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
,
58 class YoutubeBaseInfoExtractor(InfoExtractor
):
59 """Provide base functions for Youtube extractors"""
60 _LOGIN_URL
= 'https://accounts.google.com/ServiceLogin'
61 _TWOFACTOR_URL
= 'https://accounts.google.com/signin/challenge'
63 _LOOKUP_URL
= 'https://accounts.google.com/_/signin/sl/lookup'
64 _CHALLENGE_URL
= 'https://accounts.google.com/_/signin/sl/challenge'
65 _TFA_URL
= 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
67 _NETRC_MACHINE
= 'youtube'
68 # If True it will raise an error if no login info is provided
69 _LOGIN_REQUIRED
= False
71 _PLAYLIST_ID_RE
= r
'(?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)[0-9A-Za-z-_]{10,}'
73 _YOUTUBE_CLIENT_HEADERS
= {
74 'x-youtube-client-name': '1',
75 'x-youtube-client-version': '1.20200609.04.02',
78 def _set_language(self
):
80 '.youtube.com', 'PREF', 'f1=50000000&f6=8&hl=en',
81 # YouTube sets the expire time to about two months
82 expire_time
=time
.time() + 2 * 30 * 24 * 3600)
84 def _ids_to_results(self
, ids
):
86 self
.url_result(vid_id
, 'Youtube', video_id
=vid_id
)
91 Attempt to log in to YouTube.
92 True is returned if successful or skipped.
93 False is returned if login failed.
95 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
97 username
, password
= self
._get
_login
_info
()
98 # No authentication to be performed
100 if self
._LOGIN
_REQUIRED
and self
._downloader
.params
.get('cookiefile') is None:
101 raise ExtractorError('No login info available, needed for using %s.' % self
.IE_NAME
, expected
=True)
104 login_page
= self
._download
_webpage
(
105 self
._LOGIN
_URL
, None,
106 note
='Downloading login page',
107 errnote
='unable to fetch login page', fatal
=False)
108 if login_page
is False:
111 login_form
= self
._hidden
_inputs
(login_page
)
113 def req(url
, f_req
, note
, errnote
):
114 data
= login_form
.copy()
117 'checkConnection': 'youtube',
118 'checkedDomains': 'youtube',
120 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
121 'f.req': json
.dumps(f_req
),
122 'flowName': 'GlifWebSignIn',
123 'flowEntry': 'ServiceLogin',
124 # TODO: reverse actual botguard identifier generation algo
125 'bgRequest': '["identifier",""]',
127 return self
._download
_json
(
128 url
, None, note
=note
, errnote
=errnote
,
129 transform_source
=lambda s
: re
.sub(r
'^[^[]*', '', s
),
131 data
=urlencode_postdata(data
), headers
={
132 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
133 'Google-Accounts-XSRF': 1,
137 self
._downloader
.report_warning(message
)
141 None, [], None, 'US', None, None, 2, False, True,
145 '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',
147 1, [None, None, []], None, None, None, True
152 lookup_results
= req(
153 self
._LOOKUP
_URL
, lookup_req
,
154 'Looking up account info', 'Unable to look up account info')
156 if lookup_results
is False:
159 user_hash
= try_get(lookup_results
, lambda x
: x
[0][2], compat_str
)
161 warn('Unable to extract user hash')
166 None, 1, None, [1, None, None, None, [password
, None, True]],
168 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],
169 1, [None, None, []], None, None, None, True
172 challenge_results
= req(
173 self
._CHALLENGE
_URL
, challenge_req
,
174 'Logging in', 'Unable to log in')
176 if challenge_results
is False:
179 login_res
= try_get(challenge_results
, lambda x
: x
[0][5], list)
181 login_msg
= try_get(login_res
, lambda x
: x
[5], compat_str
)
183 'Unable to login: %s' % 'Invalid password'
184 if login_msg
== 'INCORRECT_ANSWER_ENTERED' else login_msg
)
187 res
= try_get(challenge_results
, lambda x
: x
[0][-1], list)
189 warn('Unable to extract result entry')
192 login_challenge
= try_get(res
, lambda x
: x
[0][0], list)
194 challenge_str
= try_get(login_challenge
, lambda x
: x
[2], compat_str
)
195 if challenge_str
== 'TWO_STEP_VERIFICATION':
196 # SEND_SUCCESS - TFA code has been successfully sent to phone
197 # QUOTA_EXCEEDED - reached the limit of TFA codes
198 status
= try_get(login_challenge
, lambda x
: x
[5], compat_str
)
199 if status
== 'QUOTA_EXCEEDED':
200 warn('Exceeded the limit of TFA codes, try later')
203 tl
= try_get(challenge_results
, lambda x
: x
[1][2], compat_str
)
205 warn('Unable to extract TL')
208 tfa_code
= self
._get
_tfa
_info
('2-step verification code')
212 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
213 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
216 tfa_code
= remove_start(tfa_code
, 'G-')
219 user_hash
, None, 2, None,
221 9, None, None, None, None, None, None, None,
222 [None, tfa_code
, True, 2]
226 self
._TFA
_URL
.format(tl
), tfa_req
,
227 'Submitting TFA code', 'Unable to submit TFA code')
229 if tfa_results
is False:
232 tfa_res
= try_get(tfa_results
, lambda x
: x
[0][5], list)
234 tfa_msg
= try_get(tfa_res
, lambda x
: x
[5], compat_str
)
236 'Unable to finish TFA: %s' % 'Invalid TFA code'
237 if tfa_msg
== 'INCORRECT_ANSWER_ENTERED' else tfa_msg
)
240 check_cookie_url
= try_get(
241 tfa_results
, lambda x
: x
[0][-1][2], compat_str
)
244 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
245 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
246 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
248 challenge
= CHALLENGES
.get(
250 '%s returned error %s.' % (self
.IE_NAME
, challenge_str
))
251 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge
)
254 check_cookie_url
= try_get(res
, lambda x
: x
[2], compat_str
)
256 if not check_cookie_url
:
257 warn('Unable to extract CheckCookie URL')
260 check_cookie_results
= self
._download
_webpage
(
261 check_cookie_url
, None, 'Checking cookie', fatal
=False)
263 if check_cookie_results
is False:
266 if 'https://myaccount.google.com/' not in check_cookie_results
:
267 warn('Unable to log in')
272 def _download_webpage_handle(self
, *args
, **kwargs
):
273 query
= kwargs
.get('query', {}).copy()
274 query
['disable_polymer'] = 'true'
275 kwargs
['query'] = query
276 return super(YoutubeBaseInfoExtractor
, self
)._download
_webpage
_handle
(
277 *args
, **compat_kwargs(kwargs
))
279 def _real_initialize(self
):
280 if self
._downloader
is None:
283 if not self
._login
():
287 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor
):
288 # Extract entries from page with "Load more" button
289 def _entries(self
, page
, playlist_id
):
290 more_widget_html
= content_html
= page
291 for page_num
in itertools
.count(1):
292 for entry
in self
._process
_page
(content_html
):
295 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
301 while count
<= retries
:
303 # Downloading page may result in intermittent 5xx HTTP error
304 # that is usually worked around with a retry
305 more
= self
._download
_json
(
306 'https://www.youtube.com/%s' % mobj
.group('more'), playlist_id
,
307 'Downloading page #%s%s'
308 % (page_num
, ' (retry #%d)' % count
if count
else ''),
309 transform_source
=uppercase_escape
,
310 headers
=self
._YOUTUBE
_CLIENT
_HEADERS
)
312 except ExtractorError
as e
:
313 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
in (500, 503):
319 content_html
= more
['content_html']
320 if not content_html
.strip():
321 # Some webpages show a "Load more" button but they don't
324 more_widget_html
= more
['load_more_widget_html']
327 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
328 def _process_page(self
, content
):
329 for video_id
, video_title
in self
.extract_videos_from_page(content
):
330 yield self
.url_result(video_id
, 'Youtube', video_id
, video_title
)
332 def extract_videos_from_page_impl(self
, video_re
, page
, ids_in_page
, titles_in_page
):
333 for mobj
in re
.finditer(video_re
, page
):
334 # The link with index 0 is not the first video of the playlist (not sure if still actual)
335 if 'index' in mobj
.groupdict() and mobj
.group('id') == '0':
337 video_id
= mobj
.group('id')
338 video_title
= unescapeHTML(
339 mobj
.group('title')) if 'title' in mobj
.groupdict() else None
341 video_title
= video_title
.strip()
342 if video_title
== '► Play all':
345 idx
= ids_in_page
.index(video_id
)
346 if video_title
and not titles_in_page
[idx
]:
347 titles_in_page
[idx
] = video_title
349 ids_in_page
.append(video_id
)
350 titles_in_page
.append(video_title
)
352 def extract_videos_from_page(self
, page
):
355 self
.extract_videos_from_page_impl(
356 self
._VIDEO
_RE
, page
, ids_in_page
, titles_in_page
)
357 return zip(ids_in_page
, titles_in_page
)
360 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor
):
361 def _process_page(self
, content
):
362 for playlist_id
in orderedSet(re
.findall(
363 r
'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
365 yield self
.url_result(
366 'https://www.youtube.com/playlist?list=%s' % playlist_id
, 'YoutubePlaylist')
368 def _real_extract(self
, url
):
369 playlist_id
= self
._match
_id
(url
)
370 webpage
= self
._download
_webpage
(url
, playlist_id
)
371 title
= self
._og
_search
_title
(webpage
, fatal
=False)
372 return self
.playlist_result(self
._entries
(webpage
, playlist_id
), playlist_id
, title
)
375 class YoutubeIE(YoutubeBaseInfoExtractor
):
376 IE_DESC
= 'YouTube.com'
377 _VALID_URL
= r
"""(?x)^
379 (?:https?://|//) # http(s):// or protocol-independent URL
380 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
381 (?:www\.)?deturl\.com/www\.youtube\.com/|
382 (?:www\.)?pwnyoutube\.com/|
383 (?:www\.)?hooktube\.com/|
384 (?:www\.)?yourepeat\.com/|
385 tube\.majestyc\.net/|
386 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
387 (?:(?:www|dev)\.)?invidio\.us/|
388 (?:(?:www|no)\.)?invidiou\.sh/|
389 (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
390 (?:www\.)?invidious\.kabi\.tk/|
391 (?:www\.)?invidious\.13ad\.de/|
392 (?:www\.)?invidious\.mastodon\.host/|
393 (?:www\.)?invidious\.nixnet\.xyz/|
394 (?:www\.)?invidious\.drycat\.fr/|
395 (?:www\.)?tube\.poal\.co/|
396 (?:www\.)?vid\.wxzm\.sx/|
397 (?:www\.)?yewtu\.be/|
398 (?:www\.)?yt\.elukerio\.org/|
399 (?:www\.)?yt\.lelux\.fi/|
400 (?:www\.)?invidious\.ggc-project\.de/|
401 (?:www\.)?yt\.maisputain\.ovh/|
402 (?:www\.)?invidious\.13ad\.de/|
403 (?:www\.)?invidious\.toot\.koeln/|
404 (?:www\.)?invidious\.fdn\.fr/|
405 (?:www\.)?watch\.nettohikari\.com/|
406 (?:www\.)?kgg2m7yk5aybusll\.onion/|
407 (?:www\.)?qklhadlycap4cnod\.onion/|
408 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
409 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
410 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
411 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
412 (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
413 (?:www\.)?4l2dgddgsrkf2ous66i6seeyi6etzfgrue332grh2n7madpwopotugyd\.onion/|
414 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
415 (?:.*?\#/)? # handle anchor (#/) redirect urls
416 (?: # the various things that can precede the ID:
417 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
418 |(?: # or the v= param in all its forms
419 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
420 (?:\?|\#!?) # the params delimiter ? or # or #!
421 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
426 youtu\.be| # just youtu.be/xxxx
427 vid\.plus| # or vid.plus/xxxx
428 zwearz\.com/watch| # or zwearz.com/watch/xxxx
430 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
432 )? # all until now is optional -> you can pass the naked ID
433 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
436 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
437 WL # WL are handled by the watch later IE
440 (?(1).+)? # if we found the ID, everything can follow
441 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
442 _NEXT_URL_RE
= r
'[\?&]next_url=([^&]+)'
444 r
'/(?P<id>[a-zA-Z0-9_-]{8,})/player_ias\.vflset(?:/[a-zA-Z]{2,3}_[a-zA-Z]{2,3})?/base\.(?P<ext>[a-z]+)$',
445 r
'\b(?P<id>vfl[a-zA-Z0-9_-]+)\b.*?\.(?P<ext>[a-z]+)$',
448 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
449 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'}
,
450 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'}
,
451 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'}
,
452 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'}
,
453 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
454 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
455 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
456 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
457 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'}
,
458 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
459 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'}
,
460 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
461 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'}
,
462 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
463 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'}
,
464 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
465 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'}
,
469 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
470 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20}
,
471 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
472 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20}
,
473 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20}
,
474 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
475 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20}
,
477 # Apple HTTP Live Streaming
478 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
479 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
480 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
481 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10}
,
482 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
483 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10}
,
484 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10}
,
485 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10}
,
488 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
489 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
490 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
491 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
492 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
493 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}
, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
494 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
495 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
496 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
497 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
498 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60}
,
499 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'}
,
502 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'}
,
503 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'}
,
504 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'}
,
505 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
506 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'}
,
507 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'}
,
508 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'}
,
511 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
512 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
513 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
514 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
515 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
516 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'}
,
517 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'}
,
518 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
519 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
520 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
521 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
522 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
523 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
524 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
525 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
526 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
527 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
528 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
529 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
530 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
531 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'}
,
532 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60}
,
535 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128}
,
536 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256}
,
538 # Dash webm audio with opus inside
539 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50}
,
540 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70}
,
541 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160}
,
544 '_rtmp': {'protocol': 'rtmp'}
,
546 # av01 video only formats sometimes served with "unknown" codecs
547 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
548 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
549 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
550 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'}
,
552 _SUBTITLE_FORMATS
= ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
559 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
563 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
564 'uploader': 'Philipp Hagemeister',
565 'uploader_id': 'phihag',
566 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
567 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
568 'channel_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
569 'upload_date': '20121002',
570 '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 .',
571 'categories': ['Science & Technology'],
572 'tags': ['youtube-dl'],
576 'dislike_count': int,
582 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
583 'note': 'Test generic use_cipher_signature video (#897)',
587 'upload_date': '20120506',
588 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
589 'alt_title': 'I Love It (feat. Charli XCX)',
590 'description': 'md5:19a2f98d9032b9311e686ed039564f63',
591 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
592 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
593 'iconic ep', 'iconic', 'love', 'it'],
595 'uploader': 'Icona Pop',
596 'uploader_id': 'IconaPop',
597 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IconaPop',
598 'creator': 'Icona Pop',
599 'track': 'I Love It (feat. Charli XCX)',
600 'artist': 'Icona Pop',
604 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
605 'note': 'Test VEVO video with age protection (#956)',
609 'upload_date': '20130703',
610 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
611 'alt_title': 'Tunnel Vision',
612 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
614 'uploader': 'justintimberlakeVEVO',
615 'uploader_id': 'justintimberlakeVEVO',
616 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
617 'creator': 'Justin Timberlake',
618 'track': 'Tunnel Vision',
619 'artist': 'Justin Timberlake',
624 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
625 'note': 'Embed-only video (#1746)',
629 'upload_date': '20120608',
630 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
631 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
632 'uploader': 'SET India',
633 'uploader_id': 'setindia',
634 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/setindia',
639 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
640 'note': 'Use the first video ID in the URL',
644 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
645 'uploader': 'Philipp Hagemeister',
646 'uploader_id': 'phihag',
647 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/phihag',
648 'upload_date': '20121002',
649 '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 .',
650 'categories': ['Science & Technology'],
651 'tags': ['youtube-dl'],
655 'dislike_count': int,
658 'skip_download': True,
662 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
663 'note': '256k DASH audio (format 141) via DASH manifest',
667 'upload_date': '20121002',
668 'uploader_id': '8KVIDEO',
669 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
671 'uploader': '8KVIDEO',
672 'title': 'UHDTV TEST 8K VIDEO.mp4'
675 'youtube_include_dash_manifest': True,
678 'skip': 'format 141 not served anymore',
680 # DASH manifest with encrypted signature
682 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
686 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
687 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
689 'uploader': 'AfrojackVEVO',
690 'uploader_id': 'AfrojackVEVO',
691 'upload_date': '20131011',
694 'youtube_include_dash_manifest': True,
695 'format': '141/bestaudio[ext=m4a]',
698 # JS player signature function name containing $
700 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
704 'title': 'Taylor Swift - Shake It Off',
705 'description': 'md5:307195cd21ff7fa352270fe884570ef0',
707 'uploader': 'TaylorSwiftVEVO',
708 'uploader_id': 'TaylorSwiftVEVO',
709 'upload_date': '20140818',
712 'youtube_include_dash_manifest': True,
713 'format': '141/bestaudio[ext=m4a]',
718 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
723 'upload_date': '20100909',
724 'uploader': 'Amazing Atheist',
725 'uploader_id': 'TheAmazingAtheist',
726 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
727 'title': 'Burning Everyone\'s Koran',
728 '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',
731 # Normal age-gate video (No vevo, embed allowed)
733 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
737 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
738 'description': r
're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
740 'uploader': 'The Witcher',
741 'uploader_id': 'WitcherGame',
742 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
743 'upload_date': '20140605',
747 # Age-gate video with encrypted signature
749 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
753 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
754 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
756 'uploader': 'LloydVEVO',
757 'uploader_id': 'LloydVEVO',
758 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
759 'upload_date': '20110629',
763 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
764 # YouTube Red ad is not captured for creator
766 'url': '__2ABJjxzNo',
771 'upload_date': '20100430',
772 'uploader_id': 'deadmau5',
773 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/deadmau5',
774 'creator': 'Dada Life, deadmau5',
775 'description': 'md5:12c56784b8032162bb936a5f76d55360',
776 'uploader': 'deadmau5',
777 'title': 'Deadmau5 - Some Chords (HD)',
778 'alt_title': 'This Machine Kills Some Chords',
780 'expected_warnings': [
781 'DASH manifest missing',
784 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
786 'url': 'lqQg6PlCWgI',
791 'upload_date': '20150827',
792 'uploader_id': 'olympic',
793 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/olympic',
794 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
795 'uploader': 'Olympic',
796 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
799 'skip_download': 'requires avconv',
804 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
808 'stretched_ratio': 16 / 9.,
810 'upload_date': '20110310',
811 'uploader_id': 'AllenMeow',
812 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
813 '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',
815 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
818 # url_encoded_fmt_stream_map is empty string
820 'url': 'qEJwOuvDf7I',
824 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
826 'upload_date': '20150404',
827 'uploader_id': 'spbelect',
828 'uploader': 'Наблюдатели Петербурга',
831 'skip_download': 'requires avconv',
833 'skip': 'This live event has ended.',
835 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
837 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
841 'title': 'md5:7b81415841e02ecd4313668cde88737a',
842 'description': 'md5:116377fd2963b81ec4ce64b542173306',
844 'upload_date': '20150625',
845 'uploader_id': 'dorappi2000',
846 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
847 'uploader': 'dorappi2000',
848 'formats': 'mincount:31',
850 'skip': 'not actual anymore',
852 # DASH manifest with segment_list
854 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
855 'md5': '8ce563a1d667b599d21064e982ab9e31',
859 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
860 'uploader': 'Airtek',
861 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
862 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
863 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
866 'youtube_include_dash_manifest': True,
867 'format': '135', # bestvideo
869 'skip': 'This live event has ended.',
872 # Multifeed videos (multiple cameras), URL is for Main Camera
873 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
876 'title': 'teamPGP: Rocket League Noob Stream',
877 'description': 'md5:dc7872fb300e143831327f1bae3af010',
883 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
884 'description': 'md5:dc7872fb300e143831327f1bae3af010',
886 'upload_date': '20150721',
887 'uploader': 'Beer Games Beer',
888 'uploader_id': 'beergamesbeer',
889 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
890 'license': 'Standard YouTube License',
896 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
897 'description': 'md5:dc7872fb300e143831327f1bae3af010',
899 'upload_date': '20150721',
900 'uploader': 'Beer Games Beer',
901 'uploader_id': 'beergamesbeer',
902 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
903 'license': 'Standard YouTube License',
909 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
910 'description': 'md5:dc7872fb300e143831327f1bae3af010',
912 'upload_date': '20150721',
913 'uploader': 'Beer Games Beer',
914 'uploader_id': 'beergamesbeer',
915 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
916 'license': 'Standard YouTube License',
922 'title': 'teamPGP: Rocket League Noob Stream (zim)',
923 'description': 'md5:dc7872fb300e143831327f1bae3af010',
925 'upload_date': '20150721',
926 'uploader': 'Beer Games Beer',
927 'uploader_id': 'beergamesbeer',
928 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
929 'license': 'Standard YouTube License',
933 'skip_download': True,
935 'skip': 'This video is not available.',
938 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
939 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
942 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
945 'skip': 'Not multifeed anymore',
948 'url': 'https://vid.plus/FlRa-iH7PGw',
949 'only_matching': True,
952 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
953 'only_matching': True,
956 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
957 # Also tests cut-off URL expansion in video description (see
958 # https://github.com/ytdl-org/youtube-dl/issues/1892,
959 # https://github.com/ytdl-org/youtube-dl/issues/8164)
960 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
964 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
965 'alt_title': 'Dark Walk - Position Music',
966 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
968 'upload_date': '20151119',
969 'uploader_id': 'IronSoulElf',
970 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
971 'uploader': 'IronSoulElf',
972 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
973 'track': 'Dark Walk - Position Music',
974 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
975 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
978 'skip_download': True,
982 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
983 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
984 'only_matching': True,
987 # Video with yt:stretch=17:0
988 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
992 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
993 'description': 'md5:ee18a25c350637c8faff806845bddee9',
994 'upload_date': '20151107',
995 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
996 'uploader': 'CH GAMER DROID',
999 'skip_download': True,
1001 'skip': 'This video does not exist.',
1004 # Video licensed under Creative Commons
1005 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
1007 'id': 'M4gD1WSo5mA',
1009 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
1010 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
1012 'upload_date': '20150127',
1013 'uploader_id': 'BerkmanCenter',
1014 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
1015 'uploader': 'The Berkman Klein Center for Internet & Society',
1016 'license': 'Creative Commons Attribution license (reuse allowed)',
1019 'skip_download': True,
1023 # Channel-like uploader_url
1024 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1026 'id': 'eQcmzGIKrzg',
1028 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1029 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
1031 'upload_date': '20151119',
1032 'uploader': 'Bernie Sanders',
1033 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1034 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1035 'license': 'Creative Commons Attribution license (reuse allowed)',
1038 'skip_download': True,
1042 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1043 'only_matching': True,
1046 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1047 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1048 'only_matching': True,
1051 # Rental video preview
1052 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1054 'id': 'uGpuVWrhIzE',
1056 'title': 'Piku - Trailer',
1057 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1058 'upload_date': '20150811',
1059 'uploader': 'FlixMatrix',
1060 'uploader_id': 'FlixMatrixKaravan',
1061 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1062 'license': 'Standard YouTube License',
1065 'skip_download': True,
1067 'skip': 'This video is not available.',
1070 # YouTube Red video with episode data
1071 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1073 'id': 'iqKdEhx-dD4',
1075 'title': 'Isolation - Mind Field (Ep 1)',
1076 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1078 'upload_date': '20170118',
1079 'uploader': 'Vsauce',
1080 'uploader_id': 'Vsauce',
1081 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1082 'series': 'Mind Field',
1084 'episode_number': 1,
1087 'skip_download': True,
1089 'expected_warnings': [
1090 'Skipping DASH manifest',
1094 # The following content has been identified by the YouTube community
1095 # as inappropriate or offensive to some audiences.
1096 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1098 'id': '6SJNVb0GnPI',
1100 'title': 'Race Differences in Intelligence',
1101 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1103 'upload_date': '20140124',
1104 'uploader': 'New Century Foundation',
1105 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1106 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1109 'skip_download': True,
1114 'url': '1t24XAntNCY',
1115 'only_matching': True,
1118 # geo restricted to JP
1119 'url': 'sJL6WA-aGkQ',
1120 'only_matching': True,
1123 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1124 'only_matching': True,
1127 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1128 'only_matching': True,
1132 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1133 'only_matching': True,
1136 # Video with unsupported adaptive stream type formats
1137 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1139 'id': 'Z4Vy8R84T1U',
1141 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1142 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1144 'upload_date': '20130923',
1145 'uploader': 'Amelia Putri Harwita',
1146 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1147 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1148 'formats': 'maxcount:10',
1151 'skip_download': True,
1152 'youtube_include_dash_manifest': False,
1154 'skip': 'not actual anymore',
1157 # Youtube Music Auto-generated description
1158 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1160 'id': 'MgNrAu2pzNs',
1162 'title': 'Voyeur Girl',
1163 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1164 'upload_date': '20190312',
1165 'uploader': 'Stephen - Topic',
1166 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1167 'artist': 'Stephen',
1168 'track': 'Voyeur Girl',
1169 'album': 'it\'s too much love to know my dear',
1170 'release_date': '20190313',
1171 'release_year': 2019,
1174 'skip_download': True,
1178 # Youtube Music Auto-generated description
1179 # Retrieve 'artist' field from 'Artist:' in video description
1180 # when it is present on youtube music video
1181 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1183 'id': 'k0jLE7tTwjY',
1185 'title': 'Latch Feat. Sam Smith',
1186 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1187 'upload_date': '20150110',
1188 'uploader': 'Various Artists - Topic',
1189 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1190 'artist': 'Disclosure',
1191 'track': 'Latch Feat. Sam Smith',
1192 'album': 'Latch Featuring Sam Smith',
1193 'release_date': '20121008',
1194 'release_year': 2012,
1197 'skip_download': True,
1201 # Youtube Music Auto-generated description
1202 # handle multiple artists on youtube music video
1203 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1205 'id': '74qn0eJSjpA',
1207 'title': 'Eastside',
1208 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1209 'upload_date': '20180710',
1210 'uploader': 'Benny Blanco - Topic',
1211 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1212 'artist': 'benny blanco, Halsey, Khalid',
1213 'track': 'Eastside',
1214 'album': 'Eastside',
1215 'release_date': '20180713',
1216 'release_year': 2018,
1219 'skip_download': True,
1223 # Youtube Music Auto-generated description
1224 # handle youtube music video with release_year and no release_date
1225 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1227 'id': '-hcAI0g-f5M',
1229 'title': 'Put It On Me',
1230 'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
1231 'upload_date': '20180426',
1232 'uploader': 'Matt Maeson - Topic',
1233 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1234 'artist': 'Matt Maeson',
1235 'track': 'Put It On Me',
1236 'album': 'The Hearse',
1237 'release_date': None,
1238 'release_year': 2018,
1241 'skip_download': True,
1245 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1246 'only_matching': True,
1249 # invalid -> valid video id redirection
1250 'url': 'DJztXj2GPfl',
1252 'id': 'DJztXj2GPfk',
1254 'title': 'Panjabi MC - Mundian To Bach Ke (The Dictator Soundtrack)',
1255 'description': 'md5:bf577a41da97918e94fa9798d9228825',
1256 'upload_date': '20090125',
1257 'uploader': 'Prochorowka',
1258 'uploader_id': 'Prochorowka',
1259 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/Prochorowka',
1260 'artist': 'Panjabi MC',
1261 'track': 'Beware of the Boys (Mundian to Bach Ke) - Motivo Hi-Lectro Remix',
1262 'album': 'Beware of the Boys (Mundian To Bach Ke)',
1265 'skip_download': True,
1270 def __init__(self
, *args
, **kwargs
):
1271 super(YoutubeIE
, self
).__init
__(*args
, **kwargs
)
1272 self
._player
_cache
= {}
1274 def report_video_info_webpage_download(self
, video_id
):
1275 """Report attempt to download video info webpage."""
1276 self
.to_screen('%s: Downloading video info webpage' % video_id
)
1278 def report_information_extraction(self
, video_id
):
1279 """Report attempt to extract video information."""
1280 self
.to_screen('%s: Extracting video information' % video_id
)
1282 def report_unavailable_format(self
, video_id
, format
):
1283 """Report extracted video URL."""
1284 self
.to_screen('%s: Format %s not available' % (video_id
, format
))
1286 def report_rtmp_download(self
):
1287 """Indicate the download will use the RTMP protocol."""
1288 self
.to_screen('RTMP download detected')
1290 def _signature_cache_id(self
, example_sig
):
1291 """ Return a string representation of a signature """
1292 return '.'.join(compat_str(len(part
)) for part
in example_sig
.split('.'))
1295 def _extract_player_info(cls
, player_url
):
1296 for player_re
in cls
._PLAYER
_INFO
_RE
:
1297 id_m
= re
.search(player_re
, player_url
)
1301 raise ExtractorError('Cannot identify player %r' % player_url
)
1302 return id_m
.group('ext'), id_m
.group('id')
1304 def _extract_signature_function(self
, video_id
, player_url
, example_sig
):
1305 player_type
, player_id
= self
._extract
_player
_info
(player_url
)
1307 # Read from filesystem cache
1308 func_id
= '%s_%s_%s' % (
1309 player_type
, player_id
, self
._signature
_cache
_id
(example_sig
))
1310 assert os
.path
.basename(func_id
) == func_id
1312 cache_spec
= self
._downloader
.cache
.load('youtube-sigfuncs', func_id
)
1313 if cache_spec
is not None:
1314 return lambda s
: ''.join(s
[i
] for i
in cache_spec
)
1317 'Downloading player %s' % player_url
1318 if self
._downloader
.params
.get('verbose') else
1319 'Downloading %s player %s' % (player_type
, player_id
)
1321 if player_type
== 'js':
1322 code
= self
._download
_webpage
(
1323 player_url
, video_id
,
1325 errnote
='Download of %s failed' % player_url
)
1326 res
= self
._parse
_sig
_js
(code
)
1327 elif player_type
== 'swf':
1328 urlh
= self
._request
_webpage
(
1329 player_url
, video_id
,
1331 errnote
='Download of %s failed' % player_url
)
1333 res
= self
._parse
_sig
_swf
(code
)
1335 assert False, 'Invalid player type %r' % player_type
1337 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1338 cache_res
= res(test_string
)
1339 cache_spec
= [ord(c
) for c
in cache_res
]
1341 self
._downloader
.cache
.store('youtube-sigfuncs', func_id
, cache_spec
)
1344 def _print_sig_code(self
, func
, example_sig
):
1345 def gen_sig_code(idxs
):
1346 def _genslice(start
, end
, step
):
1347 starts
= '' if start
== 0 else str(start
)
1348 ends
= (':%d' % (end
+ step
)) if end
+ step
>= 0 else ':'
1349 steps
= '' if step
== 1 else (':%d' % step
)
1350 return 's[%s%s%s]' % (starts
, ends
, steps
)
1353 # Quelch pyflakes warnings - start will be set when step is set
1354 start
= '(Never used)'
1355 for i
, prev
in zip(idxs
[1:], idxs
[:-1]):
1356 if step
is not None:
1357 if i
- prev
== step
:
1359 yield _genslice(start
, prev
, step
)
1362 if i
- prev
in [-1, 1]:
1367 yield 's[%d]' % prev
1371 yield _genslice(start
, i
, step
)
1373 test_string
= ''.join(map(compat_chr
, range(len(example_sig
))))
1374 cache_res
= func(test_string
)
1375 cache_spec
= [ord(c
) for c
in cache_res
]
1376 expr_code
= ' + '.join(gen_sig_code(cache_spec
))
1377 signature_id_tuple
= '(%s)' % (
1378 ', '.join(compat_str(len(p
)) for p
in example_sig
.split('.')))
1379 code
= ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1380 ' return %s\n') % (signature_id_tuple
, expr_code
)
1381 self
.to_screen('Extracted signature function:\n' + code
)
1383 def _parse_sig_js(self
, jscode
):
1384 funcname
= self
._search
_regex
(
1385 (r
'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1386 r
'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1387 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\(\s*""\s*\)',
1388 r
'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1390 r
'(["\'])signature\
1\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1391 r'\
.sig\|\|
(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1392 r'yt\
.akamaized\
.net
/\
)\s
*\|\|\s
*.*?\s
*[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?
:encodeURIComponent\s
*\
()?\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1393 r'\b[cs
]\s
*&&\s
*[adf
]\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1394 r'\b[a
-zA
-Z0
-9]+\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1395 r'\bc\s
*&&\s
*a\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1396 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
(',
1397 r'\bc\s
*&&\s
*[a
-zA
-Z0
-9]+\
.set\
([^
,]+\s
*,\s
*\
([^
)]*\
)\s
*\
(\s
*(?P
<sig
>[a
-zA
-Z0
-9$
]+)\
('),
1398 jscode, 'Initial JS player signature function name
', group='sig
')
1400 jsi = JSInterpreter(jscode)
1401 initial_function = jsi.extract_function(funcname)
1402 return lambda s: initial_function([s])
1404 def _parse_sig_swf(self, file_contents):
1405 swfi = SWFInterpreter(file_contents)
1406 TARGET_CLASSNAME = 'SignatureDecipher
'
1407 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1408 initial_function = swfi.extract_function(searched_class, 'decipher
')
1409 return lambda s: initial_function([s])
1411 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1412 """Turn the encrypted s field into a working signature"""
1414 if player_url is None:
1415 raise ExtractorError('Cannot decrypt signature without player_url
')
1417 if player_url.startswith('//'):
1418 player_url = 'https
:' + player_url
1419 elif not re.match(r'https?
://', player_url):
1420 player_url = compat_urlparse.urljoin(
1421 'https
://www
.youtube
.com
', player_url)
1423 player_id = (player_url, self._signature_cache_id(s))
1424 if player_id not in self._player_cache:
1425 func = self._extract_signature_function(
1426 video_id, player_url, s
1428 self._player_cache[player_id] = func
1429 func = self._player_cache[player_id]
1430 if self._downloader.params.get('youtube_print_sig_code
'):
1431 self._print_sig_code(func, s)
1433 except Exception as e:
1434 tb = traceback.format_exc()
1435 raise ExtractorError(
1436 'Signature extraction failed
: ' + tb, cause=e)
1438 def _get_subtitles(self, video_id, webpage, has_live_chat_replay):
1440 subs_doc = self._download_xml(
1441 'https
://video
.google
.com
/timedtext?hl
=en
&type=list&v
=%s' % video_id,
1442 video_id, note=False)
1443 except ExtractorError as err:
1444 self._downloader.report_warning('unable to download video subtitles
: %s' % error_to_compat_str(err))
1448 for track in subs_doc.findall('track
'):
1449 lang = track.attrib['lang_code
']
1450 if lang in sub_lang_list:
1453 for ext in self._SUBTITLE_FORMATS:
1454 params = compat_urllib_parse_urlencode({
1458 'name
': track.attrib['name
'].encode('utf
-8'),
1460 sub_formats.append({
1461 'url
': 'https
://www
.youtube
.com
/api
/timedtext?
' + params,
1464 sub_lang_list[lang] = sub_formats
1465 if has_live_chat_replay:
1466 sub_lang_list['live_chat
'] = [
1468 'video_id
': video_id,
1470 'protocol
': 'youtube_live_chat_replay
',
1473 if not sub_lang_list:
1474 self._downloader.report_warning('video doesn
\'t have subtitles
')
1476 return sub_lang_list
1478 def _get_ytplayer_config(self, video_id, webpage):
1480 # User data may contain arbitrary character sequences that may affect
1481 # JSON extraction with regex, e.g. when '};' is contained the second
1482 # regex won't capture the whole JSON
. Yet working around by trying more
1483 # concrete regex first keeping in mind proper quoted string handling
1484 # to be implemented in future that will replace this workaround (see
1485 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1486 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1487 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1488 r
';ytplayer\.config\s*=\s*({.+?});',
1490 config
= self
._search
_regex
(
1491 patterns
, webpage
, 'ytplayer.config', default
=None)
1493 return self
._parse
_json
(
1494 uppercase_escape(config
), video_id
, fatal
=False)
1496 def _get_yt_initial_data(self
, video_id
, webpage
):
1497 config
= self
._search
_regex
(
1498 (r
'window\["ytInitialData"\]\s*=\s*(.*?)(?<=});',
1499 r
'var\s+ytInitialData\s*=\s*(.*?)(?<=});'),
1500 webpage
, 'ytInitialData', default
=None)
1502 return self
._parse
_json
(
1503 uppercase_escape(config
), video_id
, fatal
=False)
1505 def _get_automatic_captions(self
, video_id
, webpage
):
1506 """We need the webpage for getting the captions url, pass it as an
1507 argument to speed up the process."""
1508 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1509 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1510 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1511 if not player_config
:
1512 self
._downloader
.report_warning(err_msg
)
1515 args
= player_config
['args']
1516 caption_url
= args
.get('ttsurl')
1518 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 player_response
= args
.get('player_response')
1575 if player_response
and isinstance(player_response
, compat_str
):
1576 player_response
= self
._parse
_json
(
1577 player_response
, video_id
, fatal
=False)
1579 renderer
= player_response
['captions']['playerCaptionsTracklistRenderer']
1580 base_url
= renderer
['captionTracks'][0]['baseUrl']
1582 for lang
in renderer
['translationLanguages']:
1583 lang_code
= lang
.get('languageCode')
1585 sub_lang_list
.append(lang_code
)
1586 return make_captions(base_url
, sub_lang_list
)
1588 # Some videos don't provide ttsurl but rather caption_tracks and
1589 # caption_translation_languages (e.g. 20LmZk1hakA)
1590 # Does not used anymore as of 22.06.2017
1591 caption_tracks
= args
['caption_tracks']
1592 caption_translation_languages
= args
['caption_translation_languages']
1593 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1595 for lang
in caption_translation_languages
.split(','):
1596 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1597 sub_lang
= lang_qs
.get('lc', [None])[0]
1599 sub_lang_list
.append(sub_lang
)
1600 return make_captions(caption_url
, sub_lang_list
)
1601 # An extractor error can be raise by the download process if there are
1602 # no automatic captions but there are subtitles
1603 except (KeyError, IndexError, ExtractorError
):
1604 self
._downloader
.report_warning(err_msg
)
1607 def _mark_watched(self
, video_id
, video_info
, player_response
):
1608 playback_url
= url_or_none(try_get(
1610 lambda x
: x
['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1611 video_info
, lambda x
: x
['videostats_playback_base_url'][0]))
1612 if not playback_url
:
1614 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1615 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1617 # cpn generation algorithm is reverse engineered from base.js.
1618 # In fact it works even with dummy cpn.
1619 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1620 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1626 playback_url
= compat_urlparse
.urlunparse(
1627 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1629 self
._download
_webpage
(
1630 playback_url
, video_id
, 'Marking watched',
1631 'Unable to mark watched', fatal
=False)
1634 def _extract_urls(webpage
):
1635 # Embedded YouTube player
1637 unescapeHTML(mobj
.group('url'))
1638 for mobj
in re
.finditer(r
'''(?x)
1648 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1649 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1652 # lazyYT YouTube embed
1653 entries.extend(list(map(
1655 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1657 # Wordpress "YouTube Video Importer" plugin
1658 matches = re.findall(r'''(?x
)<div
[^
>]+
1659 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1660 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1661 entries.extend(m[-1] for m in matches)
1666 def _extract_url(webpage):
1667 urls = YoutubeIE._extract_urls(webpage)
1668 return urls[0] if urls else None
1671 def extract_id(cls, url):
1672 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1674 raise ExtractorError('Invalid URL: %s' % url)
1675 video_id = mobj.group(2)
1678 def _extract_chapters_from_json(self, webpage, video_id, duration):
1681 initial_data = self._parse_json(
1683 r'window\["ytInitialData
"\] = (.+);\n', webpage,
1684 'player args', default='{}'),
1685 video_id, fatal=False)
1686 if not initial_data or not isinstance(initial_data, dict):
1688 chapters_list = try_get(
1690 lambda x: x['playerOverlays']
1691 ['playerOverlayRenderer']
1692 ['decoratedPlayerBarRenderer']
1693 ['decoratedPlayerBarRenderer']
1695 ['chapteredPlayerBarRenderer']
1698 if not chapters_list:
1701 def chapter_time(chapter):
1702 return float_or_none(
1705 lambda x: x['chapterRenderer']['timeRangeStartMillis'],
1709 for next_num, chapter in enumerate(chapters_list, start=1):
1710 start_time = chapter_time(chapter)
1711 if start_time is None:
1713 end_time = (chapter_time(chapters_list[next_num])
1714 if next_num < len(chapters_list) else duration)
1715 if end_time is None:
1718 chapter, lambda x: x['chapterRenderer']['title']['simpleText'],
1721 'start_time': start_time,
1722 'end_time': end_time,
1728 def _extract_chapters_from_description(description, duration):
1731 chapter_lines = re.findall(
1732 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\
.www\
.watch\
.player\
.seekTo
[^
>]+>(\d{1,2}
:\d{1,2}
(?
::\d{1,2}
)?
)</a
>[^
>]*)(?
=$|
<br\s
*/>)',
1734 if not chapter_lines:
1737 for next_num, (chapter_line, time_point) in enumerate(
1738 chapter_lines, start=1):
1739 start_time = parse_duration(time_point)
1740 if start_time is None:
1742 if start_time > duration:
1744 end_time = (duration if next_num == len(chapter_lines)
1745 else parse_duration(chapter_lines[next_num][1]))
1746 if end_time is None:
1748 if end_time > duration:
1750 if start_time > end_time:
1752 chapter_title = re.sub(
1753 r'<a
[^
>]+>[^
<]+</a
>', '', chapter_line).strip(' \t-')
1754 chapter_title = re.sub(r'\s
+', ' ', chapter_title)
1756 'start_time
': start_time,
1757 'end_time
': end_time,
1758 'title
': chapter_title,
1762 def _extract_chapters(self, webpage, description, video_id, duration):
1763 return (self._extract_chapters_from_json(webpage, video_id, duration)
1764 or self._extract_chapters_from_description(description, duration))
1766 def _real_extract(self, url):
1767 url, smuggled_data = unsmuggle_url(url, {})
1770 'http
' if self._downloader.params.get('prefer_insecure
', False)
1775 parsed_url = compat_urllib_parse_urlparse(url)
1776 for component in [parsed_url.fragment, parsed_url.query]:
1777 query = compat_parse_qs(component)
1778 if start_time is None and 't
' in query:
1779 start_time = parse_duration(query['t
'][0])
1780 if start_time is None and 'start
' in query:
1781 start_time = parse_duration(query['start
'][0])
1782 if end_time is None and 'end
' in query:
1783 end_time = parse_duration(query['end
'][0])
1785 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1786 mobj = re.search(self._NEXT_URL_RE, url)
1788 url = proto + '://www
.youtube
.com
/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1789 video_id = self.extract_id(url)
1792 url = proto + '://www
.youtube
.com
/watch?v
=%s&gl
=US
&hl
=en
&has_verified
=1&bpctr
=9999999999' % video_id
1793 video_webpage, urlh = self._download_webpage_handle(url, video_id)
1795 qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query)
1796 video_id = qs.get('v
', [None])[0] or video_id
1798 # Attempt to extract SWF player URL
1799 mobj = re.search(r'swfConfig
.*?
"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1800 if mobj is not None:
1801 player_url = re.sub(r'\\(.)', r'\
1', mobj.group(1))
1807 def add_dash_mpd(video_info):
1808 dash_mpd = video_info.get('dashmpd
')
1809 if dash_mpd and dash_mpd[0] not in dash_mpds:
1810 dash_mpds.append(dash_mpd[0])
1812 def add_dash_mpd_pr(pl_response):
1813 dash_mpd = url_or_none(try_get(
1814 pl_response, lambda x: x['streamingData
']['dashManifestUrl
'],
1816 if dash_mpd and dash_mpd not in dash_mpds:
1817 dash_mpds.append(dash_mpd)
1822 def extract_view_count(v_info):
1823 return int_or_none(try_get(v_info, lambda x: x['view_count
'][0]))
1825 def extract_player_response(player_response, video_id):
1826 pl_response = str_or_none(player_response)
1829 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1830 if isinstance(pl_response, dict):
1831 add_dash_mpd_pr(pl_response)
1834 player_response = {}
1838 embed_webpage = None
1839 if re.search(r'player
-age
-gate
-content
">', video_webpage) is not None:
1841 # We simulate the access to the video from www.youtube.com/v/{video_id}
1842 # this can be viewed without login into Youtube
1843 url = proto + '://www.youtube.com/embed/%s' % video_id
1844 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1845 data = compat_urllib_parse_urlencode({
1846 'video_id': video_id,
1847 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1848 'sts': self._search_regex(
1849 r'"sts
"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1851 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1853 video_info_webpage = self._download_webpage(
1854 video_info_url, video_id,
1855 note='Refetching age-gated info webpage',
1856 errnote='unable to download video info webpage')
1857 except ExtractorError:
1858 video_info_webpage = None
1859 if video_info_webpage:
1860 video_info = compat_parse_qs(video_info_webpage)
1861 pl_response = video_info.get('player_response', [None])[0]
1862 player_response = extract_player_response(pl_response, video_id)
1863 add_dash_mpd(video_info)
1864 view_count = extract_view_count(video_info)
1867 # Try looking directly into the video webpage
1868 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1870 args = ytplayer_config['args']
1871 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1872 # Convert to the same format returned by compat_parse_qs
1873 video_info = dict((k, [v]) for k, v in args.items())
1874 add_dash_mpd(video_info)
1875 # Rental video is not rented but preview is available (e.g.
1876 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1877 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1878 if not video_info and args.get('ypc_vid'):
1879 return self.url_result(
1880 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1881 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1883 if not player_response:
1884 player_response = extract_player_response(args.get('player_response'), video_id)
1885 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1886 add_dash_mpd_pr(player_response)
1888 def extract_unavailable_message():
1890 for tag, kind in (('h1', 'message'), ('div', 'submessage')):
1891 msg = self._html_search_regex(
1892 r'(?s)<{tag}[^>]+id=["\']unavailable
-{kind}
["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind),
1893 video_webpage, 'unavailable %s' % kind, default=None)
1895 messages.append(msg)
1897 return '\n'.join(messages)
1899 if not video_info and not player_response:
1900 unavailable_message = extract_unavailable_message()
1901 if not unavailable_message:
1902 unavailable_message = 'Unable to extract video data'
1903 raise ExtractorError(
1904 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1906 if not isinstance(video_info, dict):
1909 video_details = try_get(
1910 player_response, lambda x: x['videoDetails'], dict) or {}
1912 microformat = try_get(
1913 player_response, lambda x: x['microformat']['playerMicroformatRenderer'], dict) or {}
1915 video_title = video_info.get('title', [None])[0] or video_details.get('title')
1917 self._downloader.report_warning('Unable to extract video title')
1920 description_original = video_description = get_element_by_id("eow
-description
", video_webpage)
1921 if video_description:
1924 redir_url = compat_urlparse.urljoin(url, m.group(1))
1925 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1926 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1927 qs = compat_parse_qs(parsed_redir_url.query)
1933 description_original = video_description = re.sub(r'''(?x)
1935 (?:[a-zA-Z-]+="[^
"]*"\s
+)*?
1936 (?
:title|href
)="([^"]+)"\s+
1937 (?:[a-zA-Z-]+="[^
"]*"\s
+)*?
1941 ''', replace_url, video_description)
1942 video_description = clean_html(video_description)
1944 video_description = video_details.get('shortDescription') or self._html_search_meta('description', video_webpage)
1946 if not smuggled_data.get('force_singlefeed', False):
1947 if not self._downloader.params.get('noplaylist'):
1948 multifeed_metadata_list = try_get(
1950 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1951 compat_str) or try_get(
1952 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1953 if multifeed_metadata_list:
1956 for feed in multifeed_metadata_list.split(','):
1957 # Unquote should take place before split on comma (,) since textual
1958 # fields may contain comma as well (see
1959 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1960 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1962 def feed_entry(name):
1963 return try_get(feed_data, lambda x: x[name][0], compat_str)
1965 feed_id = feed_entry('id')
1968 feed_title = feed_entry('title')
1971 title += ' (%s)' % feed_title
1973 '_type': 'url_transparent',
1974 'ie_key': 'Youtube',
1976 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1977 {'force_singlefeed': True}),
1980 feed_ids.append(feed_id)
1982 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1983 % (', '.join(feed_ids), video_id))
1984 return self.playlist_result(entries, video_id, video_title, video_description)
1986 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1988 if view_count is None:
1989 view_count = extract_view_count(video_info)
1990 if view_count is None and video_details:
1991 view_count = int_or_none(video_details.get('viewCount'))
1992 if view_count is None and microformat:
1993 view_count = int_or_none(microformat.get('viewCount'))
1996 is_live = bool_or_none(video_details.get('isLive'))
1998 has_live_chat_replay = False
2000 yt_initial_data = self._get_yt_initial_data(video_id, video_webpage)
2002 yt_initial_data['contents']['twoColumnWatchNextResults']['conversationBar']['liveChatRenderer']['continuations'][0]['reloadContinuationData']['continuation']
2003 has_live_chat_replay = True
2004 except (KeyError, IndexError, TypeError):
2007 # Check for "rental
" videos
2008 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
2009 raise ExtractorError('"rental
" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
2011 def _extract_filesize(media_url):
2012 return int_or_none(self._search_regex(
2013 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
2015 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or []
2016 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or [])
2018 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
2019 self.report_rtmp_download()
2021 'format_id': '_rtmp',
2023 'url': video_info['conn'][0],
2024 'player_url': player_url,
2026 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):
2027 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
2028 if 'rtmpe%3Dyes' in encoded_url_map:
2029 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
2032 fmt_list = video_info.get('fmt_list', [''])[0]
2034 for fmt in fmt_list.split(','):
2035 spec = fmt.split('/')
2037 width_height = spec[1].split('x')
2038 if len(width_height) == 2:
2039 formats_spec[spec[0]] = {
2040 'resolution': spec[1],
2041 'width': int_or_none(width_height[0]),
2042 'height': int_or_none(width_height[1]),
2044 for fmt in streaming_formats:
2045 itag = str_or_none(fmt.get('itag'))
2048 quality = fmt.get('quality')
2049 quality_label = fmt.get('qualityLabel') or quality
2050 formats_spec[itag] = {
2051 'asr': int_or_none(fmt.get('audioSampleRate')),
2052 'filesize': int_or_none(fmt.get('contentLength')),
2053 'format_note': quality_label,
2054 'fps': int_or_none(fmt.get('fps')),
2055 'height': int_or_none(fmt.get('height')),
2056 # bitrate for itag 43 is always 2147483647
2057 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
2058 'width': int_or_none(fmt.get('width')),
2061 for fmt in streaming_formats:
2062 if fmt.get('drmFamilies') or fmt.get('drm_families'):
2064 url = url_or_none(fmt.get('url'))
2067 cipher = fmt.get('cipher') or fmt.get('signatureCipher')
2070 url_data = compat_parse_qs(cipher)
2071 url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str))
2076 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
2078 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
2079 # Unsupported FORMAT_STREAM_TYPE_OTF
2080 if stream_type == 3:
2083 format_id = fmt.get('itag') or url_data['itag'][0]
2086 format_id = compat_str(format_id)
2089 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
2090 ASSETS_RE = r'"assets
":.+?"js
":\s*("[^
"]+")'
2091 jsplayer_url_json = self._search_regex(
2093 embed_webpage if age_gate else video_webpage,
2094 'JS player
URL (1)', default=None)
2095 if not jsplayer_url_json and not age_gate:
2096 # We need the embed website after all
2097 if embed_webpage is None:
2098 embed_url = proto + '://www
.youtube
.com
/embed
/%s' % video_id
2099 embed_webpage = self._download_webpage(
2100 embed_url, video_id, 'Downloading embed webpage
')
2101 jsplayer_url_json = self._search_regex(
2102 ASSETS_RE, embed_webpage, 'JS player URL
')
2104 player_url = json.loads(jsplayer_url_json)
2105 if player_url is None:
2106 player_url_json = self._search_regex(
2107 r'ytplayer\
.config
.*?
"url"\s
*:\s
*("[^"]+")',
2108 video_webpage, 'age gate player URL')
2109 player_url = json.loads(player_url_json)
2111 if 'sig' in url_data:
2112 url += '&signature=' + url_data['sig'][0]
2113 elif 's' in url_data:
2114 encrypted_sig = url_data['s'][0]
2116 if self._downloader.params.get('verbose'):
2117 if player_url is None:
2118 player_desc = 'unknown'
2120 player_type, player_version = self._extract_player_info(player_url)
2121 player_desc = '%s player %s' % ('flash' if player_type == 'swf' else 'html5', player_version)
2122 parts_sizes = self._signature_cache_id(encrypted_sig)
2123 self.to_screen('{%s} signature length %s, %s' %
2124 (format_id, parts_sizes, player_desc))
2126 signature = self._decrypt_signature(
2127 encrypted_sig, video_id, player_url, age_gate)
2128 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2129 url += '&%s=%s' % (sp, signature)
2130 if 'ratebypass' not in url:
2131 url += '&ratebypass=yes'
2134 'format_id': format_id,
2136 'player_url': player_url,
2138 if format_id in self._formats:
2139 dct.update(self._formats[format_id])
2140 if format_id in formats_spec:
2141 dct.update(formats_spec[format_id])
2143 # Some itags are not included in DASH manifest thus corresponding formats will
2144 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2145 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2146 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2147 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2150 width = int_or_none(fmt.get('width'))
2152 height = int_or_none(fmt.get('height'))
2154 filesize = int_or_none(url_data.get(
2155 'clen', [None])[0]) or _extract_filesize(url)
2157 quality = url_data.get('quality', [None])[0] or fmt.get('quality')
2158 quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
2160 tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
2161 or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
2162 fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
2165 'filesize': filesize,
2170 'format_note': quality_label or quality,
2172 for key, value in more_fields.items():
2175 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
2177 type_split = type_.split(';')
2178 kind_ext = type_split[0].split('/')
2179 if len(kind_ext) == 2:
2181 dct['ext'] = mimetype2ext(type_split[0])
2182 if kind in ('audio', 'video'):
2184 for mobj in re.finditer(
2185 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?
)(?P
<val
>.+?
)(?P
=quote
)(?
:;|$
)', type_):
2186 if mobj.group('key
') == 'codecs
':
2187 codecs = mobj.group('val
')
2190 dct.update(parse_codecs(codecs))
2191 if dct.get('acodec
') == 'none
' or dct.get('vcodec
') == 'none
':
2192 dct['downloader_options
'] = {
2193 # Youtube throttles chunks >~10M
2194 'http_chunk_size
': 10485760,
2199 url_or_none(try_get(
2201 lambda x: x['streamingData
']['hlsManifestUrl
'],
2203 or url_or_none(try_get(
2204 video_info, lambda x: x['hlsvp
'][0], compat_str)))
2207 m3u8_formats = self._extract_m3u8_formats(
2208 manifest_url, video_id, 'mp4
', fatal=False)
2209 for a_format in m3u8_formats:
2210 itag = self._search_regex(
2211 r'/itag
/(\d
+)/', a_format['url
'], 'itag
', default=None)
2213 a_format['format_id
'] = itag
2214 if itag in self._formats:
2215 dct = self._formats[itag].copy()
2216 dct.update(a_format)
2218 a_format['player_url
'] = player_url
2219 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2220 a_format.setdefault('http_headers
', {})['Youtubedl
-no
-compression
'] = 'True'
2221 formats.append(a_format)
2223 error_message = extract_unavailable_message()
2224 if not error_message:
2225 error_message = clean_html(try_get(
2226 player_response, lambda x: x['playabilityStatus
']['reason
'],
2228 if not error_message:
2229 error_message = clean_html(
2230 try_get(video_info, lambda x: x['reason
'][0], compat_str))
2232 raise ExtractorError(error_message, expected=True)
2233 raise ExtractorError('no conn
, hlsvp
, hlsManifestUrl
or url_encoded_fmt_stream_map information found
in video info
')
2236 video_uploader = try_get(
2237 video_info, lambda x: x['author
'][0],
2238 compat_str) or str_or_none(video_details.get('author
'))
2240 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2242 self._downloader.report_warning('unable to extract uploader name
')
2245 video_uploader_id = None
2246 video_uploader_url = None
2248 r'<link itemprop
="url" href
="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2250 if mobj is not None:
2251 video_uploader_id = mobj.group('uploader_id')
2252 video_uploader_url = mobj.group('uploader_url')
2254 owner_profile_url = url_or_none(microformat.get('ownerProfileUrl'))
2255 if owner_profile_url:
2256 video_uploader_id = self._search_regex(
2257 r'(?:user|channel)/([^/]+)', owner_profile_url, 'uploader id',
2259 video_uploader_url = owner_profile_url
2262 str_or_none(video_details.get('channelId'))
2263 or self._html_search_meta(
2264 'channelId', video_webpage, 'channel id', default=None)
2265 or self._search_regex(
2266 r'data-channel-external-id=(["\'])(?P
<id>(?
:(?
!\
1).)+)\
1',
2267 video_webpage, 'channel
id', default=None, group='id'))
2268 channel_url = 'http
://www
.youtube
.com
/channel
/%s' % channel_id if channel_id else None
2271 thumbnails_list = try_get(
2272 video_details, lambda x: x['thumbnail
']['thumbnails
'], list) or []
2273 for t in thumbnails_list:
2274 if not isinstance(t, dict):
2276 thumbnail_url = url_or_none(t.get('url
'))
2277 if not thumbnail_url:
2280 'url
': thumbnail_url,
2281 'width
': int_or_none(t.get('width
')),
2282 'height
': int_or_none(t.get('height
')),
2286 video_thumbnail = None
2287 # We try first to get a high quality image:
2288 m_thumb = re.search(r'<span itemprop
="thumbnail".*?href
="(.*?)">',
2289 video_webpage, re.DOTALL)
2290 if m_thumb is not None:
2291 video_thumbnail = m_thumb.group(1)
2292 thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url
'][0], compat_str)
2294 video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
2296 thumbnails.append({'url': video_thumbnail})
2299 upload_date = self._html_search_meta(
2300 'datePublished
', video_webpage, 'upload date
', default=None)
2302 upload_date = self._search_regex(
2303 [r'(?s
)id="eow-date.*?>(.*?)</span>',
2304 r'(?:id="watch
-uploader
-info
".*?>.*?|["\']simpleText
["\']\s*:\s*["\'])(?
:Published|Uploaded|Streamed live|Started
) on (.+?
)[<"\']'],
2305 video_webpage, 'upload date', default=None)
2307 upload_date = microformat.get('publishDate') or microformat.get('uploadDate')
2308 upload_date = unified_strdate(upload_date)
2310 video_license = self._html_search_regex(
2311 r'<h4[^>]+class="title
"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2312 video_webpage, 'license', default=None)
2314 m_music = re.search(
2316 <h4[^>]+class="title
"[^>]*>\s*Music\s*</h4>\s*
2324 \bhref=["\']/red
[^
>]*>|
# drop possible
2325 >\s
*Listen ad
-free
with YouTube Red
# YouTube Red ad
2332 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2333 video_creator = clean_html(m_music.group('creator'))
2335 video_alt_title = video_creator = None
2337 def extract_meta(field):
2338 return self._html_search_regex(
2339 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2340 video_webpage, field, default=None)
2342 track = extract_meta('Song')
2343 artist = extract_meta('Artist')
2344 album = extract_meta('Album')
2346 # Youtube Music Auto-generated description
2347 release_date = release_year = None
2348 if video_description:
2349 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)
2352 track = mobj.group('track').strip()
2354 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2356 album = mobj.group('album'.strip())
2357 release_year = mobj.group('release_year')
2358 release_date = mobj.group('release_date')
2360 release_date = release_date.replace('-', '')
2361 if not release_year:
2362 release_year = int(release_date[:4])
2364 release_year = int(release_year)
2366 m_episode = re.search(
2367 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2370 series = unescapeHTML(m_episode.group('series'))
2371 season_number = int(m_episode.group('season'))
2372 episode_number = int(m_episode.group('episode'))
2374 series = season_number = episode_number = None
2376 m_cat_container = self._search_regex(
2377 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2378 video_webpage, 'categories', default=None)
2381 category = self._html_search_regex(
2382 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2386 microformat, lambda x: x['category'], compat_str)
2387 video_categories = None if category is None else [category]
2390 unescapeHTML(m.group('content'))
2391 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2393 video_tags = try_get(video_details, lambda x: x['keywords'], list)
2395 def _extract_count(count_name):
2396 return str_to_int(self._search_regex(
2397 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2398 % re.escape(count_name),
2399 video_webpage, count_name, default=None))
2401 like_count = _extract_count('like')
2402 dislike_count = _extract_count('dislike')
2404 if view_count is None:
2405 view_count = str_to_int(self._search_regex(
2406 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2407 'view count', default=None))
2410 float_or_none(video_details.get('averageRating'))
2411 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2414 video_subtitles = self.extract_subtitles(
2415 video_id, video_webpage, has_live_chat_replay)
2416 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2418 video_duration = try_get(
2419 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2420 if not video_duration:
2421 video_duration = int_or_none(video_details.get('lengthSeconds'))
2422 if not video_duration:
2423 video_duration = parse_duration(self._html_search_meta(
2424 'duration', video_webpage, 'video duration'))
2427 video_annotations = None
2428 if self._downloader.params.get('writeannotations', False):
2429 xsrf_token = self._search_regex(
2430 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
2431 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2432 invideo_url = try_get(
2433 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2434 if xsrf_token and invideo_url:
2435 xsrf_field_name = self._search_regex(
2436 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2437 video_webpage, 'xsrf field name',
2438 group='xsrf_field_name', default='session_token')
2439 video_annotations = self._download_webpage(
2440 self._proto_relative_url(invideo_url),
2441 video_id, note='Downloading annotations',
2442 errnote='Unable to download video annotations', fatal=False,
2443 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2445 chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
2447 # Look for the DASH manifest
2448 if self._downloader.params.get('youtube_include_dash_manifest', True):
2449 dash_mpd_fatal = True
2450 for mpd_url in dash_mpds:
2453 def decrypt_sig(mobj):
2455 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2456 return '/signature/%s' % dec_s
2458 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2460 for df in self._extract_mpd_formats(
2461 mpd_url, video_id, fatal=dash_mpd_fatal,
2462 formats_dict=self._formats):
2463 if not df.get('filesize'):
2464 df['filesize'] = _extract_filesize(df['url'])
2465 # Do not overwrite DASH format found in some previous DASH manifest
2466 if df['format_id'] not in dash_formats:
2467 dash_formats[df['format_id']] = df
2468 # Additional DASH manifests may end up in HTTP Error 403 therefore
2469 # allow them to fail without bug report message if we already have
2470 # some DASH manifest succeeded. This is temporary workaround to reduce
2471 # burst of bug reports until we figure out the reason and whether it
2472 # can be fixed at all.
2473 dash_mpd_fatal = False
2474 except (ExtractorError, KeyError) as e:
2475 self.report_warning(
2476 'Skipping DASH manifest: %r' % e, video_id)
2478 # Remove the formats we found through non-DASH, they
2479 # contain less info and it can be wrong, because we use
2480 # fixed values (for example the resolution). See
2481 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2483 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2484 formats.extend(dash_formats.values())
2486 # Check for malformed aspect ratio
2487 stretched_m = re.search(
2488 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2491 w = float(stretched_m.group('w'))
2492 h = float(stretched_m.group('h'))
2493 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2494 # We will only process correct ratios.
2498 if f.get('vcodec') != 'none':
2499 f['stretched_ratio'] = ratio
2502 if 'reason' in video_info:
2503 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2504 regions_allowed = self._html_search_meta(
2505 'regionsAllowed', video_webpage, default=None)
2506 countries = regions_allowed.split(',') if regions_allowed else None
2507 self.raise_geo_restricted(
2508 msg=video_info['reason'][0], countries=countries)
2509 reason = video_info['reason'][0]
2510 if 'Invalid parameters' in reason:
2511 unavailable_message = extract_unavailable_message()
2512 if unavailable_message:
2513 reason = unavailable_message
2514 raise ExtractorError(
2515 'YouTube said: %s' % reason,
2516 expected=True, video_id=video_id)
2517 if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
2518 raise ExtractorError('This video is DRM protected.', expected=True)
2520 self._sort_formats(formats)
2522 self.mark_watched(video_id, video_info, player_response)
2526 'uploader': video_uploader,
2527 'uploader_id': video_uploader_id,
2528 'uploader_url': video_uploader_url,
2529 'channel_id': channel_id,
2530 'channel_url': channel_url,
2531 'upload_date': upload_date,
2532 'license': video_license,
2533 'creator': video_creator or artist,
2534 'title': video_title,
2535 'alt_title': video_alt_title or track,
2536 'thumbnails': thumbnails,
2537 'description': video_description,
2538 'categories': video_categories,
2540 'subtitles': video_subtitles,
2541 'automatic_captions': automatic_captions,
2542 'duration': video_duration,
2543 'age_limit': 18 if age_gate else 0,
2544 'annotations': video_annotations,
2545 'chapters': chapters,
2546 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2547 'view_count': view_count,
2548 'like_count': like_count,
2549 'dislike_count': dislike_count,
2550 'average_rating': average_rating,
2553 'start_time': start_time,
2554 'end_time': end_time,
2556 'season_number': season_number,
2557 'episode_number': episode_number,
2561 'release_date': release_date,
2562 'release_year': release_year,
2566 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2567 IE_DESC = 'YouTube.com playlists'
2568 _VALID_URL = r"""(?x)(?:
2573 youtube(?:kids)?\.com|
2578 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2579 \? (?:.*?[&;])*? (?:p|a|list)=
2582 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2585 (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2586 # Top tracks, they can also include dots
2592 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2593 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2594 _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2595 _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
2596 IE_NAME = 'youtube:playlist'
2598 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2600 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2601 'uploader': 'Sergey M.',
2602 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2603 'title': 'youtube-dl public playlist',
2605 'playlist_count': 1,
2607 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2609 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2610 'uploader': 'Sergey M.',
2611 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2612 'title': 'youtube-dl empty playlist',
2614 'playlist_count': 0,
2616 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2617 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2619 'title': '29C3: Not my department',
2620 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2621 'uploader': 'Christiaan008',
2622 'uploader_id': 'ChRiStIaAn008',
2624 'playlist_count': 96,
2626 'note': 'issue #673',
2627 'url': 'PLBB231211A4F62143',
2629 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2630 'id': 'PLBB231211A4F62143',
2631 'uploader': 'Wickydoo',
2632 'uploader_id': 'Wickydoo',
2634 'playlist_mincount': 26,
2636 'note': 'Large playlist',
2637 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2639 'title': 'Uploads from Cauchemar',
2640 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2641 'uploader': 'Cauchemar',
2642 'uploader_id': 'Cauchemar89',
2644 'playlist_mincount': 799,
2646 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2648 'title': 'YDL_safe_search',
2649 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2651 'playlist_count': 2,
2652 'skip': 'This playlist is private',
2655 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2656 'playlist_count': 4,
2659 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2660 'uploader': 'milan',
2661 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2664 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2665 'playlist_mincount': 485,
2667 'title': '2018 Chinese New Singles (11/6 updated)',
2668 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2670 'uploader_id': 'sdragonfang',
2673 'note': 'Embedded SWF player',
2674 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2675 'playlist_count': 4,
2678 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2680 'skip': 'This playlist does not exist',
2682 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2683 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2685 'title': 'Uploads from Interstellar Movie',
2686 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2687 'uploader': 'Interstellar Movie',
2688 'uploader_id': 'InterstellarMovie1',
2690 'playlist_mincount': 21,
2692 # Playlist URL that does not actually serve a playlist
2693 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2695 'id': 'FqZTN594JQw',
2697 'title': "Smiley's People 01 detective, Adventure Series, Action",
2698 'uploader': 'STREEM',
2699 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2700 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2701 'upload_date': '20150526',
2702 'license': 'Standard YouTube License',
2703 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2704 'categories': ['People & Blogs'],
2708 'dislike_count': int,
2711 'skip_download': True,
2713 'skip': 'This video is not available.',
2714 'add_ie': [YoutubeIE.ie_key()],
2716 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2718 'id': 'yeWKywCrFtk',
2720 'title': 'Small Scale Baler and Braiding Rugs',
2721 'uploader': 'Backus-Page House Museum',
2722 'uploader_id': 'backuspagemuseum',
2723 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2724 'upload_date': '20161008',
2725 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2726 'categories': ['Nonprofits & Activism'],
2729 'dislike_count': int,
2733 'skip_download': True,
2736 # https://github.com/ytdl-org/youtube-dl/issues/21844
2737 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2739 'title': 'Data Analysis with Dr Mike Pound',
2740 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2741 'uploader_id': 'Computerphile',
2742 'uploader': 'Computerphile',
2744 'playlist_mincount': 11,
2746 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2747 'only_matching': True,
2749 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2750 'only_matching': True,
2752 # music album playlist
2753 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2754 'only_matching': True,
2756 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2757 'only_matching': True,
2759 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2760 'only_matching': True,
2763 def _real_initialize(self):
2766 def extract_videos_from_page(self, page):
2770 for item in re.findall(
2771 r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
2772 attrs = extract_attributes(item)
2773 video_id = attrs['data-video-id']
2774 video_title = unescapeHTML(attrs.get('data-title'))
2776 video_title = video_title.strip()
2777 ids_in_page.append(video_id)
2778 titles_in_page.append(video_title)
2780 # Fallback with old _VIDEO_RE
2781 self.extract_videos_from_page_impl(
2782 self._VIDEO_RE, page, ids_in_page, titles_in_page)
2785 self.extract_videos_from_page_impl(
2786 r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page,
2787 ids_in_page, titles_in_page)
2788 self.extract_videos_from_page_impl(
2789 r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
2790 ids_in_page, titles_in_page)
2792 return zip(ids_in_page, titles_in_page)
2794 def _extract_mix(self, playlist_id):
2795 # The mixes are generated from a single video
2796 # the id of the playlist is just 'RD' + video_id
2798 last_id = playlist_id[-11:]
2799 for n in itertools.count(1):
2800 url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2801 webpage = self._download_webpage(
2802 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2803 new_ids = orderedSet(re.findall(
2804 r'''(?xs
)data
-video
-username
=".*?".*?
2805 href
="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?
list=%s''' % re.escape(playlist_id),
2807 # Fetch new pages until all the videos are repeated, it seems that
2808 # there are always 51 unique videos.
2809 new_ids = [_id for _id in new_ids if _id not in ids]
2815 url_results = self._ids_to_results(ids)
2817 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2819 search_title('playlist-title')
2820 or search_title('title long-title')
2821 or search_title('title'))
2822 title = clean_html(title_span)
2824 return self.playlist_result(url_results, playlist_id, title)
2826 def _extract_playlist(self, playlist_id):
2827 url = self._TEMPLATE_URL % playlist_id
2828 page = self._download_webpage(url, playlist_id)
2830 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2831 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2832 match = match.strip()
2833 # Check if the playlist exists or is private
2834 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2836 reason = mobj.group('reason')
2837 message = 'This playlist %s' % reason
2838 if 'private' in reason:
2839 message += ', use --username or --netrc to access it'
2841 raise ExtractorError(message, expected=True)
2842 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2843 raise ExtractorError(
2844 'Invalid parameters. Maybe URL is incorrect.',
2846 elif re.match(r'[^<]*Choose your language[^<]*', match):
2849 self.report_warning('Youtube gives an alert message: ' + match)
2851 playlist_title = self._html_search_regex(
2852 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2853 page, 'title', default=None)
2855 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2856 uploader = self._html_search_regex(
2857 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2858 page, 'uploader', default=None)
2860 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2863 uploader_id = mobj.group('uploader_id')
2864 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2866 uploader_id = uploader_url = None
2870 if not playlist_title:
2872 # Some playlist URLs don't actually serve a playlist (e.g.
2873 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2874 next(self._entries(page, playlist_id))
2875 except StopIteration:
2878 playlist = self.playlist_result(
2879 self._entries(page, playlist_id), playlist_id, playlist_title)
2881 'uploader': uploader,
2882 'uploader_id': uploader_id,
2883 'uploader_url': uploader_url,
2886 return has_videos, playlist
2888 def _check_download_just_video(self, url, playlist_id):
2889 # Check if it's a video-specific URL
2890 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2891 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2892 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2893 'video id', default=None)
2895 if self._downloader.params.get('noplaylist'):
2896 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2897 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2899 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2900 return video_id, None
2903 def _real_extract(self, url):
2904 # Extract playlist id
2905 mobj = re.match(self._VALID_URL, url)
2907 raise ExtractorError('Invalid URL: %s' % url)
2908 playlist_id = mobj.group(1) or mobj.group(2)
2910 video_id, video = self._check_download_just_video(url, playlist_id)
2914 if playlist_id.startswith(('RD', 'UL', 'PU')):
2915 # Mixes require a custom extraction process
2916 return self._extract_mix(playlist_id)
2918 has_videos, playlist = self._extract_playlist(playlist_id)
2919 if has_videos or not video_id:
2922 # Some playlist URLs don't actually serve a playlist (see
2923 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2924 # Fallback to plain video extraction if there is a video id
2925 # along with playlist id.
2926 return self.url_result(video_id, 'Youtube', video_id=video_id)
2929 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2930 IE_DESC = 'YouTube.com channels'
2931 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2932 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2933 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2934 IE_NAME = 'youtube:channel'
2936 'note': 'paginated channel',
2937 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2938 'playlist_mincount': 91,
2940 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2941 'title': 'Uploads from lex will',
2942 'uploader': 'lex will',
2943 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2946 'note': 'Age restricted channel',
2947 # from https://www.youtube.com/user/DeusExOfficial
2948 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2949 'playlist_mincount': 64,
2951 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2952 'title': 'Uploads from Deus Ex',
2953 'uploader': 'Deus Ex',
2954 'uploader_id': 'DeusExOfficial',
2957 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2958 'only_matching': True,
2960 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
2961 'only_matching': True,
2965 def suitable(cls, url):
2966 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2967 else super(YoutubeChannelIE, cls).suitable(url))
2969 def _build_template_url(self, url, channel_id):
2970 return self._TEMPLATE_URL % channel_id
2972 def _real_extract(self, url):
2973 channel_id = self._match_id(url)
2975 url = self._build_template_url(url, channel_id)
2977 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2978 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2979 # otherwise fallback on channel by page extraction
2980 channel_page = self._download_webpage(
2981 url + '?view=57', channel_id,
2982 'Downloading channel page', fatal=False)
2983 if channel_page is False:
2984 channel_playlist_id = False
2986 channel_playlist_id = self._html_search_meta(
2987 'channelId', channel_page, 'channel id', default=None)
2988 if not channel_playlist_id:
2989 channel_url = self._html_search_meta(
2990 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2991 channel_page, 'channel url', default=None)
2993 channel_playlist_id = self._search_regex(
2994 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2995 channel_url, 'channel id', default=None)
2996 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2997 playlist_id = 'UU' + channel_playlist_id[2:]
2998 return self.url_result(
2999 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
3001 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
3002 autogenerated = re.search(r'''(?x
)
3004 channel
-header
-autogenerated
-label|
3005 yt
-channel
-title
-autogenerated
3006 )[^
"]*"''', channel_page) is not None
3009 # The videos are contained in a single page
3010 # the ajax pages can't be used, they are empty
3013 video_id, 'Youtube', video_id=video_id,
3014 video_title=video_title)
3015 for video_id, video_title in self.extract_videos_from_page(channel_page)]
3016 return self.playlist_result(entries, channel_id)
3019 next(self._entries(channel_page, channel_id))
3020 except StopIteration:
3021 alert_message = self._html_search_regex(
3022 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
3023 channel_page, 'alert', default=None, group='alert')
3025 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
3027 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
3030 class YoutubeUserIE(YoutubeChannelIE):
3031 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
3032 _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_-]+)'
3033 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
3034 IE_NAME = 'youtube:user'
3037 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
3038 'playlist_mincount': 320,
3040 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
3041 'title': 'Uploads from The Linux Foundation',
3042 'uploader': 'The Linux Foundation',
3043 'uploader_id': 'TheLinuxFoundation',
3046 # Only available via https://www.youtube.com/c/12minuteathlete/videos
3047 # but not https://www.youtube.com/user/12minuteathlete/videos
3048 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
3049 'playlist_mincount': 249,
3051 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
3052 'title': 'Uploads from 12 Minute Athlete',
3053 'uploader': '12 Minute Athlete',
3054 'uploader_id': 'the12minuteathlete',
3057 'url': 'ytuser:phihag',
3058 'only_matching': True,
3060 'url': 'https://www.youtube.com/c/gametrailers',
3061 'only_matching': True,
3063 'url': 'https://www.youtube.com/gametrailers',
3064 'only_matching': True,
3066 # This channel is not available, geo restricted to JP
3067 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
3068 'only_matching': True,
3072 def suitable(cls, url):
3073 # Don't return True if the url can be extracted with other youtube
3074 # extractor, the regex would is too permissive and it would match.
3075 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
3076 if any(ie.suitable(url) for ie in other_yt_ies):
3079 return super(YoutubeUserIE, cls).suitable(url)
3081 def _build_template_url(self, url, channel_id):
3082 mobj = re.match(self._VALID_URL, url)
3083 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
3086 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
3087 IE_DESC = 'YouTube.com live streams'
3088 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
3089 IE_NAME = 'youtube:live'
3092 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3094 'id': 'a48o2S1cPoo',
3096 'title': 'The Young Turks - Live Main Show',
3097 'uploader': 'The Young Turks',
3098 'uploader_id': 'TheYoungTurks',
3099 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3100 'upload_date': '20150715',
3101 'license': 'Standard YouTube License',
3102 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3103 'categories': ['News & Politics'],
3104 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3106 'dislike_count': int,
3109 'skip_download': True,
3112 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3113 'only_matching': True,
3115 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3116 'only_matching': True,
3118 'url': 'https://www.youtube.com/TheYoungTurks/live',
3119 'only_matching': True,
3122 def _real_extract(self, url):
3123 mobj = re.match(self._VALID_URL, url)
3124 channel_id = mobj.group('id')
3125 base_url = mobj.group('base_url')
3126 webpage = self._download_webpage(url, channel_id, fatal=False)
3128 page_type = self._og_search_property(
3129 'type', webpage, 'page type', default='')
3130 video_id = self._html_search_meta(
3131 'videoId', webpage, 'video id', default=None)
3132 if page_type.startswith('video') and video_id and re.match(
3133 r'^[0-9A-Za-z_-]{11}$', video_id):
3134 return self.url_result(video_id, YoutubeIE.ie_key())
3135 return self.url_result(base_url)
3138 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
3139 IE_DESC = 'YouTube.com user/channel playlists'
3140 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'
3141 IE_NAME = 'youtube:playlists'
3144 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3145 'playlist_mincount': 4,
3147 'id': 'ThirstForScience',
3148 'title': 'ThirstForScience',
3151 # with "Load more" button
3152 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3153 'playlist_mincount': 70,
3156 'title': 'Игорь Клейнер',
3159 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
3160 'playlist_mincount': 17,
3162 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
3163 'title': 'Chem Player',
3167 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3168 'only_matching': True,
3172 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
3173 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
3176 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
3177 IE_DESC = 'YouTube.com searches'
3178 # there doesn't appear to be a real limit, for example if you search for
3179 # 'python' you get more than 8.000.000 results
3180 _MAX_RESULTS = float('inf')
3181 IE_NAME = 'youtube:search'
3182 _SEARCH_KEY = 'ytsearch'
3183 _EXTRA_QUERY_ARGS = {}
3186 def _get_n_results(self, query, n):
3187 """Get a specified number of results for a query"""
3193 'search_query': query.encode('utf-8'),
3195 url_query.update(self._EXTRA_QUERY_ARGS)
3196 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
3198 for pagenum in itertools.count(1):
3199 data = self._download_json(
3200 result_url, video_id='query "%s"' % query,
3201 note='Downloading page %s' % pagenum,
3202 errnote='Unable to download API page',
3203 query={'spf': 'navigate'})
3204 html_content = data[1]['body']['content']
3206 if 'class="search-message' in html_content:
3207 raise ExtractorError(
3208 '[youtube] No video results', expected=True)
3210 new_videos = list(self._process_page(html_content))
3211 videos += new_videos
3212 if not new_videos or len(videos) > limit:
3214 next_link = self._html_search_regex(
3215 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
3216 html_content, 'next link', default=None)
3217 if next_link is None:
3219 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
3223 return self.playlist_result(videos, query)
3226 class YoutubeSearchDateIE(YoutubeSearchIE):
3227 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3228 _SEARCH_KEY = 'ytsearchdate'
3229 IE_DESC = 'YouTube.com searches, newest videos first'
3230 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
3233 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
3234 IE_DESC = 'YouTube.com search URLs'
3235 IE_NAME = 'youtube:search_url'
3236 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3238 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3239 'playlist_mincount': 5,
3241 'title': 'youtube-dl test video',
3244 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3245 'only_matching': True,
3248 def _real_extract(self, url):
3249 mobj = re.match(self._VALID_URL, url)
3250 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3251 webpage = self._download_webpage(url, query)
3252 return self.playlist_result(self._process_page(webpage), playlist_title=query)
3255 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3256 IE_DESC = 'YouTube.com (multi-season) shows'
3257 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3258 IE_NAME = 'youtube:show'
3260 'url': 'https://www.youtube.com/show/airdisasters',
3261 'playlist_mincount': 5,
3263 'id': 'airdisasters',
3264 'title': 'Air Disasters',
3268 def _real_extract(self, url):
3269 playlist_id = self._match_id(url)
3270 return super(YoutubeShowIE, self)._real_extract(
3271 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3274 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3276 Base class for feed extractors
3277 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3279 _LOGIN_REQUIRED = True
3283 return 'youtube:%s' % self._FEED_NAME
3285 def _real_initialize(self):
3288 def _entries(self, page):
3289 # The extraction process is the same as for playlists, but the regex
3290 # for the video ids doesn't contain an index
3292 more_widget_html = content_html = page
3293 for page_num in itertools.count(1):
3294 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3296 # 'recommended' feed has infinite 'load more' and each new portion spins
3297 # the same videos in (sometimes) slightly different order, so we'll check
3298 # for unicity and break when portion has no new videos
3299 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3305 for entry in self._ids_to_results(new_ids):
3308 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3312 more = self._download_json(
3313 'https://www.youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3314 'Downloading page #%s' % page_num,
3315 transform_source=uppercase_escape,
3316 headers=self._YOUTUBE_CLIENT_HEADERS)
3317 content_html = more['content_html']
3318 more_widget_html = more['load_more_widget_html']
3320 def _real_extract(self, url):
3321 page = self._download_webpage(
3322 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3323 self._PLAYLIST_TITLE)
3324 return self.playlist_result(
3325 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3328 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3329 IE_NAME = 'youtube:watchlater'
3330 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3331 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3334 'url': 'https://www.youtube.com/playlist?list=WL',
3335 'only_matching': True,
3337 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3338 'only_matching': True,
3341 def _real_extract(self, url):
3342 _, video = self._check_download_just_video(url, 'WL')
3345 _, playlist = self._extract_playlist('WL')
3349 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3350 IE_NAME = 'youtube:favorites'
3351 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3352 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3353 _LOGIN_REQUIRED = True
3355 def _real_extract(self, url):
3356 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3357 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3358 return self.url_result(playlist_id, 'YoutubePlaylist')
3361 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3362 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3363 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3364 _FEED_NAME = 'recommended'
3365 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3368 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3369 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3370 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3371 _FEED_NAME = 'subscriptions'
3372 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3375 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3376 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3377 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3378 _FEED_NAME = 'history'
3379 _PLAYLIST_TITLE = 'Youtube History'
3382 class YoutubeTruncatedURLIE(InfoExtractor):
3383 IE_NAME = 'youtube:truncated_url'
3384 IE_DESC = False # Do not list
3385 _VALID_URL = r'''(?x
)
3387 (?
:\w
+\
.)?
[yY
][oO
][uU
][tT
][uU
][bB
][eE
](?
:-nocookie
)?\
.com
/
3390 annotation_id
=annotation_
[^
&]+|
3396 attribution_link
\?a
=[^
&]+
3402 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3403 'only_matching': True,
3405 'url': 'https://www.youtube.com/watch?',
3406 'only_matching': True,
3408 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3409 'only_matching': True,
3411 'url': 'https://www.youtube.com/watch?feature=foo',
3412 'only_matching': True,
3414 'url': 'https://www.youtube.com/watch?hl=en-GB',
3415 'only_matching': True,
3417 'url': 'https://www.youtube.com/watch?t=2372',
3418 'only_matching': True,
3421 def _real_extract(self, url):
3422 raise ExtractorError(
3423 'Did you forget to quote the URL? Remember that & is a meta '
3424 'character in most shells, so you want to put the URL in quotes, '
3426 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3427 ' or simply youtube-dl BaW_jenozKc .',
3431 class YoutubeTruncatedIDIE(InfoExtractor):
3432 IE_NAME = 'youtube:truncated_id'
3433 IE_DESC = False # Do not list
3434 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3437 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3438 'only_matching': True,
3441 def _real_extract(self, url):
3442 video_id = self._match_id(url)
3443 raise ExtractorError(
3444 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),