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):
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 not sub_lang_list:
1466 self._downloader.report_warning('video doesn
\'t have subtitles
')
1468 return sub_lang_list
1470 def _get_ytplayer_config(self, video_id, webpage):
1472 # User data may contain arbitrary character sequences that may affect
1473 # JSON extraction with regex, e.g. when '};' is contained the second
1474 # regex won't capture the whole JSON
. Yet working around by trying more
1475 # concrete regex first keeping in mind proper quoted string handling
1476 # to be implemented in future that will replace this workaround (see
1477 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1478 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1479 r
';ytplayer\.config\s*=\s*({.+?});ytplayer',
1480 r
';ytplayer\.config\s*=\s*({.+?});',
1482 config
= self
._search
_regex
(
1483 patterns
, webpage
, 'ytplayer.config', default
=None)
1485 return self
._parse
_json
(
1486 uppercase_escape(config
), video_id
, fatal
=False)
1488 def _get_automatic_captions(self
, video_id
, webpage
):
1489 """We need the webpage for getting the captions url, pass it as an
1490 argument to speed up the process."""
1491 self
.to_screen('%s: Looking for automatic captions' % video_id
)
1492 player_config
= self
._get
_ytplayer
_config
(video_id
, webpage
)
1493 err_msg
= 'Couldn\'t find automatic captions for %s' % video_id
1494 if not player_config
:
1495 self
._downloader
.report_warning(err_msg
)
1498 args
= player_config
['args']
1499 caption_url
= args
.get('ttsurl')
1501 timestamp
= args
['timestamp']
1502 # We get the available subtitles
1503 list_params
= compat_urllib_parse_urlencode({
1508 list_url
= caption_url
+ '&' + list_params
1509 caption_list
= self
._download
_xml
(list_url
, video_id
)
1510 original_lang_node
= caption_list
.find('track')
1511 if original_lang_node
is None:
1512 self
._downloader
.report_warning('Video doesn\'t have automatic captions')
1514 original_lang
= original_lang_node
.attrib
['lang_code']
1515 caption_kind
= original_lang_node
.attrib
.get('kind', '')
1518 for lang_node
in caption_list
.findall('target'):
1519 sub_lang
= lang_node
.attrib
['lang_code']
1521 for ext
in self
._SUBTITLE
_FORMATS
:
1522 params
= compat_urllib_parse_urlencode({
1523 'lang': original_lang
,
1527 'kind': caption_kind
,
1529 sub_formats
.append({
1530 'url': caption_url
+ '&' + params
,
1533 sub_lang_list
[sub_lang
] = sub_formats
1534 return sub_lang_list
1536 def make_captions(sub_url
, sub_langs
):
1537 parsed_sub_url
= compat_urllib_parse_urlparse(sub_url
)
1538 caption_qs
= compat_parse_qs(parsed_sub_url
.query
)
1540 for sub_lang
in sub_langs
:
1542 for ext
in self
._SUBTITLE
_FORMATS
:
1544 'tlang': [sub_lang
],
1547 sub_url
= compat_urlparse
.urlunparse(parsed_sub_url
._replace
(
1548 query
=compat_urllib_parse_urlencode(caption_qs
, True)))
1549 sub_formats
.append({
1553 captions
[sub_lang
] = sub_formats
1556 # New captions format as of 22.06.2017
1557 player_response
= args
.get('player_response')
1558 if player_response
and isinstance(player_response
, compat_str
):
1559 player_response
= self
._parse
_json
(
1560 player_response
, video_id
, fatal
=False)
1562 renderer
= player_response
['captions']['playerCaptionsTracklistRenderer']
1563 base_url
= renderer
['captionTracks'][0]['baseUrl']
1565 for lang
in renderer
['translationLanguages']:
1566 lang_code
= lang
.get('languageCode')
1568 sub_lang_list
.append(lang_code
)
1569 return make_captions(base_url
, sub_lang_list
)
1571 # Some videos don't provide ttsurl but rather caption_tracks and
1572 # caption_translation_languages (e.g. 20LmZk1hakA)
1573 # Does not used anymore as of 22.06.2017
1574 caption_tracks
= args
['caption_tracks']
1575 caption_translation_languages
= args
['caption_translation_languages']
1576 caption_url
= compat_parse_qs(caption_tracks
.split(',')[0])['u'][0]
1578 for lang
in caption_translation_languages
.split(','):
1579 lang_qs
= compat_parse_qs(compat_urllib_parse_unquote_plus(lang
))
1580 sub_lang
= lang_qs
.get('lc', [None])[0]
1582 sub_lang_list
.append(sub_lang
)
1583 return make_captions(caption_url
, sub_lang_list
)
1584 # An extractor error can be raise by the download process if there are
1585 # no automatic captions but there are subtitles
1586 except (KeyError, IndexError, ExtractorError
):
1587 self
._downloader
.report_warning(err_msg
)
1590 def _mark_watched(self
, video_id
, video_info
, player_response
):
1591 playback_url
= url_or_none(try_get(
1593 lambda x
: x
['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1594 video_info
, lambda x
: x
['videostats_playback_base_url'][0]))
1595 if not playback_url
:
1597 parsed_playback_url
= compat_urlparse
.urlparse(playback_url
)
1598 qs
= compat_urlparse
.parse_qs(parsed_playback_url
.query
)
1600 # cpn generation algorithm is reverse engineered from base.js.
1601 # In fact it works even with dummy cpn.
1602 CPN_ALPHABET
= 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1603 cpn
= ''.join((CPN_ALPHABET
[random
.randint(0, 256) & 63] for _
in range(0, 16)))
1609 playback_url
= compat_urlparse
.urlunparse(
1610 parsed_playback_url
._replace
(query
=compat_urllib_parse_urlencode(qs
, True)))
1612 self
._download
_webpage
(
1613 playback_url
, video_id
, 'Marking watched',
1614 'Unable to mark watched', fatal
=False)
1617 def _extract_urls(webpage
):
1618 # Embedded YouTube player
1620 unescapeHTML(mobj
.group('url'))
1621 for mobj
in re
.finditer(r
'''(?x)
1631 (?P
<url
>(?
:https?
:)?
//(?
:www\
.)?
youtube(?
:-nocookie
)?\
.com
/
1632 (?
:embed|v|p
)/[0-9A
-Za
-z_
-]{11}
.*?
)
1635 # lazyYT YouTube embed
1636 entries.extend(list(map(
1638 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1640 # Wordpress "YouTube Video Importer" plugin
1641 matches = re.findall(r'''(?x
)<div
[^
>]+
1642 class=(?P
<q1
>[\'"])[^\'"]*\byvii
_single
_video
_player
\b[^
\'"]*(?P=q1)[^>]+
1643 data-video_id=(?P<q2>[\'"])([^
\'"]+)(?P=q2)''', webpage)
1644 entries.extend(m[-1] for m in matches)
1649 def _extract_url(webpage):
1650 urls = YoutubeIE._extract_urls(webpage)
1651 return urls[0] if urls else None
1654 def extract_id(cls, url):
1655 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1657 raise ExtractorError('Invalid URL: %s' % url)
1658 video_id = mobj.group(2)
1661 def _extract_chapters_from_json(self, webpage, video_id, duration):
1664 player = self._parse_json(
1666 r'RELATED_PLAYER_ARGS["\']\s
*:\s
*({.+}
)\s
*,?\s
*\n', webpage,
1667 'player args
', default='{}'),
1668 video_id, fatal=False)
1669 if not player or not isinstance(player, dict):
1671 watch_next_response = player.get('watch_next_response
')
1672 if not isinstance(watch_next_response, compat_str):
1674 response = self._parse_json(watch_next_response, video_id, fatal=False)
1675 if not response or not isinstance(response, dict):
1677 chapters_list = try_get(
1679 lambda x: x['playerOverlays
']
1680 ['playerOverlayRenderer
']
1681 ['decoratedPlayerBarRenderer
']
1682 ['decoratedPlayerBarRenderer
']
1684 ['chapteredPlayerBarRenderer
']
1687 if not chapters_list:
1690 def chapter_time(chapter):
1691 return float_or_none(
1694 lambda x: x['chapterRenderer
']['timeRangeStartMillis
'],
1698 for next_num, chapter in enumerate(chapters_list, start=1):
1699 start_time = chapter_time(chapter)
1700 if start_time is None:
1702 end_time = (chapter_time(chapters_list[next_num])
1703 if next_num < len(chapters_list) else duration)
1704 if end_time is None:
1707 chapter, lambda x: x['chapterRenderer
']['title
']['simpleText
'],
1710 'start_time
': start_time,
1711 'end_time
': end_time,
1717 def _extract_chapters_from_description(description, duration):
1720 chapter_lines = re.findall(
1721 r'(?
:^|
<br\s
*/>)([^
<]*<a
[^
>]+onclick
=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1723 if not chapter_lines:
1726 for next_num, (chapter_line, time_point) in enumerate(
1727 chapter_lines, start=1):
1728 start_time = parse_duration(time_point)
1729 if start_time is None:
1731 if start_time > duration:
1733 end_time = (duration if next_num == len(chapter_lines)
1734 else parse_duration(chapter_lines[next_num][1]))
1735 if end_time is None:
1737 if end_time > duration:
1739 if start_time > end_time:
1741 chapter_title = re.sub(
1742 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1743 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1745 'start_time': start_time,
1746 'end_time': end_time,
1747 'title': chapter_title,
1751 def _extract_chapters(self, webpage, description, video_id, duration):
1752 return (self._extract_chapters_from_json(webpage, video_id, duration)
1753 or self._extract_chapters_from_description(description, duration))
1755 def _real_extract(self, url):
1756 url, smuggled_data = unsmuggle_url(url, {})
1759 'http' if self._downloader.params.get('prefer_insecure', False)
1764 parsed_url = compat_urllib_parse_urlparse(url)
1765 for component in [parsed_url.fragment, parsed_url.query]:
1766 query = compat_parse_qs(component)
1767 if start_time is None and 't' in query:
1768 start_time = parse_duration(query['t'][0])
1769 if start_time is None and 'start' in query:
1770 start_time = parse_duration(query['start'][0])
1771 if end_time is None and 'end' in query:
1772 end_time = parse_duration(query['end'][0])
1774 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1775 mobj = re.search(self._NEXT_URL_RE, url)
1777 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1778 video_id = self.extract_id(url)
1781 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1782 video_webpage, urlh = self._download_webpage_handle(url, video_id)
1784 qs = compat_parse_qs(compat_urllib_parse_urlparse(urlh.geturl()).query)
1785 video_id = qs.get('v', [None])[0] or video_id
1787 # Attempt to extract SWF player URL
1788 mobj = re.search(r'swfConfig.*?"(https?
:\\/\\/.*?watch
.*?
-.*?\
.swf
)"', video_webpage)
1789 if mobj is not None:
1790 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1796 def add_dash_mpd(video_info):
1797 dash_mpd = video_info.get('dashmpd')
1798 if dash_mpd and dash_mpd[0] not in dash_mpds:
1799 dash_mpds.append(dash_mpd[0])
1801 def add_dash_mpd_pr(pl_response):
1802 dash_mpd = url_or_none(try_get(
1803 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1805 if dash_mpd and dash_mpd not in dash_mpds:
1806 dash_mpds.append(dash_mpd)
1811 def extract_view_count(v_info):
1812 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1814 def extract_player_response(player_response, video_id):
1815 pl_response = str_or_none(player_response)
1818 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1819 if isinstance(pl_response, dict):
1820 add_dash_mpd_pr(pl_response)
1823 player_response = {}
1827 embed_webpage = None
1828 if (self._og_search_property('restrictions:age', video_webpage, default=None) == '18+'
1829 or re.search(r'player-age-gate-content">', video_webpage) is not None):
1831 # We simulate the access to the video from www.youtube.com/v/{video_id}
1832 # this can be viewed without login into Youtube
1833 url = proto + '://www
.youtube
.com
/embed
/%s' % video_id
1834 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage
')
1835 data = compat_urllib_parse_urlencode({
1836 'video_id
': video_id,
1837 'eurl
': 'https
://youtube
.googleapis
.com
/v
/' + video_id,
1838 'sts
': self._search_regex(
1839 r'"sts"\s
*:\s
*(\d
+)', embed_webpage, 'sts
', default=''),
1841 video_info_url = proto + '://www
.youtube
.com
/get_video_info?
' + data
1843 video_info_webpage = self._download_webpage(
1844 video_info_url, video_id,
1845 note='Refetching age
-gated info webpage
',
1846 errnote='unable to download video info webpage
')
1847 except ExtractorError:
1848 video_info_webpage = None
1849 if video_info_webpage:
1850 video_info = compat_parse_qs(video_info_webpage)
1851 pl_response = video_info.get('player_response
', [None])[0]
1852 player_response = extract_player_response(pl_response, video_id)
1853 add_dash_mpd(video_info)
1854 view_count = extract_view_count(video_info)
1857 # Try looking directly into the video webpage
1858 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1860 args = ytplayer_config['args
']
1861 if args.get('url_encoded_fmt_stream_map
') or args.get('hlsvp
'):
1862 # Convert to the same format returned by compat_parse_qs
1863 video_info = dict((k, [v]) for k, v in args.items())
1864 add_dash_mpd(video_info)
1865 # Rental video is not rented but preview is available (e.g.
1866 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1867 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1868 if not video_info and args.get('ypc_vid
'):
1869 return self.url_result(
1870 args['ypc_vid
'], YoutubeIE.ie_key(), video_id=args['ypc_vid
'])
1871 if args.get('livestream
') == '1' or args.get('live_playback
') == 1:
1873 if not player_response:
1874 player_response = extract_player_response(args.get('player_response
'), video_id)
1875 if not video_info or self._downloader.params.get('youtube_include_dash_manifest
', True):
1876 add_dash_mpd_pr(player_response)
1878 def extract_unavailable_message():
1880 for tag, kind in (('h1
', 'message
'), ('div
', 'submessage
')):
1881 msg = self._html_search_regex(
1882 r'(?s
)<{tag}
[^
>]+id=["\']unavailable-{kind}["\'][^
>]*>(.+?
)</{tag}
>'.format(tag=tag, kind=kind),
1883 video_webpage, 'unavailable
%s' % kind, default=None)
1885 messages.append(msg)
1887 return '\n'.join(messages)
1889 if not video_info and not player_response:
1890 unavailable_message = extract_unavailable_message()
1891 if not unavailable_message:
1892 unavailable_message = 'Unable to extract video data
'
1893 raise ExtractorError(
1894 'YouTube said
: %s' % unavailable_message, expected=True, video_id=video_id)
1896 if not isinstance(video_info, dict):
1899 video_details = try_get(
1900 player_response, lambda x: x['videoDetails
'], dict) or {}
1902 microformat = try_get(
1903 player_response, lambda x: x['microformat
']['playerMicroformatRenderer
'], dict) or {}
1905 video_title = video_info.get('title
', [None])[0] or video_details.get('title
')
1907 self._downloader.report_warning('Unable to extract video title
')
1910 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1911 if video_description:
1914 redir_url = compat_urlparse.urljoin(url, m.group(1))
1915 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1916 if re.search(r'^
(?
:www\
.)?
(?
:youtube(?
:-nocookie
)?\
.com|youtu\
.be
)$
', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect
':
1917 qs = compat_parse_qs(parsed_redir_url.query)
1923 description_original = video_description = re.sub(r'''(?x)
1925 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1926 (?:title|href)="([^"]+)"\s+
1927 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1931 ''', replace_url, video_description)
1932 video_description = clean_html(video_description)
1934 video_description = video_details.get('shortDescription
') or self._html_search_meta('description
', video_webpage)
1936 if not smuggled_data.get('force_singlefeed
', False):
1937 if not self._downloader.params.get('noplaylist
'):
1938 multifeed_metadata_list = try_get(
1940 lambda x: x['multicamera
']['playerLegacyMulticameraRenderer
']['metadataList
'],
1941 compat_str) or try_get(
1942 video_info, lambda x: x['multifeed_metadata_list
'][0], compat_str)
1943 if multifeed_metadata_list:
1946 for feed in multifeed_metadata_list.split(','):
1947 # Unquote should take place before split on comma (,) since textual
1948 # fields may contain comma as well (see
1949 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1950 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1952 def feed_entry(name):
1953 return try_get(feed_data, lambda x: x[name][0], compat_str)
1955 feed_id = feed_entry('id')
1958 feed_title = feed_entry('title
')
1961 title += ' (%s)' % feed_title
1963 '_type
': 'url_transparent
',
1964 'ie_key
': 'Youtube
',
1966 '%s://www
.youtube
.com
/watch?v
=%s' % (proto, feed_data['id'][0]),
1967 {'force_singlefeed': True}),
1970 feed_ids.append(feed_id)
1972 'Downloading multifeed
video (%s) - add
--no
-playlist to just download video
%s'
1973 % (', '.join(feed_ids), video_id))
1974 return self.playlist_result(entries, video_id, video_title, video_description)
1976 self.to_screen('Downloading just video
%s because of
--no
-playlist
' % video_id)
1978 if view_count is None:
1979 view_count = extract_view_count(video_info)
1980 if view_count is None and video_details:
1981 view_count = int_or_none(video_details.get('viewCount
'))
1982 if view_count is None and microformat:
1983 view_count = int_or_none(microformat.get('viewCount
'))
1986 is_live = bool_or_none(video_details.get('isLive
'))
1988 # Check for "rental" videos
1989 if 'ypc_video_rental_bar_text
' in video_info and 'author
' not in video_info:
1990 raise ExtractorError('"rental" videos
not supported
. See https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/359 for more information
.', expected=True)
1992 def _extract_filesize(media_url):
1993 return int_or_none(self._search_regex(
1994 r'\bclen
[=/](\d
+)', media_url, 'filesize
', default=None))
1996 streaming_formats = try_get(player_response, lambda x: x['streamingData
']['formats
'], list) or []
1997 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData
']['adaptiveFormats
'], list) or [])
1999 if 'conn
' in video_info and video_info['conn
'][0].startswith('rtmp
'):
2000 self.report_rtmp_download()
2002 'format_id
': '_rtmp
',
2004 'url
': video_info['conn
'][0],
2005 'player_url
': player_url,
2007 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):
2008 encoded_url_map = video_info.get('url_encoded_fmt_stream_map
', [''])[0] + ',' + video_info.get('adaptive_fmts
', [''])[0]
2009 if 'rtmpe
%3Dyes
' in encoded_url_map:
2010 raise ExtractorError('rtmpe downloads are
not supported
, see https
://github
.com
/ytdl
-org
/youtube
-dl
/issues
/343 for more information
.', expected=True)
2013 fmt_list = video_info.get('fmt_list
', [''])[0]
2015 for fmt in fmt_list.split(','):
2016 spec = fmt.split('/')
2018 width_height = spec[1].split('x
')
2019 if len(width_height) == 2:
2020 formats_spec[spec[0]] = {
2021 'resolution
': spec[1],
2022 'width
': int_or_none(width_height[0]),
2023 'height
': int_or_none(width_height[1]),
2025 for fmt in streaming_formats:
2026 itag = str_or_none(fmt.get('itag
'))
2029 quality = fmt.get('quality
')
2030 quality_label = fmt.get('qualityLabel
') or quality
2031 formats_spec[itag] = {
2032 'asr
': int_or_none(fmt.get('audioSampleRate
')),
2033 'filesize
': int_or_none(fmt.get('contentLength
')),
2034 'format_note
': quality_label,
2035 'fps
': int_or_none(fmt.get('fps
')),
2036 'height
': int_or_none(fmt.get('height
')),
2037 # bitrate for itag 43 is always 2147483647
2038 'tbr
': float_or_none(fmt.get('averageBitrate
') or fmt.get('bitrate
'), 1000) if itag != '43' else None,
2039 'width
': int_or_none(fmt.get('width
')),
2042 for fmt in streaming_formats:
2043 if fmt.get('drmFamilies
') or fmt.get('drm_families
'):
2045 url = url_or_none(fmt.get('url
'))
2048 cipher = fmt.get('cipher
') or fmt.get('signatureCipher
')
2051 url_data = compat_parse_qs(cipher)
2052 url = url_or_none(try_get(url_data, lambda x: x['url
'][0], compat_str))
2057 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
2059 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type
'][0]))
2060 # Unsupported FORMAT_STREAM_TYPE_OTF
2061 if stream_type == 3:
2064 format_id = fmt.get('itag
') or url_data['itag
'][0]
2067 format_id = compat_str(format_id)
2070 if 's
' in url_data or self._downloader.params.get('youtube_include_dash_manifest
', True):
2071 ASSETS_RE = r'"assets":.+?
"js":\s
*("[^"]+")'
2072 jsplayer_url_json = self._search_regex(
2074 embed_webpage if age_gate else video_webpage,
2075 'JS player URL (1)', default=None)
2076 if not jsplayer_url_json and not age_gate:
2077 # We need the embed website after all
2078 if embed_webpage is None:
2079 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
2080 embed_webpage = self._download_webpage(
2081 embed_url, video_id, 'Downloading embed webpage')
2082 jsplayer_url_json = self._search_regex(
2083 ASSETS_RE, embed_webpage, 'JS player URL')
2085 player_url = json.loads(jsplayer_url_json)
2086 if player_url is None:
2087 player_url_json = self._search_regex(
2088 r'ytplayer\.config.*?"url
"\s*:\s*("[^
"]+")',
2089 video_webpage, 'age gate player URL
')
2090 player_url = json.loads(player_url_json)
2092 if 'sig
' in url_data:
2093 url += '&signature
=' + url_data['sig
'][0]
2094 elif 's
' in url_data:
2095 encrypted_sig = url_data['s
'][0]
2097 if self._downloader.params.get('verbose
'):
2098 if player_url is None:
2099 player_desc = 'unknown
'
2101 player_type, player_version = self._extract_player_info(player_url)
2102 player_desc = '%s player
%s' % ('flash
' if player_type == 'swf
' else 'html5
', player_version)
2103 parts_sizes = self._signature_cache_id(encrypted_sig)
2104 self.to_screen('{%s} signature length
%s, %s' %
2105 (format_id, parts_sizes, player_desc))
2107 signature = self._decrypt_signature(
2108 encrypted_sig, video_id, player_url, age_gate)
2109 sp = try_get(url_data, lambda x: x['sp
'][0], compat_str) or 'signature
'
2110 url += '&%s=%s' % (sp, signature)
2111 if 'ratebypass
' not in url:
2112 url += '&ratebypass
=yes
'
2115 'format_id
': format_id,
2117 'player_url
': player_url,
2119 if format_id in self._formats:
2120 dct.update(self._formats[format_id])
2121 if format_id in formats_spec:
2122 dct.update(formats_spec[format_id])
2124 # Some itags are not included in DASH manifest thus corresponding formats will
2125 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2126 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2127 mobj = re.search(r'^
(?P
<width
>\d
+)[xX
](?P
<height
>\d
+)$
', url_data.get('size
', [''])[0])
2128 width, height = (int(mobj.group('width
')), int(mobj.group('height
'))) if mobj else (None, None)
2131 width = int_or_none(fmt.get('width
'))
2133 height = int_or_none(fmt.get('height
'))
2135 filesize = int_or_none(url_data.get(
2136 'clen
', [None])[0]) or _extract_filesize(url)
2138 quality = url_data.get('quality
', [None])[0] or fmt.get('quality
')
2139 quality_label = url_data.get('quality_label
', [None])[0] or fmt.get('qualityLabel
')
2141 tbr = (float_or_none(url_data.get('bitrate
', [None])[0], 1000)
2142 or float_or_none(fmt.get('bitrate
'), 1000)) if format_id != '43' else None
2143 fps = int_or_none(url_data.get('fps
', [None])[0]) or int_or_none(fmt.get('fps
'))
2146 'filesize
': filesize,
2151 'format_note
': quality_label or quality,
2153 for key, value in more_fields.items():
2156 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType
')
2158 type_split = type_.split(';')
2159 kind_ext = type_split[0].split('/')
2160 if len(kind_ext) == 2:
2162 dct['ext
'] = mimetype2ext(type_split[0])
2163 if kind in ('audio
', 'video
'):
2165 for mobj in re.finditer(
2166 r'(?P
<key
>[a
-zA
-Z_
-]+)=(?P
<quote
>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2167 if mobj.group('key') == 'codecs':
2168 codecs = mobj.group('val')
2171 dct.update(parse_codecs(codecs))
2172 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2173 dct['downloader_options'] = {
2174 # Youtube throttles chunks >~10M
2175 'http_chunk_size': 10485760,
2180 url_or_none(try_get(
2182 lambda x: x['streamingData']['hlsManifestUrl'],
2184 or url_or_none(try_get(
2185 video_info, lambda x: x['hlsvp'][0], compat_str)))
2188 m3u8_formats = self._extract_m3u8_formats(
2189 manifest_url, video_id, 'mp4', fatal=False)
2190 for a_format in m3u8_formats:
2191 itag = self._search_regex(
2192 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2194 a_format['format_id'] = itag
2195 if itag in self._formats:
2196 dct = self._formats[itag].copy()
2197 dct.update(a_format)
2199 a_format['player_url'] = player_url
2200 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2201 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2202 formats.append(a_format)
2204 error_message = extract_unavailable_message()
2205 if not error_message:
2206 error_message = clean_html(try_get(
2207 player_response, lambda x: x['playabilityStatus']['reason'],
2209 if not error_message:
2210 error_message = clean_html(
2211 try_get(video_info, lambda x: x['reason'][0], compat_str))
2213 raise ExtractorError(error_message, expected=True)
2214 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2217 video_uploader = try_get(
2218 video_info, lambda x: x['author'][0],
2219 compat_str) or str_or_none(video_details.get('author'))
2221 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2223 self._downloader.report_warning('unable to extract uploader name')
2226 video_uploader_id = None
2227 video_uploader_url = None
2229 r'<link itemprop="url
" href="(?P
<uploader_url
>https?
://www\
.youtube\
.com
/(?
:user|channel
)/(?P
<uploader_id
>[^
"]+))">',
2231 if mobj is not None:
2232 video_uploader_id = mobj.group('uploader_id
')
2233 video_uploader_url = mobj.group('uploader_url
')
2235 owner_profile_url = url_or_none(microformat.get('ownerProfileUrl
'))
2236 if owner_profile_url:
2237 video_uploader_id = self._search_regex(
2238 r'(?
:user|channel
)/([^
/]+)', owner_profile_url, 'uploader
id',
2240 video_uploader_url = owner_profile_url
2243 str_or_none(video_details.get('channelId
'))
2244 or self._html_search_meta(
2245 'channelId
', video_webpage, 'channel
id', default=None)
2246 or self._search_regex(
2247 r'data
-channel
-external
-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
2248 video_webpage, 'channel id', default=None, group='id'))
2249 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2252 thumbnails_list = try_get(
2253 video_details, lambda x: x['thumbnail']['thumbnails'], list) or []
2254 for t in thumbnails_list:
2255 if not isinstance(t, dict):
2257 thumbnail_url = url_or_none(t.get('url'))
2258 if not thumbnail_url:
2261 'url': thumbnail_url,
2262 'width': int_or_none(t.get('width')),
2263 'height': int_or_none(t.get('height')),
2267 video_thumbnail = None
2268 # We try first to get a high quality image:
2269 m_thumb = re.search(r'<span itemprop="thumbnail
".*?href="(.*?
)">',
2270 video_webpage, re.DOTALL)
2271 if m_thumb is not None:
2272 video_thumbnail = m_thumb.group(1)
2273 thumbnail_url = try_get(video_info, lambda x: x['thumbnail_url'][0], compat_str)
2275 video_thumbnail = compat_urllib_parse_unquote_plus(thumbnail_url)
2277 thumbnails.append({'url': video_thumbnail})
2280 upload_date = self._html_search_meta(
2281 'datePublished', video_webpage, 'upload date', default=None)
2283 upload_date = self._search_regex(
2284 [r'(?s)id="eow
-date
.*?
>(.*?
)</span
>',
2285 r'(?
:id="watch-uploader-info".*?
>.*?|
["\']simpleText["\']\s
*:\s
*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2286 video_webpage, 'upload date
', default=None)
2288 upload_date = microformat.get('publishDate
') or microformat.get('uploadDate
')
2289 upload_date = unified_strdate(upload_date)
2291 video_license = self._html_search_regex(
2292 r'<h4
[^
>]+class="title"[^
>]*>\s
*License\s
*</h4
>\s
*<ul
[^
>]*>\s
*<li
>(.+?
)</li
',
2293 video_webpage, 'license
', default=None)
2295 m_music = re.search(
2297 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2305 \bhref=["\']/red[^>]*>| # drop possible
2306 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2313 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title
')))
2314 video_creator = clean_html(m_music.group('creator
'))
2316 video_alt_title = video_creator = None
2318 def extract_meta(field):
2319 return self._html_search_regex(
2320 r'<h4
[^
>]+class="title"[^
>]*>\s
*%s\s
*</h4
>\s
*<ul
[^
>]*>\s
*<li
>(.+?
)</li
>\s
*' % field,
2321 video_webpage, field, default=None)
2323 track = extract_meta('Song
')
2324 artist = extract_meta('Artist
')
2325 album = extract_meta('Album
')
2327 # Youtube Music Auto-generated description
2328 release_date = release_year = None
2329 if video_description:
2330 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)
2333 track = mobj.group('track
').strip()
2335 artist = mobj.group('clean_artist
') or ', '.join(a.strip() for a in mobj.group('artist
').split('·
'))
2337 album = mobj.group('album
'.strip())
2338 release_year = mobj.group('release_year
')
2339 release_date = mobj.group('release_date
')
2341 release_date = release_date.replace('-', '')
2342 if not release_year:
2343 release_year = int(release_date[:4])
2345 release_year = int(release_year)
2347 m_episode = re.search(
2348 r'<div
[^
>]+id="watch7-headline"[^
>]*>\s
*<span
[^
>]*>.*?
>(?P
<series
>[^
<]+)</a
></b
>\s
*S(?P
<season
>\d
+)\s
*•\s
*E(?P
<episode
>\d
+)</span
>',
2351 series = unescapeHTML(m_episode.group('series
'))
2352 season_number = int(m_episode.group('season
'))
2353 episode_number = int(m_episode.group('episode
'))
2355 series = season_number = episode_number = None
2357 m_cat_container = self._search_regex(
2358 r'(?s
)<h4
[^
>]*>\s
*Category\s
*</h4
>\s
*<ul
[^
>]*>(.*?
)</ul
>',
2359 video_webpage, 'categories
', default=None)
2362 category = self._html_search_regex(
2363 r'(?s
)<a
[^
<]+>(.*?
)</a
>', m_cat_container, 'category
',
2367 microformat, lambda x: x['category
'], compat_str)
2368 video_categories = None if category is None else [category]
2371 unescapeHTML(m.group('content
'))
2372 for m in re.finditer(self._meta_regex('og
:video
:tag
'), video_webpage)]
2374 video_tags = try_get(video_details, lambda x: x['keywords
'], list)
2376 def _extract_count(count_name):
2377 return str_to_int(self._search_regex(
2378 r'-%s-button
[^
>]+><span
[^
>]+class="yt-uix-button-content"[^
>]*>([\d
,]+)</span
>'
2379 % re.escape(count_name),
2380 video_webpage, count_name, default=None))
2382 like_count = _extract_count('like
')
2383 dislike_count = _extract_count('dislike
')
2385 if view_count is None:
2386 view_count = str_to_int(self._search_regex(
2387 r'<[^
>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2388 'view count', default=None))
2391 float_or_none(video_details.get('averageRating'))
2392 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2395 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2396 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2398 video_duration = try_get(
2399 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2400 if not video_duration:
2401 video_duration = int_or_none(video_details.get('lengthSeconds'))
2402 if not video_duration:
2403 video_duration = parse_duration(self._html_search_meta(
2404 'duration', video_webpage, 'video duration'))
2407 video_annotations = None
2408 if self._downloader.params.get('writeannotations', False):
2409 xsrf_token = self._search_regex(
2410 r'([\'"])XSRF_TOKEN\
1\s
*:\s
*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
2411 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2412 invideo_url = try_get(
2413 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2414 if xsrf_token and invideo_url:
2415 xsrf_field_name = self._search_regex(
2416 r'([\'"])XSRF_FIELD_NAME\
1\s
*:\s
*([\'"])(?P<xsrf_field_name>\w+)\2',
2417 video_webpage, 'xsrf field name',
2418 group='xsrf_field_name', default='session_token')
2419 video_annotations = self._download_webpage(
2420 self._proto_relative_url(invideo_url),
2421 video_id, note='Downloading annotations',
2422 errnote='Unable to download video annotations', fatal=False,
2423 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2425 chapters = self._extract_chapters(video_webpage, description_original, video_id, video_duration)
2427 # Look for the DASH manifest
2428 if self._downloader.params.get('youtube_include_dash_manifest', True):
2429 dash_mpd_fatal = True
2430 for mpd_url in dash_mpds:
2433 def decrypt_sig(mobj):
2435 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2436 return '/signature/%s' % dec_s
2438 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2440 for df in self._extract_mpd_formats(
2441 mpd_url, video_id, fatal=dash_mpd_fatal,
2442 formats_dict=self._formats):
2443 if not df.get('filesize'):
2444 df['filesize'] = _extract_filesize(df['url'])
2445 # Do not overwrite DASH format found in some previous DASH manifest
2446 if df['format_id'] not in dash_formats:
2447 dash_formats[df['format_id']] = df
2448 # Additional DASH manifests may end up in HTTP Error 403 therefore
2449 # allow them to fail without bug report message if we already have
2450 # some DASH manifest succeeded. This is temporary workaround to reduce
2451 # burst of bug reports until we figure out the reason and whether it
2452 # can be fixed at all.
2453 dash_mpd_fatal = False
2454 except (ExtractorError, KeyError) as e:
2455 self.report_warning(
2456 'Skipping DASH manifest: %r' % e, video_id)
2458 # Remove the formats we found through non-DASH, they
2459 # contain less info and it can be wrong, because we use
2460 # fixed values (for example the resolution). See
2461 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2463 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2464 formats.extend(dash_formats.values())
2466 # Check for malformed aspect ratio
2467 stretched_m = re.search(
2468 r'<meta\s+property="og
:video
:tag
".*?content="yt
:stretch
=(?P
<w
>[0-9]+):(?P
<h
>[0-9]+)">',
2471 w = float(stretched_m.group('w'))
2472 h = float(stretched_m.group('h'))
2473 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2474 # We will only process correct ratios.
2478 if f.get('vcodec') != 'none':
2479 f['stretched_ratio'] = ratio
2482 if 'reason' in video_info:
2483 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2484 regions_allowed = self._html_search_meta(
2485 'regionsAllowed', video_webpage, default=None)
2486 countries = regions_allowed.split(',') if regions_allowed else None
2487 self.raise_geo_restricted(
2488 msg=video_info['reason'][0], countries=countries)
2489 reason = video_info['reason'][0]
2490 if 'Invalid parameters' in reason:
2491 unavailable_message = extract_unavailable_message()
2492 if unavailable_message:
2493 reason = unavailable_message
2494 raise ExtractorError(
2495 'YouTube said: %s' % reason,
2496 expected=True, video_id=video_id)
2497 if video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos']):
2498 raise ExtractorError('This video is DRM protected.', expected=True)
2500 self._sort_formats(formats)
2502 self.mark_watched(video_id, video_info, player_response)
2506 'uploader': video_uploader,
2507 'uploader_id': video_uploader_id,
2508 'uploader_url': video_uploader_url,
2509 'channel_id': channel_id,
2510 'channel_url': channel_url,
2511 'upload_date': upload_date,
2512 'license': video_license,
2513 'creator': video_creator or artist,
2514 'title': video_title,
2515 'alt_title': video_alt_title or track,
2516 'thumbnails': thumbnails,
2517 'description': video_description,
2518 'categories': video_categories,
2520 'subtitles': video_subtitles,
2521 'automatic_captions': automatic_captions,
2522 'duration': video_duration,
2523 'age_limit': 18 if age_gate else 0,
2524 'annotations': video_annotations,
2525 'chapters': chapters,
2526 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2527 'view_count': view_count,
2528 'like_count': like_count,
2529 'dislike_count': dislike_count,
2530 'average_rating': average_rating,
2533 'start_time': start_time,
2534 'end_time': end_time,
2536 'season_number': season_number,
2537 'episode_number': episode_number,
2541 'release_date': release_date,
2542 'release_year': release_year,
2546 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2547 IE_DESC = 'YouTube.com playlists'
2548 _VALID_URL = r"""(?x)(?:
2553 youtube(?:kids)?\.com|
2558 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2559 \? (?:.*?[&;])*? (?:p|a|list)=
2562 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2565 (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2566 # Top tracks, they can also include dots
2572 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2573 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2574 _VIDEO_RE_TPL = r'href="\s
*/watch
\?v
=%s(?
:&
;(?
:[^
"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2575 _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
2576 IE_NAME = 'youtube:playlist'
2578 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2580 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2581 'uploader': 'Sergey M.',
2582 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2583 'title': 'youtube-dl public playlist',
2585 'playlist_count': 1,
2587 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2589 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2590 'uploader': 'Sergey M.',
2591 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2592 'title': 'youtube-dl empty playlist',
2594 'playlist_count': 0,
2596 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2597 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2599 'title': '29C3: Not my department',
2600 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2601 'uploader': 'Christiaan008',
2602 'uploader_id': 'ChRiStIaAn008',
2604 'playlist_count': 96,
2606 'note': 'issue #673',
2607 'url': 'PLBB231211A4F62143',
2609 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2610 'id': 'PLBB231211A4F62143',
2611 'uploader': 'Wickydoo',
2612 'uploader_id': 'Wickydoo',
2614 'playlist_mincount': 26,
2616 'note': 'Large playlist',
2617 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2619 'title': 'Uploads from Cauchemar',
2620 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2621 'uploader': 'Cauchemar',
2622 'uploader_id': 'Cauchemar89',
2624 'playlist_mincount': 799,
2626 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2628 'title': 'YDL_safe_search',
2629 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2631 'playlist_count': 2,
2632 'skip': 'This playlist is private',
2635 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2636 'playlist_count': 4,
2639 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2640 'uploader': 'milan',
2641 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2644 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2645 'playlist_mincount': 485,
2647 'title': '2018 Chinese New Singles (11/6 updated)',
2648 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2650 'uploader_id': 'sdragonfang',
2653 'note': 'Embedded SWF player',
2654 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2655 'playlist_count': 4,
2658 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2660 'skip': 'This playlist does not exist',
2662 'note': 'Buggy playlist: the webpage has a "Load more
" button but it doesn\'t have more videos',
2663 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2665 'title': 'Uploads from Interstellar Movie',
2666 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2667 'uploader': 'Interstellar Movie',
2668 'uploader_id': 'InterstellarMovie1',
2670 'playlist_mincount': 21,
2672 # Playlist URL that does not actually serve a playlist
2673 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2675 'id': 'FqZTN594JQw',
2677 'title': "Smiley
's People 01 detective, Adventure Series, Action",
2678 'uploader
': 'STREEM
',
2679 'uploader_id
': 'UCyPhqAZgwYWZfxElWVbVJng
',
2680 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/channel
/UCyPhqAZgwYWZfxElWVbVJng
',
2681 'upload_date
': '20150526',
2682 'license
': 'Standard YouTube License
',
2683 'description
': 'md5
:507cdcb5a49ac0da37a920ece610be80
',
2684 'categories
': ['People
& Blogs
'],
2688 'dislike_count
': int,
2691 'skip_download
': True,
2693 'skip
': 'This video
is not available
.',
2694 'add_ie
': [YoutubeIE.ie_key()],
2696 'url
': 'https
://youtu
.be
/yeWKywCrFtk?
list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5
',
2698 'id': 'yeWKywCrFtk
',
2700 'title
': 'Small Scale Baler
and Braiding Rugs
',
2701 'uploader
': 'Backus
-Page House Museum
',
2702 'uploader_id
': 'backuspagemuseum
',
2703 'uploader_url
': r're
:https?
://(?
:www\
.)?youtube\
.com
/user
/backuspagemuseum
',
2704 'upload_date
': '20161008',
2705 'description
': 'md5
:800c0c78d5eb128500bffd4f0b4f2e8a
',
2706 'categories
': ['Nonprofits
& Activism
'],
2709 'dislike_count
': int,
2713 'skip_download
': True,
2716 # https://github.com/ytdl-org/youtube-dl/issues/21844
2717 'url
': 'https
://www
.youtube
.com
/playlist?
list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba
',
2719 'title
': 'Data Analysis
with Dr Mike Pound
',
2720 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba
',
2721 'uploader_id
': 'Computerphile
',
2722 'uploader
': 'Computerphile
',
2724 'playlist_mincount
': 11,
2726 'url
': 'https
://youtu
.be
/uWyaPkt
-VOI?
list=PL9D9FC436B881BA21
',
2727 'only_matching
': True,
2729 'url
': 'TLGGrESM50VT6acwMjAyMjAxNw
',
2730 'only_matching
': True,
2732 # music album playlist
2733 'url
': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM
',
2734 'only_matching
': True,
2736 'url
': 'https
://invidio
.us
/playlist?
list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU
',
2737 'only_matching
': True,
2739 'url
': 'https
://www
.youtubekids
.com
/watch?v
=Agk7R8I8o5U
&list=PUZ6jURNr1WQZCNHF0ao
-c0g
',
2740 'only_matching
': True,
2743 def _real_initialize(self):
2746 def extract_videos_from_page(self, page):
2750 for item in re.findall(
2751 r'(<[^
>]*\bdata
-video
-id\s
*=\s
*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
2752 attrs = extract_attributes(item)
2753 video_id = attrs['data-video-id']
2754 video_title = unescapeHTML(attrs.get('data-title'))
2756 video_title = video_title.strip()
2757 ids_in_page.append(video_id)
2758 titles_in_page.append(video_title)
2760 # Fallback with old _VIDEO_RE
2761 self.extract_videos_from_page_impl(
2762 self._VIDEO_RE, page, ids_in_page, titles_in_page)
2765 self.extract_videos_from_page_impl(
2766 r'href="\s
*/watch
\?v\s
*=\s
*(?P
<id>[0-9A
-Za
-z_
-]{11}
)', page,
2767 ids_in_page, titles_in_page)
2768 self.extract_videos_from_page_impl(
2769 r'data
-video
-ids\s
*=\s
*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
2770 ids_in_page, titles_in_page)
2772 return zip(ids_in_page, titles_in_page)
2774 def _extract_mix(self, playlist_id):
2775 # The mixes are generated from a single video
2776 # the id of the playlist is just 'RD' + video_id
2778 last_id = playlist_id[-11:]
2779 for n in itertools.count(1):
2780 url = 'https://www.youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2781 webpage = self._download_webpage(
2782 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2783 new_ids = orderedSet(re.findall(
2784 r'''(?xs)data-video-username=".*?
".*?
2785 href="/watch
\?v
=([0-9A
-Za
-z_
-]{11}
)&
;[^
"]*?list=%s''' % re.escape(playlist_id),
2787 # Fetch new pages until all the videos are repeated, it seems that
2788 # there are always 51 unique videos.
2789 new_ids = [_id for _id in new_ids if _id not in ids]
2795 url_results = self._ids_to_results(ids)
2797 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2799 search_title('playlist-title')
2800 or search_title('title long-title')
2801 or search_title('title'))
2802 title = clean_html(title_span)
2804 return self.playlist_result(url_results, playlist_id, title)
2806 def _extract_playlist(self, playlist_id):
2807 url = self._TEMPLATE_URL % playlist_id
2808 page = self._download_webpage(url, playlist_id)
2810 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2811 for match in re.findall(r'<div class="yt
-alert
-message
"[^>]*>([^<]+)</div>', page):
2812 match = match.strip()
2813 # Check if the playlist exists or is private
2814 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2816 reason = mobj.group('reason')
2817 message = 'This playlist %s' % reason
2818 if 'private' in reason:
2819 message += ', use --username or --netrc to access it'
2821 raise ExtractorError(message, expected=True)
2822 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2823 raise ExtractorError(
2824 'Invalid parameters. Maybe URL is incorrect.',
2826 elif re.match(r'[^<]*Choose your language[^<]*', match):
2829 self.report_warning('Youtube gives an alert message: ' + match)
2831 playlist_title = self._html_search_regex(
2832 r'(?s)<h1 class="pl
-header
-title
[^
"]*"[^
>]*>\s
*(.*?
)\s
*</h1
>',
2833 page, 'title
', default=None)
2835 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2836 uploader = self._html_search_regex(
2837 r'%s["\']/(?
:user|channel
)/[^
>]+>([^
<]+)' % _UPLOADER_BASE,
2838 page, 'uploader
', default=None)
2840 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2843 uploader_id = mobj.group('uploader_id')
2844 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2846 uploader_id = uploader_url = None
2850 if not playlist_title:
2852 # Some playlist URLs don't actually serve a playlist (e.g.
2853 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2854 next(self._entries(page, playlist_id))
2855 except StopIteration:
2858 playlist = self.playlist_result(
2859 self._entries(page, playlist_id), playlist_id, playlist_title)
2861 'uploader': uploader,
2862 'uploader_id': uploader_id,
2863 'uploader_url': uploader_url,
2866 return has_videos, playlist
2868 def _check_download_just_video(self, url, playlist_id):
2869 # Check if it's a video-specific URL
2870 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2871 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2872 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2873 'video id', default=None)
2875 if self._downloader.params.get('noplaylist'):
2876 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2877 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2879 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2880 return video_id, None
2883 def _real_extract(self, url):
2884 # Extract playlist id
2885 mobj = re.match(self._VALID_URL, url)
2887 raise ExtractorError('Invalid URL: %s' % url)
2888 playlist_id = mobj.group(1) or mobj.group(2)
2890 video_id, video = self._check_download_just_video(url, playlist_id)
2894 if playlist_id.startswith(('RD', 'UL', 'PU')):
2895 # Mixes require a custom extraction process
2896 return self._extract_mix(playlist_id)
2898 has_videos, playlist = self._extract_playlist(playlist_id)
2899 if has_videos or not video_id:
2902 # Some playlist URLs don't actually serve a playlist (see
2903 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2904 # Fallback to plain video extraction if there is a video id
2905 # along with playlist id.
2906 return self.url_result(video_id, 'Youtube', video_id=video_id)
2909 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2910 IE_DESC = 'YouTube.com channels'
2911 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2912 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2913 _VIDEO_RE = r'(?:title="(?P
<title
>[^
"]+)"[^
>]+)?href
="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2914 IE_NAME = 'youtube:channel'
2916 'note': 'paginated channel',
2917 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2918 'playlist_mincount': 91,
2920 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2921 'title': 'Uploads from lex will',
2922 'uploader': 'lex will',
2923 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2926 'note': 'Age restricted channel',
2927 # from https://www.youtube.com/user/DeusExOfficial
2928 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2929 'playlist_mincount': 64,
2931 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2932 'title': 'Uploads from Deus Ex',
2933 'uploader': 'Deus Ex',
2934 'uploader_id': 'DeusExOfficial',
2937 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2938 'only_matching': True,
2940 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
2941 'only_matching': True,
2945 def suitable(cls, url):
2946 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2947 else super(YoutubeChannelIE, cls).suitable(url))
2949 def _build_template_url(self, url, channel_id):
2950 return self._TEMPLATE_URL % channel_id
2952 def _real_extract(self, url):
2953 channel_id = self._match_id(url)
2955 url = self._build_template_url(url, channel_id)
2957 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2958 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2959 # otherwise fallback on channel by page extraction
2960 channel_page = self._download_webpage(
2961 url + '?view=57', channel_id,
2962 'Downloading channel page', fatal=False)
2963 if channel_page is False:
2964 channel_playlist_id = False
2966 channel_playlist_id = self._html_search_meta(
2967 'channelId', channel_page, 'channel id', default=None)
2968 if not channel_playlist_id:
2969 channel_url = self._html_search_meta(
2970 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2971 channel_page, 'channel url', default=None)
2973 channel_playlist_id = self._search_regex(
2974 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2975 channel_url, 'channel id', default=None)
2976 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2977 playlist_id = 'UU' + channel_playlist_id[2:]
2978 return self.url_result(
2979 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2981 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2982 autogenerated = re.search(r'''(?x)
2984 channel-header-autogenerated-label|
2985 yt-channel-title-autogenerated
2986 )[^"]*"''', channel_page) is not None
2989 # The videos are contained in a single page
2990 # the ajax pages can't be used, they are empty
2993 video_id, 'Youtube', video_id=video_id,
2994 video_title=video_title)
2995 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2996 return self.playlist_result(entries, channel_id)
2999 next(self._entries(channel_page, channel_id))
3000 except StopIteration:
3001 alert_message = self._html_search_regex(
3002 r'(?s)<div[^>]+class=(["\']).*?
\byt
-alert
-message
\b.*?\
1[^
>]*>(?P
<alert
>[^
<]+)</div
>',
3003 channel_page, 'alert
', default=None, group='alert
')
3005 raise ExtractorError('Youtube said
: %s' % alert_message, expected=True)
3007 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
3010 class YoutubeUserIE(YoutubeChannelIE):
3011 IE_DESC = 'YouTube
.com user
videos (URL
or "ytuser" keyword
)'
3012 _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_%-]+)'
3013 _TEMPLATE_URL = 'https
://www
.youtube
.com
/%s/%s/videos
'
3014 IE_NAME = 'youtube
:user
'
3017 'url
': 'https
://www
.youtube
.com
/user
/TheLinuxFoundation
',
3018 'playlist_mincount
': 320,
3020 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ
',
3021 'title
': 'Uploads
from The Linux Foundation
',
3022 'uploader
': 'The Linux Foundation
',
3023 'uploader_id
': 'TheLinuxFoundation
',
3026 # Only available via https://www.youtube.com/c/12minuteathlete/videos
3027 # but not https://www.youtube.com/user/12minuteathlete/videos
3028 'url
': 'https
://www
.youtube
.com
/c
/12minuteathlete
/videos
',
3029 'playlist_mincount
': 249,
3031 'id': 'UUVjM
-zV6_opMDx7WYxnjZiQ
',
3032 'title
': 'Uploads
from 12 Minute Athlete
',
3033 'uploader
': '12 Minute Athlete
',
3034 'uploader_id
': 'the12minuteathlete
',
3037 'url
': 'ytuser
:phihag
',
3038 'only_matching
': True,
3040 'url
': 'https
://www
.youtube
.com
/c
/gametrailers
',
3041 'only_matching
': True,
3043 'url
': 'https
://www
.youtube
.com
/c
/Pawe
%C5
%82Zadro
%C5
%BCniak
',
3044 'only_matching
': True,
3046 'url
': 'https
://www
.youtube
.com
/gametrailers
',
3047 'only_matching
': True,
3049 # This channel is not available, geo restricted to JP
3050 'url
': 'https
://www
.youtube
.com
/user
/kananishinoSMEJ
/videos
',
3051 'only_matching
': True,
3055 def suitable(cls, url):
3056 # Don't
return True if the url can be extracted
with other youtube
3057 # extractor, the regex would is too permissive and it would match.
3058 other_yt_ies
= iter(klass
for (name
, klass
) in globals().items() if name
.startswith('Youtube') and name
.endswith('IE') and klass
is not cls
)
3059 if any(ie
.suitable(url
) for ie
in other_yt_ies
):
3062 return super(YoutubeUserIE
, cls
).suitable(url
)
3064 def _build_template_url(self
, url
, channel_id
):
3065 mobj
= re
.match(self
._VALID
_URL
, url
)
3066 return self
._TEMPLATE
_URL
% (mobj
.group('user') or 'user', mobj
.group('id'))
3069 class YoutubeLiveIE(YoutubeBaseInfoExtractor
):
3070 IE_DESC
= 'YouTube.com live streams'
3071 _VALID_URL
= r
'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
3072 IE_NAME
= 'youtube:live'
3075 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3077 'id': 'a48o2S1cPoo',
3079 'title': 'The Young Turks - Live Main Show',
3080 'uploader': 'The Young Turks',
3081 'uploader_id': 'TheYoungTurks',
3082 'uploader_url': r
're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3083 'upload_date': '20150715',
3084 'license': 'Standard YouTube License',
3085 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3086 'categories': ['News & Politics'],
3087 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3089 'dislike_count': int,
3092 'skip_download': True,
3095 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3096 'only_matching': True,
3098 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3099 'only_matching': True,
3101 'url': 'https://www.youtube.com/TheYoungTurks/live',
3102 'only_matching': True,
3105 def _real_extract(self
, url
):
3106 mobj
= re
.match(self
._VALID
_URL
, url
)
3107 channel_id
= mobj
.group('id')
3108 base_url
= mobj
.group('base_url')
3109 webpage
= self
._download
_webpage
(url
, channel_id
, fatal
=False)
3111 page_type
= self
._og
_search
_property
(
3112 'type', webpage
, 'page type', default
='')
3113 video_id
= self
._html
_search
_meta
(
3114 'videoId', webpage
, 'video id', default
=None)
3115 if page_type
.startswith('video') and video_id
and re
.match(
3116 r
'^[0-9A-Za-z_-]{11}$', video_id
):
3117 return self
.url_result(video_id
, YoutubeIE
.ie_key())
3118 return self
.url_result(base_url
)
3121 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor
):
3122 IE_DESC
= 'YouTube.com user/channel playlists'
3123 _VALID_URL
= r
'https?://(?:\w+\.)?youtube\.com/(?:user|channel|c)/(?P<id>[^/]+)/playlists'
3124 IE_NAME
= 'youtube:playlists'
3127 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3128 'playlist_mincount': 4,
3130 'id': 'ThirstForScience',
3131 'title': 'ThirstForScience',
3134 # with "Load more" button
3135 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3136 'playlist_mincount': 70,
3139 'title': 'Игорь Клейнер',
3142 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
3143 'playlist_mincount': 17,
3145 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
3146 'title': 'Chem Player',
3150 'url': 'https://www.youtube.com/c/ChristophLaimer/playlists',
3151 'only_matching': True,
3155 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor
):
3156 _VIDEO_RE
= r
'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
3159 class YoutubeSearchIE(SearchInfoExtractor
, YoutubeSearchBaseInfoExtractor
):
3160 IE_DESC
= 'YouTube.com searches'
3161 # there doesn't appear to be a real limit, for example if you search for
3162 # 'python' you get more than 8.000.000 results
3163 _MAX_RESULTS
= float('inf')
3164 IE_NAME
= 'youtube:search'
3165 _SEARCH_KEY
= 'ytsearch'
3166 _EXTRA_QUERY_ARGS
= {}
3169 def _get_n_results(self
, query
, n
):
3170 """Get a specified number of results for a query"""
3176 'search_query': query
.encode('utf-8'),
3178 url_query
.update(self
._EXTRA
_QUERY
_ARGS
)
3179 result_url
= 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query
)
3181 for pagenum
in itertools
.count(1):
3182 data
= self
._download
_json
(
3183 result_url
, video_id
='query "%s"' % query
,
3184 note
='Downloading page %s' % pagenum
,
3185 errnote
='Unable to download API page',
3186 query
={'spf': 'navigate'}
)
3187 html_content
= data
[1]['body']['content']
3189 if 'class="search-message' in html_content
:
3190 raise ExtractorError(
3191 '[youtube] No video results', expected
=True)
3193 new_videos
= list(self
._process
_page
(html_content
))
3194 videos
+= new_videos
3195 if not new_videos
or len(videos
) > limit
:
3197 next_link
= self
._html
_search
_regex
(
3198 r
'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
3199 html_content
, 'next link', default
=None)
3200 if next_link
is None:
3202 result_url
= compat_urlparse
.urljoin('https://www.youtube.com/', next_link
)
3206 return self
.playlist_result(videos
, query
)
3209 class YoutubeSearchDateIE(YoutubeSearchIE
):
3210 IE_NAME
= YoutubeSearchIE
.IE_NAME
+ ':date'
3211 _SEARCH_KEY
= 'ytsearchdate'
3212 IE_DESC
= 'YouTube.com searches, newest videos first'
3213 _EXTRA_QUERY_ARGS
= {'search_sort': 'video_date_uploaded'}
3216 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor
):
3217 IE_DESC
= 'YouTube.com search URLs'
3218 IE_NAME
= 'youtube:search_url'
3219 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3220 _SEARCH_DATA
= r
'window\[\"ytInitialData\"\]\W?=\W?({.*?});'
3222 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3223 'playlist_mincount': 5,
3225 'title': 'youtube-dl test video',
3228 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3229 'only_matching': True,
3232 def extract_videos_from_page_impl(self
, page
, ids_in_page
, titles_in_page
):
3233 search_response
= self
._parse
_json
(self
._search
_regex
(self
._SEARCH
_DATA
, page
, 'ytInitialData'), None)
3235 result_items
= try_get(
3237 lambda x
: x
['contents']['twoColumnSearchResultsRenderer']['primaryContents']['sectionListRenderer']['contents'][0]['itemSectionRenderer']['contents'])
3239 for plobj
in result_items
:
3240 video_id
= try_get(plobj
, lambda x
: x
['videoRenderer']['videoId'])
3241 video_title
= try_get(plobj
, lambda x
: x
['videoRenderer']['title']['runs'][0]['text'])
3243 if video_id
is None or video_title
is None:
3244 # we do not have a videoRenderer or it is empty
3247 video_title
= video_title
.strip()
3250 idx
= ids_in_page
.index(video_id
)
3251 if video_title
and not titles_in_page
[idx
]:
3252 titles_in_page
[idx
] = video_title
3254 ids_in_page
.append(video_id
)
3255 titles_in_page
.append(video_title
)
3257 def extract_videos_from_page(self
, page
):
3260 self
.extract_videos_from_page_impl(page
, ids_in_page
, titles_in_page
)
3261 return zip(ids_in_page
, titles_in_page
)
3263 def _real_extract(self
, url
):
3264 mobj
= re
.match(self
._VALID
_URL
, url
)
3265 query
= compat_urllib_parse_unquote_plus(mobj
.group('query'))
3266 webpage
= self
._download
_webpage
(url
, query
)
3267 return self
.playlist_result(self
._process
_page
(webpage
), playlist_title
=query
)
3270 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor
):
3271 IE_DESC
= 'YouTube.com (multi-season) shows'
3272 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3273 IE_NAME
= 'youtube:show'
3275 'url': 'https://www.youtube.com/show/airdisasters',
3276 'playlist_mincount': 5,
3278 'id': 'airdisasters',
3279 'title': 'Air Disasters',
3283 def _real_extract(self
, url
):
3284 playlist_id
= self
._match
_id
(url
)
3285 return super(YoutubeShowIE
, self
)._real
_extract
(
3286 'https://www.youtube.com/show/%s/playlists' % playlist_id
)
3289 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor
):
3291 Base class for feed extractors
3292 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3294 _LOGIN_REQUIRED
= True
3298 return 'youtube:%s' % self
._FEED
_NAME
3300 def _real_initialize(self
):
3303 def _entries(self
, page
):
3304 # The extraction process is the same as for playlists, but the regex
3305 # for the video ids doesn't contain an index
3307 more_widget_html
= content_html
= page
3308 for page_num
in itertools
.count(1):
3309 matches
= re
.findall(r
'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html
)
3311 # 'recommended' feed has infinite 'load more' and each new portion spins
3312 # the same videos in (sometimes) slightly different order, so we'll check
3313 # for unicity and break when portion has no new videos
3314 new_ids
= list(filter(lambda video_id
: video_id
not in ids
, orderedSet(matches
)))
3320 for entry
in self
._ids
_to
_results
(new_ids
):
3323 mobj
= re
.search(r
'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html
)
3327 more
= self
._download
_json
(
3328 'https://www.youtube.com/%s' % mobj
.group('more'), self
._PLAYLIST
_TITLE
,
3329 'Downloading page #%s' % page_num
,
3330 transform_source
=uppercase_escape
,
3331 headers
=self
._YOUTUBE
_CLIENT
_HEADERS
)
3332 content_html
= more
['content_html']
3333 more_widget_html
= more
['load_more_widget_html']
3335 def _real_extract(self
, url
):
3336 page
= self
._download
_webpage
(
3337 'https://www.youtube.com/feed/%s' % self
._FEED
_NAME
,
3338 self
._PLAYLIST
_TITLE
)
3339 return self
.playlist_result(
3340 self
._entries
(page
), playlist_title
=self
._PLAYLIST
_TITLE
)
3343 class YoutubeWatchLaterIE(YoutubePlaylistIE
):
3344 IE_NAME
= 'youtube:watchlater'
3345 IE_DESC
= 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3346 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3349 'url': 'https://www.youtube.com/playlist?list=WL',
3350 'only_matching': True,
3352 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3353 'only_matching': True,
3356 def _real_extract(self
, url
):
3357 _
, video
= self
._check
_download
_just
_video
(url
, 'WL')
3360 _
, playlist
= self
._extract
_playlist
('WL')
3364 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor
):
3365 IE_NAME
= 'youtube:favorites'
3366 IE_DESC
= 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3367 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3368 _LOGIN_REQUIRED
= True
3370 def _real_extract(self
, url
):
3371 webpage
= self
._download
_webpage
('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3372 playlist_id
= self
._search
_regex
(r
'list=(.+?)["&]', webpage
, 'favourites playlist id')
3373 return self
.url_result(playlist_id
, 'YoutubePlaylist')
3376 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor
):
3377 IE_DESC
= 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3378 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3379 _FEED_NAME
= 'recommended'
3380 _PLAYLIST_TITLE
= 'Youtube Recommended videos'
3383 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor
):
3384 IE_DESC
= 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3385 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3386 _FEED_NAME
= 'subscriptions'
3387 _PLAYLIST_TITLE
= 'Youtube Subscriptions'
3390 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor
):
3391 IE_DESC
= 'Youtube watch history, ":ythistory" for short (requires authentication)'
3392 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3393 _FEED_NAME
= 'history'
3394 _PLAYLIST_TITLE
= 'Youtube History'
3397 class YoutubeTruncatedURLIE(InfoExtractor
):
3398 IE_NAME
= 'youtube:truncated_url'
3399 IE_DESC
= False # Do not list
3400 _VALID_URL
= r
'''(?x)
3402 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3405 annotation_id=annotation_[^&]+|
3411 attribution_link\?a=[^&]+
3417 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3418 'only_matching': True,
3420 'url': 'https://www.youtube.com/watch?',
3421 'only_matching': True,
3423 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3424 'only_matching': True,
3426 'url': 'https://www.youtube.com/watch?feature=foo',
3427 'only_matching': True,
3429 'url': 'https://www.youtube.com/watch?hl=en-GB',
3430 'only_matching': True,
3432 'url': 'https://www.youtube.com/watch?t=2372',
3433 'only_matching': True,
3436 def _real_extract(self
, url
):
3437 raise ExtractorError(
3438 'Did you forget to quote the URL? Remember that & is a meta '
3439 'character in most shells, so you want to put the URL in quotes, '
3441 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3442 ' or simply youtube-dl BaW_jenozKc .',
3446 class YoutubeTruncatedIDIE(InfoExtractor
):
3447 IE_NAME
= 'youtube:truncated_id'
3448 IE_DESC
= False # Do not list
3449 _VALID_URL
= r
'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3452 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3453 'only_matching': True,
3456 def _real_extract(self
, url
):
3457 video_id
= self
._match
_id
(url
)
3458 raise ExtractorError(
3459 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id
, url
),