 else (':%d' % step
)
1319 return 's[%s%s%s]' % (starts
, ends
, steps
)
1322 # Quelch pyflakes warnings - start will be set when step is set
1323 start
= '(Never used)'
1324 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1325 if step
is not None:
1326 if i
- prev
== step
:
1328 yield _genslice(start
, prev
, step
)
1331 if i
- prev
in [-1, 1]:
1336 yield 's[%d]' % prev
1340 yield _genslice(start
, i
, step
)
1342 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1343 cache_res
= func(test_string
)
1344 cache_spec
= [ord(c
) for c
in cache_res
]
1345 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1346 signature_id_tuple
= '(%s)' % (
1347 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1348 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1349 ' return %s\n') % (signature_id_tuple
, expr_code
)
1350 self
.to_screen('Extracted signature function:\n' + code
)
1352 def _parse_sig_js(self
, jscode
):
1353 funcname
= self
._search
_regex
(
1354 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1355 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1356 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\(\s*""\s*\)',
1357 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1359 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1360 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1361 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1362 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1363 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1364 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1365 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1366 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1367 jscode, 'Initial JS player signature function name
', group='sig
')
1369 jsi = JSInterpreter(jscode)
1370 initial_function = jsi.extract_function(funcname)
1371 return lambda s: initial_function([s])
1373 def _parse_sig_swf(self, file_contents):
1374 swfi = SWFInterpreter(file_contents)
1375 TARGET_CLASSNAME = 'SignatureDecipher
'
1376 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1377 initial_function = swfi.extract_function(searched_class, 'decipher
')
1378 return lambda s: initial_function([s])
1380 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1381 """Turn the encrypted s field into a working signature"""
1383 if player_url is None:
1384 raise ExtractorError('Cannot decrypt signature without player_url
')
1386 if player_url.startswith('//'):
1387 player_url = 'https
:' + player_url
1388 elif not re.match(r'https?
://', player_url):
1389 player_url = compat_urlparse.urljoin(
1390 'https
://www
.youtube
.com
', player_url)
1392 player_id = (player_url, self._signature_cache_id(s))
1393 if player_id not in self._player_cache:
1394 func = self._extract_signature_function(
1395 video_id, player_url, s
1397 self._player_cache[player_id] = func
1398 func = self._player_cache[player_id]
1399 if self._downloader.params.get('youtube_print_sig_code
'):
1400 self._print_sig_code(func, s)
1402 except Exception as e:
1403 tb = traceback.format_exc()
1404 raise ExtractorError(
1405 'Signature extraction failed
: ' + tb, cause=e)
1407 def _get_subtitles(self, video_id, webpage, has_live_chat_replay):
1409 subs_doc = self._download_xml(
1410 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1411 video_id, note=False)
1412 except ExtractorError as err:
1413 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1417 for track in subs_doc.findall('track
'):
1418 lang = track.attrib['lang_code
']
1419 if lang in sub_lang_list:
1422 for ext in self._SUBTITLE_FORMATS:
1423 params = compat_urllib_parse_urlencode({
1427 'name
': track.attrib['name
'].encode('utf
-8'),
1429 sub_formats.append({
1430 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1433 sub_lang_list[lang] = sub_formats
1434 if has_live_chat_replay:
1435 sub_lang_list['live_chat
'] = [
1437 'video_id
': video_id,
1439 'protocol
': 'youtube_live_chat_replay
',
1442 if not sub_lang_list:
1443 self._downloader.report_warning('video doesn
\'t have subtitles
')
1445 return sub_lang_list
1447 def _get_ytplayer_config(self, video_id, webpage):
1449 # User data may contain arbitrary character sequences that may affect
1450 # JSON extraction with regex, e.g. when '};' is contained the second
1451 # regex won't capture the whole JSON
. Yet working around by trying more
1452 # concrete regex first keeping in mind proper quoted string handling
1453 # to be implemented in future that will replace this workaround (see
1454 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1455 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1456 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1457 r
';ytplayer\.config\s*=\s*({.+?});',
1458 r
'ytInitialPlayerResponse\s*=\s*({.+?});var meta'
1460 config
= self
._search
_regex
(
1461 patterns
, webpage
, 'ytplayer.config', default
=None)
1463 return self
._parse
_json
(
1464 uppercase_escape(config
), video_id
, fatal
=False)
1466 def _get_music_metadata_from_yt_initial(self
, yt_initial
):
1473 contents
= try_get(yt_initial
, lambda x
: x
['contents']['twoColumnWatchNextResults']['results']['results']['contents'])
1474 if type(contents
) is list:
1475 for content
in contents
:
1477 if type(content
) is not dict:
1479 videoSecondaryInfoRenderer
= try_get(content
, lambda x
: x
['videoSecondaryInfoRenderer'])
1480 if type(videoSecondaryInfoRenderer
) is not dict:
1482 rows
= try_get(videoSecondaryInfoRenderer
, lambda x
: x
['metadataRowContainer']['metadataRowContainerRenderer']['rows'])
1483 if type(rows
) is not list:
1486 metadataRowRenderer
= try_get(row
, lambda x
: x
['metadataRowRenderer'])
1487 if type(metadataRowRenderer
) is not dict:
1489 key
= try_get(metadataRowRenderer
, lambda x
: x
['title']['simpleText'])
1490 value
= try_get(metadataRowRenderer
, lambda x
: x
['contents'][0]['simpleText']) or \
1491 try_get(metadataRowRenderer
, lambda x
: x
['contents'][0]['runs'][0]['text'])
1492 if type(key
) is not str or type(value
) is not str:
1495 if key_map
[key
] in music_track
:
1496 # we've started on a new track
1497 music_metadata
.append(music_track
)
1499 music_track
[key_map
[key
]] = value
1500 if len(music_track
.keys()):
1501 music_metadata
.append(music_track
)
1502 return music_metadata
1504 def _get_automatic_captions(self
, video_id
, webpage
):
1505 """We need the webpage for getting the captions url, pass it as an
1506 argument to speed up the process."""
1507 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1508 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1509 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1510 if not player_config
:
1511 self
._downloader
.report_warning(err_msg
)
1514 if "args" in player_config
and "ttsurl" in player_config
["args"]:
1515 args
= player_config
['args']
1516 caption_url
= args
['ttsurl']
1517 timestamp
= args
['timestamp']
1519 # We get the available subtitles
1520 list_params
= compat_urllib_parse_urlencode({
1525 list_url
= caption_url
+ '&' + list_params
1526 caption_list
= self
._download
_xml
(list_url
, video_id
)
1527 original_lang_node
= caption_list
.find('track')
1528 if original_lang_node
is None:
1529 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1531 original_lang
= original_lang_node
.attrib
['lang_code']
1532 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1535 for lang_node
in caption_list
.findall('target'):
1536 sub_lang
= lang_node
.attrib
['lang_code']
1538 for ext
in self
._SUBTITLE
_FORMATS
:
1539 params
= compat_urllib_parse_urlencode({
1540 'lang': original_lang
,
1544 'kind': caption_kind
,
1546 sub_formats
.append({
1547 'url': caption_url
+ '&' + params
,
1550 sub_lang_list
[sub_lang
] = sub_formats
1551 return sub_lang_list
1553 def make_captions(sub_url
, sub_langs
):
1554 parsed_sub_url
= compat_urllib_parse_urlparse(sub_url
)
1555 caption_qs
= compat_parse_qs(parsed_sub_url
.query
)
1557 for sub_lang
in sub_langs
:
1559 for ext
in self
._SUBTITLE
_FORMATS
:
1561 'tlang': [sub_lang
],
1564 sub_url
= compat_urlparse
.urlunparse(parsed_sub_url
._replace
(
1565 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1566 sub_formats
.append({
1570 captions
[sub_lang
] = sub_formats
1573 # New captions format as of 22.06.2017
1574 if "args" in player_config
:
1575 player_response
= player_config
["args"].get('player_response')
1577 # New player system (ytInitialPlayerResponse) as of October 2020
1578 player_response
= player_config
1581 if isinstance(player_response
, compat_str
):
1582 player_response
= self
._parse
_json
(
1583 player_response
, video_id
, fatal
=False)
1585 renderer
= player_response
['captions']['playerCaptionsTracklistRenderer']
1586 caption_tracks
= renderer
['captionTracks']
1587 for caption_track
in caption_tracks
:
1588 if 'kind' not in caption_track
:
1589 # not an automatic transcription
1591 base_url
= caption_track
['baseUrl']
1593 for lang
in renderer
['translationLanguages']:
1594 lang_code
= lang
.get('languageCode')
1596 sub_lang_list
.append(lang_code
)
1597 return make_captions(base_url
, sub_lang_list
)
1599 self
._downloader
.report_warning("Couldn't find automatic captions for %s" % video_id
)
1602 if "args" in player_config
:
1603 args
= player_config
["args"]
1605 # Some videos don't provide ttsurl but rather caption_tracks and
1606 # caption_translation_languages (e.g. 20LmZk1hakA)
1607 # Does not used anymore as of 22.06.2017
1608 caption_tracks
= args
['caption_tracks']
1609 caption_translation_languages
= args
['caption_translation_languages']
1610 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1612 for lang
in caption_translation_languages
.split(','):
1613 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1614 sub_lang
= lang_qs
.get('lc', [None])[0]
1616 sub_lang_list
.append(sub_lang
)
1617 return make_captions(caption_url
, sub_lang_list
)
1618 # An extractor error can be raise by the download process if there are
1619 # no automatic captions but there are subtitles
1620 except (KeyError, IndexError, ExtractorError
):
1621 self
._downloader
.report_warning(err_msg
)
1624 def _mark_watched(self
, video_id
, video_info
, player_response
):
1625 playback_url
= url_or_none(try_get(
1627 lambda x
: x
['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1628 video_info
, lambda x
: x
['videostats_playback_base_url'][0]))
1629 if not playback_url
:
1631 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1632 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1634 # cpn generation algorithm is reverse engineered from base.js.
1635 # In fact it works even with dummy cpn.
1636 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1637 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1643 playback_url
= compat_urlparse
.urlunparse(
1644 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1646 self
._download
_webpage
(
1647 playback_url
, video_id
, 'Marking watched',
1648 'Unable to mark watched', fatal
=False)
1651 def _extract_urls(webpage
):
1652 # Embedded YouTube player
1654 unescapeHTML(mobj
.group('url'))
1655 for mobj
in re
.finditer(r
'''(?x)
1665 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1666 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1669 # lazyYT YouTube embed
1670 entries.extend(list(map(
1672 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1674 # Wordpress "YouTube Video Importer" plugin
1675 matches = re.findall(r'''(?x
)<div
[^
>]+
1676 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1677 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1678 entries.extend(m[-1] for m in matches)
1683 def _extract_url(webpage):
1684 urls = YoutubeIE._extract_urls(webpage)
1685 return urls[0] if urls else None
1688 def extract_id(cls, url):
1689 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1691 raise ExtractorError('Invalid URL: %s' % url)
1692 video_id = mobj.group(2)
1695 def _extract_chapters_from_json(self, webpage, video_id, duration):
1698 initial_data = self._parse_json(
1700 r'window\["ytInitialData
"\] = (.+);\n', webpage,
1701 'player args', default='{}'),
1702 video_id, fatal=False)
1703 if not initial_data or not isinstance(initial_data, dict):
1705 chapters_list = try_get(
1707 lambda x: x['playerOverlays']
1708 ['playerOverlayRenderer']
1709 ['decoratedPlayerBarRenderer']
1710 ['decoratedPlayerBarRenderer']
1712 ['chapteredPlayerBarRenderer']
1715 if not chapters_list:
1718 def chapter_time(chapter):
1719 return float_or_none(
1722 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1726 for next_num, chapter in enumerate(chapters_list, start=1):
1727 start_time = chapter_time(chapter)
1728 if start_time is None:
1730 end_time = (chapter_time(chapters_list[next_num])
1731 if next_num < len(chapters_list) else duration)
1732 if end_time is None:
1735 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1738 'start_time': start_time,
1739 'end_time': end_time,
1745 def _extract_chapters_from_description(description, duration):
1748 chapter_lines = re.findall(
1749 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\
.www\
.watch\
.player\
.seekTo
[^
>]+>(\d{1,2}
:\d{1,2}
(?
::\d{1,2}
)?
)</a
>[^
>]*)(?
=$|
<br\s
*/>)',
1751 if not chapter_lines:
1754 for next_num, (chapter_line, time_point) in enumerate(
1755 chapter_lines, start=1):
1756 start_time = parse_duration(time_point)
1757 if start_time is None:
1759 if start_time > duration:
1761 end_time = (duration if next_num == len(chapter_lines)
1762 else parse_duration(chapter_lines[next_num][1]))
1763 if end_time is None:
1765 if end_time > duration:
1767 if start_time > end_time:
1769 chapter_title = re.sub(
1770 r'<a
[^
>]+>[^
<]+</a
>', '', chapter_line).strip(' \t-')
1771 chapter_title = re.sub(r'\s
+', ' ', chapter_title)
1773 'start_time
': start_time,
1774 'end_time
': end_time,
1775 'title
': chapter_title,
1779 def _extract_chapters(self, webpage, description, video_id, duration):
1780 return (self._extract_chapters_from_json(webpage, video_id, duration)
1781 or self._extract_chapters_from_description(description, duration))
1783 def _real_extract(self, url):
1784 url, smuggled_data = unsmuggle_url(url, {})
1787 'http
' if self._downloader.params.get('prefer_insecure
', False)
1792 parsed_url = compat_urllib_parse_urlparse(url)
1793 for component in [parsed_url.fragment, parsed_url.query]:
1794 query = compat_parse_qs(component)
1795 if start_time is None and 't
' in query:
1796 start_time = parse_duration(query['t
'][0])
1797 if start_time is None and 'start
' in query:
1798 start_time = parse_duration(query['start
'][0])
1799 if end_time is None and 'end
' in query:
1800 end_time = parse_duration(query['end
'][0])
1802 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1803 mobj = re.search(self._NEXT_URL_RE, url)
1805 url = proto + '://www
.youtube
.com
/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1806 video_id = self.extract_id(url)
1809 url = proto + '://www
.youtube
.com
/watch?v
=%s&gl
=US
&hl
=en
&has_verified
=1&bpctr
=9999999999' % video_id
1810 video_webpage, urlh = self._download_webpage_handle(url, video_id)
1812 qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query)
1813 video_id = qs.get('v
', [None])[0] or video_id
1815 # Attempt to extract SWF player URL
1816 mobj = re.search(r'swfConfig
.*?
"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1817 if mobj is not None:
1818 player_url = re.sub(r'\\(.)', r'\
1', mobj.group(1))
1824 def add_dash_mpd(video_info):
1825 dash_mpd = video_info.get('dashmpd
')
1826 if dash_mpd and dash_mpd[0] not in dash_mpds:
1827 dash_mpds.append(dash_mpd[0])
1829 def add_dash_mpd_pr(pl_response):
1830 dash_mpd = url_or_none(try_get(
1831 pl_response, lambda x: x['streamingData
']['dashManifestUrl
'],
1833 if dash_mpd and dash_mpd not in dash_mpds:
1834 dash_mpds.append(dash_mpd)
1839 def extract_view_count(v_info):
1840 return int_or_none(try_get(v_info, lambda x: x['view_count
'][0]))
1842 def extract_player_response(player_response, video_id):
1843 pl_response = str_or_none(player_response)
1846 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1847 if isinstance(pl_response, dict):
1848 add_dash_mpd_pr(pl_response)
1851 def extract_embedded_config(embed_webpage, video_id):
1852 embedded_config = self._search_regex(
1853 r'setConfig\
(({.*}
)\
);',
1854 embed_webpage, 'ytInitialData
', default=None)
1856 return embedded_config
1858 player_response = {}
1862 embed_webpage = None
1863 if (self._og_search_property('restrictions
:age
', video_webpage, default=None) == '18+'
1864 or re.search(r'player
-age
-gate
-content
">', video_webpage) is not None):
1865 cookie_keys = self._get_cookies('https://www.youtube.com').keys()
1867 # We simulate the access to the video from www.youtube.com/v/{video_id}
1868 # this can be viewed without login into Youtube
1869 url = proto + '://www.youtube.com/embed/%s' % video_id
1870 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1871 ext = extract_embedded_config(embed_webpage, video_id)
1872 # playabilityStatus = re.search(r'{\\\"status\\\":\\\"(?P<playabilityStatus>[^\"]+)\\\"', ext)
1873 playable_in_embed = re.search(r'{\\\"playableInEmbed\\\":(?P<playableinEmbed>[^\,]+)', ext)
1874 if not playable_in_embed:
1875 self.to_screen('Could not determine whether playabale in embed for video %s' % video_id)
1876 playable_in_embed = ''
1878 playable_in_embed = playable_in_embed.group('playableinEmbed')
1879 # check if video is only playable on youtube in other words not playable in embed - if so it requires auth (cookies)
1880 # if re.search(r'player-unavailable">', embed_webpage) is not None:
1881 if playable_in_embed == 'false
':
1883 # TODO apply this patch when Support for Python 2.6(!) and above drops
1884 if ({'VISITOR_INFO1_LIVE', 'HSID', 'SSID', 'SID'} <= cookie_keys
1885 or {'VISITOR_INFO1_LIVE', '__Secure-3PSID', 'LOGIN_INFO'} <= cookie_keys):
1887 if (set(('VISITOR_INFO1_LIVE
', 'HSID
', 'SSID
', 'SID
')) <= set(cookie_keys)
1888 or set(('VISITOR_INFO1_LIVE
', '__Secure
-3PSID
', 'LOGIN_INFO
')) <= set(cookie_keys)):
1890 # Try looking directly into the video webpage
1891 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1893 args = ytplayer_config.get("args")
1894 if args is not None:
1895 if args.get('url_encoded_fmt_stream_map
') or args.get('hlsvp
'):
1896 # Convert to the same format returned by compat_parse_qs
1897 video_info = dict((k, [v]) for k, v in args.items())
1898 add_dash_mpd(video_info)
1899 # Rental video is not rented but preview is available (e.g.
1900 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1901 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1902 if not video_info and args.get('ypc_vid
'):
1903 return self.url_result(
1904 args['ypc_vid
'], YoutubeIE.ie_key(), video_id=args['ypc_vid
'])
1905 if args.get('livestream
') == '1' or args.get('live_playback
') == 1:
1907 if not player_response:
1908 player_response = extract_player_response(args.get('player_response
'), video_id)
1909 elif not player_response:
1910 player_response = ytplayer_config
1911 if not video_info or self._downloader.params.get('youtube_include_dash_manifest
', True):
1912 add_dash_mpd_pr(player_response)
1914 raise ExtractorError('Video
is age restricted
and only playable on Youtube
. Requires cookies
!', expected=True)
1916 data = compat_urllib_parse_urlencode({
1917 'video_id
': video_id,
1918 'eurl
': 'https
://youtube
.googleapis
.com
/v
/' + video_id,
1919 'sts
': self._search_regex(
1920 r'"sts"\s
*:\s
*(\d
+)', embed_webpage, 'sts
', default=''),
1922 video_info_url = proto + '://www
.youtube
.com
/get_video_info?
' + data
1924 video_info_webpage = self._download_webpage(
1925 video_info_url, video_id,
1926 note='Refetching age
-gated info webpage
',
1927 errnote='unable to download video info webpage
')
1928 except ExtractorError:
1929 video_info_webpage = None
1930 if video_info_webpage:
1931 video_info = compat_parse_qs(video_info_webpage)
1932 pl_response = video_info.get('player_response
', [None])[0]
1933 player_response = extract_player_response(pl_response, video_id)
1934 add_dash_mpd(video_info)
1935 view_count = extract_view_count(video_info)
1938 # Try looking directly into the video webpage
1939 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1940 args = ytplayer_config.get("args")
1941 if args is not None:
1942 if args.get('url_encoded_fmt_stream_map
') or args.get('hlsvp
'):
1943 # Convert to the same format returned by compat_parse_qs
1944 video_info = dict((k, [v]) for k, v in args.items())
1945 add_dash_mpd(video_info)
1946 # Rental video is not rented but preview is available (e.g.
1947 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1948 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1949 if not video_info and args.get('ypc_vid
'):
1950 return self.url_result(
1951 args['ypc_vid
'], YoutubeIE.ie_key(), video_id=args['ypc_vid
'])
1952 if args.get('livestream
') == '1' or args.get('live_playback
') == 1:
1954 if not player_response:
1955 player_response = extract_player_response(args.get('player_response
'), video_id)
1956 elif not player_response:
1957 player_response = ytplayer_config
1958 if not video_info or self._downloader.params.get('youtube_include_dash_manifest
', True):
1959 add_dash_mpd_pr(player_response)
1961 def extract_unavailable_message():
1963 for tag, kind in (('h1
', 'message
'), ('div
', 'submessage
')):
1964 msg = self._html_search_regex(
1965 r'(?s
)<{tag}
[^
>]+id=["\']unavailable-{kind}["\'][^
>]*>(.+?
)</{tag}
>'.format(tag=tag, kind=kind),
1966 video_webpage, 'unavailable
%s' % kind, default=None)
1968 messages.append(msg)
1970 return '\n'.join(messages)
1972 if not video_info and not player_response:
1973 unavailable_message = extract_unavailable_message()
1974 if not unavailable_message:
1975 unavailable_message = 'Unable to extract video data
'
1976 raise ExtractorError(
1977 'YouTube said
: %s' % unavailable_message, expected=True, video_id=video_id)
1979 if not isinstance(video_info, dict):
1982 video_details = try_get(
1983 player_response, lambda x: x['videoDetails
'], dict) or {}
1985 microformat = try_get(
1986 player_response, lambda x: x['microformat
']['playerMicroformatRenderer
'], dict) or {}
1988 video_title = video_info.get('title
', [None])[0] or video_details.get('title
')
1990 self._downloader.report_warning('Unable to extract video title
')
1993 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1994 if video_description:
1997 redir_url = compat_urlparse.urljoin(url, m.group(1))
1998 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1999 if re.search(r'^
(?
:www\
.)?
(?
:youtube(?
:-nocookie
)?\
.com|youtu\
.be
)$
', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect
':
2000 qs = compat_parse_qs(parsed_redir_url.query)
2006 description_original = video_description = re.sub(r'''(?x)
2008 (?:[a-zA-Z-]+="[^"]*"\s+)*?
2009 (?:title|href)="([^"]+)"\s+
2010 (?:[a-zA-Z-]+="[^"]*"\s+)*?
2014 ''', replace_url, video_description)
2015 video_description = clean_html(video_description)
2017 video_description = video_details.get('shortDescription
')
2018 if video_description is None:
2019 video_description = self._html_search_meta('description
', video_webpage)
2021 if not smuggled_data.get('force_singlefeed
', False):
2022 if not self._downloader.params.get('noplaylist
'):
2023 multifeed_metadata_list = try_get(
2025 lambda x: x['multicamera
']['playerLegacyMulticameraRenderer
']['metadataList
'],
2026 compat_str) or try_get(
2027 video_info, lambda x: x['multifeed_metadata_list
'][0], compat_str)
2028 if multifeed_metadata_list:
2031 for feed in multifeed_metadata_list.split(','):
2032 # Unquote should take place before split on comma (,) since textual
2033 # fields may contain comma as well (see
2034 # https://github.com/ytdl-org/youtube-dl/issues/8536)
2035 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
2037 def feed_entry(name):
2038 return try_get(feed_data, lambda x: x[name][0], compat_str)
2040 feed_id = feed_entry('id')
2043 feed_title = feed_entry('title
')
2046 title += ' (%s)' % feed_title
2048 '_type
': 'url_transparent
',
2049 'ie_key
': 'Youtube
',
2051 '%s://www
.youtube
.com
/watch?v
=%s' % (proto, feed_data['id'][0]),
2052 {'force_singlefeed': True}),
2055 feed_ids.append(feed_id)
2057 'Downloading multifeed
video (%s) - add
--no
-playlist to just download video
%s'
2058 % (', '.join(feed_ids), video_id))
2059 return self.playlist_result(entries, video_id, video_title, video_description)
2061 self.to_screen('Downloading just video
%s because of
--no
-playlist
' % video_id)
2063 if view_count is None:
2064 view_count = extract_view_count(video_info)
2065 if view_count is None and video_details:
2066 view_count = int_or_none(video_details.get('viewCount
'))
2067 if view_count is None and microformat:
2068 view_count = int_or_none(microformat.get('viewCount
'))
2071 is_live = bool_or_none(video_details.get('isLive
'))
2073 has_live_chat_replay = False
2075 yt_initial_data = self._get_yt_initial_data(video_id, video_webpage)
2077 yt_initial_data['contents
']['twoColumnWatchNextResults
']['conversationBar
']['liveChatRenderer
']['continuations
'][0]['reloadContinuationData
']['continuation
']
2078 has_live_chat_replay = True
2079 except (KeyError, IndexError, TypeError):
2082 # Check for "rental" videos
2083 if 'ypc_video_rental_bar_text
' in video_info and 'author
' not in video_info:
2084 raise ExtractorError('"rental" videos
not supported
. See https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/359 for more information
.', expected=True)
2086 def _extract_filesize(media_url):
2087 return int_or_none(self._search_regex(
2088 r'\bclen
[=/](\d
+)', media_url, 'filesize
', default=None))
2090 streaming_formats = try_get(player_response, lambda x: x['streamingData
']['formats
'], list) or []
2091 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData
']['adaptiveFormats
'], list) or [])
2093 if 'conn
' in video_info and video_info['conn
'][0].startswith('rtmp
'):
2094 self.report_rtmp_download()
2096 'format_id
': '_rtmp
',
2098 'url
': video_info['conn
'][0],
2099 'player_url
': player_url,
2101 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):
2102 encoded_url_map = video_info.get('url_encoded_fmt_stream_map
', [''])[0] + ',' + video_info.get('adaptive_fmts
', [''])[0]
2103 if 'rtmpe
%3Dyes
' in encoded_url_map:
2104 raise ExtractorError('rtmpe downloads are
not supported
, see https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/343 for more information
.', expected=True)
2107 fmt_list = video_info.get('fmt_list
', [''])[0]
2109 for fmt in fmt_list.split(','):
2110 spec = fmt.split('/')
2112 width_height = spec[1].split('x
')
2113 if len(width_height) == 2:
2114 formats_spec[spec[0]] = {
2115 'resolution
': spec[1],
2116 'width
': int_or_none(width_height[0]),
2117 'height
': int_or_none(width_height[1]),
2119 for fmt in streaming_formats:
2120 itag = str_or_none(fmt.get('itag
'))
2123 quality = fmt.get('quality
')
2124 quality_label = fmt.get('qualityLabel
') or quality
2125 formats_spec[itag] = {
2126 'asr
': int_or_none(fmt.get('audioSampleRate
')),
2127 'filesize
': int_or_none(fmt.get('contentLength
')),
2128 'format_note
': quality_label,
2129 'fps
': int_or_none(fmt.get('fps
')),
2130 'height
': int_or_none(fmt.get('height
')),
2131 # bitrate for itag 43 is always 2147483647
2132 'tbr
': float_or_none(fmt.get('averageBitrate
') or fmt.get('bitrate
'), 1000) if itag != '43' else None,
2133 'width
': int_or_none(fmt.get('width
')),
2136 for fmt in streaming_formats:
2137 if fmt.get('drmFamilies
') or fmt.get('drm_families
'):
2139 url = url_or_none(fmt.get('url
'))
2142 cipher = fmt.get('cipher
') or fmt.get('signatureCipher
')
2145 url_data = compat_parse_qs(cipher)
2146 url = url_or_none(try_get(url_data, lambda x: x['url
'][0], compat_str))
2151 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
2153 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type
'][0]))
2154 # Unsupported FORMAT_STREAM_TYPE_OTF
2155 if stream_type == 3:
2158 format_id = fmt.get('itag
') or url_data['itag
'][0]
2161 format_id = compat_str(format_id)
2164 if 's
' in url_data or self._downloader.params.get('youtube_include_dash_manifest
', True):
2165 ASSETS_RE = r'(?
:"assets":.+?
"js":\s
*("[^"]+"))|(?:"jsUrl
":\s*("[^
"]+"))'
2166 jsplayer_url_json = self._search_regex(
2168 embed_webpage if age_gate else video_webpage,
2169 'JS player
URL (1)', default=None)
2170 if not jsplayer_url_json and not age_gate:
2171 # We need the embed website after all
2172 if embed_webpage is None:
2173 embed_url = proto + '://www
.youtube
.com
/embed
/%s' % video_id
2174 embed_webpage = self._download_webpage(
2175 embed_url, video_id, 'Downloading embed webpage
')
2176 jsplayer_url_json = self._search_regex(
2177 ASSETS_RE, embed_webpage, 'JS player URL
')
2179 player_url = json.loads(jsplayer_url_json)
2180 if player_url is None:
2181 player_url_json = self._search_regex(
2182 r'ytplayer\
.config
.*?
"url"\s
*:\s
*("[^"]+")',
2183 video_webpage, 'age gate player URL')
2184 player_url = json.loads(player_url_json)
2186 if 'sig' in url_data:
2187 url += '&signature=' + url_data['sig'][0]
2188 elif 's' in url_data:
2189 encrypted_sig = url_data['s'][0]
2191 if self._downloader.params.get('verbose'):
2192 if player_url is None:
2193 player_desc = 'unknown'
2195 player_type, player_version = self._extract_player_info(player_url)
2196 player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version)
2197 parts_sizes = self._signature_cache_id(encrypted_sig)
2198 self.to_screen('{%s} signature length %s, %s' %
2199 (format_id, parts_sizes, player_desc))
2201 signature = self._decrypt_signature(
2202 encrypted_sig, video_id, player_url, age_gate)
2203 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2204 url += '&%s=%s' % (sp, signature)
2205 if 'ratebypass' not in url:
2206 url += '&ratebypass=yes'
2209 'format_id': format_id,
2211 'player_url': player_url,
2213 if format_id in self._formats:
2214 dct.update(self._formats[format_id])
2215 if format_id in formats_spec:
2216 dct.update(formats_spec[format_id])
2218 # Some itags are not included in DASH manifest thus corresponding formats will
2219 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2220 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2221 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2222 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2225 width = int_or_none(fmt.get('width'))
2227 height = int_or_none(fmt.get('height'))
2229 filesize = int_or_none(url_data.get(
2230 'clen', [None])[0]) or _extract_filesize(url)
2232 quality = url_data.get('quality', [None])[0] or fmt.get('quality')
2233 quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
2235 tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
2236 or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
2237 fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
2240 'filesize': filesize,
2245 'format_note': quality_label or quality,
2247 for key, value in more_fields.items():
2250 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
2252 type_split = type_.split(';')
2253 kind_ext = type_split[0].split('/')
2254 if len(kind_ext) == 2:
2256 dct['ext'] = mimetype2ext(type_split[0])
2257 if kind in ('audio', 'video'):
2259 for mobj in re.finditer(
2260 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
2261 if mobj.group('key
') == 'codecs
':
2262 codecs = mobj.group('val
')
2265 dct.update(parse_codecs(codecs))
2266 if dct.get('acodec
') == 'none
' or dct.get('vcodec
') == 'none
':
2267 dct['downloader_options
'] = {
2268 # Youtube throttles chunks >~10M
2269 'http_chunk_size
': 10485760,
2274 url_or_none(try_get(
2276 lambda x: x['streamingData
']['hlsManifestUrl
'],
2278 or url_or_none(try_get(
2279 video_info, lambda x: x['hlsvp
'][0], compat_str)))
2282 m3u8_formats = self._extract_m3u8_formats(
2283 manifest_url, video_id, 'mp4
', fatal=False)
2284 for a_format in m3u8_formats:
2285 itag = self._search_regex(
2286 r'/itag
/(\d
+)/', a_format['url
'], 'itag
', default=None)
2288 a_format['format_id
'] = itag
2289 if itag in self._formats:
2290 dct = self._formats[itag].copy()
2291 dct.update(a_format)
2293 a_format['player_url
'] = player_url
2294 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2295 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
2296 if self._downloader.params.get('youtube_include_hls_manifest
', True):
2297 formats.append(a_format)
2299 error_message = extract_unavailable_message()
2300 if not error_message:
2301 error_message = clean_html(try_get(
2302 player_response, lambda x: x['playabilityStatus
']['reason
'],
2304 if not error_message:
2305 error_message = clean_html(
2306 try_get(video_info, lambda x: x['reason
'][0], compat_str))
2308 raise ExtractorError(error_message, expected=True)
2309 raise ExtractorError('no conn
, hlsvp
, hlsManifestUrl
or url_encoded_fmt_stream_map information found
in video info
')
2312 video_uploader = try_get(
2313 video_info, lambda x: x['author
'][0],
2314 compat_str) or str_or_none(video_details.get('author
'))
2316 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2318 self._downloader.report_warning('unable to extract uploader name
')
2321 video_uploader_id = None
2322 video_uploader_url = None
2324 r'<link itemprop
="url" href
="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2326 if mobj is not None:
2327 video_uploader_id = mobj.group('uploader_id')
2328 video_uploader_url = mobj.group('uploader_url')
2330 owner_profile_url = url_or_none(microformat.get('ownerProfileUrl'))
2331 if owner_profile_url:
2332 video_uploader_id = self._search_regex(
2333 r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id',
2335 video_uploader_url = owner_profile_url
2338 str_or_none(video_details.get('channelId'))
2339 or self._html_search_meta(
2340 'channelId', video_webpage, 'channel id', default=None)
2341 or self._search_regex(
2342 r'data-channel-external-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
2343 video_webpage, 'channel
id', default=None, group='id'))
2344 channel_url = 'http
://www
.youtube
.com
/channel
/%s' % channel_id if channel_id else None
2347 thumbnails_list = try_get(
2348 video_details, lambda x: x['thumbnail
']['thumbnails
'], list) or []
2349 for t in thumbnails_list:
2350 if not isinstance(t, dict):
2352 thumbnail_url = url_or_none(t.get('url
'))
2353 if not thumbnail_url:
2356 'url
': thumbnail_url,
2357 'width
': int_or_none(t.get('width
')),
2358 'height
': int_or_none(t.get('height
')),
2362 video_thumbnail = None
2363 # We try first to get a high quality image:
2364 m_thumb = re.search(r'<span itemprop
="thumbnail".*?href
="(.*?)">',
2365 video_webpage, re.DOTALL)
2366 if m_thumb is not None:
2367 video_thumbnail = m_thumb.group(1)
2368 thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url
'][0], compat_str)
2370 video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
2372 thumbnails.append({'url': video_thumbnail})
2375 upload_date = self._html_search_meta(
2376 'datePublished
', video_webpage, 'upload date
', default=None)
2378 upload_date = self._search_regex(
2379 [r'(?s
)id="eow-date.*?>(.*?)</span>',
2380 r'(?:id="watch
-uploader
-info
".*?>.*?|["\']simpleText
["\']\s*:\s*["\'])(?
:Published|Uploaded|Streamed live|Started
) on (.+?
)[<"\']'],
2381 video_webpage, 'upload date', default=None)
2383 upload_date = microformat.get('publishDate') or microformat.get('uploadDate')
2384 upload_date = unified_strdate(upload_date)
2386 video_license = self._html_search_regex(
2387 r'<h4[^>]+class="title
"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2388 video_webpage, 'license', default=None)
2390 m_music = re.search(
2392 <h4[^>]+class="title
"[^>]*>\s*Music\s*</h4>\s*
2400 \bhref=["\']/red
[^
>]*>|
# drop possible
2401 >\s
*Listen ad
-free
with YouTube Red
# YouTube Red ad
2408 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2409 video_creator = clean_html(m_music.group('creator'))
2411 video_alt_title = video_creator = None
2413 def extract_meta(field):
2414 return self._html_search_regex(
2415 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2416 video_webpage, field, default=None)
2418 track = extract_meta('Song')
2419 artist = extract_meta('Artist')
2420 album = extract_meta('Album')
2422 # Youtube Music Auto-generated description
2423 release_date = release_year = None
2424 if video_description:
2425 mobj = re.search(r'(?s)Provided to YouTube by [^\n]+\n+(?P<track>[^·]+)·(?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]+))?', video_description)
2428 track = mobj.group('track').strip()
2430 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2432 album = mobj.group('album'.strip())
2433 release_year = mobj.group('release_year')
2434 release_date = mobj.group('release_date')
2436 release_date = release_date.replace('-', '')
2437 if not release_year:
2438 release_year = int(release_date[:4])
2440 release_year = int(release_year)
2442 yt_initial = self._get_yt_initial_data(video_id, video_webpage)
2444 music_metadata = self._get_music_metadata_from_yt_initial(yt_initial)
2445 if len(music_metadata):
2446 album = music_metadata[0].get('album')
2447 artist = music_metadata[0].get('artist')
2448 track = music_metadata[0].get('track')
2450 m_episode = re.search(
2451 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2454 series = unescapeHTML(m_episode.group('series'))
2455 season_number = int(m_episode.group('season'))
2456 episode_number = int(m_episode.group('episode'))
2458 series = season_number = episode_number = None
2460 m_cat_container = self._search_regex(
2461 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2462 video_webpage, 'categories', default=None)
2465 category = self._html_search_regex(
2466 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2470 microformat, lambda x: x['category'], compat_str)
2471 video_categories = None if category is None else [category]
2474 unescapeHTML(m.group('content'))
2475 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2477 video_tags = try_get(video_details, lambda x: x['keywords'], list)
2479 def _extract_count(count_name):
2480 return str_to_int(self._search_regex(
2481 r'"accessibilityData":\{"label":"([\d,\w]+) %ss"\}'
2482 % re.escape(count_name),
2483 video_webpage, count_name, default=None))
2485 like_count = _extract_count('like')
2486 dislike_count = _extract_count('dislike')
2488 if view_count is None:
2489 view_count = str_to_int(self._search_regex(
2490 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2491 'view count', default=None))
2494 float_or_none(video_details.get('averageRating'))
2495 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2498 video_subtitles = self.extract_subtitles(
2499 video_id, video_webpage, has_live_chat_replay)
2500 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2502 video_duration = try_get(
2503 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2504 if not video_duration:
2505 video_duration = int_or_none(video_details.get('lengthSeconds'))
2506 if not video_duration:
2507 video_duration = parse_duration(self._html_search_meta(
2508 'duration', video_webpage, 'video duration'))
2510 # Get Subscriber Count of channel
2511 subscriber_count = parse_count(self._search_regex(
2512 r'"text":"([\d\.]+\w?) subscribers"',
2519 video_annotations = None
2520 if self._downloader.params.get('writeannotations', False):
2521 xsrf_token = self._search_regex(
2522 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
2523 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2524 invideo_url = try_get(
2525 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2526 if xsrf_token and invideo_url:
2527 xsrf_field_name = self._search_regex(
2528 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2529 video_webpage, 'xsrf field name',
2530 group='xsrf_field_name', default='session_token')
2531 video_annotations = self._download_webpage(
2532 self._proto_relative_url(invideo_url),
2533 video_id, note='Downloading annotations',
2534 errnote='Unable to download video annotations', fatal=False,
2535 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2537 chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
2539 # Look for the DASH manifest
2540 if self._downloader.params.get('youtube_include_dash_manifest', True):
2541 dash_mpd_fatal = True
2542 for mpd_url in dash_mpds:
2545 def decrypt_sig(mobj):
2547 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2548 return '/signature/%s' % dec_s
2550 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2552 for df in self._extract_mpd_formats(
2553 mpd_url, video_id, fatal=dash_mpd_fatal,
2554 formats_dict=self._formats):
2555 if not df.get('filesize'):
2556 df['filesize'] = _extract_filesize(df['url'])
2557 # Do not overwrite DASH format found in some previous DASH manifest
2558 if df['format_id'] not in dash_formats:
2559 dash_formats[df['format_id']] = df
2560 # Additional DASH manifests may end up in HTTP Error 403 therefore
2561 # allow them to fail without bug report message if we already have
2562 # some DASH manifest succeeded. This is temporary workaround to reduce
2563 # burst of bug reports until we figure out the reason and whether it
2564 # can be fixed at all.
2565 dash_mpd_fatal = False
2566 except (ExtractorError, KeyError) as e:
2567 self.report_warning(
2568 'Skipping DASH manifest: %r' % e, video_id)
2570 # Remove the formats we found through non-DASH, they
2571 # contain less info and it can be wrong, because we use
2572 # fixed values (for example the resolution). See
2573 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2575 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2576 formats.extend(dash_formats.values())
2578 # Check for malformed aspect ratio
2579 stretched_m = re.search(
2580 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2583 w = float(stretched_m.group('w'))
2584 h = float(stretched_m.group('h'))
2585 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2586 # We will only process correct ratios.
2590 if f.get('vcodec') != 'none':
2591 f['stretched_ratio'] = ratio
2594 if 'reason' in video_info:
2595 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2596 regions_allowed = self._html_search_meta(
2597 'regionsAllowed', video_webpage, default=None)
2598 countries = regions_allowed.split(',') if regions_allowed else None
2599 self.raise_geo_restricted(
2600 msg=video_info['reason'][0], countries=countries)
2601 reason = video_info['reason'][0]
2602 if 'Invalid parameters' in reason:
2603 unavailable_message = extract_unavailable_message()
2604 if unavailable_message:
2605 reason = unavailable_message
2606 raise ExtractorError(
2607 'YouTube said: %s' % reason,
2608 expected=True, video_id=video_id)
2609 if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
2610 raise ExtractorError('This video is DRM protected.', expected=True)
2612 self._sort_formats(formats)
2614 self.mark_watched(video_id, video_info, player_response)
2618 'uploader': video_uploader,
2619 'uploader_id': video_uploader_id,
2620 'uploader_url': video_uploader_url,
2621 'channel_id': channel_id,
2622 'channel_url': channel_url,
2623 'upload_date': upload_date,
2624 'license': video_license,
2625 'creator': video_creator or artist,
2626 'title': video_title,
2627 'alt_title': video_alt_title or track,
2628 'thumbnails': thumbnails,
2629 'description': video_description,
2630 'categories': video_categories,
2632 'subtitles': video_subtitles,
2633 'automatic_captions': automatic_captions,
2634 'duration': video_duration,
2635 'age_limit': 18 if age_gate else 0,
2636 'annotations': video_annotations,
2637 'chapters': chapters,
2638 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2639 'view_count': view_count,
2640 'like_count': like_count,
2641 'dislike_count': dislike_count,
2642 'average_rating': average_rating,
2645 'start_time': start_time,
2646 'end_time': end_time,
2648 'season_number': season_number,
2649 'episode_number': episode_number,
2653 'release_date': release_date,
2654 'release_year': release_year,
2655 'subscriber_count': subscriber_count,
2659 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2660 IE_DESC = 'YouTube.com playlists'
2661 _VALID_URL = r"""(?x)(?:
2666 youtube(?:kids)?\.com|
2671 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2672 \? (?:.*?[&;])*? (?:p|a|list)=
2675 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2678 (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2679 # Top tracks, they can also include dots
2685 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2686 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2687 _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2688 _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
2689 IE_NAME = 'youtube:playlist'
2690 _YTM_PLAYLIST_PREFIX = 'RDCLAK5uy_'
2691 _YTM_CHANNEL_INFO = {
2692 'uploader': 'Youtube Music',
2693 'uploader_id': 'music', # or "UC-9-kyTW8ZkZNDHQJ6FgpwQ"
2694 'uploader_url': 'https://www.youtube.com/music'
2697 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2699 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2700 'uploader': 'Sergey M.',
2701 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2702 'title': 'youtube-dl public playlist',
2704 'playlist_count': 1,
2706 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2708 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2709 'uploader': 'Sergey M.',
2710 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2711 'title': 'youtube-dl empty playlist',
2713 'playlist_count': 0,
2715 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2716 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2718 'title': '29C3: Not my department',
2719 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2720 'uploader': 'Christiaan008',
2721 'uploader_id': 'ChRiStIaAn008',
2723 'playlist_count': 96,
2725 'note': 'issue #673',
2726 'url': 'PLBB231211A4F62143',
2728 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2729 'id': 'PLBB231211A4F62143',
2730 'uploader': 'Wickydoo',
2731 'uploader_id': 'Wickydoo',
2733 'playlist_mincount': 26,
2735 'note': 'Large playlist',
2736 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2738 'title': 'Uploads from Cauchemar',
2739 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2740 'uploader': 'Cauchemar',
2741 'uploader_id': 'Cauchemar89',
2743 'playlist_mincount': 799,
2745 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2747 'title': 'YDL_safe_search',
2748 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2750 'playlist_count': 2,
2751 'skip': 'This playlist is private',
2754 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2755 'playlist_count': 4,
2758 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2759 'uploader': 'milan',
2760 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2763 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2764 'playlist_mincount': 485,
2766 'title': '2018 Chinese New Singles (11/6 updated)',
2767 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2769 'uploader_id': 'sdragonfang',
2772 'note': 'Embedded SWF player',
2773 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2774 'playlist_count': 4,
2777 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2779 'skip': 'This playlist does not exist',
2781 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2782 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2784 'title': 'Uploads from Interstellar Movie',
2785 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2786 'uploader': 'Interstellar Movie',
2787 'uploader_id': 'InterstellarMovie1',
2789 'playlist_mincount': 21,
2791 # Playlist URL that does not actually serve a playlist
2792 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2794 'id': 'FqZTN594JQw',
2796 'title': "Smiley's People 01 detective, Adventure Series, Action",
2797 'uploader': 'STREEM',
2798 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2799 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2800 'upload_date': '20150526',
2801 'license': 'Standard YouTube License',
2802 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2803 'categories': ['People & Blogs'],
2807 'dislike_count': int,
2810 'skip_download': True,
2812 'skip': 'This video is not available.',
2813 'add_ie': [YoutubeIE.ie_key()],
2815 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2817 'id': 'yeWKywCrFtk',
2819 'title': 'Small Scale Baler and Braiding Rugs',
2820 'uploader': 'Backus-Page House Museum',
2821 'uploader_id': 'backuspagemuseum',
2822 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2823 'upload_date': '20161008',
2824 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2825 'categories': ['Nonprofits & Activism'],
2828 'dislike_count': int,
2832 'skip_download': True,
2835 # https://github.com/ytdl-org/youtube-dl/issues/21844
2836 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2838 'title': 'Data Analysis with Dr Mike Pound',
2839 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2840 'uploader_id': 'Computerphile',
2841 'uploader': 'Computerphile',
2843 'playlist_mincount': 11,
2845 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2846 'only_matching': True,
2848 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2849 'only_matching': True,
2851 # music album playlist
2852 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2853 'only_matching': True,
2855 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2856 'only_matching': True,
2858 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2859 'only_matching': True,
2862 def _real_initialize(self):
2865 def extract_videos_from_page(self, page):
2869 for item in re.findall(
2870 r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
2871 attrs = extract_attributes(item)
2872 video_id = attrs['data-video-id']
2873 video_title = unescapeHTML(attrs.get('data-title'))
2875 video_title = video_title.strip()
2876 ids_in_page.append(video_id)
2877 titles_in_page.append(video_title)
2879 # Fallback with old _VIDEO_RE
2880 self.extract_videos_from_page_impl(
2881 self._VIDEO_RE, page, ids_in_page, titles_in_page)
2884 self.extract_videos_from_page_impl(
2885 r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page,
2886 ids_in_page, titles_in_page)
2887 self.extract_videos_from_page_impl(
2888 r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
2889 ids_in_page, titles_in_page)
2891 return zip(ids_in_page, titles_in_page)
2893 def _extract_mix_ids_from_yt_initial(self, yt_initial):
2895 playlist_contents = try_get(yt_initial, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist']['contents'], list)
2896 if playlist_contents:
2897 for item in playlist_contents:
2898 videoId = try_get(item, lambda x: x['playlistPanelVideoRenderer']['videoId'], compat_str)
2903 def _extract_mix(self, playlist_id):
2904 # The mixes are generated from a single video
2905 # the id of the playlist is just 'RD' + video_id
2908 last_id = playlist_id[-11:]
2909 for n in itertools.count(1):
2910 url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2911 webpage = self._download_webpage(
2912 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2913 new_ids = orderedSet(re.findall(
2914 r'''(?xs
)data
-video
-username
=".*?".*?
2915 href
="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?
list=%s''' % re.escape(playlist_id),
2918 # if no ids in html of page, try using embedded json
2919 if (len(new_ids) == 0):
2920 yt_initial = self._get_yt_initial_data(playlist_id, webpage)
2922 new_ids = self._extract_mix_ids_from_yt_initial(yt_initial)
2924 # Fetch new pages until all the videos are repeated, it seems that
2925 # there are always 51 unique videos.
2926 new_ids = [_id for _id in new_ids if _id not in ids]
2932 url_results = self._ids_to_results(ids)
2934 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2936 search_title('playlist-title')
2937 or search_title('title long-title')
2938 or search_title('title'))
2939 title = clean_html(title_span)
2942 title = try_get(yt_initial, lambda x: x['contents']['twoColumnWatchNextResults']['playlist']['playlist']['title'], compat_str)
2944 return self.playlist_result(url_results, playlist_id, title)
2946 def _extract_playlist(self, playlist_id):
2947 url = self._TEMPLATE_URL % playlist_id
2948 page = self._download_webpage(url, playlist_id)
2950 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2951 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2952 match = match.strip()
2953 # Check if the playlist exists or is private
2954 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2956 reason = mobj.group('reason')
2957 message = 'This playlist %s' % reason
2958 if 'private' in reason:
2959 message += ', use --username or --netrc to access it'
2961 raise ExtractorError(message, expected=True)
2962 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2963 raise ExtractorError(
2964 'Invalid parameters. Maybe URL is incorrect.',
2966 elif re.match(r'[^<]*Choose your language[^<]*', match):
2969 self.report_warning('Youtube gives an alert message: ' + match)
2971 playlist_title = self._html_search_regex(
2972 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2973 page, 'title', default=None)
2975 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2976 uploader = self._html_search_regex(
2977 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2978 page, 'uploader', default=None)
2980 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2983 uploader_id = mobj.group('uploader_id')
2984 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2986 uploader_id = uploader_url = None
2990 if not playlist_title:
2992 # Some playlist URLs don't actually serve a playlist (e.g.
2993 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2994 next(self._entries(page, playlist_id))
2995 except StopIteration:
2998 playlist = self.playlist_result(
2999 self._entries(page, playlist_id), playlist_id, playlist_title)
3001 'uploader': uploader,
3002 'uploader_id': uploader_id,
3003 'uploader_url': uploader_url,
3005 if playlist_id.startswith(self._YTM_PLAYLIST_PREFIX):
3006 playlist.update(self._YTM_CHANNEL_INFO)
3008 return has_videos, playlist
3010 def _check_download_just_video(self, url, playlist_id):
3011 # Check if it's a video-specific URL
3012 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
3013 video_id = query_dict.get('v', [None])[0] or self._search_regex(
3014 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
3015 'video id', default=None)
3017 if self._downloader.params.get('noplaylist'):
3018 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
3019 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
3021 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
3022 return video_id, None
3025 def _real_extract(self, url):
3026 # Extract playlist id
3027 mobj = re.match(self._VALID_URL, url)
3029 raise ExtractorError('Invalid URL: %s' % url)
3030 playlist_id = mobj.group(1) or mobj.group(2)
3032 video_id, video = self._check_download_just_video(url, playlist_id)
3036 if playlist_id.startswith(('RD', 'UL', 'PU')):
3037 if not playlist_id.startswith(self._YTM_PLAYLIST_PREFIX):
3038 # Mixes require a custom extraction process,
3039 # Youtube Music playlists act like normal playlists (with randomized order)
3040 return self._extract_mix(playlist_id)
3042 has_videos, playlist = self._extract_playlist(playlist_id)
3043 if has_videos or not video_id:
3046 # Some playlist URLs don't actually serve a playlist (see
3047 # https://github.com/ytdl-org/youtube-dl/issues/10537).
3048 # Fallback to plain video extraction if there is a video id
3049 # along with playlist id.
3050 return self.url_result(video_id, 'Youtube', video_id=video_id)
3053 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
3054 IE_DESC = 'YouTube.com channels'
3055 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
3056 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
3057 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
3058 IE_NAME = 'youtube:channel'
3060 'note': 'paginated channel',
3061 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
3062 'playlist_mincount': 91,
3064 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
3065 'title': 'Uploads from lex will',
3066 'uploader': 'lex will',
3067 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
3070 'note': 'Age restricted channel',
3071 # from https://www.youtube.com/user/DeusExOfficial
3072 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
3073 'playlist_mincount': 64,
3075 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
3076 'title': 'Uploads from Deus Ex',
3077 'uploader': 'Deus Ex',
3078 'uploader_id': 'DeusExOfficial',
3081 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
3082 'only_matching': True,
3084 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
3085 'only_matching': True,
3089 def suitable(cls, url):
3090 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
3091 else super(YoutubeChannelIE, cls).suitable(url))
3093 def _build_template_url(self, url, channel_id):
3094 return self._TEMPLATE_URL % channel_id
3096 def _real_extract(self, url):
3097 channel_id = self._match_id(url)
3099 url = self._build_template_url(url, channel_id)
3101 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
3102 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
3103 # otherwise fallback on channel by page extraction
3104 channel_page = self._download_webpage(
3105 url + '?view=57', channel_id,
3106 'Downloading channel page', fatal=False)
3107 if channel_page is False:
3108 channel_playlist_id = False
3110 channel_playlist_id = self._html_search_meta(
3111 'channelId', channel_page, 'channel id', default=None)
3112 if not channel_playlist_id:
3113 channel_url = self._html_search_meta(
3114 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
3115 channel_page, 'channel url', default=None)
3117 channel_playlist_id = self._search_regex(
3118 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
3119 channel_url, 'channel id', default=None)
3120 if channel_playlist_id and channel_playlist_id.startswith('UC'):
3121 playlist_id = 'UU' + channel_playlist_id[2:]
3122 return self.url_result(
3123 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
3125 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
3126 autogenerated = re.search(r'''(?x
)
3128 channel
-header
-autogenerated
-label|
3129 yt
-channel
-title
-autogenerated
3130 )[^
"]*"''', channel_page) is not None
3133 # The videos are contained in a single page
3134 # the ajax pages can't be used, they are empty
3137 video_id, 'Youtube', video_id=video_id,
3138 video_title=video_title)
3139 for video_id, video_title in self.extract_videos_from_page(channel_page)]
3140 return self.playlist_result(entries, channel_id)
3143 next(self._entries(channel_page, channel_id))
3144 except StopIteration:
3145 alert_message = self._html_search_regex(
3146 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
3147 channel_page, 'alert', default=None, group='alert')
3149 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
3151 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
3154 class YoutubeUserIE(YoutubeChannelIE):
3155 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
3156 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results|shared)(?:$|[^a-z_A-Z0-9%-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_%-]+)'
3157 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
3158 IE_NAME = 'youtube:user'
3161 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
3162 'playlist_mincount': 320,
3164 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
3165 'title': 'Uploads from The Linux Foundation',
3166 'uploader': 'The Linux Foundation',
3167 'uploader_id': 'TheLinuxFoundation',
3170 # Only available via https://www.youtube.com/c/12minuteathlete/videos
3171 # but not https://www.youtube.com/user/12minuteathlete/videos
3172 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
3173 'playlist_mincount': 249,
3175 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
3176 'title': 'Uploads from 12 Minute Athlete',
3177 'uploader': '12 Minute Athlete',
3178 'uploader_id': 'the12minuteathlete',
3181 'url': 'ytuser:phihag',
3182 'only_matching': True,
3184 'url': 'https://www.youtube.com/c/gametrailers',
3185 'only_matching': True,
3187 'url': 'https://www.youtube.com/c/Pawe%C5%82Zadro%C5%BCniak',
3188 'only_matching': True,
3190 'url': 'https://www.youtube.com/gametrailers',
3191 'only_matching': True,
3193 # This channel is not available, geo restricted to JP
3194 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
3195 'only_matching': True,
3199 def suitable(cls, url):
3200 # Don't return True if the url can be extracted with other youtube
3201 # extractor, the regex would is too permissive and it would match.
3202 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
3203 if any(ie.suitable(url) for ie in other_yt_ies):
3206 return super(YoutubeUserIE, cls).suitable(url)
3208 def _build_template_url(self, url, channel_id):
3209 mobj = re.match(self._VALID_URL, url)
3210 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
3213 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
3214 IE_DESC = 'YouTube.com live streams'
3215 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
3216 IE_NAME = 'youtube:live'
3219 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3221 'id': 'a48o2S1cPoo',
3223 'title': 'The Young Turks - Live Main Show',
3224 'uploader': 'The Young Turks',
3225 'uploader_id': 'TheYoungTurks',
3226 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3227 'upload_date': '20150715',
3228 'license': 'Standard YouTube License',
3229 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3230 'categories': ['News & Politics'],
3231 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3233 'dislike_count': int,
3236 'skip_download': True,
3239 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3240 'only_matching': True,
3242 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3243 'only_matching': True,
3245 'url': 'https://www.youtube.com/TheYoungTurks/live',
3246 'only_matching': True,
3249 def _real_extract(self, url):
3250 mobj = re.match(self._VALID_URL, url)
3251 channel_id = mobj.group('id')
3252 base_url = mobj.group('base_url')
3253 webpage = self._download_webpage(url, channel_id, fatal=False)
3255 page_type = self._og_search_property(
3256 'type', webpage, 'page type', default='')
3257 video_id = self._html_search_meta(
3258 'videoId', webpage, 'video id', default=None)
3259 if page_type.startswith('video') and video_id and re.match(
3260 r'^[0-9A-Za-z_-]{11}$', video_id):
3261 return self.url_result(video_id, YoutubeIE.ie_key())
3262 return self.url_result(base_url)
3265 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
3266 IE_DESC = 'YouTube.com user/channel playlists'
3267 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'
3268 IE_NAME = 'youtube:playlists'
3271 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3272 'playlist_mincount': 4,
3274 'id': 'ThirstForScience',
3275 'title': 'ThirstForScience',
3278 # with "Load more" button
3279 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3280 'playlist_mincount': 70,
3283 'title': 'Игорь Клейнер',
3286 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
3287 'playlist_mincount': 17,
3289 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
3290 'title': 'Chem Player',
3294 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3295 'only_matching': True,
3299 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistBaseInfoExtractor):
3300 IE_DESC = 'YouTube.com searches'
3301 # there doesn't appear to be a real limit, for example if you search for
3302 # 'python' you get more than 8.000.000 results
3303 _MAX_RESULTS = float('inf')
3304 IE_NAME = 'youtube:search'
3305 _SEARCH_KEY = 'ytsearch'
3306 _SEARCH_PARAMS = None
3309 def _entries(self, query, n):
3313 'clientName': 'WEB',
3314 'clientVersion': '2.20201021.03.00',
3319 if self._SEARCH_PARAMS:
3320 data['params'] = self._SEARCH_PARAMS
3322 for page_num in itertools.count(1):
3323 search = self._download_json(
3324 'https://www.youtube.com/youtubei/v1/search?key=AIzaSyAO_FJ2SlqU8Q4STEHLGCilw_Y9_11qcW8',
3325 video_id='query "%s"' % query,
3326 note='Downloading page %s' % page_num,
3327 errnote='Unable to download API page', fatal=False,
3328 data=json.dumps(data).encode('utf8'),
3329 headers={'content-type': 'application/json'})
3332 slr_contents = try_get(
3334 (lambda x: x['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'],
3335 lambda x: x['onResponseReceivedCommands'][0]['appendContinuationItemsAction']['continuationItems']),
3337 if not slr_contents:
3339 isr_contents = try_get(
3341 lambda x: x[0]['itemSectionRenderer']['contents'],
3343 if not isr_contents:
3345 for content in isr_contents:
3346 if not isinstance(content, dict):
3348 video = content.get('videoRenderer')
3349 if not isinstance(video, dict):
3351 video_id = video.get('videoId')
3354 title = try_get(video, lambda x: x['title']['runs'][0]['text'], compat_str)
3355 description = try_get(video, lambda x: x['descriptionSnippet']['runs'][0]['text'], compat_str)
3356 duration = parse_duration(try_get(video, lambda x: x['lengthText']['simpleText'], compat_str))
3357 view_count_text = try_get(video, lambda x: x['viewCountText']['simpleText'], compat_str) or ''
3358 view_count = int_or_none(self._search_regex(
3359 r'^(\d+)', re.sub(r'\s', '', view_count_text),
3360 'view count', default=None))
3361 uploader = try_get(video, lambda x: x['ownerText']['runs'][0]['text'], compat_str)
3364 '_type': 'url_transparent',
3365 'ie_key': YoutubeIE.ie_key(),
3369 'description': description,
3370 'duration': duration,
3371 'view_count': view_count,
3372 'uploader': uploader,
3378 lambda x: x[1]['continuationItemRenderer']['continuationEndpoint']['continuationCommand']['token'],
3382 data['continuation'] = token
3384 def _get_n_results(self, query, n):
3385 """Get a specified number of results for a query"""
3386 return self.playlist_result(self._entries(query, n), query)
3389 class YoutubeSearchDateIE(YoutubeSearchIE):
3390 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3391 _SEARCH_KEY = 'ytsearchdate'
3392 IE_DESC = 'YouTube.com searches, newest videos first'
3393 _SEARCH_PARAMS = 'CAI%3D'
3396 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
3397 IE_DESC = 'YouTube.com search URLs'
3398 IE_NAME = 'youtube:search_url'
3399 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3401 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3402 'playlist_mincount': 5,
3404 'title': 'youtube-dl test video',
3407 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3408 'only_matching': True,
3411 def _process_json_dict(self, obj, videos, c):
3412 if "videoId" in obj:
3416 if "nextContinuationData" in obj:
3417 c["continuation"] = obj["nextContinuationData"]
3420 def _real_extract(self, url):
3421 mobj = re.match(self._VALID_URL, url)
3422 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3423 webpage = self._download_webpage(url, query)
3424 return self.playlist_result(self._entries(webpage, query, max_pages=5), playlist_title=query)
3427 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3428 IE_DESC = 'YouTube.com (multi-season) shows'
3429 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3430 IE_NAME = 'youtube:show'
3432 'url': 'https://www.youtube.com/show/airdisasters',
3433 'playlist_mincount': 5,
3435 'id': 'airdisasters',
3436 'title': 'Air Disasters',
3440 def _real_extract(self, url):
3441 playlist_id = self._match_id(url)
3442 return super(YoutubeShowIE, self)._real_extract(
3443 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3446 class YoutubeFeedsInfoExtractor(YoutubePlaylistBaseInfoExtractor):
3448 Base class for feed extractors
3449 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3451 _LOGIN_REQUIRED = True
3455 return 'youtube:%s' % self._FEED_NAME
3457 def _real_initialize(self):
3460 def _process_entries(self, entries, seen):
3463 v_id = try_get(v, lambda x: x['videoId'])
3469 if old['videoId'] == v_id:
3479 seen.extend(new_info)
3480 for video in new_info:
3481 yield self.url_result(try_get(video, lambda x: x['videoId']), YoutubeIE.ie_key(), video_title=self._extract_title(video))
3483 def _real_extract(self, url):
3484 page = self._download_webpage(
3485 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3486 self._PLAYLIST_TITLE)
3487 return self.playlist_result(self._entries(page, self._PLAYLIST_TITLE),
3488 playlist_title=self._PLAYLIST_TITLE)
3491 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3492 IE_NAME = 'youtube:watchlater'
3493 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3494 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3497 'url': 'https://www.youtube.com/playlist?list=WL',
3498 'only_matching': True,
3500 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3501 'only_matching': True,
3504 def _real_extract(self, url):
3505 _, video = self._check_download_just_video(url, 'WL')
3508 _, playlist = self._extract_playlist('WL')
3512 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3513 IE_NAME = 'youtube:favorites'
3514 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3515 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3516 _LOGIN_REQUIRED = True
3518 def _real_extract(self, url):
3519 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3520 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3521 return self.url_result(playlist_id, 'YoutubePlaylist')
3524 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3525 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3526 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3527 _FEED_NAME = 'recommended'
3528 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3531 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3532 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3533 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3534 _FEED_NAME = 'subscriptions'
3535 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3538 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3539 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3540 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3541 _FEED_NAME = 'history'
3542 _PLAYLIST_TITLE = 'Youtube History'
3545 class YoutubeTruncatedURLIE(InfoExtractor):
3546 IE_NAME = 'youtube:truncated_url'
3547 IE_DESC = False # Do not list
3548 _VALID_URL = r'''(?x
)
3550 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3553 annotation_id
=annotation_
[^
&]+|
3559 attribution_link
\?a
=[^
&]+
3565 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3566 'only_matching': True,
3568 'url': 'https://www.youtube.com/watch?',
3569 'only_matching': True,
3571 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3572 'only_matching': True,
3574 'url': 'https://www.youtube.com/watch?feature=foo',
3575 'only_matching': True,
3577 'url': 'https://www.youtube.com/watch?hl=en-GB',
3578 'only_matching': True,
3580 'url': 'https://www.youtube.com/watch?t=2372',
3581 'only_matching': True,
3584 def _real_extract(self, url):
3585 raise ExtractorError(
3586 'Did you forget to quote the URL? Remember that & is a meta '
3587 'character in most shells, so you want to put the URL in quotes, '
3589 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3590 ' or simply youtube-dl BaW_jenozKc .',
3594 class YoutubeTruncatedIDIE(InfoExtractor):
3595 IE_NAME = 'youtube:truncated_id'
3596 IE_DESC = False # Do not list
3597 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3600 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3601 'only_matching': True,
3604 def _real_extract(self, url):
3605 video_id = self._match_id(url)
3606 raise ExtractorError(
3607 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),