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|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)?\.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\.enkirton\.net/|
387 (?:www\.)?invidious\.13ad\.de/|
388 (?:www\.)?invidious\.mastodon\.host/|
389 (?:www\.)?invidious\.nixnet\.xyz/|
390 (?:www\.)?tube\.poal\.co/|
391 (?:www\.)?vid\.wxzm\.sx/|
392 (?:www\.)?yt\.elukerio\.org/|
393 (?:www\.)?kgg2m7yk5aybusll\.onion/|
394 (?:www\.)?qklhadlycap4cnod\.onion/|
395 (?:www\.)?axqzx4s6s54s32yentfqojs3x5i7faxza6xo3ehd4bzzsg2ii4fv2iid\.onion/|
396 (?:www\.)?c7hqkpkpemu6e7emz5b4vyz7idjgdvgaaa3dyimmeojqbgpea3xqjoid\.onion/|
397 (?:www\.)?fz253lmuao3strwbfbmx46yu7acac2jz27iwtorgmbqlkurlclmancad\.onion/|
398 (?:www\.)?invidious\.l4qlywnpwqsluw65ts7md3khrivpirse744un3x7mlskqauz5pyuzgqd\.onion/|
399 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
400 (?:.*?\#/)? # handle anchor (#/) redirect urls
401 (?: # the various things that can precede the ID:
402 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
403 |(?: # or the v= param in all its forms
404 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
405 (?:\?|\#!?) # the params delimiter ? or # or #!
406 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
411 youtu\.be| # just youtu.be/xxxx
412 vid\.plus| # or vid.plus/xxxx
413 zwearz\.com/watch| # or zwearz.com/watch/xxxx
415 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
417 )? # all until now is optional -> you can pass the naked ID
418 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
421 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
422 WL # WL are handled by the watch later IE
425 (?(1).+)? # if we found the ID, everything can follow
426 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
427 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
429 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
430 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
431 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
432 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
433 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
434 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
435 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
436 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
437 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
438 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
439 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
440 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
441 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
442 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
443 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
444 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
445 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
446 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
450 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
451 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
452 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
453 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
454 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
455 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
456 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
458 # Apple HTTP Live Streaming
459 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
460 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
461 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
462 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
463 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
464 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
465 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
466 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
469 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
470 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
471 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
472 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
473 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
474 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
475 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
476 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
477 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
478 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
479 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
480 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
483 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
484 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
485 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
486 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
487 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
488 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
489 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
492 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
493 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
494 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
495 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
496 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
497 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
498 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
499 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
500 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
501 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
502 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
503 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
504 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
505 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
506 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
507 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
508 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
509 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
510 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
511 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
512 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
513 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
516 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
517 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
519 # Dash webm audio with opus inside
520 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
521 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
522 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
525 '_rtmp': {'protocol': 'rtmp'},
527 # av01 video only formats sometimes served with "unknown" codecs
528 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
529 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
530 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
531 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
533 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
540 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
544 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
545 'uploader': 'Philipp Hagemeister',
546 'uploader_id': 'phihag',
547 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
548 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
549 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
550 'upload_date': '20121002',
551 '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 .',
552 'categories': ['Science & Technology'],
553 'tags': ['youtube-dl'],
557 'dislike_count': int,
563 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
564 'note': 'Test generic use_cipher_signature video (#897)',
568 'upload_date': '20120506',
569 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
570 'alt_title': 'I Love It (feat. Charli XCX)',
571 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
572 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
573 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
574 'iconic ep', 'iconic', 'love', 'it'],
576 'uploader': 'Icona Pop',
577 'uploader_id': 'IconaPop',
578 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
579 'creator': 'Icona Pop',
580 'track': 'I Love It (feat. Charli XCX)',
581 'artist': 'Icona Pop',
585 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
586 'note': 'Test VEVO video with age protection (#956)',
590 'upload_date': '20130703',
591 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
592 'alt_title': 'Tunnel Vision',
593 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
595 'uploader': 'justintimberlakeVEVO',
596 'uploader_id': 'justintimberlakeVEVO',
597 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
598 'creator': 'Justin Timberlake',
599 'track': 'Tunnel Vision',
600 'artist': 'Justin Timberlake',
605 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
606 'note': 'Embed-only video (#1746)',
610 'upload_date': '20120608',
611 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
612 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
613 'uploader': 'SET India',
614 'uploader_id': 'setindia',
615 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
620 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
621 'note': 'Use the first video ID in the URL',
625 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
626 'uploader': 'Philipp Hagemeister',
627 'uploader_id': 'phihag',
628 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
629 'upload_date': '20121002',
630 '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 .',
631 'categories': ['Science & Technology'],
632 'tags': ['youtube-dl'],
636 'dislike_count': int,
639 'skip_download': True,
643 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
644 'note': '256k DASH audio (format 141) via DASH manifest',
648 'upload_date': '20121002',
649 'uploader_id': '8KVIDEO',
650 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
652 'uploader': '8KVIDEO',
653 'title': 'UHDTV TEST 8K VIDEO.mp4'
656 'youtube_include_dash_manifest': True,
659 'skip': 'format 141 not served anymore',
661 # DASH manifest with encrypted signature
663 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
667 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
668 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
670 'uploader': 'AfrojackVEVO',
671 'uploader_id': 'AfrojackVEVO',
672 'upload_date': '20131011',
675 'youtube_include_dash_manifest': True,
676 'format': '141/bestaudio[ext=m4a]',
679 # JS player signature function name containing $
681 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
685 'title': 'Taylor Swift - Shake It Off',
686 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
688 'uploader': 'TaylorSwiftVEVO',
689 'uploader_id': 'TaylorSwiftVEVO',
690 'upload_date': '20140818',
691 'creator': 'Taylor Swift',
694 'youtube_include_dash_manifest': True,
695 'format': '141/bestaudio[ext=m4a]',
700 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
705 'upload_date': '20100909',
706 'uploader': 'Amazing Atheist',
707 'uploader_id': 'TheAmazingAtheist',
708 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
709 'title': 'Burning Everyone\'s Koran',
710 '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',
713 # Normal age-gate video (No vevo, embed allowed)
715 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
719 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
720 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
722 'uploader': 'The Witcher',
723 'uploader_id': 'WitcherGame',
724 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
725 'upload_date': '20140605',
729 # Age-gate video with encrypted signature
731 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
735 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
736 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
738 'uploader': 'LloydVEVO',
739 'uploader_id': 'LloydVEVO',
740 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
741 'upload_date': '20110629',
745 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
746 # YouTube Red ad is not captured for creator
748 'url': '__2ABJjxzNo',
753 'upload_date': '20100430',
754 'uploader_id': 'deadmau5',
755 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
756 'creator': 'deadmau5',
757 'description': 'md5:12c56784b8032162bb936a5f76d55360',
758 'uploader': 'deadmau5',
759 'title': 'Deadmau5 - Some Chords (HD)',
760 'alt_title': 'Some Chords',
762 'expected_warnings': [
763 'DASH manifest missing',
766 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
768 'url': 'lqQg6PlCWgI',
773 'upload_date': '20150827',
774 'uploader_id': 'olympic',
775 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
776 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
777 'uploader': 'Olympic',
778 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
781 'skip_download': 'requires avconv',
786 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
790 'stretched_ratio': 16 / 9.,
792 'upload_date': '20110310',
793 'uploader_id': 'AllenMeow',
794 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
795 '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',
797 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
800 # url_encoded_fmt_stream_map is empty string
802 'url': 'qEJwOuvDf7I',
806 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
808 'upload_date': '20150404',
809 'uploader_id': 'spbelect',
810 'uploader': 'Наблюдатели Петербурга',
813 'skip_download': 'requires avconv',
815 'skip': 'This live event has ended.',
817 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
819 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
823 'title': 'md5:7b81415841e02ecd4313668cde88737a',
824 'description': 'md5:116377fd2963b81ec4ce64b542173306',
826 'upload_date': '20150625',
827 'uploader_id': 'dorappi2000',
828 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
829 'uploader': 'dorappi2000',
830 'formats': 'mincount:31',
832 'skip': 'not actual anymore',
834 # DASH manifest with segment_list
836 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
837 'md5': '8ce563a1d667b599d21064e982ab9e31',
841 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
842 'uploader': 'Airtek',
843 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
844 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
845 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
848 'youtube_include_dash_manifest': True,
849 'format': '135', # bestvideo
851 'skip': 'This live event has ended.',
854 # Multifeed videos (multiple cameras), URL is for Main Camera
855 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
858 'title': 'teamPGP: Rocket League Noob Stream',
859 'description': 'md5:dc7872fb300e143831327f1bae3af010',
865 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
866 'description': 'md5:dc7872fb300e143831327f1bae3af010',
868 'upload_date': '20150721',
869 'uploader': 'Beer Games Beer',
870 'uploader_id': 'beergamesbeer',
871 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
872 'license': 'Standard YouTube License',
878 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
879 'description': 'md5:dc7872fb300e143831327f1bae3af010',
881 'upload_date': '20150721',
882 'uploader': 'Beer Games Beer',
883 'uploader_id': 'beergamesbeer',
884 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
885 'license': 'Standard YouTube License',
891 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
892 'description': 'md5:dc7872fb300e143831327f1bae3af010',
894 'upload_date': '20150721',
895 'uploader': 'Beer Games Beer',
896 'uploader_id': 'beergamesbeer',
897 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
898 'license': 'Standard YouTube License',
904 'title': 'teamPGP: Rocket League Noob Stream (zim)',
905 'description': 'md5:dc7872fb300e143831327f1bae3af010',
907 'upload_date': '20150721',
908 'uploader': 'Beer Games Beer',
909 'uploader_id': 'beergamesbeer',
910 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
911 'license': 'Standard YouTube License',
915 'skip_download': True,
917 'skip': 'This video is not available.',
920 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
921 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
924 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
927 'skip': 'Not multifeed anymore',
930 'url': 'https://vid.plus/FlRa-iH7PGw',
931 'only_matching': True,
934 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
935 'only_matching': True,
938 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
939 # Also tests cut-off URL expansion in video description (see
940 # https://github.com/ytdl-org/youtube-dl/issues/1892,
941 # https://github.com/ytdl-org/youtube-dl/issues/8164)
942 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
946 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
947 'alt_title': 'Dark Walk - Position Music',
948 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
950 'upload_date': '20151119',
951 'uploader_id': 'IronSoulElf',
952 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
953 'uploader': 'IronSoulElf',
954 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
955 'track': 'Dark Walk - Position Music',
956 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
957 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
960 'skip_download': True,
964 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
965 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
966 'only_matching': True,
969 # Video with yt:stretch=17:0
970 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
974 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
975 'description': 'md5:ee18a25c350637c8faff806845bddee9',
976 'upload_date': '20151107',
977 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
978 'uploader': 'CH GAMER DROID',
981 'skip_download': True,
983 'skip': 'This video does not exist.',
986 # Video licensed under Creative Commons
987 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
991 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
992 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
994 'upload_date': '20150127',
995 'uploader_id': 'BerkmanCenter',
996 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
997 'uploader': 'The Berkman Klein Center for Internet & Society',
998 'license': 'Creative Commons Attribution license (reuse allowed)',
1001 'skip_download': True,
1005 # Channel-like uploader_url
1006 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
1008 'id': 'eQcmzGIKrzg',
1010 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
1011 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
1013 'upload_date': '20151119',
1014 'uploader': 'Bernie Sanders',
1015 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
1016 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
1017 'license': 'Creative Commons Attribution license (reuse allowed)',
1020 'skip_download': True,
1024 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1025 'only_matching': True,
1028 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1029 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1030 'only_matching': True,
1033 # Rental video preview
1034 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1036 'id': 'uGpuVWrhIzE',
1038 'title': 'Piku - Trailer',
1039 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1040 'upload_date': '20150811',
1041 'uploader': 'FlixMatrix',
1042 'uploader_id': 'FlixMatrixKaravan',
1043 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1044 'license': 'Standard YouTube License',
1047 'skip_download': True,
1049 'skip': 'This video is not available.',
1052 # YouTube Red video with episode data
1053 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1055 'id': 'iqKdEhx-dD4',
1057 'title': 'Isolation - Mind Field (Ep 1)',
1058 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1060 'upload_date': '20170118',
1061 'uploader': 'Vsauce',
1062 'uploader_id': 'Vsauce',
1063 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1064 'series': 'Mind Field',
1066 'episode_number': 1,
1069 'skip_download': True,
1071 'expected_warnings': [
1072 'Skipping DASH manifest',
1076 # The following content has been identified by the YouTube community
1077 # as inappropriate or offensive to some audiences.
1078 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1080 'id': '6SJNVb0GnPI',
1082 'title': 'Race Differences in Intelligence',
1083 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1085 'upload_date': '20140124',
1086 'uploader': 'New Century Foundation',
1087 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1088 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1091 'skip_download': True,
1096 'url': '1t24XAntNCY',
1097 'only_matching': True,
1100 # geo restricted to JP
1101 'url': 'sJL6WA-aGkQ',
1102 'only_matching': True,
1105 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1106 'only_matching': True,
1109 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1110 'only_matching': True,
1114 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1115 'only_matching': True,
1118 # Video with unsupported adaptive stream type formats
1119 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1121 'id': 'Z4Vy8R84T1U',
1123 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1124 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1126 'upload_date': '20130923',
1127 'uploader': 'Amelia Putri Harwita',
1128 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1129 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1130 'formats': 'maxcount:10',
1133 'skip_download': True,
1134 'youtube_include_dash_manifest': False,
1138 # Youtube Music Auto-generated description
1139 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1141 'id': 'MgNrAu2pzNs',
1143 'title': 'Voyeur Girl',
1144 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1145 'upload_date': '20190312',
1146 'uploader': 'Various Artists - Topic',
1147 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1148 'artist': 'Stephen',
1149 'track': 'Voyeur Girl',
1150 'album': 'it\'s too much love to know my dear',
1151 'release_date': '20190313',
1152 'release_year': 2019,
1155 'skip_download': True,
1159 # Youtube Music Auto-generated description
1160 # Retrieve 'artist' field from 'Artist:' in video description
1161 # when it is present on youtube music video
1162 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1164 'id': 'k0jLE7tTwjY',
1166 'title': 'Latch Feat. Sam Smith',
1167 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1168 'upload_date': '20150110',
1169 'uploader': 'Various Artists - Topic',
1170 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1171 'artist': 'Disclosure',
1172 'track': 'Latch Feat. Sam Smith',
1173 'album': 'Latch Featuring Sam Smith',
1174 'release_date': '20121008',
1175 'release_year': 2012,
1178 'skip_download': True,
1182 # Youtube Music Auto-generated description
1183 # handle multiple artists on youtube music video
1184 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1186 'id': '74qn0eJSjpA',
1188 'title': 'Eastside',
1189 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1190 'upload_date': '20180710',
1191 'uploader': 'Benny Blanco - Topic',
1192 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1193 'artist': 'benny blanco, Halsey, Khalid',
1194 'track': 'Eastside',
1195 'album': 'Eastside',
1196 'release_date': '20180713',
1197 'release_year': 2018,
1200 'skip_download': True,
1204 # Youtube Music Auto-generated description
1205 # handle youtube music video with release_year and no release_date
1206 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1208 'id': '-hcAI0g-f5M',
1210 'title': 'Put It On Me',
1211 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1212 'upload_date': '20180426',
1213 'uploader': 'Matt Maeson - Topic',
1214 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1215 'artist': 'Matt Maeson',
1216 'track': 'Put It On Me',
1217 'album': 'The Hearse',
1218 'release_date': None,
1219 'release_year': 2018,
1222 'skip_download': True,
1227 def __init__(self, *args, **kwargs):
1228 super(YoutubeIE, self).__init__(*args, **kwargs)
1229 self._player_cache = {}
1231 def report_video_info_webpage_download(self, video_id):
1232 """Report attempt to download video info webpage."""
1233 self.to_screen('%s: Downloading video info webpage' % video_id)
1235 def report_information_extraction(self, video_id):
1236 """Report attempt to extract video information."""
1237 self.to_screen('%s: Extracting video information' % video_id)
1239 def report_unavailable_format(self, video_id, format):
1240 """Report extracted video URL."""
1241 self.to_screen('%s: Format %s not available' % (video_id, format))
1243 def report_rtmp_download(self):
1244 """Indicate the download will use the RTMP protocol."""
1245 self.to_screen('RTMP download detected')
1247 def _signature_cache_id(self, example_sig):
1248 """ Return a string representation of a signature """
1249 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1251 def _extract_signature_function(self, video_id, player_url, example_sig):
1253 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1256 raise ExtractorError('Cannot identify player %r' % player_url)
1257 player_type = id_m.group('ext')
1258 player_id = id_m.group('id')
1260 # Read from filesystem cache
1261 func_id = '%s_%s_%s' % (
1262 player_type, player_id, self._signature_cache_id(example_sig))
1263 assert os.path.basename(func_id) == func_id
1265 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1266 if cache_spec is not None:
1267 return lambda s: ''.join(s[i] for i in cache_spec)
1270 'Downloading player %s' % player_url
1271 if self._downloader.params.get('verbose') else
1272 'Downloading %s player %s' % (player_type, player_id)
1274 if player_type == 'js':
1275 code = self._download_webpage(
1276 player_url, video_id,
1278 errnote='Download of %s failed' % player_url)
1279 res = self._parse_sig_js(code)
1280 elif player_type == 'swf':
1281 urlh = self._request_webpage(
1282 player_url, video_id,
1284 errnote='Download of %s failed' % player_url)
1286 res = self._parse_sig_swf(code)
1288 assert False, 'Invalid player type %r' % player_type
1290 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1291 cache_res = res(test_string)
1292 cache_spec = [ord(c) for c in cache_res]
1294 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1297 def _print_sig_code(self, func, example_sig):
1298 def gen_sig_code(idxs):
1299 def _genslice(start, end, step):
1300 starts = '' if start == 0 else str(start)
1301 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1302 steps = '' if step == 1 else (':%d' % step)
1303 return 's[%s%s%s]' % (starts, ends, steps)
1306 # Quelch pyflakes warnings - start will be set when step is set
1307 start = '(Never used)'
1308 for i, prev in zip(idxs[1:], idxs[:-1]):
1309 if step is not None:
1310 if i - prev == step:
1312 yield _genslice(start, prev, step)
1315 if i - prev in [-1, 1]:
1320 yield 's[%d]' % prev
1324 yield _genslice(start, i, step)
1326 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1327 cache_res = func(test_string)
1328 cache_spec = [ord(c) for c in cache_res]
1329 expr_code = ' + '.join(gen_sig_code(cache_spec))
1330 signature_id_tuple = '(%s)' % (
1331 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1332 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1333 ' return %s\n') % (signature_id_tuple, expr_code)
1334 self.to_screen('Extracted signature function:\n' + code)
1336 def _parse_sig_js(self, jscode):
1337 funcname = self._search_regex(
1338 (r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1339 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*encodeURIComponent\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1340 r'(?P<sig>[a-zA-Z0-9$]+)\s*=\s*function\(\s*a\s*\)\s*{\s*a\s*=\s*a\.split\(\s*""\s*\)',
1342 r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1343 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1344 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1345 r'\b[cs]\s*&&\s*[adf]\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1346 r'\b[a-zA-Z0-9]+\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1347 r'\bc\s*&&\s*a\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1348 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1349 r'\bc\s*&&\s*[a-zA-Z0-9]+\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1350 jscode, 'Initial JS player signature function name', group='sig')
1352 jsi = JSInterpreter(jscode)
1353 initial_function = jsi.extract_function(funcname)
1354 return lambda s: initial_function([s])
1356 def _parse_sig_swf(self, file_contents):
1357 swfi = SWFInterpreter(file_contents)
1358 TARGET_CLASSNAME = 'SignatureDecipher'
1359 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1360 initial_function = swfi.extract_function(searched_class, 'decipher')
1361 return lambda s: initial_function([s])
1363 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1364 """Turn the encrypted s field into a working signature"""
1366 if player_url is None:
1367 raise ExtractorError('Cannot decrypt signature without player_url')
1369 if player_url.startswith('//'):
1370 player_url = 'https:' + player_url
1371 elif not re.match(r'https?://', player_url):
1372 player_url = compat_urlparse.urljoin(
1373 'https://www.youtube.com', player_url)
1375 player_id = (player_url, self._signature_cache_id(s))
1376 if player_id not in self._player_cache:
1377 func = self._extract_signature_function(
1378 video_id, player_url, s
1380 self._player_cache[player_id] = func
1381 func = self._player_cache[player_id]
1382 if self._downloader.params.get('youtube_print_sig_code'):
1383 self._print_sig_code(func, s)
1385 except Exception as e:
1386 tb = traceback.format_exc()
1387 raise ExtractorError(
1388 'Signature extraction failed: ' + tb, cause=e)
1390 def _get_subtitles(self, video_id, webpage):
1392 subs_doc = self._download_xml(
1393 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1394 video_id, note=False)
1395 except ExtractorError as err:
1396 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1400 for track in subs_doc.findall('track'):
1401 lang = track.attrib['lang_code']
1402 if lang in sub_lang_list:
1405 for ext in self._SUBTITLE_FORMATS:
1406 params = compat_urllib_parse_urlencode({
1410 'name': track.attrib['name'].encode('utf-8'),
1412 sub_formats.append({
1413 'url': 'https://www.youtube.com/api/timedtext?' + params,
1416 sub_lang_list[lang] = sub_formats
1417 if not sub_lang_list:
1418 self._downloader.report_warning('video doesn\'t have subtitles')
1420 return sub_lang_list
1422 def _get_ytplayer_config(self, video_id, webpage):
1424 # User data may contain arbitrary character sequences that may affect
1425 # JSON extraction with regex, e.g. when '};' is contained the second
1426 # regex won't capture the whole JSON. Yet working around by trying more
1427 # concrete regex first keeping in mind proper quoted string handling
1428 # to be implemented in future that will replace this workaround (see
1429 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1430 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1431 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1432 r';ytplayer\.config\s*=\s*({.+?});',
1434 config = self._search_regex(
1435 patterns, webpage, 'ytplayer.config', default=None)
1437 return self._parse_json(
1438 uppercase_escape(config), video_id, fatal=False)
1440 def _get_automatic_captions(self, video_id, webpage):
1441 """We need the webpage for getting the captions url, pass it as an
1442 argument to speed up the process."""
1443 self.to_screen('%s: Looking for automatic captions' % video_id)
1444 player_config = self._get_ytplayer_config(video_id, webpage)
1445 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1446 if not player_config:
1447 self._downloader.report_warning(err_msg)
1450 args = player_config['args']
1451 caption_url = args.get('ttsurl')
1453 timestamp = args['timestamp']
1454 # We get the available subtitles
1455 list_params = compat_urllib_parse_urlencode({
1460 list_url = caption_url + '&' + list_params
1461 caption_list = self._download_xml(list_url, video_id)
1462 original_lang_node = caption_list.find('track')
1463 if original_lang_node is None:
1464 self._downloader.report_warning('Video doesn\'t have automatic captions')
1466 original_lang = original_lang_node.attrib['lang_code']
1467 caption_kind = original_lang_node.attrib.get('kind', '')
1470 for lang_node in caption_list.findall('target'):
1471 sub_lang = lang_node.attrib['lang_code']
1473 for ext in self._SUBTITLE_FORMATS:
1474 params = compat_urllib_parse_urlencode({
1475 'lang': original_lang,
1479 'kind': caption_kind,
1481 sub_formats.append({
1482 'url': caption_url + '&' + params,
1485 sub_lang_list[sub_lang] = sub_formats
1486 return sub_lang_list
1488 def make_captions(sub_url, sub_langs):
1489 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1490 caption_qs = compat_parse_qs(parsed_sub_url.query)
1492 for sub_lang in sub_langs:
1494 for ext in self._SUBTITLE_FORMATS:
1496 'tlang': [sub_lang],
1499 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1500 query=compat_urllib_parse_urlencode(caption_qs, True)))
1501 sub_formats.append({
1505 captions[sub_lang] = sub_formats
1508 # New captions format as of 22.06.2017
1509 player_response = args.get('player_response')
1510 if player_response and isinstance(player_response, compat_str):
1511 player_response = self._parse_json(
1512 player_response, video_id, fatal=False)
1514 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1515 base_url = renderer['captionTracks'][0]['baseUrl']
1517 for lang in renderer['translationLanguages']:
1518 lang_code = lang.get('languageCode')
1520 sub_lang_list.append(lang_code)
1521 return make_captions(base_url, sub_lang_list)
1523 # Some videos don't provide ttsurl but rather caption_tracks and
1524 # caption_translation_languages (e.g. 20LmZk1hakA)
1525 # Does not used anymore as of 22.06.2017
1526 caption_tracks = args['caption_tracks']
1527 caption_translation_languages = args['caption_translation_languages']
1528 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1530 for lang in caption_translation_languages.split(','):
1531 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1532 sub_lang = lang_qs.get('lc', [None])[0]
1534 sub_lang_list.append(sub_lang)
1535 return make_captions(caption_url, sub_lang_list)
1536 # An extractor error can be raise by the download process if there are
1537 # no automatic captions but there are subtitles
1538 except (KeyError, IndexError, ExtractorError):
1539 self._downloader.report_warning(err_msg)
1542 def _mark_watched(self, video_id, video_info, player_response):
1543 playback_url = url_or_none(try_get(
1545 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1546 video_info, lambda x: x['videostats_playback_base_url'][0]))
1547 if not playback_url:
1549 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1550 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1552 # cpn generation algorithm is reverse engineered from base.js.
1553 # In fact it works even with dummy cpn.
1554 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1555 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1561 playback_url = compat_urlparse.urlunparse(
1562 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1564 self._download_webpage(
1565 playback_url, video_id, 'Marking watched',
1566 'Unable to mark watched', fatal=False)
1569 def _extract_urls(webpage):
1570 # Embedded YouTube player
1572 unescapeHTML(mobj.group('url'))
1573 for mobj in re.finditer(r'''(?x)
1583 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1584 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1587 # lazyYT YouTube embed
1588 entries.extend(list(map(
1590 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1592 # Wordpress "YouTube Video Importer" plugin
1593 matches = re.findall(r'''(?x)<div[^>]+
1594 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1595 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1596 entries.extend(m[-1] for m in matches)
1601 def _extract_url(webpage):
1602 urls = YoutubeIE._extract_urls(webpage)
1603 return urls[0] if urls else None
1606 def extract_id(cls, url):
1607 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1609 raise ExtractorError('Invalid URL: %s' % url)
1610 video_id = mobj.group(2)
1614 def _extract_chapters(description, duration):
1617 chapter_lines = re.findall(
1618 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1620 if not chapter_lines:
1623 for next_num, (chapter_line, time_point) in enumerate(
1624 chapter_lines, start=1):
1625 start_time = parse_duration(time_point)
1626 if start_time is None:
1628 if start_time > duration:
1630 end_time = (duration if next_num == len(chapter_lines)
1631 else parse_duration(chapter_lines[next_num][1]))
1632 if end_time is None:
1634 if end_time > duration:
1636 if start_time > end_time:
1638 chapter_title = re.sub(
1639 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1640 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1642 'start_time': start_time,
1643 'end_time': end_time,
1644 'title': chapter_title,
1648 def _real_extract(self, url):
1649 url, smuggled_data = unsmuggle_url(url, {})
1652 'http' if self._downloader.params.get('prefer_insecure', False)
1657 parsed_url = compat_urllib_parse_urlparse(url)
1658 for component in [parsed_url.fragment, parsed_url.query]:
1659 query = compat_parse_qs(component)
1660 if start_time is None and 't' in query:
1661 start_time = parse_duration(query['t'][0])
1662 if start_time is None and 'start' in query:
1663 start_time = parse_duration(query['start'][0])
1664 if end_time is None and 'end' in query:
1665 end_time = parse_duration(query['end'][0])
1667 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1668 mobj = re.search(self._NEXT_URL_RE, url)
1670 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1671 video_id = self.extract_id(url)
1674 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1675 video_webpage = self._download_webpage(url, video_id)
1677 # Attempt to extract SWF player URL
1678 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1679 if mobj is not None:
1680 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1686 def add_dash_mpd(video_info):
1687 dash_mpd = video_info.get('dashmpd')
1688 if dash_mpd and dash_mpd[0] not in dash_mpds:
1689 dash_mpds.append(dash_mpd[0])
1691 def add_dash_mpd_pr(pl_response):
1692 dash_mpd = url_or_none(try_get(
1693 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1695 if dash_mpd and dash_mpd not in dash_mpds:
1696 dash_mpds.append(dash_mpd)
1701 def extract_view_count(v_info):
1702 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1704 def extract_token(v_info):
1705 return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
1707 def extract_player_response(player_response, video_id):
1708 pl_response = str_or_none(player_response)
1711 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1712 if isinstance(pl_response, dict):
1713 add_dash_mpd_pr(pl_response)
1716 player_response = {}
1719 embed_webpage = None
1720 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1722 # We simulate the access to the video from www.youtube.com/v/{video_id}
1723 # this can be viewed without login into Youtube
1724 url = proto + '://www.youtube.com/embed/%s' % video_id
1725 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1726 data = compat_urllib_parse_urlencode({
1727 'video_id': video_id,
1728 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1729 'sts': self._search_regex(
1730 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1732 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1733 video_info_webpage = self._download_webpage(
1734 video_info_url, video_id,
1735 note='Refetching age-gated info webpage',
1736 errnote='unable to download video info webpage')
1737 video_info = compat_parse_qs(video_info_webpage)
1738 pl_response = video_info.get('player_response', [None])[0]
1739 player_response = extract_player_response(pl_response, video_id)
1740 add_dash_mpd(video_info)
1741 view_count = extract_view_count(video_info)
1746 # Try looking directly into the video webpage
1747 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1749 args = ytplayer_config['args']
1750 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1751 # Convert to the same format returned by compat_parse_qs
1752 video_info = dict((k, [v]) for k, v in args.items())
1753 add_dash_mpd(video_info)
1754 # Rental video is not rented but preview is available (e.g.
1755 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1756 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1757 if not video_info and args.get('ypc_vid'):
1758 return self.url_result(
1759 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1760 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1762 sts = ytplayer_config.get('sts')
1763 if not player_response:
1764 player_response = extract_player_response(args.get('player_response'), video_id)
1765 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1766 add_dash_mpd_pr(player_response)
1767 # We also try looking in get_video_info since it may contain different dashmpd
1768 # URL that points to a DASH manifest with possibly different itag set (some itags
1769 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1770 # manifest pointed by get_video_info's dashmpd).
1771 # The general idea is to take a union of itags of both DASH manifests (for example
1772 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1773 self.report_video_info_webpage_download(video_id)
1774 for el in ('embedded', 'detailpage', 'vevo', ''):
1776 'video_id': video_id,
1786 video_info_webpage = self._download_webpage(
1787 '%s://www.youtube.com/get_video_info' % proto,
1788 video_id, note=False,
1789 errnote='unable to download video info webpage',
1790 fatal=False, query=query)
1791 if not video_info_webpage:
1793 get_video_info = compat_parse_qs(video_info_webpage)
1794 if not player_response:
1795 pl_response = get_video_info.get('player_response', [None])[0]
1796 player_response = extract_player_response(pl_response, video_id)
1797 add_dash_mpd(get_video_info)
1798 if view_count is None:
1799 view_count = extract_view_count(get_video_info)
1801 video_info = get_video_info
1802 get_token = extract_token(get_video_info)
1804 # Different get_video_info requests may report different results, e.g.
1805 # some may report video unavailability, but some may serve it without
1806 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1807 # the original webpage as well as el=info and el=embedded get_video_info
1808 # requests report video unavailability due to geo restriction while
1809 # el=detailpage succeeds and returns valid data). This is probably
1810 # due to YouTube measures against IP ranges of hosting providers.
1811 # Working around by preferring the first succeeded video_info containing
1812 # the token if no such video_info yet was found.
1813 token = extract_token(video_info)
1815 video_info = get_video_info
1818 def extract_unavailable_message():
1820 for tag, kind in (('h1', 'message'), ('div', 'submessage')):
1821 msg = self._html_search_regex(
1822 r'(?s)<{tag}[^>]+id=["\']unavailable-{kind}["\'][^>]*>(.+?)</{tag}>'.format(tag=tag, kind=kind),
1823 video_webpage, 'unavailable %s' % kind, default=None)
1825 messages.append(msg)
1827 return '\n'.join(messages)
1830 unavailable_message = extract_unavailable_message()
1831 if not unavailable_message:
1832 unavailable_message = 'Unable to extract video data'
1833 raise ExtractorError(
1834 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1836 video_details = try_get(
1837 player_response, lambda x: x['videoDetails'], dict) or {}
1839 video_title = video_info.get('title', [None])[0] or video_details.get('title')
1841 self._downloader.report_warning('Unable to extract video title')
1844 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1845 if video_description:
1848 redir_url = compat_urlparse.urljoin(url, m.group(1))
1849 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1850 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1851 qs = compat_parse_qs(parsed_redir_url.query)
1857 description_original = video_description = re.sub(r'''(?x)
1859 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1860 (?:title|href)="([^"]+)"\s+
1861 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1865 ''', replace_url, video_description)
1866 video_description = clean_html(video_description)
1868 video_description = self._html_search_meta('description', video_webpage) or video_details.get('shortDescription')
1870 if not smuggled_data.get('force_singlefeed', False):
1871 if not self._downloader.params.get('noplaylist'):
1872 multifeed_metadata_list = try_get(
1874 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1875 compat_str) or try_get(
1876 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1877 if multifeed_metadata_list:
1880 for feed in multifeed_metadata_list.split(','):
1881 # Unquote should take place before split on comma (,) since textual
1882 # fields may contain comma as well (see
1883 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1884 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1886 '_type': 'url_transparent',
1887 'ie_key': 'Youtube',
1889 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1890 {'force_singlefeed': True}),
1891 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1893 feed_ids.append(feed_data['id'][0])
1895 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1896 % (', '.join(feed_ids), video_id))
1897 return self.playlist_result(entries, video_id, video_title, video_description)
1899 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1901 if view_count is None:
1902 view_count = extract_view_count(video_info)
1903 if view_count is None and video_details:
1904 view_count = int_or_none(video_details.get('viewCount'))
1907 is_live = bool_or_none(video_details.get('isLive'))
1909 # Check for "rental" videos
1910 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1911 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1913 def _extract_filesize(media_url):
1914 return int_or_none(self._search_regex(
1915 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1917 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list) or []
1918 streaming_formats.extend(try_get(player_response, lambda x: x['streamingData']['adaptiveFormats'], list) or [])
1920 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1921 self.report_rtmp_download()
1923 'format_id': '_rtmp',
1925 'url': video_info['conn'][0],
1926 'player_url': player_url,
1928 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):
1929 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1930 if 'rtmpe%3Dyes' in encoded_url_map:
1931 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1934 fmt_list = video_info.get('fmt_list', [''])[0]
1936 for fmt in fmt_list.split(','):
1937 spec = fmt.split('/')
1939 width_height = spec[1].split('x')
1940 if len(width_height) == 2:
1941 formats_spec[spec[0]] = {
1942 'resolution': spec[1],
1943 'width': int_or_none(width_height[0]),
1944 'height': int_or_none(width_height[1]),
1946 for fmt in streaming_formats:
1947 itag = str_or_none(fmt.get('itag'))
1950 quality = fmt.get('quality')
1951 quality_label = fmt.get('qualityLabel') or quality
1952 formats_spec[itag] = {
1953 'asr': int_or_none(fmt.get('audioSampleRate')),
1954 'filesize': int_or_none(fmt.get('contentLength')),
1955 'format_note': quality_label,
1956 'fps': int_or_none(fmt.get('fps')),
1957 'height': int_or_none(fmt.get('height')),
1958 # bitrate for itag 43 is always 2147483647
1959 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1960 'width': int_or_none(fmt.get('width')),
1963 for fmt in streaming_formats:
1964 if fmt.get('drm_families'):
1966 url = url_or_none(fmt.get('url'))
1969 cipher = fmt.get('cipher')
1972 url_data = compat_parse_qs(cipher)
1973 url = url_or_none(try_get(url_data, lambda x: x['url'][0], compat_str))
1978 url_data = compat_parse_qs(compat_urllib_parse_urlparse(url).query)
1980 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1981 # Unsupported FORMAT_STREAM_TYPE_OTF
1982 if stream_type == 3:
1985 format_id = fmt.get('itag') or url_data['itag'][0]
1988 format_id = compat_str(format_id)
1991 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1992 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1993 jsplayer_url_json = self._search_regex(
1995 embed_webpage if age_gate else video_webpage,
1996 'JS player URL (1)', default=None)
1997 if not jsplayer_url_json and not age_gate:
1998 # We need the embed website after all
1999 if embed_webpage is None:
2000 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
2001 embed_webpage = self._download_webpage(
2002 embed_url, video_id, 'Downloading embed webpage')
2003 jsplayer_url_json = self._search_regex(
2004 ASSETS_RE, embed_webpage, 'JS player URL')
2006 player_url = json.loads(jsplayer_url_json)
2007 if player_url is None:
2008 player_url_json = self._search_regex(
2009 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
2010 video_webpage, 'age gate player URL')
2011 player_url = json.loads(player_url_json)
2013 if 'sig' in url_data:
2014 url += '&signature=' + url_data['sig'][0]
2015 elif 's' in url_data:
2016 encrypted_sig = url_data['s'][0]
2018 if self._downloader.params.get('verbose'):
2019 if player_url is None:
2020 player_version = 'unknown'
2021 player_desc = 'unknown'
2023 if player_url.endswith('swf'):
2024 player_version = self._search_regex(
2025 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
2026 'flash player', fatal=False)
2027 player_desc = 'flash player %s' % player_version
2029 player_version = self._search_regex(
2030 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
2031 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
2033 'html5 player', fatal=False)
2034 player_desc = 'html5 player %s' % player_version
2036 parts_sizes = self._signature_cache_id(encrypted_sig)
2037 self.to_screen('{%s} signature length %s, %s' %
2038 (format_id, parts_sizes, player_desc))
2040 signature = self._decrypt_signature(
2041 encrypted_sig, video_id, player_url, age_gate)
2042 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
2043 url += '&%s=%s' % (sp, signature)
2044 if 'ratebypass' not in url:
2045 url += '&ratebypass=yes'
2048 'format_id': format_id,
2050 'player_url': player_url,
2052 if format_id in self._formats:
2053 dct.update(self._formats[format_id])
2054 if format_id in formats_spec:
2055 dct.update(formats_spec[format_id])
2057 # Some itags are not included in DASH manifest thus corresponding formats will
2058 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2059 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2060 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2061 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2064 width = int_or_none(fmt.get('width'))
2066 height = int_or_none(fmt.get('height'))
2068 filesize = int_or_none(url_data.get(
2069 'clen', [None])[0]) or _extract_filesize(url)
2071 quality = url_data.get('quality', [None])[0] or fmt.get('quality')
2072 quality_label = url_data.get('quality_label', [None])[0] or fmt.get('qualityLabel')
2074 tbr = (float_or_none(url_data.get('bitrate', [None])[0], 1000)
2075 or float_or_none(fmt.get('bitrate'), 1000)) if format_id != '43' else None
2076 fps = int_or_none(url_data.get('fps', [None])[0]) or int_or_none(fmt.get('fps'))
2079 'filesize': filesize,
2084 'format_note': quality_label or quality,
2086 for key, value in more_fields.items():
2089 type_ = url_data.get('type', [None])[0] or fmt.get('mimeType')
2091 type_split = type_.split(';')
2092 kind_ext = type_split[0].split('/')
2093 if len(kind_ext) == 2:
2095 dct['ext'] = mimetype2ext(type_split[0])
2096 if kind in ('audio', 'video'):
2098 for mobj in re.finditer(
2099 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2100 if mobj.group('key') == 'codecs':
2101 codecs = mobj.group('val')
2104 dct.update(parse_codecs(codecs))
2105 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2106 dct['downloader_options'] = {
2107 # Youtube throttles chunks >~10M
2108 'http_chunk_size': 10485760,
2113 url_or_none(try_get(
2115 lambda x: x['streamingData']['hlsManifestUrl'],
2117 or url_or_none(try_get(
2118 video_info, lambda x: x['hlsvp'][0], compat_str)))
2121 m3u8_formats = self._extract_m3u8_formats(
2122 manifest_url, video_id, 'mp4', fatal=False)
2123 for a_format in m3u8_formats:
2124 itag = self._search_regex(
2125 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2127 a_format['format_id'] = itag
2128 if itag in self._formats:
2129 dct = self._formats[itag].copy()
2130 dct.update(a_format)
2132 a_format['player_url'] = player_url
2133 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2134 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2135 formats.append(a_format)
2137 error_message = extract_unavailable_message()
2138 if not error_message:
2139 error_message = clean_html(try_get(
2140 player_response, lambda x: x['playabilityStatus']['reason'],
2142 if not error_message:
2143 error_message = clean_html(
2144 try_get(video_info, lambda x: x['reason'][0], compat_str))
2146 raise ExtractorError(error_message, expected=True)
2147 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2150 video_uploader = try_get(
2151 video_info, lambda x: x['author'][0],
2152 compat_str) or str_or_none(video_details.get('author'))
2154 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2156 self._downloader.report_warning('unable to extract uploader name')
2159 video_uploader_id = None
2160 video_uploader_url = None
2162 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2164 if mobj is not None:
2165 video_uploader_id = mobj.group('uploader_id')
2166 video_uploader_url = mobj.group('uploader_url')
2168 self._downloader.report_warning('unable to extract uploader nickname')
2171 str_or_none(video_details.get('channelId'))
2172 or self._html_search_meta(
2173 'channelId', video_webpage, 'channel id', default=None)
2174 or self._search_regex(
2175 r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
2176 video_webpage, 'channel id', default=None, group='id'))
2177 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2180 # We try first to get a high quality image:
2181 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2182 video_webpage, re.DOTALL)
2183 if m_thumb is not None:
2184 video_thumbnail = m_thumb.group(1)
2185 elif 'thumbnail_url' not in video_info:
2186 self._downloader.report_warning('unable to extract video thumbnail')
2187 video_thumbnail = None
2188 else: # don't panic if we can't find it
2189 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2192 upload_date = self._html_search_meta(
2193 'datePublished', video_webpage, 'upload date', default=None)
2195 upload_date = self._search_regex(
2196 [r'(?s)id="eow-date.*?>(.*?)</span>',
2197 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2198 video_webpage, 'upload date', default=None)
2199 upload_date = unified_strdate(upload_date)
2201 video_license = self._html_search_regex(
2202 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2203 video_webpage, 'license', default=None)
2205 m_music = re.search(
2207 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2215 \bhref=["\']/red[^>]*>| # drop possible
2216 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2223 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2224 video_creator = clean_html(m_music.group('creator'))
2226 video_alt_title = video_creator = None
2228 def extract_meta(field):
2229 return self._html_search_regex(
2230 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2231 video_webpage, field, default=None)
2233 track = extract_meta('Song')
2234 artist = extract_meta('Artist')
2235 album = extract_meta('Album')
2237 # Youtube Music Auto-generated description
2238 release_date = release_year = None
2239 if video_description:
2240 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)
2243 track = mobj.group('track').strip()
2245 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2247 album = mobj.group('album'.strip())
2248 release_year = mobj.group('release_year')
2249 release_date = mobj.group('release_date')
2251 release_date = release_date.replace('-', '')
2252 if not release_year:
2253 release_year = int(release_date[:4])
2255 release_year = int(release_year)
2257 m_episode = re.search(
2258 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2261 series = unescapeHTML(m_episode.group('series'))
2262 season_number = int(m_episode.group('season'))
2263 episode_number = int(m_episode.group('episode'))
2265 series = season_number = episode_number = None
2267 m_cat_container = self._search_regex(
2268 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2269 video_webpage, 'categories', default=None)
2271 category = self._html_search_regex(
2272 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2274 video_categories = None if category is None else [category]
2276 video_categories = None
2279 unescapeHTML(m.group('content'))
2280 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2282 def _extract_count(count_name):
2283 return str_to_int(self._search_regex(
2284 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2285 % re.escape(count_name),
2286 video_webpage, count_name, default=None))
2288 like_count = _extract_count('like')
2289 dislike_count = _extract_count('dislike')
2291 if view_count is None:
2292 view_count = str_to_int(self._search_regex(
2293 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2294 'view count', default=None))
2297 float_or_none(video_details.get('averageRating'))
2298 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2301 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2302 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2304 video_duration = try_get(
2305 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2306 if not video_duration:
2307 video_duration = int_or_none(video_details.get('lengthSeconds'))
2308 if not video_duration:
2309 video_duration = parse_duration(self._html_search_meta(
2310 'duration', video_webpage, 'video duration'))
2313 video_annotations = None
2314 if self._downloader.params.get('writeannotations', False):
2315 xsrf_token = self._search_regex(
2316 r'([\'"])XSRF_TOKEN\1\s*:\s*([\'"])(?P<xsrf_token>[A-Za-z0-9+/=]+)\2',
2317 video_webpage, 'xsrf token', group='xsrf_token', fatal=False)
2318 invideo_url = try_get(
2319 player_response, lambda x: x['annotations'][0]['playerAnnotationsUrlsRenderer']['invideoUrl'], compat_str)
2320 if xsrf_token and invideo_url:
2321 xsrf_field_name = self._search_regex(
2322 r'([\'"])XSRF_FIELD_NAME\1\s*:\s*([\'"])(?P<xsrf_field_name>\w+)\2',
2323 video_webpage, 'xsrf field name',
2324 group='xsrf_field_name', default='session_token')
2325 video_annotations = self._download_webpage(
2326 self._proto_relative_url(invideo_url),
2327 video_id, note='Downloading annotations',
2328 errnote='Unable to download video annotations', fatal=False,
2329 data=urlencode_postdata({xsrf_field_name: xsrf_token}))
2331 chapters = self._extract_chapters(description_original, video_duration)
2333 # Look for the DASH manifest
2334 if self._downloader.params.get('youtube_include_dash_manifest', True):
2335 dash_mpd_fatal = True
2336 for mpd_url in dash_mpds:
2339 def decrypt_sig(mobj):
2341 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2342 return '/signature/%s' % dec_s
2344 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2346 for df in self._extract_mpd_formats(
2347 mpd_url, video_id, fatal=dash_mpd_fatal,
2348 formats_dict=self._formats):
2349 if not df.get('filesize'):
2350 df['filesize'] = _extract_filesize(df['url'])
2351 # Do not overwrite DASH format found in some previous DASH manifest
2352 if df['format_id'] not in dash_formats:
2353 dash_formats[df['format_id']] = df
2354 # Additional DASH manifests may end up in HTTP Error 403 therefore
2355 # allow them to fail without bug report message if we already have
2356 # some DASH manifest succeeded. This is temporary workaround to reduce
2357 # burst of bug reports until we figure out the reason and whether it
2358 # can be fixed at all.
2359 dash_mpd_fatal = False
2360 except (ExtractorError, KeyError) as e:
2361 self.report_warning(
2362 'Skipping DASH manifest: %r' % e, video_id)
2364 # Remove the formats we found through non-DASH, they
2365 # contain less info and it can be wrong, because we use
2366 # fixed values (for example the resolution). See
2367 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2369 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2370 formats.extend(dash_formats.values())
2372 # Check for malformed aspect ratio
2373 stretched_m = re.search(
2374 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2377 w = float(stretched_m.group('w'))
2378 h = float(stretched_m.group('h'))
2379 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2380 # We will only process correct ratios.
2384 if f.get('vcodec') != 'none':
2385 f['stretched_ratio'] = ratio
2388 token = extract_token(video_info)
2390 if 'reason' in video_info:
2391 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2392 regions_allowed = self._html_search_meta(
2393 'regionsAllowed', video_webpage, default=None)
2394 countries = regions_allowed.split(',') if regions_allowed else None
2395 self.raise_geo_restricted(
2396 msg=video_info['reason'][0], countries=countries)
2397 reason = video_info['reason'][0]
2398 if 'Invalid parameters' in reason:
2399 unavailable_message = extract_unavailable_message()
2400 if unavailable_message:
2401 reason = unavailable_message
2402 raise ExtractorError(
2403 'YouTube said: %s' % reason,
2404 expected=True, video_id=video_id)
2406 raise ExtractorError(
2407 '"token" parameter not in video info for unknown reason',
2410 if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
2411 raise ExtractorError('This video is DRM protected.', expected=True)
2413 self._sort_formats(formats)
2415 self.mark_watched(video_id, video_info, player_response)
2419 'uploader': video_uploader,
2420 'uploader_id': video_uploader_id,
2421 'uploader_url': video_uploader_url,
2422 'channel_id': channel_id,
2423 'channel_url': channel_url,
2424 'upload_date': upload_date,
2425 'license': video_license,
2426 'creator': video_creator or artist,
2427 'title': video_title,
2428 'alt_title': video_alt_title or track,
2429 'thumbnail': video_thumbnail,
2430 'description': video_description,
2431 'categories': video_categories,
2433 'subtitles': video_subtitles,
2434 'automatic_captions': automatic_captions,
2435 'duration': video_duration,
2436 'age_limit': 18 if age_gate else 0,
2437 'annotations': video_annotations,
2438 'chapters': chapters,
2439 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2440 'view_count': view_count,
2441 'like_count': like_count,
2442 'dislike_count': dislike_count,
2443 'average_rating': average_rating,
2446 'start_time': start_time,
2447 'end_time': end_time,
2449 'season_number': season_number,
2450 'episode_number': episode_number,
2454 'release_date': release_date,
2455 'release_year': release_year,
2459 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2460 IE_DESC = 'YouTube.com playlists'
2461 _VALID_URL = r"""(?x)(?:
2471 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2472 \? (?:.*?[&;])*? (?:p|a|list)=
2475 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2478 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2479 # Top tracks, they can also include dots
2485 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2486 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2487 _VIDEO_RE_TPL = r'href="\s*/watch\?v=%s(?:&(?:[^"]*?index=(?P<index>\d+))?(?:[^>]+>(?P<title>[^<]+))?)?'
2488 _VIDEO_RE = _VIDEO_RE_TPL % r'(?P<id>[0-9A-Za-z_-]{11})'
2489 IE_NAME = 'youtube:playlist'
2491 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2493 'title': 'ytdl test PL',
2494 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2496 'playlist_count': 3,
2498 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2500 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2501 'title': 'YDL_Empty_List',
2503 'playlist_count': 0,
2504 'skip': 'This playlist is private',
2506 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2507 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2509 'title': '29C3: Not my department',
2510 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2511 'uploader': 'Christiaan008',
2512 'uploader_id': 'ChRiStIaAn008',
2514 'playlist_count': 95,
2516 'note': 'issue #673',
2517 'url': 'PLBB231211A4F62143',
2519 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2520 'id': 'PLBB231211A4F62143',
2521 'uploader': 'Wickydoo',
2522 'uploader_id': 'Wickydoo',
2524 'playlist_mincount': 26,
2526 'note': 'Large playlist',
2527 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2529 'title': 'Uploads from Cauchemar',
2530 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2531 'uploader': 'Cauchemar',
2532 'uploader_id': 'Cauchemar89',
2534 'playlist_mincount': 799,
2536 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2538 'title': 'YDL_safe_search',
2539 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2541 'playlist_count': 2,
2542 'skip': 'This playlist is private',
2545 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2546 'playlist_count': 4,
2549 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2550 'uploader': 'milan',
2551 'uploader_id': 'UCEI1-PVPcYXjB73Hfelbmaw',
2554 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2555 'playlist_mincount': 485,
2557 'title': '2018 Chinese New Singles (11/6 updated)',
2558 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2560 'uploader_id': 'sdragonfang',
2563 'note': 'Embedded SWF player',
2564 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2565 'playlist_count': 4,
2568 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2570 'skip': 'This playlist does not exist',
2572 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2573 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2575 'title': 'Uploads from Interstellar Movie',
2576 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2577 'uploader': 'Interstellar Movie',
2578 'uploader_id': 'InterstellarMovie1',
2580 'playlist_mincount': 21,
2582 # Playlist URL that does not actually serve a playlist
2583 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2585 'id': 'FqZTN594JQw',
2587 'title': "Smiley's People 01 detective, Adventure Series, Action",
2588 'uploader': 'STREEM',
2589 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2590 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2591 'upload_date': '20150526',
2592 'license': 'Standard YouTube License',
2593 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2594 'categories': ['People & Blogs'],
2598 'dislike_count': int,
2601 'skip_download': True,
2603 'skip': 'This video is not available.',
2604 'add_ie': [YoutubeIE.ie_key()],
2606 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2608 'id': 'yeWKywCrFtk',
2610 'title': 'Small Scale Baler and Braiding Rugs',
2611 'uploader': 'Backus-Page House Museum',
2612 'uploader_id': 'backuspagemuseum',
2613 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2614 'upload_date': '20161008',
2615 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2616 'categories': ['Nonprofits & Activism'],
2619 'dislike_count': int,
2623 'skip_download': True,
2626 # https://github.com/ytdl-org/youtube-dl/issues/21844
2627 'url': 'https://www.youtube.com/playlist?list=PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2629 'title': 'Data Analysis with Dr Mike Pound',
2630 'id': 'PLzH6n4zXuckpfMu_4Ff8E7Z1behQks5ba',
2631 'uploader_id': 'Computerphile',
2632 'uploader': 'Computerphile',
2634 'playlist_mincount': 11,
2636 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2637 'only_matching': True,
2639 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2640 'only_matching': True,
2642 # music album playlist
2643 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2644 'only_matching': True,
2646 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2647 'only_matching': True,
2650 def _real_initialize(self):
2653 def extract_videos_from_page(self, page):
2657 for item in re.findall(
2658 r'(<[^>]*\bdata-video-id\s*=\s*["\'][0-9A-Za-z_-]{11}[^>]+>)', page):
2659 attrs = extract_attributes(item)
2660 video_id = attrs['data-video-id']
2661 video_title = unescapeHTML(attrs.get('data-title'))
2663 video_title = video_title.strip()
2664 ids_in_page.append(video_id)
2665 titles_in_page.append(video_title)
2667 # Fallback with old _VIDEO_RE
2668 self.extract_videos_from_page_impl(
2669 self._VIDEO_RE, page, ids_in_page, titles_in_page)
2672 self.extract_videos_from_page_impl(
2673 r'href="\s*/watch\?v\s*=\s*(?P<id>[0-9A-Za-z_-]{11})', page,
2674 ids_in_page, titles_in_page)
2675 self.extract_videos_from_page_impl(
2676 r'data-video-ids\s*=\s*["\'](?P<id>[0-9A-Za-z_-]{11})', page,
2677 ids_in_page, titles_in_page)
2679 return zip(ids_in_page, titles_in_page)
2681 def _extract_mix(self, playlist_id):
2682 # The mixes are generated from a single video
2683 # the id of the playlist is just 'RD' + video_id
2685 last_id = playlist_id[-11:]
2686 for n in itertools.count(1):
2687 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2688 webpage = self._download_webpage(
2689 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2690 new_ids = orderedSet(re.findall(
2691 r'''(?xs)data-video-username=".*?".*?
2692 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2694 # Fetch new pages until all the videos are repeated, it seems that
2695 # there are always 51 unique videos.
2696 new_ids = [_id for _id in new_ids if _id not in ids]
2702 url_results = self._ids_to_results(ids)
2704 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2706 search_title('playlist-title')
2707 or search_title('title long-title')
2708 or search_title('title'))
2709 title = clean_html(title_span)
2711 return self.playlist_result(url_results, playlist_id, title)
2713 def _extract_playlist(self, playlist_id):
2714 url = self._TEMPLATE_URL % playlist_id
2715 page = self._download_webpage(url, playlist_id)
2717 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2718 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2719 match = match.strip()
2720 # Check if the playlist exists or is private
2721 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2723 reason = mobj.group('reason')
2724 message = 'This playlist %s' % reason
2725 if 'private' in reason:
2726 message += ', use --username or --netrc to access it'
2728 raise ExtractorError(message, expected=True)
2729 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2730 raise ExtractorError(
2731 'Invalid parameters. Maybe URL is incorrect.',
2733 elif re.match(r'[^<]*Choose your language[^<]*', match):
2736 self.report_warning('Youtube gives an alert message: ' + match)
2738 playlist_title = self._html_search_regex(
2739 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2740 page, 'title', default=None)
2742 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2743 uploader = self._search_regex(
2744 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2745 page, 'uploader', default=None)
2747 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2750 uploader_id = mobj.group('uploader_id')
2751 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2753 uploader_id = uploader_url = None
2757 if not playlist_title:
2759 # Some playlist URLs don't actually serve a playlist (e.g.
2760 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2761 next(self._entries(page, playlist_id))
2762 except StopIteration:
2765 playlist = self.playlist_result(
2766 self._entries(page, playlist_id), playlist_id, playlist_title)
2768 'uploader': uploader,
2769 'uploader_id': uploader_id,
2770 'uploader_url': uploader_url,
2773 return has_videos, playlist
2775 def _check_download_just_video(self, url, playlist_id):
2776 # Check if it's a video-specific URL
2777 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2778 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2779 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2780 'video id', default=None)
2782 if self._downloader.params.get('noplaylist'):
2783 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2784 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2786 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2787 return video_id, None
2790 def _real_extract(self, url):
2791 # Extract playlist id
2792 mobj = re.match(self._VALID_URL, url)
2794 raise ExtractorError('Invalid URL: %s' % url)
2795 playlist_id = mobj.group(1) or mobj.group(2)
2797 video_id, video = self._check_download_just_video(url, playlist_id)
2801 if playlist_id.startswith(('RD', 'UL', 'PU')):
2802 # Mixes require a custom extraction process
2803 return self._extract_mix(playlist_id)
2805 has_videos, playlist = self._extract_playlist(playlist_id)
2806 if has_videos or not video_id:
2809 # Some playlist URLs don't actually serve a playlist (see
2810 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2811 # Fallback to plain video extraction if there is a video id
2812 # along with playlist id.
2813 return self.url_result(video_id, 'Youtube', video_id=video_id)
2816 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2817 IE_DESC = 'YouTube.com channels'
2818 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2819 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2820 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2821 IE_NAME = 'youtube:channel'
2823 'note': 'paginated channel',
2824 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2825 'playlist_mincount': 91,
2827 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2828 'title': 'Uploads from lex will',
2829 'uploader': 'lex will',
2830 'uploader_id': 'UCKfVa3S1e4PHvxWcwyMMg8w',
2833 'note': 'Age restricted channel',
2834 # from https://www.youtube.com/user/DeusExOfficial
2835 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2836 'playlist_mincount': 64,
2838 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2839 'title': 'Uploads from Deus Ex',
2840 'uploader': 'Deus Ex',
2841 'uploader_id': 'DeusExOfficial',
2844 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2845 'only_matching': True,
2849 def suitable(cls, url):
2850 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2851 else super(YoutubeChannelIE, cls).suitable(url))
2853 def _build_template_url(self, url, channel_id):
2854 return self._TEMPLATE_URL % channel_id
2856 def _real_extract(self, url):
2857 channel_id = self._match_id(url)
2859 url = self._build_template_url(url, channel_id)
2861 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2862 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2863 # otherwise fallback on channel by page extraction
2864 channel_page = self._download_webpage(
2865 url + '?view=57', channel_id,
2866 'Downloading channel page', fatal=False)
2867 if channel_page is False:
2868 channel_playlist_id = False
2870 channel_playlist_id = self._html_search_meta(
2871 'channelId', channel_page, 'channel id', default=None)
2872 if not channel_playlist_id:
2873 channel_url = self._html_search_meta(
2874 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2875 channel_page, 'channel url', default=None)
2877 channel_playlist_id = self._search_regex(
2878 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2879 channel_url, 'channel id', default=None)
2880 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2881 playlist_id = 'UU' + channel_playlist_id[2:]
2882 return self.url_result(
2883 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2885 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2886 autogenerated = re.search(r'''(?x)
2888 channel-header-autogenerated-label|
2889 yt-channel-title-autogenerated
2890 )[^"]*"''', channel_page) is not None
2893 # The videos are contained in a single page
2894 # the ajax pages can't be used, they are empty
2897 video_id, 'Youtube', video_id=video_id,
2898 video_title=video_title)
2899 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2900 return self.playlist_result(entries, channel_id)
2903 next(self._entries(channel_page, channel_id))
2904 except StopIteration:
2905 alert_message = self._html_search_regex(
2906 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2907 channel_page, 'alert', default=None, group='alert')
2909 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2911 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2914 class YoutubeUserIE(YoutubeChannelIE):
2915 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2916 _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_-]+)'
2917 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2918 IE_NAME = 'youtube:user'
2921 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2922 'playlist_mincount': 320,
2924 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2925 'title': 'Uploads from The Linux Foundation',
2926 'uploader': 'The Linux Foundation',
2927 'uploader_id': 'TheLinuxFoundation',
2930 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2931 # but not https://www.youtube.com/user/12minuteathlete/videos
2932 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2933 'playlist_mincount': 249,
2935 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2936 'title': 'Uploads from 12 Minute Athlete',
2937 'uploader': '12 Minute Athlete',
2938 'uploader_id': 'the12minuteathlete',
2941 'url': 'ytuser:phihag',
2942 'only_matching': True,
2944 'url': 'https://www.youtube.com/c/gametrailers',
2945 'only_matching': True,
2947 'url': 'https://www.youtube.com/gametrailers',
2948 'only_matching': True,
2950 # This channel is not available, geo restricted to JP
2951 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2952 'only_matching': True,
2956 def suitable(cls, url):
2957 # Don't return True if the url can be extracted with other youtube
2958 # extractor, the regex would is too permissive and it would match.
2959 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2960 if any(ie.suitable(url) for ie in other_yt_ies):
2963 return super(YoutubeUserIE, cls).suitable(url)
2965 def _build_template_url(self, url, channel_id):
2966 mobj = re.match(self._VALID_URL, url)
2967 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2970 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2971 IE_DESC = 'YouTube.com live streams'
2972 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2973 IE_NAME = 'youtube:live'
2976 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2978 'id': 'a48o2S1cPoo',
2980 'title': 'The Young Turks - Live Main Show',
2981 'uploader': 'The Young Turks',
2982 'uploader_id': 'TheYoungTurks',
2983 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2984 'upload_date': '20150715',
2985 'license': 'Standard YouTube License',
2986 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2987 'categories': ['News & Politics'],
2988 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2990 'dislike_count': int,
2993 'skip_download': True,
2996 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2997 'only_matching': True,
2999 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
3000 'only_matching': True,
3002 'url': 'https://www.youtube.com/TheYoungTurks/live',
3003 'only_matching': True,
3006 def _real_extract(self, url):
3007 mobj = re.match(self._VALID_URL, url)
3008 channel_id = mobj.group('id')
3009 base_url = mobj.group('base_url')
3010 webpage = self._download_webpage(url, channel_id, fatal=False)
3012 page_type = self._og_search_property(
3013 'type', webpage, 'page type', default='')
3014 video_id = self._html_search_meta(
3015 'videoId', webpage, 'video id', default=None)
3016 if page_type.startswith('video') and video_id and re.match(
3017 r'^[0-9A-Za-z_-]{11}$', video_id):
3018 return self.url_result(video_id, YoutubeIE.ie_key())
3019 return self.url_result(base_url)
3022 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
3023 IE_DESC = 'YouTube.com user/channel playlists'
3024 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
3025 IE_NAME = 'youtube:playlists'
3028 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
3029 'playlist_mincount': 4,
3031 'id': 'ThirstForScience',
3032 'title': 'ThirstForScience',
3035 # with "Load more" button
3036 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
3037 'playlist_mincount': 70,
3040 'title': 'Игорь Клейнер',
3043 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
3044 'playlist_mincount': 17,
3046 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
3047 'title': 'Chem Player',
3053 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
3054 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
3057 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
3058 IE_DESC = 'YouTube.com searches'
3059 # there doesn't appear to be a real limit, for example if you search for
3060 # 'python' you get more than 8.000.000 results
3061 _MAX_RESULTS = float('inf')
3062 IE_NAME = 'youtube:search'
3063 _SEARCH_KEY = 'ytsearch'
3064 _EXTRA_QUERY_ARGS = {}
3067 def _get_n_results(self, query, n):
3068 """Get a specified number of results for a query"""
3074 'search_query': query.encode('utf-8'),
3076 url_query.update(self._EXTRA_QUERY_ARGS)
3077 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
3079 for pagenum in itertools.count(1):
3080 data = self._download_json(
3081 result_url, video_id='query "%s"' % query,
3082 note='Downloading page %s' % pagenum,
3083 errnote='Unable to download API page',
3084 query={'spf': 'navigate'})
3085 html_content = data[1]['body']['content']
3087 if 'class="search-message' in html_content:
3088 raise ExtractorError(
3089 '[youtube] No video results', expected=True)
3091 new_videos = list(self._process_page(html_content))
3092 videos += new_videos
3093 if not new_videos or len(videos) > limit:
3095 next_link = self._html_search_regex(
3096 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
3097 html_content, 'next link', default=None)
3098 if next_link is None:
3100 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
3104 return self.playlist_result(videos, query)
3107 class YoutubeSearchDateIE(YoutubeSearchIE):
3108 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
3109 _SEARCH_KEY = 'ytsearchdate'
3110 IE_DESC = 'YouTube.com searches, newest videos first'
3111 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
3114 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
3115 IE_DESC = 'YouTube.com search URLs'
3116 IE_NAME = 'youtube:search_url'
3117 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
3119 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
3120 'playlist_mincount': 5,
3122 'title': 'youtube-dl test video',
3125 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
3126 'only_matching': True,
3129 def _real_extract(self, url):
3130 mobj = re.match(self._VALID_URL, url)
3131 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
3132 webpage = self._download_webpage(url, query)
3133 return self.playlist_result(self._process_page(webpage), playlist_title=query)
3136 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
3137 IE_DESC = 'YouTube.com (multi-season) shows'
3138 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3139 IE_NAME = 'youtube:show'
3141 'url': 'https://www.youtube.com/show/airdisasters',
3142 'playlist_mincount': 5,
3144 'id': 'airdisasters',
3145 'title': 'Air Disasters',
3149 def _real_extract(self, url):
3150 playlist_id = self._match_id(url)
3151 return super(YoutubeShowIE, self)._real_extract(
3152 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3155 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3157 Base class for feed extractors
3158 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3160 _LOGIN_REQUIRED = True
3164 return 'youtube:%s' % self._FEED_NAME
3166 def _real_initialize(self):
3169 def _entries(self, page):
3170 # The extraction process is the same as for playlists, but the regex
3171 # for the video ids doesn't contain an index
3173 more_widget_html = content_html = page
3174 for page_num in itertools.count(1):
3175 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3177 # 'recommended' feed has infinite 'load more' and each new portion spins
3178 # the same videos in (sometimes) slightly different order, so we'll check
3179 # for unicity and break when portion has no new videos
3180 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3186 for entry in self._ids_to_results(new_ids):
3189 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3193 more = self._download_json(
3194 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3195 'Downloading page #%s' % page_num,
3196 transform_source=uppercase_escape)
3197 content_html = more['content_html']
3198 more_widget_html = more['load_more_widget_html']
3200 def _real_extract(self, url):
3201 page = self._download_webpage(
3202 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3203 self._PLAYLIST_TITLE)
3204 return self.playlist_result(
3205 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3208 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3209 IE_NAME = 'youtube:watchlater'
3210 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3211 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3214 'url': 'https://www.youtube.com/playlist?list=WL',
3215 'only_matching': True,
3217 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3218 'only_matching': True,
3221 def _real_extract(self, url):
3222 _, video = self._check_download_just_video(url, 'WL')
3225 _, playlist = self._extract_playlist('WL')
3229 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3230 IE_NAME = 'youtube:favorites'
3231 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3232 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3233 _LOGIN_REQUIRED = True
3235 def _real_extract(self, url):
3236 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3237 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3238 return self.url_result(playlist_id, 'YoutubePlaylist')
3241 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3242 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3243 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3244 _FEED_NAME = 'recommended'
3245 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3248 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3249 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3250 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3251 _FEED_NAME = 'subscriptions'
3252 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3255 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3256 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3257 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3258 _FEED_NAME = 'history'
3259 _PLAYLIST_TITLE = 'Youtube History'
3262 class YoutubeTruncatedURLIE(InfoExtractor):
3263 IE_NAME = 'youtube:truncated_url'
3264 IE_DESC = False # Do not list
3265 _VALID_URL = r'''(?x)
3267 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3270 annotation_id=annotation_[^&]+|
3276 attribution_link\?a=[^&]+
3282 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3283 'only_matching': True,
3285 'url': 'https://www.youtube.com/watch?',
3286 'only_matching': True,
3288 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3289 'only_matching': True,
3291 'url': 'https://www.youtube.com/watch?feature=foo',
3292 'only_matching': True,
3294 'url': 'https://www.youtube.com/watch?hl=en-GB',
3295 'only_matching': True,
3297 'url': 'https://www.youtube.com/watch?t=2372',
3298 'only_matching': True,
3301 def _real_extract(self, url):
3302 raise ExtractorError(
3303 'Did you forget to quote the URL? Remember that & is a meta '
3304 'character in most shells, so you want to put the URL in quotes, '
3306 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3307 ' or simply youtube-dl BaW_jenozKc .',
3311 class YoutubeTruncatedIDIE(InfoExtractor):
3312 IE_NAME = 'youtube:truncated_id'
3313 IE_DESC = False # Do not list
3314 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3317 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3318 'only_matching': True,
3321 def _real_extract(self, url):
3322 video_id = self._match_id(url)
3323 raise ExtractorError(
3324 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),