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,
37 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|PU|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_impl(self, video_re, page, ids_in_page, titles_in_page):
328 for mobj in re.finditer(video_re, page):
329 # The link with index 0 is not the first video of the playlist (not sure if still actual)
330 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
332 video_id = mobj.group('id')
333 video_title = unescapeHTML(
334 mobj.group('title')) if 'title' in mobj.groupdict() else None
336 video_title = video_title.strip()
337 if video_title == '► Play all':
340 idx = ids_in_page.index(video_id)
341 if video_title and not titles_in_page[idx]:
342 titles_in_page[idx] = video_title
344 ids_in_page.append(video_id)
345 titles_in_page.append(video_title)
347 def extract_videos_from_page(self, page):
350 self.extract_videos_from_page_impl(
351 self._VIDEO_RE, page, ids_in_page, titles_in_page)
352 return zip(ids_in_page, titles_in_page)
355 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
356 def _process_page(self, content):
357 for playlist_id in orderedSet(re.findall(
358 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
360 yield self.url_result(
361 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
363 def _real_extract(self, url):
364 playlist_id = self._match_id(url)
365 webpage = self._download_webpage(url, playlist_id)
366 title = self._og_search_title(webpage, fatal=False)
367 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
370 class YoutubeIE(YoutubeBaseInfoExtractor):
371 IE_DESC = 'YouTube.com'
372 _VALID_URL = r"""(?x)^
374 (?:https?://|//) # http(s):// or protocol-independent URL
375 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie|kids)?\.com/|
376 (?:www\.)?deturl\.com/www\.youtube\.com/|
377 (?:www\.)?pwnyoutube\.com/|
378 (?:www\.)?hooktube\.com/|
379 (?:www\.)?yourepeat\.com/|
380 tube\.majestyc\.net/|
381 # Invidious instances taken from https://github.com/omarroth/invidious/wiki/Invidious-Instances
382 (?:(?:www|dev)\.)?invidio\.us/|
383 (?:(?:www|no)\.)?invidiou\.sh/|
384 (?:(?:www|fi|de)\.)?invidious\.snopyta\.org/|
385 (?:www\.)?invidious\.kabi\.tk/|
386 (?:www\.)?invidious\.13ad\.de/|
387 (?:www\.)?invidious\.mastodon\.host/|
388 (?:www\.)?invidious\.nixnet\.xyz/|
389 (?:www\.)?invidious\.drycat\.fr/|
390 (?:www\.)?tube\.poal\.co/|
391 (?:www\.)?vid\.wxzm\.sx/|
392 (?:www\.)?yt\.elukerio\.org/|
393 (?:www\.)?yt\.lelux\.fi/|
394 (?:www\.)?kgg2m7yk5aybusll\.onion/|
395 (?:www\.)?qklhadlycap4cnod\.onion/|
396 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
397 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
398 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
399 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
400 (?:www\.)?owxfohz4kjyv25fvlqilyxast7inivgiktls3th44jhk3ej3i7ya\.b32\.i2p/|
401 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
402 (?:.*?\#/)? # handle anchor (#/) redirect urls
403 (?: # the various things that can precede the ID:
404 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
405 |(?: # or the v= param in all its forms
406 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
407 (?:\?|\#!?) # the params delimiter ? or # or #!
408 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
413 youtu\.be| # just youtu.be/xxxx
414 vid\.plus| # or vid.plus/xxxx
415 zwearz\.com/watch| # or zwearz.com/watch/xxxx
417 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
419 )? # all until now is optional -> you can pass the naked ID
420 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
423 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
424 WL # WL are handled by the watch later IE
427 (?(1).+)? # if we found the ID, everything can follow
428 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
429 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
431 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
432 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
433 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
434 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
435 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
436 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
437 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
438 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
439 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
440 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
441 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
442 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
443 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
444 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
445 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
446 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
447 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
448 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
452 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
453 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
454 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
455 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
456 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
457 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
458 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
460 # Apple HTTP Live Streaming
461 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
462 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
463 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
464 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
465 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
466 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
467 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
468 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
471 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
472 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
473 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
474 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
475 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
476 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
477 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
478 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
479 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
480 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
481 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
482 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
485 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
486 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
487 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
488 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
489 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
490 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
491 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
494 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
495 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
496 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
497 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
498 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
499 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
500 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
501 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
502 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
503 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
504 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
505 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
506 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
507 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
508 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
509 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
510 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
511 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
512 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
513 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
514 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
515 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
518 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
519 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
521 # Dash webm audio with opus inside
522 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
523 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
524 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
527 '_rtmp': {'protocol': 'rtmp'},
529 # av01 video only formats sometimes served with "unknown" codecs
530 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
531 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
532 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
533 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
535 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
542 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
546 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
547 'uploader': 'Philipp Hagemeister',
548 'uploader_id': 'phihag',
549 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
550 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
551 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
552 'upload_date': '20121002',
553 '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 .',
554 'categories': ['Science & Technology'],
555 'tags': ['youtube-dl'],
559 'dislike_count': int,
565 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
566 'note': 'Test generic use_cipher_signature video (#897)',
570 'upload_date': '20120506',
571 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
572 'alt_title': 'I Love It (feat. Charli XCX)',
573 'description': 'md5:19a2f98d9032b9311e686ed039564f63',
574 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
575 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
576 'iconic ep', 'iconic', 'love', 'it'],
578 'uploader': 'Icona Pop',
579 'uploader_id': 'IconaPop',
580 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
581 'creator': 'Icona Pop',
582 'track': 'I Love It (feat. Charli XCX)',
583 'artist': 'Icona Pop',
587 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
588 'note': 'Test VEVO video with age protection (#956)',
592 'upload_date': '20130703',
593 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
594 'alt_title': 'Tunnel Vision',
595 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
597 'uploader': 'justintimberlakeVEVO',
598 'uploader_id': 'justintimberlakeVEVO',
599 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
600 'creator': 'Justin Timberlake',
601 'track': 'Tunnel Vision',
602 'artist': 'Justin Timberlake',
607 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
608 'note': 'Embed-only video (#1746)',
612 'upload_date': '20120608',
613 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
614 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
615 'uploader': 'SET India',
616 'uploader_id': 'setindia',
617 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
622 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
623 'note': 'Use the first video ID in the URL',
627 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
628 'uploader': 'Philipp Hagemeister',
629 'uploader_id': 'phihag',
630 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
631 'upload_date': '20121002',
632 '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 .',
633 'categories': ['Science & Technology'],
634 'tags': ['youtube-dl'],
638 'dislike_count': int,
641 'skip_download': True,
645 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
646 'note': '256k DASH audio (format 141) via DASH manifest',
650 'upload_date': '20121002',
651 'uploader_id': '8KVIDEO',
652 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
654 'uploader': '8KVIDEO',
655 'title': 'UHDTV TEST 8K VIDEO.mp4'
658 'youtube_include_dash_manifest': True,
661 'skip': 'format 141 not served anymore',
663 # DASH manifest with encrypted signature
665 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
669 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
670 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
672 'uploader': 'AfrojackVEVO',
673 'uploader_id': 'AfrojackVEVO',
674 'upload_date': '20131011',
677 'youtube_include_dash_manifest': True,
678 'format': '141/bestaudio[ext=m4a]',
681 # JS player signature function name containing $
683 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
687 'title': 'Taylor Swift - Shake It Off',
688 'description': 'md5:307195cd21ff7fa352270fe884570ef0',
690 'uploader': 'TaylorSwiftVEVO',
691 'uploader_id': 'TaylorSwiftVEVO',
692 'upload_date': '20140818',
695 'youtube_include_dash_manifest': True,
696 'format': '141/bestaudio[ext=m4a]',
701 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
706 'upload_date': '20100909',
707 'uploader': 'Amazing Atheist',
708 'uploader_id': 'TheAmazingAtheist',
709 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
710 'title': 'Burning Everyone\'s Koran',
711 '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',
714 # Normal age-gate video (No vevo, embed allowed)
716 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
720 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
721 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
723 'uploader': 'The Witcher',
724 'uploader_id': 'WitcherGame',
725 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
726 'upload_date': '20140605',
730 # Age-gate video with encrypted signature
732 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
736 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
737 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
739 'uploader': 'LloydVEVO',
740 'uploader_id': 'LloydVEVO',
741 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
742 'upload_date': '20110629',
746 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
747 # YouTube Red ad is not captured for creator
749 'url': '__2ABJjxzNo',
754 'upload_date': '20100430',
755 'uploader_id': 'deadmau5',
756 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
757 'creator': 'Dada Life, deadmau5',
758 'description': 'md5:12c56784b8032162bb936a5f76d55360',
759 'uploader': 'deadmau5',
760 'title': 'Deadmau5 - Some Chords (HD)',
761 'alt_title': 'This Machine Kills Some Chords',
763 'expected_warnings': [
764 'DASH manifest missing',
767 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
769 'url': 'lqQg6PlCWgI',
774 'upload_date': '20150827',
775 'uploader_id': 'olympic',
776 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
777 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
778 'uploader': 'Olympic',
779 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
782 'skip_download': 'requires avconv',
787 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
791 'stretched_ratio': 16 / 9.,
793 'upload_date': '20110310',
794 'uploader_id': 'AllenMeow',
795 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
796 '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',
798 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
801 # url_encoded_fmt_stream_map is empty string
803 'url': 'qEJwOuvDf7I',
807 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
809 'upload_date': '20150404',
810 'uploader_id': 'spbelect',
811 'uploader': 'Наблюдатели Петербурга',
814 'skip_download': 'requires avconv',
816 'skip': 'This live event has ended.',
818 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
820 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
824 'title': 'md5:7b81415841e02ecd4313668cde88737a',
825 'description': 'md5:116377fd2963b81ec4ce64b542173306',
827 'upload_date': '20150625',
828 'uploader_id': 'dorappi2000',
829 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
830 'uploader': 'dorappi2000',
831 'formats': 'mincount:31',
833 'skip': 'not actual anymore',
835 # DASH manifest with segment_list
837 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
838 'md5': '8ce563a1d667b599d21064e982ab9e31',
842 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
843 'uploader': 'Airtek',
844 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
845 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
846 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
849 'youtube_include_dash_manifest': True,
850 'format': '135', # bestvideo
852 'skip': 'This live event has ended.',
855 # Multifeed videos (multiple cameras), URL is for Main Camera
856 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
859 'title': 'teamPGP: Rocket League Noob Stream',
860 'description': 'md5:dc7872fb300e143831327f1bae3af010',
866 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
867 'description': 'md5:dc7872fb300e143831327f1bae3af010',
869 'upload_date': '20150721',
870 'uploader': 'Beer Games Beer',
871 'uploader_id': 'beergamesbeer',
872 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
873 'license': 'Standard YouTube License',
879 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
880 'description': 'md5:dc7872fb300e143831327f1bae3af010',
882 'upload_date': '20150721',
883 'uploader': 'Beer Games Beer',
884 'uploader_id': 'beergamesbeer',
885 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
886 'license': 'Standard YouTube License',
892 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
893 'description': 'md5:dc7872fb300e143831327f1bae3af010',
895 'upload_date': '20150721',
896 'uploader': 'Beer Games Beer',
897 'uploader_id': 'beergamesbeer',
898 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
899 'license': 'Standard YouTube License',
905 'title': 'teamPGP: Rocket League Noob Stream (zim)',
906 'description': 'md5:dc7872fb300e143831327f1bae3af010',
908 'upload_date': '20150721',
909 'uploader': 'Beer Games Beer',
910 'uploader_id': 'beergamesbeer',
911 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
912 'license': 'Standard YouTube License',
916 'skip_download': True,
918 'skip': 'This video is not available.',
921 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
922 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
925 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
928 'skip': 'Not multifeed anymore',
931 'url': 'https://vid.plus/FlRa-iH7PGw',
932 'only_matching': True,
935 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
936 'only_matching': True,
939 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
940 # Also tests cut-off URL expansion in video description (see
941 # https://github.com/ytdl-org/youtube-dl/issues/1892,
942 # https://github.com/ytdl-org/youtube-dl/issues/8164)
943 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
947 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
948 'alt_title': 'Dark Walk - Position Music',
949 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
951 'upload_date': '20151119',
952 'uploader_id': 'IronSoulElf',
953 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
954 'uploader': 'IronSoulElf',
955 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
956 'track': 'Dark Walk - Position Music',
957 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
958 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
961 'skip_download': True,
965 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
966 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
967 'only_matching': True,
970 # Video with yt:stretch=17:0
971 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
975 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
976 'description': 'md5:ee18a25c350637c8faff806845bddee9',
977 'upload_date': '20151107',
978 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
979 'uploader': 'CH GAMER DROID',
982 'skip_download': True,
984 'skip': 'This video does not exist.',
987 # Video licensed under Creative Commons
988 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
992 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
993 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
995 'upload_date': '20150127',
996 'uploader_id': 'BerkmanCenter',
997 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
998 'uploader': 'The Berkman Klein Center for Internet & Society',
999 'license': 'Creative Commons Attribution license (reuse allowed)',
1002 'skip_download': True,
1006 # Channel-like uploader_url
1007 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1009 'id': 'eQcmzGIKrzg',
1011 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1012 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
1014 'upload_date': '20151119',
1015 'uploader': 'Bernie Sanders',
1016 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1017 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1018 'license': 'Creative Commons Attribution license (reuse allowed)',
1021 'skip_download': True,
1025 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1026 'only_matching': True,
1029 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1030 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1031 'only_matching': True,
1034 # Rental video preview
1035 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1037 'id': 'uGpuVWrhIzE',
1039 'title': 'Piku - Trailer',
1040 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1041 'upload_date': '20150811',
1042 'uploader': 'FlixMatrix',
1043 'uploader_id': 'FlixMatrixKaravan',
1044 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1045 'license': 'Standard YouTube License',
1048 'skip_download': True,
1050 'skip': 'This video is not available.',
1053 # YouTube Red video with episode data
1054 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1056 'id': 'iqKdEhx-dD4',
1058 'title': 'Isolation - Mind Field (Ep 1)',
1059 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1061 'upload_date': '20170118',
1062 'uploader': 'Vsauce',
1063 'uploader_id': 'Vsauce',
1064 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1065 'series': 'Mind Field',
1067 'episode_number': 1,
1070 'skip_download': True,
1072 'expected_warnings': [
1073 'Skipping DASH manifest',
1077 # The following content has been identified by the YouTube community
1078 # as inappropriate or offensive to some audiences.
1079 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1081 'id': '6SJNVb0GnPI',
1083 'title': 'Race Differences in Intelligence',
1084 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1086 'upload_date': '20140124',
1087 'uploader': 'New Century Foundation',
1088 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1089 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1092 'skip_download': True,
1097 'url': '1t24XAntNCY',
1098 'only_matching': True,
1101 # geo restricted to JP
1102 'url': 'sJL6WA-aGkQ',
1103 'only_matching': True,
1106 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1107 'only_matching': True,
1110 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1111 'only_matching': True,
1115 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1116 'only_matching': True,
1119 # Video with unsupported adaptive stream type formats
1120 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1122 'id': 'Z4Vy8R84T1U',
1124 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1125 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1127 'upload_date': '20130923',
1128 'uploader': 'Amelia Putri Harwita',
1129 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1130 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1131 'formats': 'maxcount:10',
1134 'skip_download': True,
1135 'youtube_include_dash_manifest': False,
1137 'skip': 'not actual anymore',
1140 # Youtube Music Auto-generated description
1141 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1143 'id': 'MgNrAu2pzNs',
1145 'title': 'Voyeur Girl',
1146 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1147 'upload_date': '20190312',
1148 'uploader': 'Stephen - Topic',
1149 'uploader_id': 'UC-pWHpBjdGG69N9mM2auIAA',
1150 'artist': 'Stephen',
1151 'track': 'Voyeur Girl',
1152 'album': 'it\'s too much love to know my dear',
1153 'release_date': '20190313',
1154 'release_year': 2019,
1157 'skip_download': True,
1161 # Youtube Music Auto-generated description
1162 # Retrieve 'artist' field from 'Artist:' in video description
1163 # when it is present on youtube music video
1164 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1166 'id': 'k0jLE7tTwjY',
1168 'title': 'Latch Feat. Sam Smith',
1169 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1170 'upload_date': '20150110',
1171 'uploader': 'Various Artists - Topic',
1172 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1173 'artist': 'Disclosure',
1174 'track': 'Latch Feat. Sam Smith',
1175 'album': 'Latch Featuring Sam Smith',
1176 'release_date': '20121008',
1177 'release_year': 2012,
1180 'skip_download': True,
1184 # Youtube Music Auto-generated description
1185 # handle multiple artists on youtube music video
1186 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1188 'id': '74qn0eJSjpA',
1190 'title': 'Eastside',
1191 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1192 'upload_date': '20180710',
1193 'uploader': 'Benny Blanco - Topic',
1194 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1195 'artist': 'benny blanco, Halsey, Khalid',
1196 'track': 'Eastside',
1197 'album': 'Eastside',
1198 'release_date': '20180713',
1199 'release_year': 2018,
1202 'skip_download': True,
1206 # Youtube Music Auto-generated description
1207 # handle youtube music video with release_year and no release_date
1208 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1210 'id': '-hcAI0g-f5M',
1212 'title': 'Put It On Me',
1213 'description': 'md5:f6422397c07c4c907c6638e1fee380a5',
1214 'upload_date': '20180426',
1215 'uploader': 'Matt Maeson - Topic',
1216 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1217 'artist': 'Matt Maeson',
1218 'track': 'Put It On Me',
1219 'album': 'The Hearse',
1220 'release_date': None,
1221 'release_year': 2018,
1224 'skip_download': True,
1228 'url': 'https://www.youtubekids.com/watch?v=3b8nCWDgZ6Q',
1229 'only_matching': True,
1233 def __init__(self, *args, **kwargs):
1234 super(YoutubeIE, self).__init__(*args, **kwargs)
1235 self._player_cache = {}
1237 def report_video_info_webpage_download(self, video_id):
1238 """Report attempt to download video info webpage."""
1239 self.to_screen('%s: Downloading video info webpage' % video_id)
1241 def report_information_extraction(self, video_id):
1242 """Report attempt to extract video information."""
1243 self.to_screen('%s: Extracting video information' % video_id)
1245 def report_unavailable_format(self, video_id, format):
1246 """Report extracted video URL."""
1247 self.to_screen('%s: Format %s not available' % (video_id, format))
1249 def report_rtmp_download(self):
1250 """Indicate the download will use the RTMP protocol."""
1251 self.to_screen('RTMP download detected')
1253 def _signature_cache_id(self, example_sig):
1254 """ Return a string representation of a signature """
1255 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1257 def _extract_signature_function(self, video_id, player_url, example_sig):
1259 r'.*?[-.](?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1262 raise ExtractorError('Cannot identify player %r' % player_url)
1263 player_type = id_m.group('ext')
1264 player_id = id_m.group('id')
1266 # Read from filesystem cache
1267 func_id = '%s_%s_%s' % (
1268 player_type, player_id, self._signature_cache_id(example_sig))
1269 assert os.path.basename(func_id) == func_id
1271 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1272 if cache_spec is not None:
1273 return lambda s: ''.join(s[i] for i in cache_spec)
1276 'Downloading player %s' % player_url
1277 if self._downloader.params.get('verbose') else
1278 'Downloading %s player %s' % (player_type, player_id)
1280 if player_type == 'js':
1281 code = self._download_webpage(
1282 player_url, video_id,
1284 errnote='Download of %s failed' % player_url)
1285 res = self._parse_sig_js(code)
1286 elif player_type == 'swf':
1287 urlh = self._request_webpage(
1288 player_url, video_id,
1290 errnote='Download of %s failed' % player_url)
1292 res = self._parse_sig_swf(code)
1294 assert False, 'Invalid player type %r' % player_type
1296 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1297 cache_res = res(test_string)
1298 cache_spec = [ord(c) for c in cache_res]
1300 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1303 def _print_sig_code(self, func, example_sig):
1304 def gen_sig_code(idxs):
1305 def _genslice(start, end, step):
1306 starts = '' if start == 0 else str(start)
1307 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1308 steps = '' if step == 1 else (':%d' % step)
1309 return 's[%s%s%s]' % (starts, ends, steps)
1312 # Quelch pyflakes warnings - start will be set when step is set
1313 start = '(Never used)'
1314 for i, prev in zip(idxs[1:], idxs[:-1]):
1315 if step is not None:
1316 if i - prev == step:
1318 yield _genslice(start, prev, step)
1321 if i - prev in [-1, 1]:
1326 yield 's[%d]' % prev
1330 yield _genslice(start, i, step)
1332 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1333 cache_res = func(test_string)
1334 cache_spec = [ord(c) for c in cache_res]
1335 expr_code = ' + '.join(gen_sig_code(cache_spec))
1336 signature_id_tuple = '(%s)' % (
1337 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1338 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1339 ' return %s\n') % (signature_id_tuple, expr_code)
1340 self.to_screen('Extracted signature function:\n' + code)
1342 def _parse_sig_js(self, jscode):
1343 funcname = self._search_regex(
1344 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1345 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1346 r'\b(?P<sig>[a-zA-Z0-9$]{2})\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1347 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1349 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1350 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1351 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1352 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1353 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1354 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1355 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1356 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1357 jscode, 'Initial JS player signature function name', group='sig')
1359 jsi = JSInterpreter(jscode)
1360 initial_function = jsi.extract_function(funcname)
1361 return lambda s: initial_function([s])
1363 def _parse_sig_swf(self, file_contents):
1364 swfi = SWFInterpreter(file_contents)
1365 TARGET_CLASSNAME = 'SignatureDecipher'
1366 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1367 initial_function = swfi.extract_function(searched_class, 'decipher')
1368 return lambda s: initial_function([s])
1370 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1371 """Turn the encrypted s field into a working signature"""
1373 if player_url is None:
1374 raise ExtractorError('Cannot decrypt signature without player_url')
1376 if player_url.startswith('//'):
1377 player_url = 'https:' + player_url
1378 elif not re.match(r'https?://', player_url):
1379 player_url = compat_urlparse.urljoin(
1380 'https://www.youtube.com', player_url)
1382 player_id = (player_url, self._signature_cache_id(s))
1383 if player_id not in self._player_cache:
1384 func = self._extract_signature_function(
1385 video_id, player_url, s
1387 self._player_cache[player_id] = func
1388 func = self._player_cache[player_id]
1389 if self._downloader.params.get('youtube_print_sig_code'):
1390 self._print_sig_code(func, s)
1392 except Exception as e:
1393 tb = traceback.format_exc()
1394 raise ExtractorError(
1395 'Signature extraction failed: ' + tb, cause=e)
1397 def _get_subtitles(self, video_id, webpage):
1399 subs_doc = self._download_xml(
1400 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1401 video_id, note=False)
1402 except ExtractorError as err:
1403 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1407 for track in subs_doc.findall('track'):
1408 lang = track.attrib['lang_code']
1409 if lang in sub_lang_list:
1412 for ext in self._SUBTITLE_FORMATS:
1413 params = compat_urllib_parse_urlencode({
1417 'name': track.attrib['name'].encode('utf-8'),
1419 sub_formats.append({
1420 'url': 'https://www.youtube.com/api/timedtext?' + params,
1423 sub_lang_list[lang] = sub_formats
1424 if not sub_lang_list:
1425 self._downloader.report_warning('video doesn\'t have subtitles')
1427 return sub_lang_list
1429 def _get_ytplayer_config(self, video_id, webpage):
1431 # User data may contain arbitrary character sequences that may affect
1432 # JSON extraction with regex, e.g. when '};' is contained the second
1433 # regex won't capture the whole JSON. Yet working around by trying more
1434 # concrete regex first keeping in mind proper quoted string handling
1435 # to be implemented in future that will replace this workaround (see
1436 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1437 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1438 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1439 r';ytplayer\.config\s*=\s*({.+?});',
1441 config = self._search_regex(
1442 patterns, webpage, 'ytplayer.config', default=None)
1444 return self._parse_json(
1445 uppercase_escape(config), video_id, fatal=False)
1447 def _get_automatic_captions(self, video_id, webpage):
1448 """We need the webpage for getting the captions url, pass it as an
1449 argument to speed up the process."""
1450 self.to_screen('%s: Looking for automatic captions' % video_id)
1451 player_config = self._get_ytplayer_config(video_id, webpage)
1452 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1453 if not player_config:
1454 self._downloader.report_warning(err_msg)
1457 args = player_config['args']
1458 caption_url = args.get('ttsurl')
1460 timestamp = args['timestamp']
1461 # We get the available subtitles
1462 list_params = compat_urllib_parse_urlencode({
1467 list_url = caption_url + '&' + list_params
1468 caption_list = self._download_xml(list_url, video_id)
1469 original_lang_node = caption_list.find('track')
1470 if original_lang_node is None:
1471 self._downloader.report_warning('Video doesn\'t have automatic captions')
1473 original_lang = original_lang_node.attrib['lang_code']
1474 caption_kind = original_lang_node.attrib.get('kind', '')
1477 for lang_node in caption_list.findall('target'):
1478 sub_lang = lang_node.attrib['lang_code']
1480 for ext in self._SUBTITLE_FORMATS:
1481 params = compat_urllib_parse_urlencode({
1482 'lang': original_lang,
1486 'kind': caption_kind,
1488 sub_formats.append({
1489 'url': caption_url + '&' + params,
1492 sub_lang_list[sub_lang] = sub_formats
1493 return sub_lang_list
1495 def make_captions(sub_url, sub_langs):
1496 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1497 caption_qs = compat_parse_qs(parsed_sub_url.query)
1499 for sub_lang in sub_langs:
1501 for ext in self._SUBTITLE_FORMATS:
1503 'tlang': [sub_lang],
1506 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1507 query=compat_urllib_parse_urlencode(caption_qs, True)))
1508 sub_formats.append({
1512 captions[sub_lang] = sub_formats
1515 # New captions format as of 22.06.2017
1516 player_response = args.get('player_response')
1517 if player_response and isinstance(player_response, compat_str):
1518 player_response = self._parse_json(
1519 player_response, video_id, fatal=False)
1521 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1522 base_url = renderer['captionTracks'][0]['baseUrl']
1524 for lang in renderer['translationLanguages']:
1525 lang_code = lang.get('languageCode')
1527 sub_lang_list.append(lang_code)
1528 return make_captions(base_url, sub_lang_list)
1530 # Some videos don't provide ttsurl but rather caption_tracks and
1531 # caption_translation_languages (e.g. 20LmZk1hakA)
1532 # Does not used anymore as of 22.06.2017
1533 caption_tracks = args['caption_tracks']
1534 caption_translation_languages = args['caption_translation_languages']
1535 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1537 for lang in caption_translation_languages.split(','):
1538 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1539 sub_lang = lang_qs.get('lc', [None])[0]
1541 sub_lang_list.append(sub_lang)
1542 return make_captions(caption_url, sub_lang_list)
1543 # An extractor error can be raise by the download process if there are
1544 # no automatic captions but there are subtitles
1545 except (KeyError, IndexError, ExtractorError):
1546 self._downloader.report_warning(err_msg)
1549 def _mark_watched(self, video_id, video_info, player_response):
1550 playback_url = url_or_none(try_get(
1552 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1553 video_info, lambda x: x['videostats_playback_base_url'][0]))
1554 if not playback_url:
1556 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1557 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1559 # cpn generation algorithm is reverse engineered from base.js.
1560 # In fact it works even with dummy cpn.
1561 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1562 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1568 playback_url = compat_urlparse.urlunparse(
1569 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1571 self._download_webpage(
1572 playback_url, video_id, 'Marking watched',
1573 'Unable to mark watched', fatal=False)
1576 def _extract_urls(webpage):
1577 # Embedded YouTube player
1579 unescapeHTML(mobj.group('url'))
1580 for mobj in re.finditer(r'''(?x)
1590 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1591 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1594 # lazyYT YouTube embed
1595 entries.extend(list(map(
1597 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1599 # Wordpress "YouTube Video Importer" plugin
1600 matches = re.findall(r'''(?x)<div[^>]+
1601 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1602 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1603 entries.extend(m[-1] for m in matches)
1608 def _extract_url(webpage):
1609 urls = YoutubeIE._extract_urls(webpage)
1610 return urls[0] if urls else None
1613 def extract_id(cls, url):
1614 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1616 raise ExtractorError('Invalid URL: %s' % url)
1617 video_id = mobj.group(2)
1621 def _extract_chapters(description, duration):
1624 chapter_lines = re.findall(
1625 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1627 if not chapter_lines:
1630 for next_num, (chapter_line, time_point) in enumerate(
1631 chapter_lines, start=1):
1632 start_time = parse_duration(time_point)
1633 if start_time is None:
1635 if start_time > duration:
1637 end_time = (duration if next_num == len(chapter_lines)
1638 else parse_duration(chapter_lines[next_num][1]))
1639 if end_time is None:
1641 if end_time > duration:
1643 if start_time > end_time:
1645 chapter_title = re.sub(
1646 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1647 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1649 'start_time': start_time,
1650 'end_time': end_time,
1651 'title': chapter_title,
1655 def _real_extract(self, url):
1656 url, smuggled_data = unsmuggle_url(url, {})
1659 'http' if self._downloader.params.get('prefer_insecure', False)
1664 parsed_url = compat_urllib_parse_urlparse(url)
1665 for component in [parsed_url.fragment, parsed_url.query]:
1666 query = compat_parse_qs(component)
1667 if start_time is None and 't' in query:
1668 start_time = parse_duration(query['t'][0])
1669 if start_time is None and 'start' in query:
1670 start_time = parse_duration(query['start'][0])
1671 if end_time is None and 'end' in query:
1672 end_time = parse_duration(query['end'][0])
1674 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1675 mobj = re.search(self._NEXT_URL_RE, url)
1677 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1678 video_id = self.extract_id(url)
1681 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1682 video_webpage = self._download_webpage(url, video_id)
1684 # Attempt to extract SWF player URL
1685 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1686 if mobj is not None:
1687 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1693 def add_dash_mpd(video_info):
1694 dash_mpd = video_info.get('dashmpd')
1695 if dash_mpd and dash_mpd[0] not in dash_mpds:
1696 dash_mpds.append(dash_mpd[0])
1698 def add_dash_mpd_pr(pl_response):
1699 dash_mpd = url_or_none(try_get(
1700 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1702 if dash_mpd and dash_mpd not in dash_mpds:
1703 dash_mpds.append(dash_mpd)
1708 def extract_view_count(v_info):
1709 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1711 def extract_token(v_info):
1712 return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
1714 def extract_player_response(player_response, video_id):
1715 pl_response = str_or_none(player_response)
1718 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1719 if isinstance(pl_response, dict):
1720 add_dash_mpd_pr(pl_response)
1723 player_response = {}
1726 embed_webpage = None
1727 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1730 # We simulate the access to the video from www.youtube.com/v/{video_id}
1731 # this can be viewed without login into Youtube
1732 url = proto + '://www.youtube.com/embed/%s' % video_id
1733 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1734 data = compat_urllib_parse_urlencode({
1735 'video_id': video_id,
1736 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1737 'sts': self._search_regex(
1738 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1740 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1742 video_info_webpage = self._download_webpage(
1743 video_info_url, video_id,
1744 note='Refetching age-gated info webpage',
1745 errnote='unable to download video info webpage')
1746 except ExtractorError:
1747 video_info_webpage = None
1748 if video_info_webpage:
1749 video_info = compat_parse_qs(video_info_webpage)
1750 pl_response = video_info.get('player_response', [None])[0]
1751 player_response = extract_player_response(pl_response, video_id)
1752 add_dash_mpd(video_info)
1753 view_count = extract_view_count(video_info)
1758 # Try looking directly into the video webpage
1759 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1761 args = ytplayer_config['args']
1762 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1763 # Convert to the same format returned by compat_parse_qs
1764 video_info = dict((k, [v]) for k, v in args.items())
1765 add_dash_mpd(video_info)
1766 # Rental video is not rented but preview is available (e.g.
1767 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1768 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1769 if not video_info and args.get('ypc_vid'):
1770 return self.url_result(
1771 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1772 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1774 sts = ytplayer_config.get('sts')
1775 if not player_response:
1776 player_response = extract_player_response(args.get('player_response'), video_id)
1777 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1778 add_dash_mpd_pr(player_response)
1779 # We also try looking in get_video_info since it may contain different dashmpd
1780 # URL that points to a DASH manifest with possibly different itag set (some itags
1781 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1782 # manifest pointed by get_video_info's dashmpd).
1783 # The general idea is to take a union of itags of both DASH manifests (for example
1784 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1785 self.report_video_info_webpage_download(video_id)
1786 for el in ('embedded', 'detailpage', 'vevo', ''):
1788 'video_id': video_id,
1799 video_info_webpage = self._download_webpage(
1800 '%s://www.youtube.com/get_video_info' % proto,
1801 video_id, note=False,
1802 errnote='unable to download video info webpage',
1804 except ExtractorError as e:
1805 # Skip further retries if we get 429 since solving
1806 # captcha only unblocks access to website but
1807 # not get_video_info end point
1808 if isinstance(e.cause, compat_HTTPError) and e.cause.code == 429:
1811 if not video_info_webpage:
1813 get_video_info = compat_parse_qs(video_info_webpage)
1814 if not player_response:
1815 pl_response = get_video_info.get('player_response', [None])[0]
1816 player_response = extract_player_response(pl_response, video_id)
1817 add_dash_mpd(get_video_info)
1818 if view_count is None:
1819 view_count = extract_view_count(get_video_info)
1821 video_info = get_video_info
1822 get_token = extract_token(get_video_info)
1824 # Different get_video_info requests may report different results, e.g.
1825 # some may report video unavailability, but some may serve it without
1826 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1827 # the original webpage as well as el=info and el=embedded get_video_info
1828 # requests report video unavailability due to geo restriction while
1829 # el=detailpage succeeds and returns valid data). This is probably
1830 # due to YouTube measures against IP ranges of hosting providers.
1831 # Working around by preferring the first succeeded video_info containing
1832 # the token if no such video_info yet was found.
1833 token = extract_token(video_info)
1835 video_info = get_video_info
1838 def extract_unavailable_message():
1840 for tag, kind in (('h1', 'message'), ('div', 'submessage')):
1841 msg = self._html_search_regex(
1842 r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind),
1843 video_webpage, 'unavailable %s' % kind, default=None)
1845 messages.append(msg)
1847 return '\n'.join(messages)
1849 if not video_info and not player_response:
1850 unavailable_message = extract_unavailable_message()
1851 if not unavailable_message:
1852 unavailable_message = 'Unable to extract video data'
1853 raise ExtractorError(
1854 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1856 if not isinstance(video_info, dict):
1859 video_details = try_get(
1860 player_response, lambda x: x['videoDetails'], dict) or {}
1862 video_title = video_info.get('title', [None])[0] or video_details.get('title')
1864 self._downloader.report_warning('Unable to extract video title')
1867 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1868 if video_description:
1871 redir_url = compat_urlparse.urljoin(url, m.group(1))
1872 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1873 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1874 qs = compat_parse_qs(parsed_redir_url.query)
1880 description_original = video_description = re.sub(r'''(?x)
1882 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1883 (?:title|href)="([^"]+)"\s+
1884 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1888 ''', replace_url, video_description)
1889 video_description = clean_html(video_description)
1891 video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
1893 if not smuggled_data.get('force_singlefeed', False):
1894 if not self._downloader.params.get('noplaylist'):
1895 multifeed_metadata_list = try_get(
1897 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1898 compat_str) or try_get(
1899 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1900 if multifeed_metadata_list:
1903 for feed in multifeed_metadata_list.split(','):
1904 # Unquote should take place before split on comma (,) since textual
1905 # fields may contain comma as well (see
1906 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1907 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1909 '_type': 'url_transparent',
1910 'ie_key': 'Youtube',
1912 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1913 {'force_singlefeed': True}),
1914 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1916 feed_ids.append(feed_data['id'][0])
1918 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1919 % (', '.join(feed_ids), video_id))
1920 return self.playlist_result(entries, video_id, video_title, video_description)
1922 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1924 if view_count is None:
1925 view_count = extract_view_count(video_info)
1926 if view_count is None and video_details:
1927 view_count = int_or_none(video_details.get('viewCount'))
1930 is_live = bool_or_none(video_details.get('isLive'))
1932 # Check for "rental" videos
1933 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1934 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1936 def _extract_filesize(media_url):
1937 return int_or_none(self._search_regex(
1938 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1940 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or []
1941 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or [])
1943 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1944 self.report_rtmp_download()
1946 'format_id': '_rtmp',
1948 'url': video_info['conn'][0],
1949 'player_url': player_url,
1951 elif not is_live and (streaming_formats or len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
1952 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1953 if 'rtmpe%3Dyes' in encoded_url_map:
1954 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1957 fmt_list = video_info.get('fmt_list', [''])[0]
1959 for fmt in fmt_list.split(','):
1960 spec = fmt.split('/')
1962 width_height = spec[1].split('x')
1963 if len(width_height) == 2:
1964 formats_spec[spec[0]] = {
1965 'resolution': spec[1],
1966 'width': int_or_none(width_height[0]),
1967 'height': int_or_none(width_height[1]),
1969 for fmt in streaming_formats:
1970 itag = str_or_none(fmt.get('itag'))
1973 quality = fmt.get('quality')
1974 quality_label = fmt.get('qualityLabel') or quality
1975 formats_spec[itag] = {
1976 'asr': int_or_none(fmt.get('audioSampleRate')),
1977 'filesize': int_or_none(fmt.get('contentLength')),
1978 'format_note': quality_label,
1979 'fps': int_or_none(fmt.get('fps')),
1980 'height': int_or_none(fmt.get('height')),
1981 # bitrate for itag 43 is always 2147483647
1982 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1983 'width': int_or_none(fmt.get('width')),
1986 for fmt in streaming_formats:
1987 if fmt.get('drm_families'):
1989 url = url_or_none(fmt.get('url'))
1992 cipher = fmt.get('cipher')
1995 url_data = compat_parse_qs(cipher)
1996 url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str))
2001 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
2003 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
2004 # Unsupported FORMAT_STREAM_TYPE_OTF
2005 if stream_type == 3:
2008 format_id = fmt.get('itag') or url_data['itag'][0]
2011 format_id = compat_str(format_id)
2014 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
2015 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
2016 jsplayer_url_json = self._search_regex(
2018 embed_webpage if age_gate else video_webpage,
2019 'JS player URL (1)', default=None)
2020 if not jsplayer_url_json and not age_gate:
2021 # We need the embed website after all
2022 if embed_webpage is None:
2023 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
2024 embed_webpage = self._download_webpage(
2025 embed_url, video_id, 'Downloading embed webpage')
2026 jsplayer_url_json = self._search_regex(
2027 ASSETS_RE, embed_webpage, 'JS player URL')
2029 player_url = json.loads(jsplayer_url_json)
2030 if player_url is None:
2031 player_url_json = self._search_regex(
2032 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
2033 video_webpage, 'age gate player URL')
2034 player_url = json.loads(player_url_json)
2036 if 'sig' in url_data:
2037 url += '&signature=' + url_data['sig'][0]
2038 elif 's' in url_data:
2039 encrypted_sig = url_data['s'][0]
2041 if self._downloader.params.get('verbose'):
2042 if player_url is None:
2043 player_version = 'unknown'
2044 player_desc = 'unknown'
2046 if player_url.endswith('swf'):
2047 player_version = self._search_regex(
2048 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
2049 'flash player', fatal=False)
2050 player_desc = 'flash player %s' % player_version
2052 player_version = self._search_regex(
2053 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
2054 r'(?:www|player(?:_ias)?)[-.]([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
2056 'html5 player', fatal=False)
2057 player_desc = 'html5 player %s' % player_version
2059 parts_sizes = self._signature_cache_id(encrypted_sig)
2060 self.to_screen('{%s} signature length %s, %s' %
2061 (format_id, parts_sizes, player_desc))
2063 signature = self._decrypt_signature(
2064 encrypted_sig, video_id, player_url, age_gate)
2065 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2066 url += '&%s=%s' % (sp, signature)
2067 if 'ratebypass' not in url:
2068 url += '&ratebypass=yes'
2071 'format_id': format_id,
2073 'player_url': player_url,
2075 if format_id in self._formats:
2076 dct.update(self._formats[format_id])
2077 if format_id in formats_spec:
2078 dct.update(formats_spec[format_id])
2080 # Some itags are not included in DASH manifest thus corresponding formats will
2081 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2082 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2083 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2084 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2087 width = int_or_none(fmt.get('width'))
2089 height = int_or_none(fmt.get('height'))
2091 filesize = int_or_none(url_data.get(
2092 'clen', [None])[0]) or _extract_filesize(url)
2094 quality = url_data.get('quality', [None])[0] or fmt.get('quality')
2095 quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
2097 tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
2098 or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
2099 fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
2102 'filesize': filesize,
2107 'format_note': quality_label or quality,
2109 for key, value in more_fields.items():
2112 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
2114 type_split = type_.split(';')
2115 kind_ext = type_split[0].split('/')
2116 if len(kind_ext) == 2:
2118 dct['ext'] = mimetype2ext(type_split[0])
2119 if kind in ('audio', 'video'):
2121 for mobj in re.finditer(
2122 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2123 if mobj.group('key') == 'codecs':
2124 codecs = mobj.group('val')
2127 dct.update(parse_codecs(codecs))
2128 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2129 dct['downloader_options'] = {
2130 # Youtube throttles chunks >~10M
2131 'http_chunk_size': 10485760,
2136 url_or_none(try_get(
2138 lambda x: x['streamingData']['hlsManifestUrl'],
2140 or url_or_none(try_get(
2141 video_info, lambda x: x['hlsvp'][0], compat_str)))
2144 m3u8_formats = self._extract_m3u8_formats(
2145 manifest_url, video_id, 'mp4', fatal=False)
2146 for a_format in m3u8_formats:
2147 itag = self._search_regex(
2148 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2150 a_format['format_id'] = itag
2151 if itag in self._formats:
2152 dct = self._formats[itag].copy()
2153 dct.update(a_format)
2155 a_format['player_url'] = player_url
2156 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2157 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2158 formats.append(a_format)
2160 error_message = extract_unavailable_message()
2161 if not error_message:
2162 error_message = clean_html(try_get(
2163 player_response, lambda x: x['playabilityStatus']['reason'],
2165 if not error_message:
2166 error_message = clean_html(
2167 try_get(video_info, lambda x: x['reason'][0], compat_str))
2169 raise ExtractorError(error_message, expected=True)
2170 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2173 video_uploader = try_get(
2174 video_info, lambda x: x['author'][0],
2175 compat_str) or str_or_none(video_details.get('author'))
2177 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2179 self._downloader.report_warning('unable to extract uploader name')
2182 video_uploader_id = None
2183 video_uploader_url = None
2185 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2187 if mobj is not None:
2188 video_uploader_id = mobj.group('uploader_id')
2189 video_uploader_url = mobj.group('uploader_url')
2191 self._downloader.report_warning('unable to extract uploader nickname')
2194 str_or_none(video_details.get('channelId'))
2195 or self._html_search_meta(
2196 'channelId', video_webpage, 'channel id', default=None)
2197 or self._search_regex(
2198 r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
2199 video_webpage, 'channel id', default=None, group='id'))
2200 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2203 # We try first to get a high quality image:
2204 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2205 video_webpage, re.DOTALL)
2206 if m_thumb is not None:
2207 video_thumbnail = m_thumb.group(1)
2208 elif 'thumbnail_url' not in video_info:
2209 self._downloader.report_warning('unable to extract video thumbnail')
2210 video_thumbnail = None
2211 else: # don't panic if we can't find it
2212 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2215 upload_date = self._html_search_meta(
2216 'datePublished', video_webpage, 'upload date', default=None)
2218 upload_date = self._search_regex(
2219 [r'(?s)id="eow-date.*?>(.*?)</span>',
2220 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2221 video_webpage, 'upload date', default=None)
2222 upload_date = unified_strdate(upload_date)
2224 video_license = self._html_search_regex(
2225 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2226 video_webpage, 'license', default=None)
2228 m_music = re.search(
2230 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2238 \bhref=["\']/red[^>]*>| # drop possible
2239 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2246 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2247 video_creator = clean_html(m_music.group('creator'))
2249 video_alt_title = video_creator = None
2251 def extract_meta(field):
2252 return self._html_search_regex(
2253 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2254 video_webpage, field, default=None)
2256 track = extract_meta('Song')
2257 artist = extract_meta('Artist')
2258 album = extract_meta('Album')
2260 # Youtube Music Auto-generated description
2261 release_date = release_year = None
2262 if video_description:
2263 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)
2266 track = mobj.group('track').strip()
2268 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2270 album = mobj.group('album'.strip())
2271 release_year = mobj.group('release_year')
2272 release_date = mobj.group('release_date')
2274 release_date = release_date.replace('-', '')
2275 if not release_year:
2276 release_year = int(release_date[:4])
2278 release_year = int(release_year)
2280 m_episode = re.search(
2281 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2284 series = unescapeHTML(m_episode.group('series'))
2285 season_number = int(m_episode.group('season'))
2286 episode_number = int(m_episode.group('episode'))
2288 series = season_number = episode_number = None
2290 m_cat_container = self._search_regex(
2291 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2292 video_webpage, 'categories', default=None)
2294 category = self._html_search_regex(
2295 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2297 video_categories = None if category is None else [category]
2299 video_categories = None
2302 unescapeHTML(m.group('content'))
2303 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2305 def _extract_count(count_name):
2306 return str_to_int(self._search_regex(
2307 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2308 % re.escape(count_name),
2309 video_webpage, count_name, default=None))
2311 like_count = _extract_count('like')
2312 dislike_count = _extract_count('dislike')
2314 if view_count is None:
2315 view_count = str_to_int(self._search_regex(
2316 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2317 'view count', default=None))
2320 float_or_none(video_details.get('averageRating'))
2321 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2324 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2325 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2327 video_duration = try_get(
2328 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2329 if not video_duration:
2330 video_duration = int_or_none(video_details.get('lengthSeconds'))
2331 if not video_duration:
2332 video_duration = parse_duration(self._html_search_meta(
2333 'duration', video_webpage, 'video duration'))
2336 video_annotations = None
2337 if self._downloader.params.get('writeannotations', False):
2338 xsrf_token = self._search_regex(
2339 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
2340 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2341 invideo_url = try_get(
2342 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2343 if xsrf_token and invideo_url:
2344 xsrf_field_name = self._search_regex(
2345 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2346 video_webpage, 'xsrf field name',
2347 group='xsrf_field_name', default='session_token')
2348 video_annotations = self._download_webpage(
2349 self._proto_relative_url(invideo_url),
2350 video_id, note='Downloading annotations',
2351 errnote='Unable to download video annotations', fatal=False,
2352 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2354 chapters = self._extract_chapters(description_original, video_duration)
2356 # Look for the DASH manifest
2357 if self._downloader.params.get('youtube_include_dash_manifest', True):
2358 dash_mpd_fatal = True
2359 for mpd_url in dash_mpds:
2362 def decrypt_sig(mobj):
2364 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2365 return '/signature/%s' % dec_s
2367 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2369 for df in self._extract_mpd_formats(
2370 mpd_url, video_id, fatal=dash_mpd_fatal,
2371 formats_dict=self._formats):
2372 if not df.get('filesize'):
2373 df['filesize'] = _extract_filesize(df['url'])
2374 # Do not overwrite DASH format found in some previous DASH manifest
2375 if df['format_id'] not in dash_formats:
2376 dash_formats[df['format_id']] = df
2377 # Additional DASH manifests may end up in HTTP Error 403 therefore
2378 # allow them to fail without bug report message if we already have
2379 # some DASH manifest succeeded. This is temporary workaround to reduce
2380 # burst of bug reports until we figure out the reason and whether it
2381 # can be fixed at all.
2382 dash_mpd_fatal = False
2383 except (ExtractorError, KeyError) as e:
2384 self.report_warning(
2385 'Skipping DASH manifest: %r' % e, video_id)
2387 # Remove the formats we found through non-DASH, they
2388 # contain less info and it can be wrong, because we use
2389 # fixed values (for example the resolution). See
2390 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2392 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2393 formats.extend(dash_formats.values())
2395 # Check for malformed aspect ratio
2396 stretched_m = re.search(
2397 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2400 w = float(stretched_m.group('w'))
2401 h = float(stretched_m.group('h'))
2402 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2403 # We will only process correct ratios.
2407 if f.get('vcodec') != 'none':
2408 f['stretched_ratio'] = ratio
2411 token = extract_token(video_info)
2413 if 'reason' in video_info:
2414 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2415 regions_allowed = self._html_search_meta(
2416 'regionsAllowed', video_webpage, default=None)
2417 countries = regions_allowed.split(',') if regions_allowed else None
2418 self.raise_geo_restricted(
2419 msg=video_info['reason'][0], countries=countries)
2420 reason = video_info['reason'][0]
2421 if 'Invalid parameters' in reason:
2422 unavailable_message = extract_unavailable_message()
2423 if unavailable_message:
2424 reason = unavailable_message
2425 raise ExtractorError(
2426 'YouTube said: %s' % reason,
2427 expected=True, video_id=video_id)
2429 raise ExtractorError(
2430 '"token" parameter not in video info for unknown reason',
2433 if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
2434 raise ExtractorError('This video is DRM protected.', expected=True)
2436 self._sort_formats(formats)
2438 self.mark_watched(video_id, video_info, player_response)
2442 'uploader': video_uploader,
2443 'uploader_id': video_uploader_id,
2444 'uploader_url': video_uploader_url,
2445 'channel_id': channel_id,
2446 'channel_url': channel_url,
2447 'upload_date': upload_date,
2448 'license': video_license,
2449 'creator': video_creator or artist,
2450 'title': video_title,
2451 'alt_title': video_alt_title or track,
2452 'thumbnail': video_thumbnail,
2453 'description': video_description,
2454 'categories': video_categories,
2456 'subtitles': video_subtitles,
2457 'automatic_captions': automatic_captions,
2458 'duration': video_duration,
2459 'age_limit': 18 if age_gate else 0,
2460 'annotations': video_annotations,
2461 'chapters': chapters,
2462 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2463 'view_count': view_count,
2464 'like_count': like_count,
2465 'dislike_count': dislike_count,
2466 'average_rating': average_rating,
2469 'start_time': start_time,
2470 'end_time': end_time,
2472 'season_number': season_number,
2473 'episode_number': episode_number,
2477 'release_date': release_date,
2478 'release_year': release_year,
2482 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2483 IE_DESC = 'YouTube.com playlists'
2484 _VALID_URL = r"""(?x)(?:
2489 youtube(?:kids)?\.com|
2494 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2495 \? (?:.*?[&;])*? (?:p|a|list)=
2498 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2501 (?:PL|LL|EC|UU|FL|RD|UL|TL|PU|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2502 # Top tracks, they can also include dots
2508 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2509 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2510 _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2511 _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
2512 IE_NAME = 'youtube:playlist'
2514 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2516 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2517 'uploader': 'Sergey M.',
2518 'id': 'PL4lCao7KL_QFVb7Iudeipvc2BCavECqzc',
2519 'title': 'youtube-dl public playlist',
2521 'playlist_count': 1,
2523 'url': 'https://www.youtube.com/playlist?list=PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2525 'uploader_id': 'UCmlqkdCBesrv2Lak1mF_MxA',
2526 'uploader': 'Sergey M.',
2527 'id': 'PL4lCao7KL_QFodcLWhDpGCYnngnHtQ-Xf',
2528 'title': 'youtube-dl empty playlist',
2530 'playlist_count': 0,
2532 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2533 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2535 'title': '29C3: Not my department',
2536 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2537 'uploader': 'Christiaan008',
2538 'uploader_id': 'ChRiStIaAn008',
2540 'playlist_count': 96,
2542 'note': 'issue #673',
2543 'url': 'PLBB231211A4F62143',
2545 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2546 'id': 'PLBB231211A4F62143',
2547 'uploader': 'Wickydoo',
2548 'uploader_id': 'Wickydoo',
2550 'playlist_mincount': 26,
2552 'note': 'Large playlist',
2553 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2555 'title': 'Uploads from Cauchemar',
2556 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2557 'uploader': 'Cauchemar',
2558 'uploader_id': 'Cauchemar89',
2560 'playlist_mincount': 799,
2562 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2564 'title': 'YDL_safe_search',
2565 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2567 'playlist_count': 2,
2568 'skip': 'This playlist is private',
2571 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2572 'playlist_count': 4,
2575 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2576 'uploader': 'milan',
2577 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2580 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2581 'playlist_mincount': 485,
2583 'title': '2018 Chinese New Singles (11/6 updated)',
2584 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2586 'uploader_id': 'sdragonfang',
2589 'note': 'Embedded SWF player',
2590 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2591 'playlist_count': 4,
2594 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2596 'skip': 'This playlist does not exist',
2598 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2599 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2601 'title': 'Uploads from Interstellar Movie',
2602 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2603 'uploader': 'Interstellar Movie',
2604 'uploader_id': 'InterstellarMovie1',
2606 'playlist_mincount': 21,
2608 # Playlist URL that does not actually serve a playlist
2609 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2611 'id': 'FqZTN594JQw',
2613 'title': "Smiley's People 01 detective, Adventure Series, Action",
2614 'uploader': 'STREEM',
2615 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2616 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2617 'upload_date': '20150526',
2618 'license': 'Standard YouTube License',
2619 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2620 'categories': ['People & Blogs'],
2624 'dislike_count': int,
2627 'skip_download': True,
2629 'skip': 'This video is not available.',
2630 'add_ie': [YoutubeIE.ie_key()],
2632 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2634 'id': 'yeWKywCrFtk',
2636 'title': 'Small Scale Baler and Braiding Rugs',
2637 'uploader': 'Backus-Page House Museum',
2638 'uploader_id': 'backuspagemuseum',
2639 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2640 'upload_date': '20161008',
2641 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2642 'categories': ['Nonprofits & Activism'],
2645 'dislike_count': int,
2649 'skip_download': True,
2652 # https://github.com/ytdl-org/youtube-dl/issues/21844
2653 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2655 'title': 'Data Analysis with Dr Mike Pound',
2656 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2657 'uploader_id': 'Computerphile',
2658 'uploader': 'Computerphile',
2660 'playlist_mincount': 11,
2662 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2663 'only_matching': True,
2665 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2666 'only_matching': True,
2668 # music album playlist
2669 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2670 'only_matching': True,
2672 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2673 'only_matching': True,
2675 'url': 'https://www.youtubekids.com/watch?v=Agk7R8I8o5U&list=PUZ6jURNr1WQZCNHF0ao-c0g',
2676 'only_matching': True,
2679 def _real_initialize(self):
2682 def extract_videos_from_page(self, page):
2686 for item in re.findall(
2687 r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
2688 attrs = extract_attributes(item)
2689 video_id = attrs['data-video-id']
2690 video_title = unescapeHTML(attrs.get('data-title'))
2692 video_title = video_title.strip()
2693 ids_in_page.append(video_id)
2694 titles_in_page.append(video_title)
2696 # Fallback with old _VIDEO_RE
2697 self.extract_videos_from_page_impl(
2698 self._VIDEO_RE, page, ids_in_page, titles_in_page)
2701 self.extract_videos_from_page_impl(
2702 r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page,
2703 ids_in_page, titles_in_page)
2704 self.extract_videos_from_page_impl(
2705 r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
2706 ids_in_page, titles_in_page)
2708 return zip(ids_in_page, titles_in_page)
2710 def _extract_mix(self, playlist_id):
2711 # The mixes are generated from a single video
2712 # the id of the playlist is just 'RD' + video_id
2714 last_id = playlist_id[-11:]
2715 for n in itertools.count(1):
2716 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2717 webpage = self._download_webpage(
2718 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2719 new_ids = orderedSet(re.findall(
2720 r'''(?xs)data-video-username=".*?".*?
2721 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2723 # Fetch new pages until all the videos are repeated, it seems that
2724 # there are always 51 unique videos.
2725 new_ids = [_id for _id in new_ids if _id not in ids]
2731 url_results = self._ids_to_results(ids)
2733 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2735 search_title('playlist-title')
2736 or search_title('title long-title')
2737 or search_title('title'))
2738 title = clean_html(title_span)
2740 return self.playlist_result(url_results, playlist_id, title)
2742 def _extract_playlist(self, playlist_id):
2743 url = self._TEMPLATE_URL % playlist_id
2744 page = self._download_webpage(url, playlist_id)
2746 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2747 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2748 match = match.strip()
2749 # Check if the playlist exists or is private
2750 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2752 reason = mobj.group('reason')
2753 message = 'This playlist %s' % reason
2754 if 'private' in reason:
2755 message += ', use --username or --netrc to access it'
2757 raise ExtractorError(message, expected=True)
2758 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2759 raise ExtractorError(
2760 'Invalid parameters. Maybe URL is incorrect.',
2762 elif re.match(r'[^<]*Choose your language[^<]*', match):
2765 self.report_warning('Youtube gives an alert message: ' + match)
2767 playlist_title = self._html_search_regex(
2768 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2769 page, 'title', default=None)
2771 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2772 uploader = self._html_search_regex(
2773 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2774 page, 'uploader', default=None)
2776 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2779 uploader_id = mobj.group('uploader_id')
2780 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2782 uploader_id = uploader_url = None
2786 if not playlist_title:
2788 # Some playlist URLs don't actually serve a playlist (e.g.
2789 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2790 next(self._entries(page, playlist_id))
2791 except StopIteration:
2794 playlist = self.playlist_result(
2795 self._entries(page, playlist_id), playlist_id, playlist_title)
2797 'uploader': uploader,
2798 'uploader_id': uploader_id,
2799 'uploader_url': uploader_url,
2802 return has_videos, playlist
2804 def _check_download_just_video(self, url, playlist_id):
2805 # Check if it's a video-specific URL
2806 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2807 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2808 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2809 'video id', default=None)
2811 if self._downloader.params.get('noplaylist'):
2812 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2813 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2815 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2816 return video_id, None
2819 def _real_extract(self, url):
2820 # Extract playlist id
2821 mobj = re.match(self._VALID_URL, url)
2823 raise ExtractorError('Invalid URL: %s' % url)
2824 playlist_id = mobj.group(1) or mobj.group(2)
2826 video_id, video = self._check_download_just_video(url, playlist_id)
2830 if playlist_id.startswith(('RD', 'UL', 'PU')):
2831 # Mixes require a custom extraction process
2832 return self._extract_mix(playlist_id)
2834 has_videos, playlist = self._extract_playlist(playlist_id)
2835 if has_videos or not video_id:
2838 # Some playlist URLs don't actually serve a playlist (see
2839 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2840 # Fallback to plain video extraction if there is a video id
2841 # along with playlist id.
2842 return self.url_result(video_id, 'Youtube', video_id=video_id)
2845 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2846 IE_DESC = 'YouTube.com channels'
2847 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie|kids)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2848 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2849 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2850 IE_NAME = 'youtube:channel'
2852 'note': 'paginated channel',
2853 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2854 'playlist_mincount': 91,
2856 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2857 'title': 'Uploads from lex will',
2858 'uploader': 'lex will',
2859 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2862 'note': 'Age restricted channel',
2863 # from https://www.youtube.com/user/DeusExOfficial
2864 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2865 'playlist_mincount': 64,
2867 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2868 'title': 'Uploads from Deus Ex',
2869 'uploader': 'Deus Ex',
2870 'uploader_id': 'DeusExOfficial',
2873 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2874 'only_matching': True,
2876 'url': 'https://www.youtubekids.com/channel/UCyu8StPfZWapR6rfW_JgqcA',
2877 'only_matching': True,
2881 def suitable(cls, url):
2882 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2883 else super(YoutubeChannelIE, cls).suitable(url))
2885 def _build_template_url(self, url, channel_id):
2886 return self._TEMPLATE_URL % channel_id
2888 def _real_extract(self, url):
2889 channel_id = self._match_id(url)
2891 url = self._build_template_url(url, channel_id)
2893 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2894 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2895 # otherwise fallback on channel by page extraction
2896 channel_page = self._download_webpage(
2897 url + '?view=57', channel_id,
2898 'Downloading channel page', fatal=False)
2899 if channel_page is False:
2900 channel_playlist_id = False
2902 channel_playlist_id = self._html_search_meta(
2903 'channelId', channel_page, 'channel id', default=None)
2904 if not channel_playlist_id:
2905 channel_url = self._html_search_meta(
2906 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2907 channel_page, 'channel url', default=None)
2909 channel_playlist_id = self._search_regex(
2910 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2911 channel_url, 'channel id', default=None)
2912 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2913 playlist_id = 'UU' + channel_playlist_id[2:]
2914 return self.url_result(
2915 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2917 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2918 autogenerated = re.search(r'''(?x)
2920 channel-header-autogenerated-label|
2921 yt-channel-title-autogenerated
2922 )[^"]*"''', channel_page) is not None
2925 # The videos are contained in a single page
2926 # the ajax pages can't be used, they are empty
2929 video_id, 'Youtube', video_id=video_id,
2930 video_title=video_title)
2931 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2932 return self.playlist_result(entries, channel_id)
2935 next(self._entries(channel_page, channel_id))
2936 except StopIteration:
2937 alert_message = self._html_search_regex(
2938 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2939 channel_page, 'alert', default=None, group='alert')
2941 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2943 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2946 class YoutubeUserIE(YoutubeChannelIE):
2947 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2948 _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_-]+)'
2949 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2950 IE_NAME = 'youtube:user'
2953 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2954 'playlist_mincount': 320,
2956 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2957 'title': 'Uploads from The Linux Foundation',
2958 'uploader': 'The Linux Foundation',
2959 'uploader_id': 'TheLinuxFoundation',
2962 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2963 # but not https://www.youtube.com/user/12minuteathlete/videos
2964 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2965 'playlist_mincount': 249,
2967 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2968 'title': 'Uploads from 12 Minute Athlete',
2969 'uploader': '12 Minute Athlete',
2970 'uploader_id': 'the12minuteathlete',
2973 'url': 'ytuser:phihag',
2974 'only_matching': True,
2976 'url': 'https://www.youtube.com/c/gametrailers',
2977 'only_matching': True,
2979 'url': 'https://www.youtube.com/gametrailers',
2980 'only_matching': True,
2982 # This channel is not available, geo restricted to JP
2983 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2984 'only_matching': True,
2988 def suitable(cls, url):
2989 # Don't return True if the url can be extracted with other youtube
2990 # extractor, the regex would is too permissive and it would match.
2991 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2992 if any(ie.suitable(url) for ie in other_yt_ies):
2995 return super(YoutubeUserIE, cls).suitable(url)
2997 def _build_template_url(self, url, channel_id):
2998 mobj = re.match(self._VALID_URL, url)
2999 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
3002 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
3003 IE_DESC = 'YouTube.com live streams'
3004 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
3005 IE_NAME = 'youtube:live'
3008 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
3010 'id': 'a48o2S1cPoo',
3012 'title': 'The Young Turks - Live Main Show',
3013 'uploader': 'The Young Turks',
3014 'uploader_id': 'TheYoungTurks',
3015 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
3016 'upload_date': '20150715',
3017 'license': 'Standard YouTube License',
3018 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
3019 'categories': ['News & Politics'],
3020 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
3022 'dislike_count': int,
3025 'skip_download': True,
3028 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
3029 'only_matching': True,
3031 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3032 'only_matching': True,
3034 'url': 'https://www.youtube.com/TheYoungTurks/live',
3035 'only_matching': True,
3038 def _real_extract(self, url):
3039 mobj = re.match(self._VALID_URL, url)
3040 channel_id = mobj.group('id')
3041 base_url = mobj.group('base_url')
3042 webpage = self._download_webpage(url, channel_id, fatal=False)
3044 page_type = self._og_search_property(
3045 'type', webpage, 'page type', default='')
3046 video_id = self._html_search_meta(
3047 'videoId', webpage, 'video id', default=None)
3048 if page_type.startswith('video') and video_id and re.match(
3049 r'^[0-9A-Za-z_-]{11}$', video_id):
3050 return self.url_result(video_id, YoutubeIE.ie_key())
3051 return self.url_result(base_url)
3054 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
3055 IE_DESC = 'YouTube.com user/channel playlists'
3056 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
3057 IE_NAME = 'youtube:playlists'
3060 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3061 'playlist_mincount': 4,
3063 'id': 'ThirstForScience',
3064 'title': 'ThirstForScience',
3067 # with "Load more" button
3068 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3069 'playlist_mincount': 70,
3072 'title': 'Игорь Клейнер',
3075 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
3076 'playlist_mincount': 17,
3078 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
3079 'title': 'Chem Player',
3085 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
3086 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
3089 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
3090 IE_DESC = 'YouTube.com searches'
3091 # there doesn't appear to be a real limit, for example if you search for
3092 # 'python' you get more than 8.000.000 results
3093 _MAX_RESULTS = float('inf')
3094 IE_NAME = 'youtube:search'
3095 _SEARCH_KEY = 'ytsearch'
3096 _EXTRA_QUERY_ARGS = {}
3099 def _get_n_results(self, query, n):
3100 """Get a specified number of results for a query"""
3106 'search_query': query.encode('utf-8'),
3108 url_query.update(self._EXTRA_QUERY_ARGS)
3109 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
3111 for pagenum in itertools.count(1):
3112 data = self._download_json(
3113 result_url, video_id='query "%s"' % query,
3114 note='Downloading page %s' % pagenum,
3115 errnote='Unable to download API page',
3116 query={'spf': 'navigate'})
3117 html_content = data[1]['body']['content']
3119 if 'class="search-message' in html_content:
3120 raise ExtractorError(
3121 '[youtube] No video results', expected=True)
3123 new_videos = list(self._process_page(html_content))
3124 videos += new_videos
3125 if not new_videos or len(videos) > limit:
3127 next_link = self._html_search_regex(
3128 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
3129 html_content, 'next link', default=None)
3130 if next_link is None:
3132 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
3136 return self.playlist_result(videos, query)
3139 class YoutubeSearchDateIE(YoutubeSearchIE):
3140 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3141 _SEARCH_KEY = 'ytsearchdate'
3142 IE_DESC = 'YouTube.com searches, newest videos first'
3143 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
3146 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
3147 IE_DESC = 'YouTube.com search URLs'
3148 IE_NAME = 'youtube:search_url'
3149 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3151 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3152 'playlist_mincount': 5,
3154 'title': 'youtube-dl test video',
3157 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3158 'only_matching': True,
3161 def _real_extract(self, url):
3162 mobj = re.match(self._VALID_URL, url)
3163 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3164 webpage = self._download_webpage(url, query)
3165 return self.playlist_result(self._process_page(webpage), playlist_title=query)
3168 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3169 IE_DESC = 'YouTube.com (multi-season) shows'
3170 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3171 IE_NAME = 'youtube:show'
3173 'url': 'https://www.youtube.com/show/airdisasters',
3174 'playlist_mincount': 5,
3176 'id': 'airdisasters',
3177 'title': 'Air Disasters',
3181 def _real_extract(self, url):
3182 playlist_id = self._match_id(url)
3183 return super(YoutubeShowIE, self)._real_extract(
3184 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3187 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3189 Base class for feed extractors
3190 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3192 _LOGIN_REQUIRED = True
3196 return 'youtube:%s' % self._FEED_NAME
3198 def _real_initialize(self):
3201 def _entries(self, page):
3202 # The extraction process is the same as for playlists, but the regex
3203 # for the video ids doesn't contain an index
3205 more_widget_html = content_html = page
3206 for page_num in itertools.count(1):
3207 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3209 # 'recommended' feed has infinite 'load more' and each new portion spins
3210 # the same videos in (sometimes) slightly different order, so we'll check
3211 # for unicity and break when portion has no new videos
3212 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3218 for entry in self._ids_to_results(new_ids):
3221 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3225 more = self._download_json(
3226 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3227 'Downloading page #%s' % page_num,
3228 transform_source=uppercase_escape)
3229 content_html = more['content_html']
3230 more_widget_html = more['load_more_widget_html']
3232 def _real_extract(self, url):
3233 page = self._download_webpage(
3234 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3235 self._PLAYLIST_TITLE)
3236 return self.playlist_result(
3237 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3240 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3241 IE_NAME = 'youtube:watchlater'
3242 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3243 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3246 'url': 'https://www.youtube.com/playlist?list=WL',
3247 'only_matching': True,
3249 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3250 'only_matching': True,
3253 def _real_extract(self, url):
3254 _, video = self._check_download_just_video(url, 'WL')
3257 _, playlist = self._extract_playlist('WL')
3261 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3262 IE_NAME = 'youtube:favorites'
3263 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3264 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3265 _LOGIN_REQUIRED = True
3267 def _real_extract(self, url):
3268 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3269 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3270 return self.url_result(playlist_id, 'YoutubePlaylist')
3273 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3274 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3275 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3276 _FEED_NAME = 'recommended'
3277 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3280 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3281 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3282 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3283 _FEED_NAME = 'subscriptions'
3284 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3287 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3288 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3289 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3290 _FEED_NAME = 'history'
3291 _PLAYLIST_TITLE = 'Youtube History'
3294 class YoutubeTruncatedURLIE(InfoExtractor):
3295 IE_NAME = 'youtube:truncated_url'
3296 IE_DESC = False # Do not list
3297 _VALID_URL = r'''(?x)
3299 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3302 annotation_id=annotation_[^&]+|
3308 attribution_link\?a=[^&]+
3314 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3315 'only_matching': True,
3317 'url': 'https://www.youtube.com/watch?',
3318 'only_matching': True,
3320 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3321 'only_matching': True,
3323 'url': 'https://www.youtube.com/watch?feature=foo',
3324 'only_matching': True,
3326 'url': 'https://www.youtube.com/watch?hl=en-GB',
3327 'only_matching': True,
3329 'url': 'https://www.youtube.com/watch?t=2372',
3330 'only_matching': True,
3333 def _real_extract(self, url):
3334 raise ExtractorError(
3335 'Did you forget to quote the URL? Remember that & is a meta '
3336 'character in most shells, so you want to put the URL in quotes, '
3338 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3339 ' or simply youtube-dl BaW_jenozKc .',
3343 class YoutubeTruncatedIDIE(InfoExtractor):
3344 IE_NAME = 'youtube:truncated_id'
3345 IE_DESC = False # Do not list
3346 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3349 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3350 'only_matching': True,
3353 def _real_extract(self, url):
3354 video_id = self._match_id(url)
3355 raise ExtractorError(
3356 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),