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,
59 class YoutubeBaseInfoExtractor(InfoExtractor):
60 """Provide base functions for Youtube extractors"""
61 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
62 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
64 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
65 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
66 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
68 _NETRC_MACHINE = 'youtube'
69 # If True it will raise an error if no login info is provided
70 _LOGIN_REQUIRED = False
72 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
74 def _set_language(self):
76 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
77 # YouTube sets the expire time to about two months
78 expire_time=time.time() + 2 * 30 * 24 * 3600)
80 def _ids_to_results(self, ids):
82 self.url_result(vid_id, 'Youtube', video_id=vid_id)
87 Attempt to log in to YouTube.
88 True is returned if successful or skipped.
89 False is returned if login failed.
91 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
93 username, password = self._get_login_info()
94 # No authentication to be performed
96 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
97 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
100 login_page = self._download_webpage(
101 self._LOGIN_URL, None,
102 note='Downloading login page',
103 errnote='unable to fetch login page', fatal=False)
104 if login_page is False:
107 login_form = self._hidden_inputs(login_page)
109 def req(url, f_req, note, errnote):
110 data = login_form.copy()
113 'checkConnection': 'youtube',
114 'checkedDomains': 'youtube',
116 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
117 'f.req': json.dumps(f_req),
118 'flowName': 'GlifWebSignIn',
119 'flowEntry': 'ServiceLogin',
120 # TODO: reverse actual botguard identifier generation algo
121 'bgRequest': '["identifier",""]',
123 return self._download_json(
124 url, None, note=note, errnote=errnote,
125 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
127 data=urlencode_postdata(data), headers={
128 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
129 'Google-Accounts-XSRF': 1,
133 self._downloader.report_warning(message)
137 None, [], None, 'US', None, None, 2, False, True,
141 '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',
143 1, [None, None, []], None, None, None, True
148 lookup_results = req(
149 self._LOOKUP_URL, lookup_req,
150 'Looking up account info', 'Unable to look up account info')
152 if lookup_results is False:
155 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
157 warn('Unable to extract user hash')
162 None, 1, None, [1, None, None, None, [password, None, True]],
164 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],
165 1, [None, None, []], None, None, None, True
168 challenge_results = req(
169 self._CHALLENGE_URL, challenge_req,
170 'Logging in', 'Unable to log in')
172 if challenge_results is False:
175 login_res = try_get(challenge_results, lambda x: x[0][5], list)
177 login_msg = try_get(login_res, lambda x: x[5], compat_str)
179 'Unable to login: %s' % 'Invalid password'
180 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
183 res = try_get(challenge_results, lambda x: x[0][-1], list)
185 warn('Unable to extract result entry')
188 login_challenge = try_get(res, lambda x: x[0][0], list)
190 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
191 if challenge_str == 'TWO_STEP_VERIFICATION':
192 # SEND_SUCCESS - TFA code has been successfully sent to phone
193 # QUOTA_EXCEEDED - reached the limit of TFA codes
194 status = try_get(login_challenge, lambda x: x[5], compat_str)
195 if status == 'QUOTA_EXCEEDED':
196 warn('Exceeded the limit of TFA codes, try later')
199 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
201 warn('Unable to extract TL')
204 tfa_code = self._get_tfa_info('2-step verification code')
208 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
209 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
212 tfa_code = remove_start(tfa_code, 'G-')
215 user_hash, None, 2, None,
217 9, None, None, None, None, None, None, None,
218 [None, tfa_code, True, 2]
222 self._TFA_URL.format(tl), tfa_req,
223 'Submitting TFA code', 'Unable to submit TFA code')
225 if tfa_results is False:
228 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
230 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
232 'Unable to finish TFA: %s' % 'Invalid TFA code'
233 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
236 check_cookie_url = try_get(
237 tfa_results, lambda x: x[0][-1][2], compat_str)
240 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
241 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
242 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
244 challenge = CHALLENGES.get(
246 '%s returned error %s.' % (self.IE_NAME, challenge_str))
247 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
250 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
252 if not check_cookie_url:
253 warn('Unable to extract CheckCookie URL')
256 check_cookie_results = self._download_webpage(
257 check_cookie_url, None, 'Checking cookie', fatal=False)
259 if check_cookie_results is False:
262 if 'https://myaccount.google.com/' not in check_cookie_results:
263 warn('Unable to log in')
268 def _download_webpage_handle(self, *args, **kwargs):
269 query = kwargs.get('query', {}).copy()
270 query['disable_polymer'] = 'true'
271 kwargs['query'] = query
272 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
273 *args, **compat_kwargs(kwargs))
275 def _real_initialize(self):
276 if self._downloader is None:
279 if not self._login():
283 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
284 # Extract entries from page with "Load more" button
285 def _entries(self, page, playlist_id):
286 more_widget_html = content_html = page
287 for page_num in itertools.count(1):
288 for entry in self._process_page(content_html):
291 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
297 while count <= retries:
299 # Downloading page may result in intermittent 5xx HTTP error
300 # that is usually worked around with a retry
301 more = self._download_json(
302 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
303 'Downloading page #%s%s'
304 % (page_num, ' (retry #%d)' % count if count else ''),
305 transform_source=uppercase_escape)
307 except ExtractorError as e:
308 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
314 content_html = more['content_html']
315 if not content_html.strip():
316 # Some webpages show a "Load more" button but they don't
319 more_widget_html = more['load_more_widget_html']
322 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
323 def _process_page(self, content):
324 for video_id, video_title in self.extract_videos_from_page(content):
325 yield self.url_result(video_id, 'Youtube', video_id, video_title)
327 def extract_videos_from_page(self, page):
330 for mobj in re.finditer(self._VIDEO_RE, page):
331 # The link with index 0 is not the first video of the playlist (not sure if still actual)
332 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
334 video_id = mobj.group('id')
335 video_title = unescapeHTML(mobj.group('title'))
337 video_title = video_title.strip()
339 idx = ids_in_page.index(video_id)
340 if video_title and not titles_in_page[idx]:
341 titles_in_page[idx] = video_title
343 ids_in_page.append(video_id)
344 titles_in_page.append(video_title)
345 return zip(ids_in_page, titles_in_page)
348 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
349 def _process_page(self, content):
350 for playlist_id in orderedSet(re.findall(
351 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
353 yield self.url_result(
354 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
356 def _real_extract(self, url):
357 playlist_id = self._match_id(url)
358 webpage = self._download_webpage(url, playlist_id)
359 title = self._og_search_title(webpage, fatal=False)
360 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
363 class YoutubeIE(YoutubeBaseInfoExtractor):
364 IE_DESC = 'YouTube.com'
365 _VALID_URL = r"""(?x)^
367 (?:https?://|//) # http(s):// or protocol-independent URL
368 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
369 (?:www\.)?deturl\.com/www\.youtube\.com/|
370 (?:www\.)?pwnyoutube\.com/|
371 (?:www\.)?hooktube\.com/|
372 (?:www\.)?yourepeat\.com/|
373 tube\.majestyc\.net/|
374 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
375 (?:(?:www|dev)\.)?invidio\.us/|
376 (?:(?:www|no)\.)?invidiou\.sh/|
377 (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
378 (?:www\.)?invidious\.kabi\.tk/|
379 (?:www\.)?invidious\.enkirton\.net/|
380 (?:www\.)?invidious\.13ad\.de/|
381 (?:www\.)?tube\.poal\.co/|
382 (?:www\.)?vid\.wxzm\.sx/|
383 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
384 (?:.*?\#/)? # handle anchor (#/) redirect urls
385 (?: # the various things that can precede the ID:
386 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
387 |(?: # or the v= param in all its forms
388 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
389 (?:\?|\#!?) # the params delimiter ? or # or #!
390 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
395 youtu\.be| # just youtu.be/xxxx
396 vid\.plus| # or vid.plus/xxxx
397 zwearz\.com/watch| # or zwearz.com/watch/xxxx
399 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
401 )? # all until now is optional -> you can pass the naked ID
402 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
405 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
406 WL # WL are handled by the watch later IE
409 (?(1).+)? # if we found the ID, everything can follow
410 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
411 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
413 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
414 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
415 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
416 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
417 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
418 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
419 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
420 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
421 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
422 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
423 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
424 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
425 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
426 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
427 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
428 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
429 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
430 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
434 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
435 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
436 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
437 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
438 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
439 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
440 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
442 # Apple HTTP Live Streaming
443 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
444 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
445 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
446 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
447 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
448 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
449 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
450 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
453 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
454 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
455 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
456 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
457 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
458 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
459 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
460 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
461 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
462 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
463 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
464 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
467 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
468 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
469 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
470 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
471 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
472 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
473 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
476 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
477 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
478 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
479 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
480 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
481 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
482 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
483 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
484 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
485 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
486 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
487 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
488 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
489 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
490 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
491 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
492 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
493 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
494 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
495 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
496 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
497 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
500 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
501 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
503 # Dash webm audio with opus inside
504 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
505 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
506 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
509 '_rtmp': {'protocol': 'rtmp'},
511 # av01 video only formats sometimes served with "unknown" codecs
512 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
513 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
514 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
515 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
517 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
524 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
528 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
529 'uploader': 'Philipp Hagemeister',
530 'uploader_id': 'phihag',
531 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
532 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
533 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
534 'upload_date': '20121002',
535 '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 .',
536 'categories': ['Science & Technology'],
537 'tags': ['youtube-dl'],
541 'dislike_count': int,
547 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
548 'note': 'Test generic use_cipher_signature video (#897)',
552 'upload_date': '20120506',
553 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
554 'alt_title': 'I Love It (feat. Charli XCX)',
555 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
556 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
557 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
558 'iconic ep', 'iconic', 'love', 'it'],
560 'uploader': 'Icona Pop',
561 'uploader_id': 'IconaPop',
562 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
563 'creator': 'Icona Pop',
564 'track': 'I Love It (feat. Charli XCX)',
565 'artist': 'Icona Pop',
569 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
570 'note': 'Test VEVO video with age protection (#956)',
574 'upload_date': '20130703',
575 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
576 'alt_title': 'Tunnel Vision',
577 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
579 'uploader': 'justintimberlakeVEVO',
580 'uploader_id': 'justintimberlakeVEVO',
581 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
582 'creator': 'Justin Timberlake',
583 'track': 'Tunnel Vision',
584 'artist': 'Justin Timberlake',
589 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
590 'note': 'Embed-only video (#1746)',
594 'upload_date': '20120608',
595 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
596 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
597 'uploader': 'SET India',
598 'uploader_id': 'setindia',
599 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
604 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
605 'note': 'Use the first video ID in the URL',
609 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
610 'uploader': 'Philipp Hagemeister',
611 'uploader_id': 'phihag',
612 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
613 'upload_date': '20121002',
614 '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 .',
615 'categories': ['Science & Technology'],
616 'tags': ['youtube-dl'],
620 'dislike_count': int,
623 'skip_download': True,
627 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
628 'note': '256k DASH audio (format 141) via DASH manifest',
632 'upload_date': '20121002',
633 'uploader_id': '8KVIDEO',
634 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
636 'uploader': '8KVIDEO',
637 'title': 'UHDTV TEST 8K VIDEO.mp4'
640 'youtube_include_dash_manifest': True,
643 'skip': 'format 141 not served anymore',
645 # DASH manifest with encrypted signature
647 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
651 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
652 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
654 'uploader': 'AfrojackVEVO',
655 'uploader_id': 'AfrojackVEVO',
656 'upload_date': '20131011',
659 'youtube_include_dash_manifest': True,
660 'format': '141/bestaudio[ext=m4a]',
663 # JS player signature function name containing $
665 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
669 'title': 'Taylor Swift - Shake It Off',
670 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
672 'uploader': 'TaylorSwiftVEVO',
673 'uploader_id': 'TaylorSwiftVEVO',
674 'upload_date': '20140818',
675 'creator': 'Taylor Swift',
678 'youtube_include_dash_manifest': True,
679 'format': '141/bestaudio[ext=m4a]',
684 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
689 'upload_date': '20100909',
690 'uploader': 'Amazing Atheist',
691 'uploader_id': 'TheAmazingAtheist',
692 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
693 'title': 'Burning Everyone\'s Koran',
694 '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',
697 # Normal age-gate video (No vevo, embed allowed)
699 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
703 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
704 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
706 'uploader': 'The Witcher',
707 'uploader_id': 'WitcherGame',
708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
709 'upload_date': '20140605',
713 # Age-gate video with encrypted signature
715 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
719 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
720 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
722 'uploader': 'LloydVEVO',
723 'uploader_id': 'LloydVEVO',
724 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
725 'upload_date': '20110629',
729 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
730 # YouTube Red ad is not captured for creator
732 'url': '__2ABJjxzNo',
737 'upload_date': '20100430',
738 'uploader_id': 'deadmau5',
739 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
740 'creator': 'deadmau5',
741 'description': 'md5:12c56784b8032162bb936a5f76d55360',
742 'uploader': 'deadmau5',
743 'title': 'Deadmau5 - Some Chords (HD)',
744 'alt_title': 'Some Chords',
746 'expected_warnings': [
747 'DASH manifest missing',
750 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
752 'url': 'lqQg6PlCWgI',
757 'upload_date': '20150827',
758 'uploader_id': 'olympic',
759 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
760 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
761 'uploader': 'Olympic',
762 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
765 'skip_download': 'requires avconv',
770 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
774 'stretched_ratio': 16 / 9.,
776 'upload_date': '20110310',
777 'uploader_id': 'AllenMeow',
778 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
779 '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',
781 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
784 # url_encoded_fmt_stream_map is empty string
786 'url': 'qEJwOuvDf7I',
790 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
792 'upload_date': '20150404',
793 'uploader_id': 'spbelect',
794 'uploader': 'Наблюдатели Петербурга',
797 'skip_download': 'requires avconv',
799 'skip': 'This live event has ended.',
801 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
803 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
807 'title': 'md5:7b81415841e02ecd4313668cde88737a',
808 'description': 'md5:116377fd2963b81ec4ce64b542173306',
810 'upload_date': '20150625',
811 'uploader_id': 'dorappi2000',
812 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
813 'uploader': 'dorappi2000',
814 'formats': 'mincount:31',
816 'skip': 'not actual anymore',
818 # DASH manifest with segment_list
820 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
821 'md5': '8ce563a1d667b599d21064e982ab9e31',
825 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
826 'uploader': 'Airtek',
827 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
828 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
829 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
832 'youtube_include_dash_manifest': True,
833 'format': '135', # bestvideo
835 'skip': 'This live event has ended.',
838 # Multifeed videos (multiple cameras), URL is for Main Camera
839 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
842 'title': 'teamPGP: Rocket League Noob Stream',
843 'description': 'md5:dc7872fb300e143831327f1bae3af010',
849 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
850 'description': 'md5:dc7872fb300e143831327f1bae3af010',
852 'upload_date': '20150721',
853 'uploader': 'Beer Games Beer',
854 'uploader_id': 'beergamesbeer',
855 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
856 'license': 'Standard YouTube License',
862 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
863 'description': 'md5:dc7872fb300e143831327f1bae3af010',
865 'upload_date': '20150721',
866 'uploader': 'Beer Games Beer',
867 'uploader_id': 'beergamesbeer',
868 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
869 'license': 'Standard YouTube License',
875 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
876 'description': 'md5:dc7872fb300e143831327f1bae3af010',
878 'upload_date': '20150721',
879 'uploader': 'Beer Games Beer',
880 'uploader_id': 'beergamesbeer',
881 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
882 'license': 'Standard YouTube License',
888 'title': 'teamPGP: Rocket League Noob Stream (zim)',
889 'description': 'md5:dc7872fb300e143831327f1bae3af010',
891 'upload_date': '20150721',
892 'uploader': 'Beer Games Beer',
893 'uploader_id': 'beergamesbeer',
894 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
895 'license': 'Standard YouTube License',
899 'skip_download': True,
901 'skip': 'This video is not available.',
904 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
905 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
908 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
911 'skip': 'Not multifeed anymore',
914 'url': 'https://vid.plus/FlRa-iH7PGw',
915 'only_matching': True,
918 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
919 'only_matching': True,
922 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
923 # Also tests cut-off URL expansion in video description (see
924 # https://github.com/ytdl-org/youtube-dl/issues/1892,
925 # https://github.com/ytdl-org/youtube-dl/issues/8164)
926 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
930 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
931 'alt_title': 'Dark Walk - Position Music',
932 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
934 'upload_date': '20151119',
935 'uploader_id': 'IronSoulElf',
936 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
937 'uploader': 'IronSoulElf',
938 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
939 'track': 'Dark Walk - Position Music',
940 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
941 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
944 'skip_download': True,
948 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
949 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
950 'only_matching': True,
953 # Video with yt:stretch=17:0
954 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
958 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
959 'description': 'md5:ee18a25c350637c8faff806845bddee9',
960 'upload_date': '20151107',
961 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
962 'uploader': 'CH GAMER DROID',
965 'skip_download': True,
967 'skip': 'This video does not exist.',
970 # Video licensed under Creative Commons
971 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
975 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
976 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
978 'upload_date': '20150127',
979 'uploader_id': 'BerkmanCenter',
980 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
981 'uploader': 'The Berkman Klein Center for Internet & Society',
982 'license': 'Creative Commons Attribution license (reuse allowed)',
985 'skip_download': True,
989 # Channel-like uploader_url
990 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
994 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
995 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
997 'upload_date': '20151119',
998 'uploader': 'Bernie Sanders',
999 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1000 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1001 'license': 'Creative Commons Attribution license (reuse allowed)',
1004 'skip_download': True,
1008 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1009 'only_matching': True,
1012 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1013 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1014 'only_matching': True,
1017 # Rental video preview
1018 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1020 'id': 'uGpuVWrhIzE',
1022 'title': 'Piku - Trailer',
1023 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1024 'upload_date': '20150811',
1025 'uploader': 'FlixMatrix',
1026 'uploader_id': 'FlixMatrixKaravan',
1027 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1028 'license': 'Standard YouTube License',
1031 'skip_download': True,
1033 'skip': 'This video is not available.',
1036 # YouTube Red video with episode data
1037 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1039 'id': 'iqKdEhx-dD4',
1041 'title': 'Isolation - Mind Field (Ep 1)',
1042 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1044 'upload_date': '20170118',
1045 'uploader': 'Vsauce',
1046 'uploader_id': 'Vsauce',
1047 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1048 'series': 'Mind Field',
1050 'episode_number': 1,
1053 'skip_download': True,
1055 'expected_warnings': [
1056 'Skipping DASH manifest',
1060 # The following content has been identified by the YouTube community
1061 # as inappropriate or offensive to some audiences.
1062 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1064 'id': '6SJNVb0GnPI',
1066 'title': 'Race Differences in Intelligence',
1067 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1069 'upload_date': '20140124',
1070 'uploader': 'New Century Foundation',
1071 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1072 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1075 'skip_download': True,
1080 'url': '1t24XAntNCY',
1081 'only_matching': True,
1084 # geo restricted to JP
1085 'url': 'sJL6WA-aGkQ',
1086 'only_matching': True,
1089 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1090 'only_matching': True,
1093 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1094 'only_matching': True,
1098 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1099 'only_matching': True,
1102 # Video with unsupported adaptive stream type formats
1103 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1105 'id': 'Z4Vy8R84T1U',
1107 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1108 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1110 'upload_date': '20130923',
1111 'uploader': 'Amelia Putri Harwita',
1112 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1113 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1114 'formats': 'maxcount:10',
1117 'skip_download': True,
1118 'youtube_include_dash_manifest': False,
1122 # Youtube Music Auto-generated description
1123 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1125 'id': 'MgNrAu2pzNs',
1127 'title': 'Voyeur Girl',
1128 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1129 'upload_date': '20190312',
1130 'uploader': 'Various Artists - Topic',
1131 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1132 'artist': 'Stephen',
1133 'track': 'Voyeur Girl',
1134 'album': 'it\'s too much love to know my dear',
1135 'release_date': '20190313',
1136 'release_year': 2019,
1139 'skip_download': True,
1143 # Youtube Music Auto-generated description
1144 # Retrieve 'artist' field from 'Artist:' in video description
1145 # when it is present on youtube music video
1146 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1148 'id': 'k0jLE7tTwjY',
1150 'title': 'Latch Feat. Sam Smith',
1151 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1152 'upload_date': '20150110',
1153 'uploader': 'Various Artists - Topic',
1154 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1155 'artist': 'Disclosure',
1156 'track': 'Latch Feat. Sam Smith',
1157 'album': 'Latch Featuring Sam Smith',
1158 'release_date': '20121008',
1159 'release_year': 2012,
1162 'skip_download': True,
1166 # Youtube Music Auto-generated description
1167 # handle multiple artists on youtube music video
1168 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1170 'id': '74qn0eJSjpA',
1172 'title': 'Eastside',
1173 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1174 'upload_date': '20180710',
1175 'uploader': 'Benny Blanco - Topic',
1176 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1177 'artist': 'benny blanco, Halsey, Khalid',
1178 'track': 'Eastside',
1179 'album': 'Eastside',
1180 'release_date': '20180713',
1181 'release_year': 2018,
1184 'skip_download': True,
1188 # Youtube Music Auto-generated description
1189 # handle youtube music video with release_year and no release_date
1190 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1192 'id': '-hcAI0g-f5M',
1194 'title': 'Put It On Me',
1195 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1196 'upload_date': '20180426',
1197 'uploader': 'Matt Maeson - Topic',
1198 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1199 'artist': 'Matt Maeson',
1200 'track': 'Put It On Me',
1201 'album': 'The Hearse',
1202 'release_date': None,
1203 'release_year': 2018,
1206 'skip_download': True,
1211 def __init__(self, *args, **kwargs):
1212 super(YoutubeIE, self).__init__(*args, **kwargs)
1213 self._player_cache = {}
1215 def report_video_info_webpage_download(self, video_id):
1216 """Report attempt to download video info webpage."""
1217 self.to_screen('%s: Downloading video info webpage' % video_id)
1219 def report_information_extraction(self, video_id):
1220 """Report attempt to extract video information."""
1221 self.to_screen('%s: Extracting video information' % video_id)
1223 def report_unavailable_format(self, video_id, format):
1224 """Report extracted video URL."""
1225 self.to_screen('%s: Format %s not available' % (video_id, format))
1227 def report_rtmp_download(self):
1228 """Indicate the download will use the RTMP protocol."""
1229 self.to_screen('RTMP download detected')
1231 def _signature_cache_id(self, example_sig):
1232 """ Return a string representation of a signature """
1233 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1235 def _extract_signature_function(self, video_id, player_url, example_sig):
1237 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1240 raise ExtractorError('Cannot identify player %r' % player_url)
1241 player_type = id_m.group('ext')
1242 player_id = id_m.group('id')
1244 # Read from filesystem cache
1245 func_id = '%s_%s_%s' % (
1246 player_type, player_id, self._signature_cache_id(example_sig))
1247 assert os.path.basename(func_id) == func_id
1249 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1250 if cache_spec is not None:
1251 return lambda s: ''.join(s[i] for i in cache_spec)
1254 'Downloading player %s' % player_url
1255 if self._downloader.params.get('verbose') else
1256 'Downloading %s player %s' % (player_type, player_id)
1258 if player_type == 'js':
1259 code = self._download_webpage(
1260 player_url, video_id,
1262 errnote='Download of %s failed' % player_url)
1263 res = self._parse_sig_js(code)
1264 elif player_type == 'swf':
1265 urlh = self._request_webpage(
1266 player_url, video_id,
1268 errnote='Download of %s failed' % player_url)
1270 res = self._parse_sig_swf(code)
1272 assert False, 'Invalid player type %r' % player_type
1274 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1275 cache_res = res(test_string)
1276 cache_spec = [ord(c) for c in cache_res]
1278 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1281 def _print_sig_code(self, func, example_sig):
1282 def gen_sig_code(idxs):
1283 def _genslice(start, end, step):
1284 starts = '' if start == 0 else str(start)
1285 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1286 steps = '' if step == 1 else (':%d' % step)
1287 return 's[%s%s%s]' % (starts, ends, steps)
1290 # Quelch pyflakes warnings - start will be set when step is set
1291 start = '(Never used)'
1292 for i, prev in zip(idxs[1:], idxs[:-1]):
1293 if step is not None:
1294 if i - prev == step:
1296 yield _genslice(start, prev, step)
1299 if i - prev in [-1, 1]:
1304 yield 's[%d]' % prev
1308 yield _genslice(start, i, step)
1310 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1311 cache_res = func(test_string)
1312 cache_spec = [ord(c) for c in cache_res]
1313 expr_code = ' + '.join(gen_sig_code(cache_spec))
1314 signature_id_tuple = '(%s)' % (
1315 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1316 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1317 ' return %s\n') % (signature_id_tuple, expr_code)
1318 self.to_screen('Extracted signature function:\n' + code)
1320 def _parse_sig_js(self, jscode):
1321 funcname = self._search_regex(
1322 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1323 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1324 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1326 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1327 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1328 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1329 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1330 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1331 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1332 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1333 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1334 jscode, 'Initial JS player signature function name', group='sig')
1336 jsi = JSInterpreter(jscode)
1337 initial_function = jsi.extract_function(funcname)
1338 return lambda s: initial_function([s])
1340 def _parse_sig_swf(self, file_contents):
1341 swfi = SWFInterpreter(file_contents)
1342 TARGET_CLASSNAME = 'SignatureDecipher'
1343 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1344 initial_function = swfi.extract_function(searched_class, 'decipher')
1345 return lambda s: initial_function([s])
1347 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1348 """Turn the encrypted s field into a working signature"""
1350 if player_url is None:
1351 raise ExtractorError('Cannot decrypt signature without player_url')
1353 if player_url.startswith('//'):
1354 player_url = 'https:' + player_url
1355 elif not re.match(r'https?://', player_url):
1356 player_url = compat_urlparse.urljoin(
1357 'https://www.youtube.com', player_url)
1359 player_id = (player_url, self._signature_cache_id(s))
1360 if player_id not in self._player_cache:
1361 func = self._extract_signature_function(
1362 video_id, player_url, s
1364 self._player_cache[player_id] = func
1365 func = self._player_cache[player_id]
1366 if self._downloader.params.get('youtube_print_sig_code'):
1367 self._print_sig_code(func, s)
1369 except Exception as e:
1370 tb = traceback.format_exc()
1371 raise ExtractorError(
1372 'Signature extraction failed: ' + tb, cause=e)
1374 def _get_subtitles(self, video_id, webpage):
1376 subs_doc = self._download_xml(
1377 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1378 video_id, note=False)
1379 except ExtractorError as err:
1380 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1384 for track in subs_doc.findall('track'):
1385 lang = track.attrib['lang_code']
1386 if lang in sub_lang_list:
1389 for ext in self._SUBTITLE_FORMATS:
1390 params = compat_urllib_parse_urlencode({
1394 'name': track.attrib['name'].encode('utf-8'),
1396 sub_formats.append({
1397 'url': 'https://www.youtube.com/api/timedtext?' + params,
1400 sub_lang_list[lang] = sub_formats
1401 if not sub_lang_list:
1402 self._downloader.report_warning('video doesn\'t have subtitles')
1404 return sub_lang_list
1406 def _get_ytplayer_config(self, video_id, webpage):
1408 # User data may contain arbitrary character sequences that may affect
1409 # JSON extraction with regex, e.g. when '};' is contained the second
1410 # regex won't capture the whole JSON. Yet working around by trying more
1411 # concrete regex first keeping in mind proper quoted string handling
1412 # to be implemented in future that will replace this workaround (see
1413 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1414 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1415 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1416 r';ytplayer\.config\s*=\s*({.+?});',
1418 config = self._search_regex(
1419 patterns, webpage, 'ytplayer.config', default=None)
1421 return self._parse_json(
1422 uppercase_escape(config), video_id, fatal=False)
1424 def _get_automatic_captions(self, video_id, webpage):
1425 """We need the webpage for getting the captions url, pass it as an
1426 argument to speed up the process."""
1427 self.to_screen('%s: Looking for automatic captions' % video_id)
1428 player_config = self._get_ytplayer_config(video_id, webpage)
1429 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1430 if not player_config:
1431 self._downloader.report_warning(err_msg)
1434 args = player_config['args']
1435 caption_url = args.get('ttsurl')
1437 timestamp = args['timestamp']
1438 # We get the available subtitles
1439 list_params = compat_urllib_parse_urlencode({
1444 list_url = caption_url + '&' + list_params
1445 caption_list = self._download_xml(list_url, video_id)
1446 original_lang_node = caption_list.find('track')
1447 if original_lang_node is None:
1448 self._downloader.report_warning('Video doesn\'t have automatic captions')
1450 original_lang = original_lang_node.attrib['lang_code']
1451 caption_kind = original_lang_node.attrib.get('kind', '')
1454 for lang_node in caption_list.findall('target'):
1455 sub_lang = lang_node.attrib['lang_code']
1457 for ext in self._SUBTITLE_FORMATS:
1458 params = compat_urllib_parse_urlencode({
1459 'lang': original_lang,
1463 'kind': caption_kind,
1465 sub_formats.append({
1466 'url': caption_url + '&' + params,
1469 sub_lang_list[sub_lang] = sub_formats
1470 return sub_lang_list
1472 def make_captions(sub_url, sub_langs):
1473 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1474 caption_qs = compat_parse_qs(parsed_sub_url.query)
1476 for sub_lang in sub_langs:
1478 for ext in self._SUBTITLE_FORMATS:
1480 'tlang': [sub_lang],
1483 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1484 query=compat_urllib_parse_urlencode(caption_qs, True)))
1485 sub_formats.append({
1489 captions[sub_lang] = sub_formats
1492 # New captions format as of 22.06.2017
1493 player_response = args.get('player_response')
1494 if player_response and isinstance(player_response, compat_str):
1495 player_response = self._parse_json(
1496 player_response, video_id, fatal=False)
1498 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1499 base_url = renderer['captionTracks'][0]['baseUrl']
1501 for lang in renderer['translationLanguages']:
1502 lang_code = lang.get('languageCode')
1504 sub_lang_list.append(lang_code)
1505 return make_captions(base_url, sub_lang_list)
1507 # Some videos don't provide ttsurl but rather caption_tracks and
1508 # caption_translation_languages (e.g. 20LmZk1hakA)
1509 # Does not used anymore as of 22.06.2017
1510 caption_tracks = args['caption_tracks']
1511 caption_translation_languages = args['caption_translation_languages']
1512 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1514 for lang in caption_translation_languages.split(','):
1515 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1516 sub_lang = lang_qs.get('lc', [None])[0]
1518 sub_lang_list.append(sub_lang)
1519 return make_captions(caption_url, sub_lang_list)
1520 # An extractor error can be raise by the download process if there are
1521 # no automatic captions but there are subtitles
1522 except (KeyError, IndexError, ExtractorError):
1523 self._downloader.report_warning(err_msg)
1526 def _mark_watched(self, video_id, video_info, player_response):
1527 playback_url = url_or_none(try_get(
1529 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1530 video_info, lambda x: x['videostats_playback_base_url'][0]))
1531 if not playback_url:
1533 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1534 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1536 # cpn generation algorithm is reverse engineered from base.js.
1537 # In fact it works even with dummy cpn.
1538 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1539 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1545 playback_url = compat_urlparse.urlunparse(
1546 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1548 self._download_webpage(
1549 playback_url, video_id, 'Marking watched',
1550 'Unable to mark watched', fatal=False)
1553 def _extract_urls(webpage):
1554 # Embedded YouTube player
1556 unescapeHTML(mobj.group('url'))
1557 for mobj in re.finditer(r'''(?x)
1567 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1568 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1571 # lazyYT YouTube embed
1572 entries.extend(list(map(
1574 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1576 # Wordpress "YouTube Video Importer" plugin
1577 matches = re.findall(r'''(?x)<div[^>]+
1578 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1579 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1580 entries.extend(m[-1] for m in matches)
1585 def _extract_url(webpage):
1586 urls = YoutubeIE._extract_urls(webpage)
1587 return urls[0] if urls else None
1590 def extract_id(cls, url):
1591 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1593 raise ExtractorError('Invalid URL: %s' % url)
1594 video_id = mobj.group(2)
1597 def _extract_annotations(self, video_id):
1598 return self._download_webpage(
1599 'https://www.youtube.com/annotations_invideo', video_id,
1600 note='Downloading annotations',
1601 errnote='Unable to download video annotations', fatal=False,
1605 'video_id': video_id,
1609 def _extract_chapters(description, duration):
1612 chapter_lines = re.findall(
1613 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1615 if not chapter_lines:
1618 for next_num, (chapter_line, time_point) in enumerate(
1619 chapter_lines, start=1):
1620 start_time = parse_duration(time_point)
1621 if start_time is None:
1623 if start_time > duration:
1625 end_time = (duration if next_num == len(chapter_lines)
1626 else parse_duration(chapter_lines[next_num][1]))
1627 if end_time is None:
1629 if end_time > duration:
1631 if start_time > end_time:
1633 chapter_title = re.sub(
1634 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1635 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1637 'start_time': start_time,
1638 'end_time': end_time,
1639 'title': chapter_title,
1643 def _real_extract(self, url):
1644 url, smuggled_data = unsmuggle_url(url, {})
1647 'http' if self._downloader.params.get('prefer_insecure', False)
1652 parsed_url = compat_urllib_parse_urlparse(url)
1653 for component in [parsed_url.fragment, parsed_url.query]:
1654 query = compat_parse_qs(component)
1655 if start_time is None and 't' in query:
1656 start_time = parse_duration(query['t'][0])
1657 if start_time is None and 'start' in query:
1658 start_time = parse_duration(query['start'][0])
1659 if end_time is None and 'end' in query:
1660 end_time = parse_duration(query['end'][0])
1662 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1663 mobj = re.search(self._NEXT_URL_RE, url)
1665 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1666 video_id = self.extract_id(url)
1669 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1670 video_webpage = self._download_webpage(url, video_id)
1672 # Attempt to extract SWF player URL
1673 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1674 if mobj is not None:
1675 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1681 def add_dash_mpd(video_info):
1682 dash_mpd = video_info.get('dashmpd')
1683 if dash_mpd and dash_mpd[0] not in dash_mpds:
1684 dash_mpds.append(dash_mpd[0])
1686 def add_dash_mpd_pr(pl_response):
1687 dash_mpd = url_or_none(try_get(
1688 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1690 if dash_mpd and dash_mpd not in dash_mpds:
1691 dash_mpds.append(dash_mpd)
1696 def extract_view_count(v_info):
1697 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1699 def extract_token(v_info):
1700 return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
1702 player_response = {}
1705 embed_webpage = None
1706 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1708 # We simulate the access to the video from www.youtube.com/v/{video_id}
1709 # this can be viewed without login into Youtube
1710 url = proto + '://www.youtube.com/embed/%s' % video_id
1711 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1712 data = compat_urllib_parse_urlencode({
1713 'video_id': video_id,
1714 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1715 'sts': self._search_regex(
1716 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1718 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1719 video_info_webpage = self._download_webpage(
1720 video_info_url, video_id,
1721 note='Refetching age-gated info webpage',
1722 errnote='unable to download video info webpage')
1723 video_info = compat_parse_qs(video_info_webpage)
1724 add_dash_mpd(video_info)
1729 # Try looking directly into the video webpage
1730 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1732 args = ytplayer_config['args']
1733 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1734 # Convert to the same format returned by compat_parse_qs
1735 video_info = dict((k, [v]) for k, v in args.items())
1736 add_dash_mpd(video_info)
1737 # Rental video is not rented but preview is available (e.g.
1738 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1739 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1740 if not video_info and args.get('ypc_vid'):
1741 return self.url_result(
1742 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1743 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1745 sts = ytplayer_config.get('sts')
1746 if not player_response:
1747 pl_response = str_or_none(args.get('player_response'))
1749 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1750 if isinstance(pl_response, dict):
1751 player_response = pl_response
1752 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1753 add_dash_mpd_pr(player_response)
1754 # We also try looking in get_video_info since it may contain different dashmpd
1755 # URL that points to a DASH manifest with possibly different itag set (some itags
1756 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1757 # manifest pointed by get_video_info's dashmpd).
1758 # The general idea is to take a union of itags of both DASH manifests (for example
1759 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1760 self.report_video_info_webpage_download(video_id)
1761 for el in ('embedded', 'detailpage', 'vevo', ''):
1763 'video_id': video_id,
1773 video_info_webpage = self._download_webpage(
1774 '%s://www.youtube.com/get_video_info' % proto,
1775 video_id, note=False,
1776 errnote='unable to download video info webpage',
1777 fatal=False, query=query)
1778 if not video_info_webpage:
1780 get_video_info = compat_parse_qs(video_info_webpage)
1781 if not player_response:
1782 pl_response = get_video_info.get('player_response', [None])[0]
1783 if isinstance(pl_response, dict):
1784 player_response = pl_response
1785 add_dash_mpd_pr(player_response)
1786 add_dash_mpd(get_video_info)
1787 if view_count is None:
1788 view_count = extract_view_count(get_video_info)
1790 video_info = get_video_info
1791 get_token = extract_token(get_video_info)
1793 # Different get_video_info requests may report different results, e.g.
1794 # some may report video unavailability, but some may serve it without
1795 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1796 # the original webpage as well as el=info and el=embedded get_video_info
1797 # requests report video unavailability due to geo restriction while
1798 # el=detailpage succeeds and returns valid data). This is probably
1799 # due to YouTube measures against IP ranges of hosting providers.
1800 # Working around by preferring the first succeeded video_info containing
1801 # the token if no such video_info yet was found.
1802 token = extract_token(video_info)
1804 video_info = get_video_info
1807 def extract_unavailable_message():
1808 return self._html_search_regex(
1809 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1810 video_webpage, 'unavailable message', default=None)
1813 unavailable_message = extract_unavailable_message()
1814 if not unavailable_message:
1815 unavailable_message = 'Unable to extract video data'
1816 raise ExtractorError(
1817 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1819 video_details = try_get(
1820 player_response, lambda x: x['videoDetails'], dict) or {}
1823 if 'title' in video_info:
1824 video_title = video_info['title'][0]
1825 elif 'title' in player_response:
1826 video_title = video_details['title']
1828 self._downloader.report_warning('Unable to extract video title')
1832 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1833 if video_description:
1836 redir_url = compat_urlparse.urljoin(url, m.group(1))
1837 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1838 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1839 qs = compat_parse_qs(parsed_redir_url.query)
1845 description_original = video_description = re.sub(r'''(?x)
1847 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1848 (?:title|href)="([^"]+)"\s+
1849 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1853 ''', replace_url, video_description)
1854 video_description = clean_html(video_description)
1856 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1858 video_description = unescapeHTML(fd_mobj.group(1))
1860 video_description = ''
1862 if not smuggled_data.get('force_singlefeed', False):
1863 if not self._downloader.params.get('noplaylist'):
1864 multifeed_metadata_list = try_get(
1866 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1867 compat_str) or try_get(
1868 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1869 if multifeed_metadata_list:
1872 for feed in multifeed_metadata_list.split(','):
1873 # Unquote should take place before split on comma (,) since textual
1874 # fields may contain comma as well (see
1875 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1876 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1878 '_type': 'url_transparent',
1879 'ie_key': 'Youtube',
1881 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1882 {'force_singlefeed': True}),
1883 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1885 feed_ids.append(feed_data['id'][0])
1887 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1888 % (', '.join(feed_ids), video_id))
1889 return self.playlist_result(entries, video_id, video_title, video_description)
1891 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1893 if view_count is None:
1894 view_count = extract_view_count(video_info)
1895 if view_count is None and video_details:
1896 view_count = int_or_none(video_details.get('viewCount'))
1899 is_live = bool_or_none(video_details.get('isLive'))
1901 # Check for "rental" videos
1902 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1903 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1905 def _extract_filesize(media_url):
1906 return int_or_none(self._search_regex(
1907 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1909 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1910 self.report_rtmp_download()
1912 'format_id': '_rtmp',
1914 'url': video_info['conn'][0],
1915 'player_url': player_url,
1917 elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
1918 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1919 if 'rtmpe%3Dyes' in encoded_url_map:
1920 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1922 fmt_list = video_info.get('fmt_list', [''])[0]
1924 for fmt in fmt_list.split(','):
1925 spec = fmt.split('/')
1927 width_height = spec[1].split('x')
1928 if len(width_height) == 2:
1929 formats_spec[spec[0]] = {
1930 'resolution': spec[1],
1931 'width': int_or_none(width_height[0]),
1932 'height': int_or_none(width_height[1]),
1934 q = qualities(['small', 'medium', 'hd720'])
1935 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1936 if streaming_formats:
1937 for fmt in streaming_formats:
1938 itag = str_or_none(fmt.get('itag'))
1941 quality = fmt.get('quality')
1942 quality_label = fmt.get('qualityLabel') or quality
1943 formats_spec[itag] = {
1944 'asr': int_or_none(fmt.get('audioSampleRate')),
1945 'filesize': int_or_none(fmt.get('contentLength')),
1946 'format_note': quality_label,
1947 'fps': int_or_none(fmt.get('fps')),
1948 'height': int_or_none(fmt.get('height')),
1949 'quality': q(quality),
1950 # bitrate for itag 43 is always 2147483647
1951 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1952 'width': int_or_none(fmt.get('width')),
1955 for url_data_str in encoded_url_map.split(','):
1956 url_data = compat_parse_qs(url_data_str)
1957 if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
1959 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1960 # Unsupported FORMAT_STREAM_TYPE_OTF
1961 if stream_type == 3:
1963 format_id = url_data['itag'][0]
1964 url = url_data['url'][0]
1966 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1967 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1968 jsplayer_url_json = self._search_regex(
1970 embed_webpage if age_gate else video_webpage,
1971 'JS player URL (1)', default=None)
1972 if not jsplayer_url_json and not age_gate:
1973 # We need the embed website after all
1974 if embed_webpage is None:
1975 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1976 embed_webpage = self._download_webpage(
1977 embed_url, video_id, 'Downloading embed webpage')
1978 jsplayer_url_json = self._search_regex(
1979 ASSETS_RE, embed_webpage, 'JS player URL')
1981 player_url = json.loads(jsplayer_url_json)
1982 if player_url is None:
1983 player_url_json = self._search_regex(
1984 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1985 video_webpage, 'age gate player URL')
1986 player_url = json.loads(player_url_json)
1988 if 'sig' in url_data:
1989 url += '&signature=' + url_data['sig'][0]
1990 elif 's' in url_data:
1991 encrypted_sig = url_data['s'][0]
1993 if self._downloader.params.get('verbose'):
1994 if player_url is None:
1995 player_version = 'unknown'
1996 player_desc = 'unknown'
1998 if player_url.endswith('swf'):
1999 player_version = self._search_regex(
2000 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
2001 'flash player', fatal=False)
2002 player_desc = 'flash player %s' % player_version
2004 player_version = self._search_regex(
2005 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
2006 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
2008 'html5 player', fatal=False)
2009 player_desc = 'html5 player %s' % player_version
2011 parts_sizes = self._signature_cache_id(encrypted_sig)
2012 self.to_screen('{%s} signature length %s, %s' %
2013 (format_id, parts_sizes, player_desc))
2015 signature = self._decrypt_signature(
2016 encrypted_sig, video_id, player_url, age_gate)
2017 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2018 url += '&%s=%s' % (sp, signature)
2019 if 'ratebypass' not in url:
2020 url += '&ratebypass=yes'
2023 'format_id': format_id,
2025 'player_url': player_url,
2027 if format_id in self._formats:
2028 dct.update(self._formats[format_id])
2029 if format_id in formats_spec:
2030 dct.update(formats_spec[format_id])
2032 # Some itags are not included in DASH manifest thus corresponding formats will
2033 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2034 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2035 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2036 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2038 filesize = int_or_none(url_data.get(
2039 'clen', [None])[0]) or _extract_filesize(url)
2041 quality = url_data.get('quality', [None])[0]
2044 'filesize': filesize,
2045 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
2048 'fps': int_or_none(url_data.get('fps', [None])[0]),
2049 'format_note': url_data.get('quality_label', [None])[0] or quality,
2050 'quality': q(quality),
2052 for key, value in more_fields.items():
2055 type_ = url_data.get('type', [None])[0]
2057 type_split = type_.split(';')
2058 kind_ext = type_split[0].split('/')
2059 if len(kind_ext) == 2:
2061 dct['ext'] = mimetype2ext(type_split[0])
2062 if kind in ('audio', 'video'):
2064 for mobj in re.finditer(
2065 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2066 if mobj.group('key') == 'codecs':
2067 codecs = mobj.group('val')
2070 dct.update(parse_codecs(codecs))
2071 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2072 dct['downloader_options'] = {
2073 # Youtube throttles chunks >~10M
2074 'http_chunk_size': 10485760,
2079 url_or_none(try_get(
2081 lambda x: x['streamingData']['hlsManifestUrl'],
2083 or url_or_none(try_get(
2084 video_info, lambda x: x['hlsvp'][0], compat_str)))
2087 m3u8_formats = self._extract_m3u8_formats(
2088 manifest_url, video_id, 'mp4', fatal=False)
2089 for a_format in m3u8_formats:
2090 itag = self._search_regex(
2091 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2093 a_format['format_id'] = itag
2094 if itag in self._formats:
2095 dct = self._formats[itag].copy()
2096 dct.update(a_format)
2098 a_format['player_url'] = player_url
2099 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2100 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2101 formats.append(a_format)
2103 error_message = clean_html(video_info.get('reason', [None])[0])
2104 if not error_message:
2105 error_message = extract_unavailable_message()
2107 raise ExtractorError(error_message, expected=True)
2108 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2111 video_uploader = try_get(
2112 video_info, lambda x: x['author'][0],
2113 compat_str) or str_or_none(video_details.get('author'))
2115 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2117 self._downloader.report_warning('unable to extract uploader name')
2120 video_uploader_id = None
2121 video_uploader_url = None
2123 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2125 if mobj is not None:
2126 video_uploader_id = mobj.group('uploader_id')
2127 video_uploader_url = mobj.group('uploader_url')
2129 self._downloader.report_warning('unable to extract uploader nickname')
2132 str_or_none(video_details.get('channelId'))
2133 or self._html_search_meta(
2134 'channelId', video_webpage, 'channel id', default=None)
2135 or self._search_regex(
2136 r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
2137 video_webpage, 'channel id', default=None, group='id'))
2138 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2141 # We try first to get a high quality image:
2142 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2143 video_webpage, re.DOTALL)
2144 if m_thumb is not None:
2145 video_thumbnail = m_thumb.group(1)
2146 elif 'thumbnail_url' not in video_info:
2147 self._downloader.report_warning('unable to extract video thumbnail')
2148 video_thumbnail = None
2149 else: # don't panic if we can't find it
2150 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2153 upload_date = self._html_search_meta(
2154 'datePublished', video_webpage, 'upload date', default=None)
2156 upload_date = self._search_regex(
2157 [r'(?s)id="eow-date.*?>(.*?)</span>',
2158 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2159 video_webpage, 'upload date', default=None)
2160 upload_date = unified_strdate(upload_date)
2162 video_license = self._html_search_regex(
2163 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2164 video_webpage, 'license', default=None)
2166 m_music = re.search(
2168 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2176 \bhref=["\']/red[^>]*>| # drop possible
2177 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2184 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2185 video_creator = clean_html(m_music.group('creator'))
2187 video_alt_title = video_creator = None
2189 def extract_meta(field):
2190 return self._html_search_regex(
2191 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2192 video_webpage, field, default=None)
2194 track = extract_meta('Song')
2195 artist = extract_meta('Artist')
2196 album = extract_meta('Album')
2198 # Youtube Music Auto-generated description
2199 release_date = release_year = None
2200 if video_description:
2201 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)
2204 track = mobj.group('track').strip()
2206 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2208 album = mobj.group('album'.strip())
2209 release_year = mobj.group('release_year')
2210 release_date = mobj.group('release_date')
2212 release_date = release_date.replace('-', '')
2213 if not release_year:
2214 release_year = int(release_date[:4])
2216 release_year = int(release_year)
2218 m_episode = re.search(
2219 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2222 series = unescapeHTML(m_episode.group('series'))
2223 season_number = int(m_episode.group('season'))
2224 episode_number = int(m_episode.group('episode'))
2226 series = season_number = episode_number = None
2228 m_cat_container = self._search_regex(
2229 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2230 video_webpage, 'categories', default=None)
2232 category = self._html_search_regex(
2233 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2235 video_categories = None if category is None else [category]
2237 video_categories = None
2240 unescapeHTML(m.group('content'))
2241 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2243 def _extract_count(count_name):
2244 return str_to_int(self._search_regex(
2245 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2246 % re.escape(count_name),
2247 video_webpage, count_name, default=None))
2249 like_count = _extract_count('like')
2250 dislike_count = _extract_count('dislike')
2252 if view_count is None:
2253 view_count = str_to_int(self._search_regex(
2254 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2255 'view count', default=None))
2258 float_or_none(video_details.get('averageRating'))
2259 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2262 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2263 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2265 video_duration = try_get(
2266 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2267 if not video_duration:
2268 video_duration = int_or_none(video_details.get('lengthSeconds'))
2269 if not video_duration:
2270 video_duration = parse_duration(self._html_search_meta(
2271 'duration', video_webpage, 'video duration'))
2274 video_annotations = None
2275 if self._downloader.params.get('writeannotations', False):
2276 video_annotations = self._extract_annotations(video_id)
2278 chapters = self._extract_chapters(description_original, video_duration)
2280 # Look for the DASH manifest
2281 if self._downloader.params.get('youtube_include_dash_manifest', True):
2282 dash_mpd_fatal = True
2283 for mpd_url in dash_mpds:
2286 def decrypt_sig(mobj):
2288 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2289 return '/signature/%s' % dec_s
2291 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2293 for df in self._extract_mpd_formats(
2294 mpd_url, video_id, fatal=dash_mpd_fatal,
2295 formats_dict=self._formats):
2296 if not df.get('filesize'):
2297 df['filesize'] = _extract_filesize(df['url'])
2298 # Do not overwrite DASH format found in some previous DASH manifest
2299 if df['format_id'] not in dash_formats:
2300 dash_formats[df['format_id']] = df
2301 # Additional DASH manifests may end up in HTTP Error 403 therefore
2302 # allow them to fail without bug report message if we already have
2303 # some DASH manifest succeeded. This is temporary workaround to reduce
2304 # burst of bug reports until we figure out the reason and whether it
2305 # can be fixed at all.
2306 dash_mpd_fatal = False
2307 except (ExtractorError, KeyError) as e:
2308 self.report_warning(
2309 'Skipping DASH manifest: %r' % e, video_id)
2311 # Remove the formats we found through non-DASH, they
2312 # contain less info and it can be wrong, because we use
2313 # fixed values (for example the resolution). See
2314 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2316 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2317 formats.extend(dash_formats.values())
2319 # Check for malformed aspect ratio
2320 stretched_m = re.search(
2321 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2324 w = float(stretched_m.group('w'))
2325 h = float(stretched_m.group('h'))
2326 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2327 # We will only process correct ratios.
2331 if f.get('vcodec') != 'none':
2332 f['stretched_ratio'] = ratio
2335 token = extract_token(video_info)
2337 if 'reason' in video_info:
2338 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2339 regions_allowed = self._html_search_meta(
2340 'regionsAllowed', video_webpage, default=None)
2341 countries = regions_allowed.split(',') if regions_allowed else None
2342 self.raise_geo_restricted(
2343 msg=video_info['reason'][0], countries=countries)
2344 reason = video_info['reason'][0]
2345 if 'Invalid parameters' in reason:
2346 unavailable_message = extract_unavailable_message()
2347 if unavailable_message:
2348 reason = unavailable_message
2349 raise ExtractorError(
2350 'YouTube said: %s' % reason,
2351 expected=True, video_id=video_id)
2353 raise ExtractorError(
2354 '"token" parameter not in video info for unknown reason',
2357 if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
2358 raise ExtractorError('This video is DRM protected.', expected=True)
2360 self._sort_formats(formats)
2362 self.mark_watched(video_id, video_info, player_response)
2366 'uploader': video_uploader,
2367 'uploader_id': video_uploader_id,
2368 'uploader_url': video_uploader_url,
2369 'channel_id': channel_id,
2370 'channel_url': channel_url,
2371 'upload_date': upload_date,
2372 'license': video_license,
2373 'creator': video_creator or artist,
2374 'title': video_title,
2375 'alt_title': video_alt_title or track,
2376 'thumbnail': video_thumbnail,
2377 'description': video_description,
2378 'categories': video_categories,
2380 'subtitles': video_subtitles,
2381 'automatic_captions': automatic_captions,
2382 'duration': video_duration,
2383 'age_limit': 18 if age_gate else 0,
2384 'annotations': video_annotations,
2385 'chapters': chapters,
2386 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2387 'view_count': view_count,
2388 'like_count': like_count,
2389 'dislike_count': dislike_count,
2390 'average_rating': average_rating,
2393 'start_time': start_time,
2394 'end_time': end_time,
2396 'season_number': season_number,
2397 'episode_number': episode_number,
2401 'release_date': release_date,
2402 'release_year': release_year,
2406 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2407 IE_DESC = 'YouTube.com playlists'
2408 _VALID_URL = r"""(?x)(?:
2418 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2419 \? (?:.*?[&;])*? (?:p|a|list)=
2422 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2425 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2426 # Top tracks, they can also include dots
2432 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2433 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2434 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2435 IE_NAME = 'youtube:playlist'
2437 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2439 'title': 'ytdl test PL',
2440 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2442 'playlist_count': 3,
2444 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2446 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2447 'title': 'YDL_Empty_List',
2449 'playlist_count': 0,
2450 'skip': 'This playlist is private',
2452 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2453 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2455 'title': '29C3: Not my department',
2456 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2458 'playlist_count': 95,
2460 'note': 'issue #673',
2461 'url': 'PLBB231211A4F62143',
2463 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2464 'id': 'PLBB231211A4F62143',
2466 'playlist_mincount': 26,
2468 'note': 'Large playlist',
2469 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2471 'title': 'Uploads from Cauchemar',
2472 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2474 'playlist_mincount': 799,
2476 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2478 'title': 'YDL_safe_search',
2479 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2481 'playlist_count': 2,
2482 'skip': 'This playlist is private',
2485 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2486 'playlist_count': 4,
2489 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2492 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2493 'playlist_mincount': 485,
2495 'title': '2017 華語最新單曲 (2/24更新)',
2496 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2499 'note': 'Embedded SWF player',
2500 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2501 'playlist_count': 4,
2504 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2507 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2508 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2510 'title': 'Uploads from Interstellar Movie',
2511 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2513 'playlist_mincount': 21,
2515 # Playlist URL that does not actually serve a playlist
2516 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2518 'id': 'FqZTN594JQw',
2520 'title': "Smiley's People 01 detective, Adventure Series, Action",
2521 'uploader': 'STREEM',
2522 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2523 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2524 'upload_date': '20150526',
2525 'license': 'Standard YouTube License',
2526 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2527 'categories': ['People & Blogs'],
2531 'dislike_count': int,
2534 'skip_download': True,
2536 'add_ie': [YoutubeIE.ie_key()],
2538 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2540 'id': 'yeWKywCrFtk',
2542 'title': 'Small Scale Baler and Braiding Rugs',
2543 'uploader': 'Backus-Page House Museum',
2544 'uploader_id': 'backuspagemuseum',
2545 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2546 'upload_date': '20161008',
2547 'license': 'Standard YouTube License',
2548 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2549 'categories': ['Nonprofits & Activism'],
2552 'dislike_count': int,
2556 'skip_download': True,
2559 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2560 'only_matching': True,
2562 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2563 'only_matching': True,
2565 # music album playlist
2566 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2567 'only_matching': True,
2569 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2570 'only_matching': True,
2573 def _real_initialize(self):
2576 def _extract_mix(self, playlist_id):
2577 # The mixes are generated from a single video
2578 # the id of the playlist is just 'RD' + video_id
2580 last_id = playlist_id[-11:]
2581 for n in itertools.count(1):
2582 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2583 webpage = self._download_webpage(
2584 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2585 new_ids = orderedSet(re.findall(
2586 r'''(?xs)data-video-username=".*?".*?
2587 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2589 # Fetch new pages until all the videos are repeated, it seems that
2590 # there are always 51 unique videos.
2591 new_ids = [_id for _id in new_ids if _id not in ids]
2597 url_results = self._ids_to_results(ids)
2599 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2601 search_title('playlist-title')
2602 or search_title('title long-title')
2603 or search_title('title'))
2604 title = clean_html(title_span)
2606 return self.playlist_result(url_results, playlist_id, title)
2608 def _extract_playlist(self, playlist_id):
2609 url = self._TEMPLATE_URL % playlist_id
2610 page = self._download_webpage(url, playlist_id)
2612 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2613 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2614 match = match.strip()
2615 # Check if the playlist exists or is private
2616 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2618 reason = mobj.group('reason')
2619 message = 'This playlist %s' % reason
2620 if 'private' in reason:
2621 message += ', use --username or --netrc to access it'
2623 raise ExtractorError(message, expected=True)
2624 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2625 raise ExtractorError(
2626 'Invalid parameters. Maybe URL is incorrect.',
2628 elif re.match(r'[^<]*Choose your language[^<]*', match):
2631 self.report_warning('Youtube gives an alert message: ' + match)
2633 playlist_title = self._html_search_regex(
2634 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2635 page, 'title', default=None)
2637 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2638 uploader = self._search_regex(
2639 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2640 page, 'uploader', default=None)
2642 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2645 uploader_id = mobj.group('uploader_id')
2646 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2648 uploader_id = uploader_url = None
2652 if not playlist_title:
2654 # Some playlist URLs don't actually serve a playlist (e.g.
2655 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2656 next(self._entries(page, playlist_id))
2657 except StopIteration:
2660 playlist = self.playlist_result(
2661 self._entries(page, playlist_id), playlist_id, playlist_title)
2663 'uploader': uploader,
2664 'uploader_id': uploader_id,
2665 'uploader_url': uploader_url,
2668 return has_videos, playlist
2670 def _check_download_just_video(self, url, playlist_id):
2671 # Check if it's a video-specific URL
2672 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2673 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2674 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2675 'video id', default=None)
2677 if self._downloader.params.get('noplaylist'):
2678 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2679 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2681 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2682 return video_id, None
2685 def _real_extract(self, url):
2686 # Extract playlist id
2687 mobj = re.match(self._VALID_URL, url)
2689 raise ExtractorError('Invalid URL: %s' % url)
2690 playlist_id = mobj.group(1) or mobj.group(2)
2692 video_id, video = self._check_download_just_video(url, playlist_id)
2696 if playlist_id.startswith(('RD', 'UL', 'PU')):
2697 # Mixes require a custom extraction process
2698 return self._extract_mix(playlist_id)
2700 has_videos, playlist = self._extract_playlist(playlist_id)
2701 if has_videos or not video_id:
2704 # Some playlist URLs don't actually serve a playlist (see
2705 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2706 # Fallback to plain video extraction if there is a video id
2707 # along with playlist id.
2708 return self.url_result(video_id, 'Youtube', video_id=video_id)
2711 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2712 IE_DESC = 'YouTube.com channels'
2713 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2714 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2715 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2716 IE_NAME = 'youtube:channel'
2718 'note': 'paginated channel',
2719 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2720 'playlist_mincount': 91,
2722 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2723 'title': 'Uploads from lex will',
2726 'note': 'Age restricted channel',
2727 # from https://www.youtube.com/user/DeusExOfficial
2728 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2729 'playlist_mincount': 64,
2731 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2732 'title': 'Uploads from Deus Ex',
2735 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2736 'only_matching': True,
2740 def suitable(cls, url):
2741 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2742 else super(YoutubeChannelIE, cls).suitable(url))
2744 def _build_template_url(self, url, channel_id):
2745 return self._TEMPLATE_URL % channel_id
2747 def _real_extract(self, url):
2748 channel_id = self._match_id(url)
2750 url = self._build_template_url(url, channel_id)
2752 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2753 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2754 # otherwise fallback on channel by page extraction
2755 channel_page = self._download_webpage(
2756 url + '?view=57', channel_id,
2757 'Downloading channel page', fatal=False)
2758 if channel_page is False:
2759 channel_playlist_id = False
2761 channel_playlist_id = self._html_search_meta(
2762 'channelId', channel_page, 'channel id', default=None)
2763 if not channel_playlist_id:
2764 channel_url = self._html_search_meta(
2765 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2766 channel_page, 'channel url', default=None)
2768 channel_playlist_id = self._search_regex(
2769 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2770 channel_url, 'channel id', default=None)
2771 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2772 playlist_id = 'UU' + channel_playlist_id[2:]
2773 return self.url_result(
2774 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2776 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2777 autogenerated = re.search(r'''(?x)
2779 channel-header-autogenerated-label|
2780 yt-channel-title-autogenerated
2781 )[^"]*"''', channel_page) is not None
2784 # The videos are contained in a single page
2785 # the ajax pages can't be used, they are empty
2788 video_id, 'Youtube', video_id=video_id,
2789 video_title=video_title)
2790 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2791 return self.playlist_result(entries, channel_id)
2794 next(self._entries(channel_page, channel_id))
2795 except StopIteration:
2796 alert_message = self._html_search_regex(
2797 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2798 channel_page, 'alert', default=None, group='alert')
2800 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2802 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2805 class YoutubeUserIE(YoutubeChannelIE):
2806 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2807 _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_-]+)'
2808 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2809 IE_NAME = 'youtube:user'
2812 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2813 'playlist_mincount': 320,
2815 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2816 'title': 'Uploads from The Linux Foundation',
2819 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2820 # but not https://www.youtube.com/user/12minuteathlete/videos
2821 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2822 'playlist_mincount': 249,
2824 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2825 'title': 'Uploads from 12 Minute Athlete',
2828 'url': 'ytuser:phihag',
2829 'only_matching': True,
2831 'url': 'https://www.youtube.com/c/gametrailers',
2832 'only_matching': True,
2834 'url': 'https://www.youtube.com/gametrailers',
2835 'only_matching': True,
2837 # This channel is not available, geo restricted to JP
2838 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2839 'only_matching': True,
2843 def suitable(cls, url):
2844 # Don't return True if the url can be extracted with other youtube
2845 # extractor, the regex would is too permissive and it would match.
2846 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2847 if any(ie.suitable(url) for ie in other_yt_ies):
2850 return super(YoutubeUserIE, cls).suitable(url)
2852 def _build_template_url(self, url, channel_id):
2853 mobj = re.match(self._VALID_URL, url)
2854 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2857 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2858 IE_DESC = 'YouTube.com live streams'
2859 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2860 IE_NAME = 'youtube:live'
2863 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2865 'id': 'a48o2S1cPoo',
2867 'title': 'The Young Turks - Live Main Show',
2868 'uploader': 'The Young Turks',
2869 'uploader_id': 'TheYoungTurks',
2870 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2871 'upload_date': '20150715',
2872 'license': 'Standard YouTube License',
2873 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2874 'categories': ['News & Politics'],
2875 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2877 'dislike_count': int,
2880 'skip_download': True,
2883 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2884 'only_matching': True,
2886 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2887 'only_matching': True,
2889 'url': 'https://www.youtube.com/TheYoungTurks/live',
2890 'only_matching': True,
2893 def _real_extract(self, url):
2894 mobj = re.match(self._VALID_URL, url)
2895 channel_id = mobj.group('id')
2896 base_url = mobj.group('base_url')
2897 webpage = self._download_webpage(url, channel_id, fatal=False)
2899 page_type = self._og_search_property(
2900 'type', webpage, 'page type', default='')
2901 video_id = self._html_search_meta(
2902 'videoId', webpage, 'video id', default=None)
2903 if page_type.startswith('video') and video_id and re.match(
2904 r'^[0-9A-Za-z_-]{11}$', video_id):
2905 return self.url_result(video_id, YoutubeIE.ie_key())
2906 return self.url_result(base_url)
2909 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2910 IE_DESC = 'YouTube.com user/channel playlists'
2911 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2912 IE_NAME = 'youtube:playlists'
2915 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2916 'playlist_mincount': 4,
2918 'id': 'ThirstForScience',
2919 'title': 'Thirst for Science',
2922 # with "Load more" button
2923 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2924 'playlist_mincount': 70,
2927 'title': 'Игорь Клейнер',
2930 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2931 'playlist_mincount': 17,
2933 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2934 'title': 'Chem Player',
2939 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2940 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2943 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2944 IE_DESC = 'YouTube.com searches'
2945 # there doesn't appear to be a real limit, for example if you search for
2946 # 'python' you get more than 8.000.000 results
2947 _MAX_RESULTS = float('inf')
2948 IE_NAME = 'youtube:search'
2949 _SEARCH_KEY = 'ytsearch'
2950 _EXTRA_QUERY_ARGS = {}
2953 def _get_n_results(self, query, n):
2954 """Get a specified number of results for a query"""
2960 'search_query': query.encode('utf-8'),
2962 url_query.update(self._EXTRA_QUERY_ARGS)
2963 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2965 for pagenum in itertools.count(1):
2966 data = self._download_json(
2967 result_url, video_id='query "%s"' % query,
2968 note='Downloading page %s' % pagenum,
2969 errnote='Unable to download API page',
2970 query={'spf': 'navigate'})
2971 html_content = data[1]['body']['content']
2973 if 'class="search-message' in html_content:
2974 raise ExtractorError(
2975 '[youtube] No video results', expected=True)
2977 new_videos = list(self._process_page(html_content))
2978 videos += new_videos
2979 if not new_videos or len(videos) > limit:
2981 next_link = self._html_search_regex(
2982 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2983 html_content, 'next link', default=None)
2984 if next_link is None:
2986 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2990 return self.playlist_result(videos, query)
2993 class YoutubeSearchDateIE(YoutubeSearchIE):
2994 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2995 _SEARCH_KEY = 'ytsearchdate'
2996 IE_DESC = 'YouTube.com searches, newest videos first'
2997 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
3000 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
3001 IE_DESC = 'YouTube.com search URLs'
3002 IE_NAME = 'youtube:search_url'
3003 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3005 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3006 'playlist_mincount': 5,
3008 'title': 'youtube-dl test video',
3011 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3012 'only_matching': True,
3015 def _real_extract(self, url):
3016 mobj = re.match(self._VALID_URL, url)
3017 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3018 webpage = self._download_webpage(url, query)
3019 return self.playlist_result(self._process_page(webpage), playlist_title=query)
3022 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3023 IE_DESC = 'YouTube.com (multi-season) shows'
3024 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3025 IE_NAME = 'youtube:show'
3027 'url': 'https://www.youtube.com/show/airdisasters',
3028 'playlist_mincount': 5,
3030 'id': 'airdisasters',
3031 'title': 'Air Disasters',
3035 def _real_extract(self, url):
3036 playlist_id = self._match_id(url)
3037 return super(YoutubeShowIE, self)._real_extract(
3038 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3041 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3043 Base class for feed extractors
3044 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3046 _LOGIN_REQUIRED = True
3050 return 'youtube:%s' % self._FEED_NAME
3052 def _real_initialize(self):
3055 def _entries(self, page):
3056 # The extraction process is the same as for playlists, but the regex
3057 # for the video ids doesn't contain an index
3059 more_widget_html = content_html = page
3060 for page_num in itertools.count(1):
3061 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3063 # 'recommended' feed has infinite 'load more' and each new portion spins
3064 # the same videos in (sometimes) slightly different order, so we'll check
3065 # for unicity and break when portion has no new videos
3066 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3072 for entry in self._ids_to_results(new_ids):
3075 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3079 more = self._download_json(
3080 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3081 'Downloading page #%s' % page_num,
3082 transform_source=uppercase_escape)
3083 content_html = more['content_html']
3084 more_widget_html = more['load_more_widget_html']
3086 def _real_extract(self, url):
3087 page = self._download_webpage(
3088 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3089 self._PLAYLIST_TITLE)
3090 return self.playlist_result(
3091 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3094 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3095 IE_NAME = 'youtube:watchlater'
3096 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3097 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3100 'url': 'https://www.youtube.com/playlist?list=WL',
3101 'only_matching': True,
3103 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3104 'only_matching': True,
3107 def _real_extract(self, url):
3108 _, video = self._check_download_just_video(url, 'WL')
3111 _, playlist = self._extract_playlist('WL')
3115 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3116 IE_NAME = 'youtube:favorites'
3117 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3118 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3119 _LOGIN_REQUIRED = True
3121 def _real_extract(self, url):
3122 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3123 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3124 return self.url_result(playlist_id, 'YoutubePlaylist')
3127 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3128 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3129 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3130 _FEED_NAME = 'recommended'
3131 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3134 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3135 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3136 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3137 _FEED_NAME = 'subscriptions'
3138 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3141 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3142 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3143 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3144 _FEED_NAME = 'history'
3145 _PLAYLIST_TITLE = 'Youtube History'
3148 class YoutubeTruncatedURLIE(InfoExtractor):
3149 IE_NAME = 'youtube:truncated_url'
3150 IE_DESC = False # Do not list
3151 _VALID_URL = r'''(?x)
3153 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3156 annotation_id=annotation_[^&]+|
3162 attribution_link\?a=[^&]+
3168 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3169 'only_matching': True,
3171 'url': 'https://www.youtube.com/watch?',
3172 'only_matching': True,
3174 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3175 'only_matching': True,
3177 'url': 'https://www.youtube.com/watch?feature=foo',
3178 'only_matching': True,
3180 'url': 'https://www.youtube.com/watch?hl=en-GB',
3181 'only_matching': True,
3183 'url': 'https://www.youtube.com/watch?t=2372',
3184 'only_matching': True,
3187 def _real_extract(self, url):
3188 raise ExtractorError(
3189 'Did you forget to quote the URL? Remember that & is a meta '
3190 'character in most shells, so you want to put the URL in quotes, '
3192 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3193 ' or simply youtube-dl BaW_jenozKc .',
3197 class YoutubeTruncatedIDIE(InfoExtractor):
3198 IE_NAME = 'youtube:truncated_id'
3199 IE_DESC = False # Do not list
3200 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3203 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3204 'only_matching': True,
3207 def _real_extract(self, url):
3208 video_id = self._match_id(url)
3209 raise ExtractorError(
3210 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),