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,
35 get_element_by_attribute,
58 class YoutubeBaseInfoExtractor(InfoExtractor):
59 """Provide base functions for Youtube extractors"""
60 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
61 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
63 _LOOKUP_URL = 'https://accounts.google.com/_/signin/sl/lookup'
64 _CHALLENGE_URL = 'https://accounts.google.com/_/signin/sl/challenge'
65 _TFA_URL = 'https://accounts.google.com/_/signin/challenge?hl=en&TL={0}'
67 _NETRC_MACHINE = 'youtube'
68 # If True it will raise an error if no login info is provided
69 _LOGIN_REQUIRED = False
71 _PLAYLIST_ID_RE = r'(?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)[0-9A-Za-z-_]{10,}'
73 def _set_language(self):
75 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
76 # YouTube sets the expire time to about two months
77 expire_time=time.time() + 2 * 30 * 24 * 3600)
79 def _ids_to_results(self, ids):
81 self.url_result(vid_id, 'Youtube', video_id=vid_id)
86 Attempt to log in to YouTube.
87 True is returned if successful or skipped.
88 False is returned if login failed.
90 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
92 username, password = self._get_login_info()
93 # No authentication to be performed
95 if self._LOGIN_REQUIRED and self._downloader.params.get('cookiefile') is None:
96 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
99 login_page = self._download_webpage(
100 self._LOGIN_URL, None,
101 note='Downloading login page',
102 errnote='unable to fetch login page', fatal=False)
103 if login_page is False:
106 login_form = self._hidden_inputs(login_page)
108 def req(url, f_req, note, errnote):
109 data = login_form.copy()
112 'checkConnection': 'youtube',
113 'checkedDomains': 'youtube',
115 'deviceinfo': '[null,null,null,[],null,"US",null,null,[],"GlifWebSignIn",null,[null,null,[]]]',
116 'f.req': json.dumps(f_req),
117 'flowName': 'GlifWebSignIn',
118 'flowEntry': 'ServiceLogin',
120 return self._download_json(
121 url, None, note=note, errnote=errnote,
122 transform_source=lambda s: re.sub(r'^[^[]*', '', s),
124 data=urlencode_postdata(data), headers={
125 'Content-Type': 'application/x-www-form-urlencoded;charset=utf-8',
126 'Google-Accounts-XSRF': 1,
130 self._downloader.report_warning(message)
134 None, [], None, 'US', None, None, 2, False, True,
138 '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',
140 1, [None, None, []], None, None, None, True
145 lookup_results = req(
146 self._LOOKUP_URL, lookup_req,
147 'Looking up account info', 'Unable to look up account info')
149 if lookup_results is False:
152 user_hash = try_get(lookup_results, lambda x: x[0][2], compat_str)
154 warn('Unable to extract user hash')
159 None, 1, None, [1, None, None, None, [password, None, True]],
161 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],
162 1, [None, None, []], None, None, None, True
165 challenge_results = req(
166 self._CHALLENGE_URL, challenge_req,
167 'Logging in', 'Unable to log in')
169 if challenge_results is False:
172 login_res = try_get(challenge_results, lambda x: x[0][5], list)
174 login_msg = try_get(login_res, lambda x: x[5], compat_str)
176 'Unable to login: %s' % 'Invalid password'
177 if login_msg == 'INCORRECT_ANSWER_ENTERED' else login_msg)
180 res = try_get(challenge_results, lambda x: x[0][-1], list)
182 warn('Unable to extract result entry')
185 login_challenge = try_get(res, lambda x: x[0][0], list)
187 challenge_str = try_get(login_challenge, lambda x: x[2], compat_str)
188 if challenge_str == 'TWO_STEP_VERIFICATION':
189 # SEND_SUCCESS - TFA code has been successfully sent to phone
190 # QUOTA_EXCEEDED - reached the limit of TFA codes
191 status = try_get(login_challenge, lambda x: x[5], compat_str)
192 if status == 'QUOTA_EXCEEDED':
193 warn('Exceeded the limit of TFA codes, try later')
196 tl = try_get(challenge_results, lambda x: x[1][2], compat_str)
198 warn('Unable to extract TL')
201 tfa_code = self._get_tfa_info('2-step verification code')
205 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
206 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
209 tfa_code = remove_start(tfa_code, 'G-')
212 user_hash, None, 2, None,
214 9, None, None, None, None, None, None, None,
215 [None, tfa_code, True, 2]
219 self._TFA_URL.format(tl), tfa_req,
220 'Submitting TFA code', 'Unable to submit TFA code')
222 if tfa_results is False:
225 tfa_res = try_get(tfa_results, lambda x: x[0][5], list)
227 tfa_msg = try_get(tfa_res, lambda x: x[5], compat_str)
229 'Unable to finish TFA: %s' % 'Invalid TFA code'
230 if tfa_msg == 'INCORRECT_ANSWER_ENTERED' else tfa_msg)
233 check_cookie_url = try_get(
234 tfa_results, lambda x: x[0][-1][2], compat_str)
237 'LOGIN_CHALLENGE': "This device isn't recognized. For your security, Google wants to make sure it's really you.",
238 'USERNAME_RECOVERY': 'Please provide additional information to aid in the recovery process.',
239 'REAUTH': "There is something unusual about your activity. For your security, Google wants to make sure it's really you.",
241 challenge = CHALLENGES.get(
243 '%s returned error %s.' % (self.IE_NAME, challenge_str))
244 warn('%s\nGo to https://accounts.google.com/, login and solve a challenge.' % challenge)
247 check_cookie_url = try_get(res, lambda x: x[2], compat_str)
249 if not check_cookie_url:
250 warn('Unable to extract CheckCookie URL')
253 check_cookie_results = self._download_webpage(
254 check_cookie_url, None, 'Checking cookie', fatal=False)
256 if check_cookie_results is False:
259 if 'https://myaccount.google.com/' not in check_cookie_results:
260 warn('Unable to log in')
265 def _download_webpage_handle(self, *args, **kwargs):
266 query = kwargs.get('query', {}).copy()
267 query['disable_polymer'] = 'true'
268 kwargs['query'] = query
269 return super(YoutubeBaseInfoExtractor, self)._download_webpage_handle(
270 *args, **compat_kwargs(kwargs))
272 def _real_initialize(self):
273 if self._downloader is None:
276 if not self._login():
280 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
281 # Extract entries from page with "Load more" button
282 def _entries(self, page, playlist_id):
283 more_widget_html = content_html = page
284 for page_num in itertools.count(1):
285 for entry in self._process_page(content_html):
288 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
294 while count <= retries:
296 # Downloading page may result in intermittent 5xx HTTP error
297 # that is usually worked around with a retry
298 more = self._download_json(
299 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
300 'Downloading page #%s%s'
301 % (page_num, ' (retry #%d)' % count if count else ''),
302 transform_source=uppercase_escape)
304 except ExtractorError as e:
305 if isinstance(e.cause, compat_HTTPError) and e.cause.code in (500, 503):
311 content_html = more['content_html']
312 if not content_html.strip():
313 # Some webpages show a "Load more" button but they don't
316 more_widget_html = more['load_more_widget_html']
319 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
320 def _process_page(self, content):
321 for video_id, video_title in self.extract_videos_from_page(content):
322 yield self.url_result(video_id, 'Youtube', video_id, video_title)
324 def extract_videos_from_page(self, page):
327 for mobj in re.finditer(self._VIDEO_RE, page):
328 # The link with index 0 is not the first video of the playlist (not sure if still actual)
329 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
331 video_id = mobj.group('id')
332 video_title = unescapeHTML(mobj.group('title'))
334 video_title = video_title.strip()
336 idx = ids_in_page.index(video_id)
337 if video_title and not titles_in_page[idx]:
338 titles_in_page[idx] = video_title
340 ids_in_page.append(video_id)
341 titles_in_page.append(video_title)
342 return zip(ids_in_page, titles_in_page)
345 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
346 def _process_page(self, content):
347 for playlist_id in orderedSet(re.findall(
348 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
350 yield self.url_result(
351 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
353 def _real_extract(self, url):
354 playlist_id = self._match_id(url)
355 webpage = self._download_webpage(url, playlist_id)
356 title = self._og_search_title(webpage, fatal=False)
357 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
360 class YoutubeIE(YoutubeBaseInfoExtractor):
361 IE_DESC = 'YouTube.com'
362 _VALID_URL = r"""(?x)^
364 (?:https?://|//) # http(s):// or protocol-independent URL
365 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
366 (?:www\.)?deturl\.com/www\.youtube\.com/|
367 (?:www\.)?pwnyoutube\.com/|
368 (?:www\.)?hooktube\.com/|
369 (?:www\.)?yourepeat\.com/|
370 tube\.majestyc\.net/|
371 (?:(?:www|dev)\.)?invidio\.us/|
372 (?:www\.)?invidiou\.sh/|
373 (?:www\.)?invidious\.snopyta\.org/|
374 (?:www\.)?invidious\.kabi\.tk/|
375 (?:www\.)?vid\.wxzm\.sx/|
376 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
377 (?:.*?\#/)? # handle anchor (#/) redirect urls
378 (?: # the various things that can precede the ID:
379 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
380 |(?: # or the v= param in all its forms
381 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
382 (?:\?|\#!?) # the params delimiter ? or # or #!
383 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
388 youtu\.be| # just youtu.be/xxxx
389 vid\.plus| # or vid.plus/xxxx
390 zwearz\.com/watch| # or zwearz.com/watch/xxxx
392 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
394 )? # all until now is optional -> you can pass the naked ID
395 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
398 %(playlist_id)s| # combined list/video URLs are handled by the playlist IE
399 WL # WL are handled by the watch later IE
402 (?(1).+)? # if we found the ID, everything can follow
403 $""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
404 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
406 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
407 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
408 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
409 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
410 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
411 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
412 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
413 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
414 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
415 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
416 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
417 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
418 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
419 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
420 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
421 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
422 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
423 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
427 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
428 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
429 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
430 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
431 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
432 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
433 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
435 # Apple HTTP Live Streaming
436 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
437 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
438 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
439 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
440 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
441 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
442 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
443 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
446 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264'},
447 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264'},
448 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
449 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264'},
450 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264'},
451 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264'}, # Height can vary (https://github.com/ytdl-org/youtube-dl/issues/4559)
452 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264'},
453 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264'},
454 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264'},
455 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
456 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60},
457 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264'},
460 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'container': 'm4a_dash'},
461 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'container': 'm4a_dash'},
462 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'container': 'm4a_dash'},
463 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
464 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'container': 'm4a_dash'},
465 '325': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'dtse', 'container': 'm4a_dash'},
466 '328': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'ec-3', 'container': 'm4a_dash'},
469 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
470 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
471 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
472 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
473 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
474 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8'},
475 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9'},
476 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9'},
477 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9'},
478 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
479 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
480 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9'},
481 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9'},
482 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9'},
483 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9'},
484 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
485 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
486 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
487 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
488 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
489 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9'},
490 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60},
493 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128},
494 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256},
496 # Dash webm audio with opus inside
497 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50},
498 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70},
499 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160},
502 '_rtmp': {'protocol': 'rtmp'},
504 # av01 video only formats sometimes served with "unknown" codecs
505 '394': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
506 '395': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
507 '396': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
508 '397': {'acodec': 'none', 'vcodec': 'av01.0.05M.08'},
510 _SUBTITLE_FORMATS = ('srv1', 'srv2', 'srv3', 'ttml', 'vtt')
517 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
521 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
522 'uploader': 'Philipp Hagemeister',
523 'uploader_id': 'phihag',
524 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
525 'channel_id': 'UCLqxVugv74EIW3VWh2NOa3Q',
526 'channel_url': r're:https?://(?:www\.)?youtube\.com/channel/UCLqxVugv74EIW3VWh2NOa3Q',
527 'upload_date': '20121002',
528 '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 .',
529 'categories': ['Science & Technology'],
530 'tags': ['youtube-dl'],
534 'dislike_count': int,
540 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
541 'note': 'Test generic use_cipher_signature video (#897)',
545 'upload_date': '20120506',
546 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
547 'alt_title': 'I Love It (feat. Charli XCX)',
548 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
549 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
550 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
551 'iconic ep', 'iconic', 'love', 'it'],
553 'uploader': 'Icona Pop',
554 'uploader_id': 'IconaPop',
555 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
556 'creator': 'Icona Pop',
557 'track': 'I Love It (feat. Charli XCX)',
558 'artist': 'Icona Pop',
562 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
563 'note': 'Test VEVO video with age protection (#956)',
567 'upload_date': '20130703',
568 'title': 'Justin Timberlake - Tunnel Vision (Official Music Video) (Explicit)',
569 'alt_title': 'Tunnel Vision',
570 'description': 'md5:07dab3356cde4199048e4c7cd93471e1',
572 'uploader': 'justintimberlakeVEVO',
573 'uploader_id': 'justintimberlakeVEVO',
574 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
575 'creator': 'Justin Timberlake',
576 'track': 'Tunnel Vision',
577 'artist': 'Justin Timberlake',
582 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
583 'note': 'Embed-only video (#1746)',
587 'upload_date': '20120608',
588 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
589 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
590 'uploader': 'SET India',
591 'uploader_id': 'setindia',
592 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
597 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
598 'note': 'Use the first video ID in the URL',
602 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
603 'uploader': 'Philipp Hagemeister',
604 'uploader_id': 'phihag',
605 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
606 'upload_date': '20121002',
607 '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 .',
608 'categories': ['Science & Technology'],
609 'tags': ['youtube-dl'],
613 'dislike_count': int,
616 'skip_download': True,
620 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
621 'note': '256k DASH audio (format 141) via DASH manifest',
625 'upload_date': '20121002',
626 'uploader_id': '8KVIDEO',
627 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
629 'uploader': '8KVIDEO',
630 'title': 'UHDTV TEST 8K VIDEO.mp4'
633 'youtube_include_dash_manifest': True,
636 'skip': 'format 141 not served anymore',
638 # DASH manifest with encrypted signature
640 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
644 'title': 'Afrojack, Spree Wilson - The Spark (Official Music Video) ft. Spree Wilson',
645 'description': 'md5:8f5e2b82460520b619ccac1f509d43bf',
647 'uploader': 'AfrojackVEVO',
648 'uploader_id': 'AfrojackVEVO',
649 'upload_date': '20131011',
652 'youtube_include_dash_manifest': True,
653 'format': '141/bestaudio[ext=m4a]',
656 # JS player signature function name containing $
658 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
662 'title': 'Taylor Swift - Shake It Off',
663 'description': 'md5:bec2185232c05479482cb5a9b82719bf',
665 'uploader': 'TaylorSwiftVEVO',
666 'uploader_id': 'TaylorSwiftVEVO',
667 'upload_date': '20140818',
668 'creator': 'Taylor Swift',
671 'youtube_include_dash_manifest': True,
672 'format': '141/bestaudio[ext=m4a]',
677 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
682 'upload_date': '20100909',
683 'uploader': 'Amazing Atheist',
684 'uploader_id': 'TheAmazingAtheist',
685 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
686 'title': 'Burning Everyone\'s Koran',
687 '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',
690 # Normal age-gate video (No vevo, embed allowed)
692 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
696 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
697 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
699 'uploader': 'The Witcher',
700 'uploader_id': 'WitcherGame',
701 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
702 'upload_date': '20140605',
706 # Age-gate video with encrypted signature
708 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
712 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
713 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
715 'uploader': 'LloydVEVO',
716 'uploader_id': 'LloydVEVO',
717 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
718 'upload_date': '20110629',
722 # video_info is None (https://github.com/ytdl-org/youtube-dl/issues/4421)
723 # YouTube Red ad is not captured for creator
725 'url': '__2ABJjxzNo',
730 'upload_date': '20100430',
731 'uploader_id': 'deadmau5',
732 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
733 'creator': 'deadmau5',
734 'description': 'md5:12c56784b8032162bb936a5f76d55360',
735 'uploader': 'deadmau5',
736 'title': 'Deadmau5 - Some Chords (HD)',
737 'alt_title': 'Some Chords',
739 'expected_warnings': [
740 'DASH manifest missing',
743 # Olympics (https://github.com/ytdl-org/youtube-dl/issues/4431)
745 'url': 'lqQg6PlCWgI',
750 'upload_date': '20150827',
751 'uploader_id': 'olympic',
752 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
753 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
754 'uploader': 'Olympic',
755 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
758 'skip_download': 'requires avconv',
763 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
767 'stretched_ratio': 16 / 9.,
769 'upload_date': '20110310',
770 'uploader_id': 'AllenMeow',
771 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
772 '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',
774 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
777 # url_encoded_fmt_stream_map is empty string
779 'url': 'qEJwOuvDf7I',
783 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
785 'upload_date': '20150404',
786 'uploader_id': 'spbelect',
787 'uploader': 'Наблюдатели Петербурга',
790 'skip_download': 'requires avconv',
792 'skip': 'This live event has ended.',
794 # Extraction from multiple DASH manifests (https://github.com/ytdl-org/youtube-dl/pull/6097)
796 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
800 'title': 'md5:7b81415841e02ecd4313668cde88737a',
801 'description': 'md5:116377fd2963b81ec4ce64b542173306',
803 'upload_date': '20150625',
804 'uploader_id': 'dorappi2000',
805 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
806 'uploader': 'dorappi2000',
807 'formats': 'mincount:31',
809 'skip': 'not actual anymore',
811 # DASH manifest with segment_list
813 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
814 'md5': '8ce563a1d667b599d21064e982ab9e31',
818 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
819 'uploader': 'Airtek',
820 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
821 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
822 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
825 'youtube_include_dash_manifest': True,
826 'format': '135', # bestvideo
828 'skip': 'This live event has ended.',
831 # Multifeed videos (multiple cameras), URL is for Main Camera
832 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
835 'title': 'teamPGP: Rocket League Noob Stream',
836 'description': 'md5:dc7872fb300e143831327f1bae3af010',
842 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
843 'description': 'md5:dc7872fb300e143831327f1bae3af010',
845 'upload_date': '20150721',
846 'uploader': 'Beer Games Beer',
847 'uploader_id': 'beergamesbeer',
848 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
849 'license': 'Standard YouTube License',
855 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
856 'description': 'md5:dc7872fb300e143831327f1bae3af010',
858 'upload_date': '20150721',
859 'uploader': 'Beer Games Beer',
860 'uploader_id': 'beergamesbeer',
861 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
862 'license': 'Standard YouTube License',
868 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
869 'description': 'md5:dc7872fb300e143831327f1bae3af010',
871 'upload_date': '20150721',
872 'uploader': 'Beer Games Beer',
873 'uploader_id': 'beergamesbeer',
874 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
875 'license': 'Standard YouTube License',
881 'title': 'teamPGP: Rocket League Noob Stream (zim)',
882 'description': 'md5:dc7872fb300e143831327f1bae3af010',
884 'upload_date': '20150721',
885 'uploader': 'Beer Games Beer',
886 'uploader_id': 'beergamesbeer',
887 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
888 'license': 'Standard YouTube License',
892 'skip_download': True,
894 'skip': 'This video is not available.',
897 # Multifeed video with comma in title (see https://github.com/ytdl-org/youtube-dl/issues/8536)
898 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
901 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
904 'skip': 'Not multifeed anymore',
907 'url': 'https://vid.plus/FlRa-iH7PGw',
908 'only_matching': True,
911 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
912 'only_matching': True,
915 # Title with JS-like syntax "};" (see https://github.com/ytdl-org/youtube-dl/issues/7468)
916 # Also tests cut-off URL expansion in video description (see
917 # https://github.com/ytdl-org/youtube-dl/issues/1892,
918 # https://github.com/ytdl-org/youtube-dl/issues/8164)
919 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
923 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
924 'alt_title': 'Dark Walk - Position Music',
925 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
927 'upload_date': '20151119',
928 'uploader_id': 'IronSoulElf',
929 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
930 'uploader': 'IronSoulElf',
931 'creator': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
932 'track': 'Dark Walk - Position Music',
933 'artist': 'Todd Haberman, Daniel Law Heath and Aaron Kaplan',
934 'album': 'Position Music - Production Music Vol. 143 - Dark Walk',
937 'skip_download': True,
941 # Tags with '};' (see https://github.com/ytdl-org/youtube-dl/issues/7468)
942 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
943 'only_matching': True,
946 # Video with yt:stretch=17:0
947 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
951 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
952 'description': 'md5:ee18a25c350637c8faff806845bddee9',
953 'upload_date': '20151107',
954 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
955 'uploader': 'CH GAMER DROID',
958 'skip_download': True,
960 'skip': 'This video does not exist.',
963 # Video licensed under Creative Commons
964 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
968 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
969 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
971 'upload_date': '20150127',
972 'uploader_id': 'BerkmanCenter',
973 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
974 'uploader': 'The Berkman Klein Center for Internet & Society',
975 'license': 'Creative Commons Attribution license (reuse allowed)',
978 'skip_download': True,
982 # Channel-like uploader_url
983 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
987 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
988 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
990 'upload_date': '20151119',
991 'uploader': 'Bernie Sanders',
992 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
993 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
994 'license': 'Creative Commons Attribution license (reuse allowed)',
997 'skip_download': True,
1001 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
1002 'only_matching': True,
1005 # YouTube Red paid video (https://github.com/ytdl-org/youtube-dl/issues/10059)
1006 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
1007 'only_matching': True,
1010 # Rental video preview
1011 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
1013 'id': 'uGpuVWrhIzE',
1015 'title': 'Piku - Trailer',
1016 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
1017 'upload_date': '20150811',
1018 'uploader': 'FlixMatrix',
1019 'uploader_id': 'FlixMatrixKaravan',
1020 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
1021 'license': 'Standard YouTube License',
1024 'skip_download': True,
1026 'skip': 'This video is not available.',
1029 # YouTube Red video with episode data
1030 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
1032 'id': 'iqKdEhx-dD4',
1034 'title': 'Isolation - Mind Field (Ep 1)',
1035 'description': 'md5:46a29be4ceffa65b92d277b93f463c0f',
1037 'upload_date': '20170118',
1038 'uploader': 'Vsauce',
1039 'uploader_id': 'Vsauce',
1040 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
1041 'series': 'Mind Field',
1043 'episode_number': 1,
1046 'skip_download': True,
1048 'expected_warnings': [
1049 'Skipping DASH manifest',
1053 # The following content has been identified by the YouTube community
1054 # as inappropriate or offensive to some audiences.
1055 'url': 'https://www.youtube.com/watch?v=6SJNVb0GnPI',
1057 'id': '6SJNVb0GnPI',
1059 'title': 'Race Differences in Intelligence',
1060 'description': 'md5:5d161533167390427a1f8ee89a1fc6f1',
1062 'upload_date': '20140124',
1063 'uploader': 'New Century Foundation',
1064 'uploader_id': 'UCEJYpZGqgUob0zVVEaLhvVg',
1065 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCEJYpZGqgUob0zVVEaLhvVg',
1068 'skip_download': True,
1073 'url': '1t24XAntNCY',
1074 'only_matching': True,
1077 # geo restricted to JP
1078 'url': 'sJL6WA-aGkQ',
1079 'only_matching': True,
1082 'url': 'https://www.youtube.com/watch?v=MuAGGZNfUkU&list=RDMM',
1083 'only_matching': True,
1086 'url': 'https://invidio.us/watch?v=BaW_jenozKc',
1087 'only_matching': True,
1091 'url': 'https://www.youtube.com/watch?v=s7_qI6_mIXc',
1092 'only_matching': True,
1095 # Video with unsupported adaptive stream type formats
1096 'url': 'https://www.youtube.com/watch?v=Z4Vy8R84T1U',
1098 'id': 'Z4Vy8R84T1U',
1100 'title': 'saman SMAN 53 Jakarta(Sancety) opening COFFEE4th at SMAN 53 Jakarta',
1101 'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
1103 'upload_date': '20130923',
1104 'uploader': 'Amelia Putri Harwita',
1105 'uploader_id': 'UCpOxM49HJxmC1qCalXyB3_Q',
1106 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCpOxM49HJxmC1qCalXyB3_Q',
1107 'formats': 'maxcount:10',
1110 'skip_download': True,
1111 'youtube_include_dash_manifest': False,
1115 # Youtube Music Auto-generated description
1116 'url': 'https://music.youtube.com/watch?v=MgNrAu2pzNs',
1118 'id': 'MgNrAu2pzNs',
1120 'title': 'Voyeur Girl',
1121 'description': 'md5:7ae382a65843d6df2685993e90a8628f',
1122 'upload_date': '20190312',
1123 'uploader': 'Various Artists - Topic',
1124 'uploader_id': 'UCVWKBi1ELZn0QX2CBLSkiyw',
1125 'artist': 'Stephen',
1126 'track': 'Voyeur Girl',
1127 'album': 'it\'s too much love to know my dear',
1128 'release_date': '20190313',
1129 'release_year': 2019,
1132 'skip_download': True,
1136 # Youtube Music Auto-generated description
1137 # Retrieve 'artist' field from 'Artist:' in video description
1138 # when it is present on youtube music video
1139 'url': 'https://www.youtube.com/watch?v=k0jLE7tTwjY',
1141 'id': 'k0jLE7tTwjY',
1143 'title': 'Latch Feat. Sam Smith',
1144 'description': 'md5:3cb1e8101a7c85fcba9b4fb41b951335',
1145 'upload_date': '20150110',
1146 'uploader': 'Various Artists - Topic',
1147 'uploader_id': 'UCNkEcmYdjrH4RqtNgh7BZ9w',
1148 'artist': 'Disclosure',
1149 'track': 'Latch Feat. Sam Smith',
1150 'album': 'Latch Featuring Sam Smith',
1151 'release_date': '20121008',
1152 'release_year': 2012,
1155 'skip_download': True,
1159 # Youtube Music Auto-generated description
1160 # handle multiple artists on youtube music video
1161 'url': 'https://www.youtube.com/watch?v=74qn0eJSjpA',
1163 'id': '74qn0eJSjpA',
1165 'title': 'Eastside',
1166 'description': 'md5:290516bb73dcbfab0dcc4efe6c3de5f2',
1167 'upload_date': '20180710',
1168 'uploader': 'Benny Blanco - Topic',
1169 'uploader_id': 'UCzqz_ksRu_WkIzmivMdIS7A',
1170 'artist': 'benny blanco, Halsey, Khalid',
1171 'track': 'Eastside',
1172 'album': 'Eastside',
1173 'release_date': '20180713',
1174 'release_year': 2018,
1177 'skip_download': True,
1181 # Youtube Music Auto-generated description
1182 # handle youtube music video with release_year and no release_date
1183 'url': 'https://www.youtube.com/watch?v=-hcAI0g-f5M',
1185 'id': '-hcAI0g-f5M',
1187 'title': 'Put It On Me',
1188 'description': 'md5:93c55acc682ae7b0c668f2e34e1c069e',
1189 'upload_date': '20180426',
1190 'uploader': 'Matt Maeson - Topic',
1191 'uploader_id': 'UCnEkIGqtGcQMLk73Kp-Q5LQ',
1192 'artist': 'Matt Maeson',
1193 'track': 'Put It On Me',
1194 'album': 'The Hearse',
1195 'release_date': None,
1196 'release_year': 2018,
1199 'skip_download': True,
1204 def __init__(self, *args, **kwargs):
1205 super(YoutubeIE, self).__init__(*args, **kwargs)
1206 self._player_cache = {}
1208 def report_video_info_webpage_download(self, video_id):
1209 """Report attempt to download video info webpage."""
1210 self.to_screen('%s: Downloading video info webpage' % video_id)
1212 def report_information_extraction(self, video_id):
1213 """Report attempt to extract video information."""
1214 self.to_screen('%s: Extracting video information' % video_id)
1216 def report_unavailable_format(self, video_id, format):
1217 """Report extracted video URL."""
1218 self.to_screen('%s: Format %s not available' % (video_id, format))
1220 def report_rtmp_download(self):
1221 """Indicate the download will use the RTMP protocol."""
1222 self.to_screen('RTMP download detected')
1224 def _signature_cache_id(self, example_sig):
1225 """ Return a string representation of a signature """
1226 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
1228 def _extract_signature_function(self, video_id, player_url, example_sig):
1230 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|(?:/[a-z]{2,3}_[A-Z]{2})?/base)?\.(?P<ext>[a-z]+)$',
1233 raise ExtractorError('Cannot identify player %r' % player_url)
1234 player_type = id_m.group('ext')
1235 player_id = id_m.group('id')
1237 # Read from filesystem cache
1238 func_id = '%s_%s_%s' % (
1239 player_type, player_id, self._signature_cache_id(example_sig))
1240 assert os.path.basename(func_id) == func_id
1242 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
1243 if cache_spec is not None:
1244 return lambda s: ''.join(s[i] for i in cache_spec)
1247 'Downloading player %s' % player_url
1248 if self._downloader.params.get('verbose') else
1249 'Downloading %s player %s' % (player_type, player_id)
1251 if player_type == 'js':
1252 code = self._download_webpage(
1253 player_url, video_id,
1255 errnote='Download of %s failed' % player_url)
1256 res = self._parse_sig_js(code)
1257 elif player_type == 'swf':
1258 urlh = self._request_webpage(
1259 player_url, video_id,
1261 errnote='Download of %s failed' % player_url)
1263 res = self._parse_sig_swf(code)
1265 assert False, 'Invalid player type %r' % player_type
1267 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1268 cache_res = res(test_string)
1269 cache_spec = [ord(c) for c in cache_res]
1271 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
1274 def _print_sig_code(self, func, example_sig):
1275 def gen_sig_code(idxs):
1276 def _genslice(start, end, step):
1277 starts = '' if start == 0 else str(start)
1278 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
1279 steps = '' if step == 1 else (':%d' % step)
1280 return 's[%s%s%s]' % (starts, ends, steps)
1283 # Quelch pyflakes warnings - start will be set when step is set
1284 start = '(Never used)'
1285 for i, prev in zip(idxs[1:], idxs[:-1]):
1286 if step is not None:
1287 if i - prev == step:
1289 yield _genslice(start, prev, step)
1292 if i - prev in [-1, 1]:
1297 yield 's[%d]' % prev
1301 yield _genslice(start, i, step)
1303 test_string = ''.join(map(compat_chr, range(len(example_sig))))
1304 cache_res = func(test_string)
1305 cache_spec = [ord(c) for c in cache_res]
1306 expr_code = ' + '.join(gen_sig_code(cache_spec))
1307 signature_id_tuple = '(%s)' % (
1308 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1309 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1310 ' return %s\n') % (signature_id_tuple, expr_code)
1311 self.to_screen('Extracted signature function:\n' + code)
1313 def _parse_sig_js(self, jscode):
1314 funcname = self._search_regex(
1315 (r'(["\'])signature\1\s*,\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1316 r'\.sig\|\|(?P<sig>[a-zA-Z0-9$]+)\(',
1317 r'yt\.akamaized\.net/\)\s*\|\|\s*.*?\s*c\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?(?P<sig>[a-zA-Z0-9$]+)\(',
1318 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*(?:encodeURIComponent\s*\()?\s*(?P<sig>[a-zA-Z0-9$]+)\(',
1319 r'\bc\s*&&\s*d\.set\([^,]+\s*,\s*\([^)]*\)\s*\(\s*(?P<sig>[a-zA-Z0-9$]+)\('),
1320 jscode, 'Initial JS player signature function name', group='sig')
1322 jsi = JSInterpreter(jscode)
1323 initial_function = jsi.extract_function(funcname)
1324 return lambda s: initial_function([s])
1326 def _parse_sig_swf(self, file_contents):
1327 swfi = SWFInterpreter(file_contents)
1328 TARGET_CLASSNAME = 'SignatureDecipher'
1329 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1330 initial_function = swfi.extract_function(searched_class, 'decipher')
1331 return lambda s: initial_function([s])
1333 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1334 """Turn the encrypted s field into a working signature"""
1336 if player_url is None:
1337 raise ExtractorError('Cannot decrypt signature without player_url')
1339 if player_url.startswith('//'):
1340 player_url = 'https:' + player_url
1341 elif not re.match(r'https?://', player_url):
1342 player_url = compat_urlparse.urljoin(
1343 'https://www.youtube.com', player_url)
1345 player_id = (player_url, self._signature_cache_id(s))
1346 if player_id not in self._player_cache:
1347 func = self._extract_signature_function(
1348 video_id, player_url, s
1350 self._player_cache[player_id] = func
1351 func = self._player_cache[player_id]
1352 if self._downloader.params.get('youtube_print_sig_code'):
1353 self._print_sig_code(func, s)
1355 except Exception as e:
1356 tb = traceback.format_exc()
1357 raise ExtractorError(
1358 'Signature extraction failed: ' + tb, cause=e)
1360 def _get_subtitles(self, video_id, webpage):
1362 subs_doc = self._download_xml(
1363 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1364 video_id, note=False)
1365 except ExtractorError as err:
1366 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1370 for track in subs_doc.findall('track'):
1371 lang = track.attrib['lang_code']
1372 if lang in sub_lang_list:
1375 for ext in self._SUBTITLE_FORMATS:
1376 params = compat_urllib_parse_urlencode({
1380 'name': track.attrib['name'].encode('utf-8'),
1382 sub_formats.append({
1383 'url': 'https://www.youtube.com/api/timedtext?' + params,
1386 sub_lang_list[lang] = sub_formats
1387 if not sub_lang_list:
1388 self._downloader.report_warning('video doesn\'t have subtitles')
1390 return sub_lang_list
1392 def _get_ytplayer_config(self, video_id, webpage):
1394 # User data may contain arbitrary character sequences that may affect
1395 # JSON extraction with regex, e.g. when '};' is contained the second
1396 # regex won't capture the whole JSON. Yet working around by trying more
1397 # concrete regex first keeping in mind proper quoted string handling
1398 # to be implemented in future that will replace this workaround (see
1399 # https://github.com/ytdl-org/youtube-dl/issues/7468,
1400 # https://github.com/ytdl-org/youtube-dl/pull/7599)
1401 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1402 r';ytplayer\.config\s*=\s*({.+?});',
1404 config = self._search_regex(
1405 patterns, webpage, 'ytplayer.config', default=None)
1407 return self._parse_json(
1408 uppercase_escape(config), video_id, fatal=False)
1410 def _get_automatic_captions(self, video_id, webpage):
1411 """We need the webpage for getting the captions url, pass it as an
1412 argument to speed up the process."""
1413 self.to_screen('%s: Looking for automatic captions' % video_id)
1414 player_config = self._get_ytplayer_config(video_id, webpage)
1415 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1416 if not player_config:
1417 self._downloader.report_warning(err_msg)
1420 args = player_config['args']
1421 caption_url = args.get('ttsurl')
1423 timestamp = args['timestamp']
1424 # We get the available subtitles
1425 list_params = compat_urllib_parse_urlencode({
1430 list_url = caption_url + '&' + list_params
1431 caption_list = self._download_xml(list_url, video_id)
1432 original_lang_node = caption_list.find('track')
1433 if original_lang_node is None:
1434 self._downloader.report_warning('Video doesn\'t have automatic captions')
1436 original_lang = original_lang_node.attrib['lang_code']
1437 caption_kind = original_lang_node.attrib.get('kind', '')
1440 for lang_node in caption_list.findall('target'):
1441 sub_lang = lang_node.attrib['lang_code']
1443 for ext in self._SUBTITLE_FORMATS:
1444 params = compat_urllib_parse_urlencode({
1445 'lang': original_lang,
1449 'kind': caption_kind,
1451 sub_formats.append({
1452 'url': caption_url + '&' + params,
1455 sub_lang_list[sub_lang] = sub_formats
1456 return sub_lang_list
1458 def make_captions(sub_url, sub_langs):
1459 parsed_sub_url = compat_urllib_parse_urlparse(sub_url)
1460 caption_qs = compat_parse_qs(parsed_sub_url.query)
1462 for sub_lang in sub_langs:
1464 for ext in self._SUBTITLE_FORMATS:
1466 'tlang': [sub_lang],
1469 sub_url = compat_urlparse.urlunparse(parsed_sub_url._replace(
1470 query=compat_urllib_parse_urlencode(caption_qs, True)))
1471 sub_formats.append({
1475 captions[sub_lang] = sub_formats
1478 # New captions format as of 22.06.2017
1479 player_response = args.get('player_response')
1480 if player_response and isinstance(player_response, compat_str):
1481 player_response = self._parse_json(
1482 player_response, video_id, fatal=False)
1484 renderer = player_response['captions']['playerCaptionsTracklistRenderer']
1485 base_url = renderer['captionTracks'][0]['baseUrl']
1487 for lang in renderer['translationLanguages']:
1488 lang_code = lang.get('languageCode')
1490 sub_lang_list.append(lang_code)
1491 return make_captions(base_url, sub_lang_list)
1493 # Some videos don't provide ttsurl but rather caption_tracks and
1494 # caption_translation_languages (e.g. 20LmZk1hakA)
1495 # Does not used anymore as of 22.06.2017
1496 caption_tracks = args['caption_tracks']
1497 caption_translation_languages = args['caption_translation_languages']
1498 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1500 for lang in caption_translation_languages.split(','):
1501 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1502 sub_lang = lang_qs.get('lc', [None])[0]
1504 sub_lang_list.append(sub_lang)
1505 return make_captions(caption_url, sub_lang_list)
1506 # An extractor error can be raise by the download process if there are
1507 # no automatic captions but there are subtitles
1508 except (KeyError, IndexError, ExtractorError):
1509 self._downloader.report_warning(err_msg)
1512 def _mark_watched(self, video_id, video_info, player_response):
1513 playback_url = url_or_none(try_get(
1515 lambda x: x['playbackTracking']['videostatsPlaybackUrl']['baseUrl']) or try_get(
1516 video_info, lambda x: x['videostats_playback_base_url'][0]))
1517 if not playback_url:
1519 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1520 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1522 # cpn generation algorithm is reverse engineered from base.js.
1523 # In fact it works even with dummy cpn.
1524 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1525 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1531 playback_url = compat_urlparse.urlunparse(
1532 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1534 self._download_webpage(
1535 playback_url, video_id, 'Marking watched',
1536 'Unable to mark watched', fatal=False)
1539 def _extract_urls(webpage):
1540 # Embedded YouTube player
1542 unescapeHTML(mobj.group('url'))
1543 for mobj in re.finditer(r'''(?x)
1553 (?P<url>(?:https?:)?//(?:www\.)?youtube(?:-nocookie)?\.com/
1554 (?:embed|v|p)/[0-9A-Za-z_-]{11}.*?)
1557 # lazyYT YouTube embed
1558 entries.extend(list(map(
1560 re.findall(r'class="lazyYT" data-youtube-id="([^"]+)"', webpage))))
1562 # Wordpress "YouTube Video Importer" plugin
1563 matches = re.findall(r'''(?x)<div[^>]+
1564 class=(?P<q1>[\'"])[^\'"]*\byvii_single_video_player\b[^\'"]*(?P=q1)[^>]+
1565 data-video_id=(?P<q2>[\'"])([^\'"]+)(?P=q2)''', webpage)
1566 entries.extend(m[-1] for m in matches)
1571 def _extract_url(webpage):
1572 urls = YoutubeIE._extract_urls(webpage)
1573 return urls[0] if urls else None
1576 def extract_id(cls, url):
1577 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1579 raise ExtractorError('Invalid URL: %s' % url)
1580 video_id = mobj.group(2)
1583 def _extract_annotations(self, video_id):
1584 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1585 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1588 def _extract_chapters(description, duration):
1591 chapter_lines = re.findall(
1592 r'(?:^|<br\s*/>)([^<]*<a[^>]+onclick=["\']yt\.www\.watch\.player\.seekTo[^>]+>(\d{1,2}:\d{1,2}(?::\d{1,2})?)</a>[^>]*)(?=$|<br\s*/>)',
1594 if not chapter_lines:
1597 for next_num, (chapter_line, time_point) in enumerate(
1598 chapter_lines, start=1):
1599 start_time = parse_duration(time_point)
1600 if start_time is None:
1602 if start_time > duration:
1604 end_time = (duration if next_num == len(chapter_lines)
1605 else parse_duration(chapter_lines[next_num][1]))
1606 if end_time is None:
1608 if end_time > duration:
1610 if start_time > end_time:
1612 chapter_title = re.sub(
1613 r'<a[^>]+>[^<]+</a>', '', chapter_line).strip(' \t-')
1614 chapter_title = re.sub(r'\s+', ' ', chapter_title)
1616 'start_time': start_time,
1617 'end_time': end_time,
1618 'title': chapter_title,
1622 def _real_extract(self, url):
1623 url, smuggled_data = unsmuggle_url(url, {})
1626 'http' if self._downloader.params.get('prefer_insecure', False)
1631 parsed_url = compat_urllib_parse_urlparse(url)
1632 for component in [parsed_url.fragment, parsed_url.query]:
1633 query = compat_parse_qs(component)
1634 if start_time is None and 't' in query:
1635 start_time = parse_duration(query['t'][0])
1636 if start_time is None and 'start' in query:
1637 start_time = parse_duration(query['start'][0])
1638 if end_time is None and 'end' in query:
1639 end_time = parse_duration(query['end'][0])
1641 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1642 mobj = re.search(self._NEXT_URL_RE, url)
1644 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1645 video_id = self.extract_id(url)
1648 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1649 video_webpage = self._download_webpage(url, video_id)
1651 # Attempt to extract SWF player URL
1652 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1653 if mobj is not None:
1654 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1660 def add_dash_mpd(video_info):
1661 dash_mpd = video_info.get('dashmpd')
1662 if dash_mpd and dash_mpd[0] not in dash_mpds:
1663 dash_mpds.append(dash_mpd[0])
1665 def add_dash_mpd_pr(pl_response):
1666 dash_mpd = url_or_none(try_get(
1667 pl_response, lambda x: x['streamingData']['dashManifestUrl'],
1669 if dash_mpd and dash_mpd not in dash_mpds:
1670 dash_mpds.append(dash_mpd)
1675 def extract_view_count(v_info):
1676 return int_or_none(try_get(v_info, lambda x: x['view_count'][0]))
1678 def extract_token(v_info):
1679 return dict_get(v_info, ('account_playback_token', 'accountPlaybackToken', 'token'))
1681 player_response = {}
1684 embed_webpage = None
1685 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1687 # We simulate the access to the video from www.youtube.com/v/{video_id}
1688 # this can be viewed without login into Youtube
1689 url = proto + '://www.youtube.com/embed/%s' % video_id
1690 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1691 data = compat_urllib_parse_urlencode({
1692 'video_id': video_id,
1693 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1694 'sts': self._search_regex(
1695 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1697 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1698 video_info_webpage = self._download_webpage(
1699 video_info_url, video_id,
1700 note='Refetching age-gated info webpage',
1701 errnote='unable to download video info webpage')
1702 video_info = compat_parse_qs(video_info_webpage)
1703 add_dash_mpd(video_info)
1708 # Try looking directly into the video webpage
1709 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1711 args = ytplayer_config['args']
1712 if args.get('url_encoded_fmt_stream_map') or args.get('hlsvp'):
1713 # Convert to the same format returned by compat_parse_qs
1714 video_info = dict((k, [v]) for k, v in args.items())
1715 add_dash_mpd(video_info)
1716 # Rental video is not rented but preview is available (e.g.
1717 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1718 # https://github.com/ytdl-org/youtube-dl/issues/10532)
1719 if not video_info and args.get('ypc_vid'):
1720 return self.url_result(
1721 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1722 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1724 sts = ytplayer_config.get('sts')
1725 if not player_response:
1726 pl_response = str_or_none(args.get('player_response'))
1728 pl_response = self._parse_json(pl_response, video_id, fatal=False)
1729 if isinstance(pl_response, dict):
1730 player_response = pl_response
1731 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1732 add_dash_mpd_pr(player_response)
1733 # We also try looking in get_video_info since it may contain different dashmpd
1734 # URL that points to a DASH manifest with possibly different itag set (some itags
1735 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1736 # manifest pointed by get_video_info's dashmpd).
1737 # The general idea is to take a union of itags of both DASH manifests (for example
1738 # video with such 'manifest behavior' see https://github.com/ytdl-org/youtube-dl/issues/6093)
1739 self.report_video_info_webpage_download(video_id)
1740 for el in ('embedded', 'detailpage', 'vevo', ''):
1742 'video_id': video_id,
1752 video_info_webpage = self._download_webpage(
1753 '%s://www.youtube.com/get_video_info' % proto,
1754 video_id, note=False,
1755 errnote='unable to download video info webpage',
1756 fatal=False, query=query)
1757 if not video_info_webpage:
1759 get_video_info = compat_parse_qs(video_info_webpage)
1760 if not player_response:
1761 pl_response = get_video_info.get('player_response', [None])[0]
1762 if isinstance(pl_response, dict):
1763 player_response = pl_response
1764 add_dash_mpd_pr(player_response)
1765 add_dash_mpd(get_video_info)
1766 if view_count is None:
1767 view_count = extract_view_count(get_video_info)
1769 video_info = get_video_info
1770 get_token = extract_token(get_video_info)
1772 # Different get_video_info requests may report different results, e.g.
1773 # some may report video unavailability, but some may serve it without
1774 # any complaint (see https://github.com/ytdl-org/youtube-dl/issues/7362,
1775 # the original webpage as well as el=info and el=embedded get_video_info
1776 # requests report video unavailability due to geo restriction while
1777 # el=detailpage succeeds and returns valid data). This is probably
1778 # due to YouTube measures against IP ranges of hosting providers.
1779 # Working around by preferring the first succeeded video_info containing
1780 # the token if no such video_info yet was found.
1781 token = extract_token(video_info)
1783 video_info = get_video_info
1786 def extract_unavailable_message():
1787 return self._html_search_regex(
1788 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1789 video_webpage, 'unavailable message', default=None)
1792 unavailable_message = extract_unavailable_message()
1793 if not unavailable_message:
1794 unavailable_message = 'Unable to extract video data'
1795 raise ExtractorError(
1796 'YouTube said: %s' % unavailable_message, expected=True, video_id=video_id)
1798 video_details = try_get(
1799 player_response, lambda x: x['videoDetails'], dict) or {}
1802 if 'title' in video_info:
1803 video_title = video_info['title'][0]
1804 elif 'title' in player_response:
1805 video_title = video_details['title']
1807 self._downloader.report_warning('Unable to extract video title')
1811 description_original = video_description = get_element_by_id("eow-description", video_webpage)
1812 if video_description:
1815 redir_url = compat_urlparse.urljoin(url, m.group(1))
1816 parsed_redir_url = compat_urllib_parse_urlparse(redir_url)
1817 if re.search(r'^(?:www\.)?(?:youtube(?:-nocookie)?\.com|youtu\.be)$', parsed_redir_url.netloc) and parsed_redir_url.path == '/redirect':
1818 qs = compat_parse_qs(parsed_redir_url.query)
1824 description_original = video_description = re.sub(r'''(?x)
1826 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1827 (?:title|href)="([^"]+)"\s+
1828 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1832 ''', replace_url, video_description)
1833 video_description = clean_html(video_description)
1835 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1837 video_description = unescapeHTML(fd_mobj.group(1))
1839 video_description = ''
1841 if not smuggled_data.get('force_singlefeed', False):
1842 if not self._downloader.params.get('noplaylist'):
1843 multifeed_metadata_list = try_get(
1845 lambda x: x['multicamera']['playerLegacyMulticameraRenderer']['metadataList'],
1846 compat_str) or try_get(
1847 video_info, lambda x: x['multifeed_metadata_list'][0], compat_str)
1848 if multifeed_metadata_list:
1851 for feed in multifeed_metadata_list.split(','):
1852 # Unquote should take place before split on comma (,) since textual
1853 # fields may contain comma as well (see
1854 # https://github.com/ytdl-org/youtube-dl/issues/8536)
1855 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1857 '_type': 'url_transparent',
1858 'ie_key': 'Youtube',
1860 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1861 {'force_singlefeed': True}),
1862 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1864 feed_ids.append(feed_data['id'][0])
1866 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1867 % (', '.join(feed_ids), video_id))
1868 return self.playlist_result(entries, video_id, video_title, video_description)
1870 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1872 if view_count is None:
1873 view_count = extract_view_count(video_info)
1874 if view_count is None and video_details:
1875 view_count = int_or_none(video_details.get('viewCount'))
1877 # Check for "rental" videos
1878 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1879 raise ExtractorError('"rental" videos not supported. See https://github.com/ytdl-org/youtube-dl/issues/359 for more information.', expected=True)
1881 def _extract_filesize(media_url):
1882 return int_or_none(self._search_regex(
1883 r'\bclen[=/](\d+)', media_url, 'filesize', default=None))
1885 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1886 self.report_rtmp_download()
1888 'format_id': '_rtmp',
1890 'url': video_info['conn'][0],
1891 'player_url': player_url,
1893 elif not is_live and (len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1):
1894 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1895 if 'rtmpe%3Dyes' in encoded_url_map:
1896 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/ytdl-org/youtube-dl/issues/343 for more information.', expected=True)
1898 fmt_list = video_info.get('fmt_list', [''])[0]
1900 for fmt in fmt_list.split(','):
1901 spec = fmt.split('/')
1903 width_height = spec[1].split('x')
1904 if len(width_height) == 2:
1905 formats_spec[spec[0]] = {
1906 'resolution': spec[1],
1907 'width': int_or_none(width_height[0]),
1908 'height': int_or_none(width_height[1]),
1910 q = qualities(['small', 'medium', 'hd720'])
1911 streaming_formats = try_get(player_response, lambda x: x['streamingData']['formats'], list)
1912 if streaming_formats:
1913 for fmt in streaming_formats:
1914 itag = str_or_none(fmt.get('itag'))
1917 quality = fmt.get('quality')
1918 quality_label = fmt.get('qualityLabel') or quality
1919 formats_spec[itag] = {
1920 'asr': int_or_none(fmt.get('audioSampleRate')),
1921 'filesize': int_or_none(fmt.get('contentLength')),
1922 'format_note': quality_label,
1923 'fps': int_or_none(fmt.get('fps')),
1924 'height': int_or_none(fmt.get('height')),
1925 'quality': q(quality),
1926 # bitrate for itag 43 is always 2147483647
1927 'tbr': float_or_none(fmt.get('averageBitrate') or fmt.get('bitrate'), 1000) if itag != '43' else None,
1928 'width': int_or_none(fmt.get('width')),
1931 for url_data_str in encoded_url_map.split(','):
1932 url_data = compat_parse_qs(url_data_str)
1933 if 'itag' not in url_data or 'url' not in url_data or url_data.get('drm_families'):
1935 stream_type = int_or_none(try_get(url_data, lambda x: x['stream_type'][0]))
1936 # Unsupported FORMAT_STREAM_TYPE_OTF
1937 if stream_type == 3:
1939 format_id = url_data['itag'][0]
1940 url = url_data['url'][0]
1942 if 's' in url_data or self._downloader.params.get('youtube_include_dash_manifest', True):
1943 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1944 jsplayer_url_json = self._search_regex(
1946 embed_webpage if age_gate else video_webpage,
1947 'JS player URL (1)', default=None)
1948 if not jsplayer_url_json and not age_gate:
1949 # We need the embed website after all
1950 if embed_webpage is None:
1951 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1952 embed_webpage = self._download_webpage(
1953 embed_url, video_id, 'Downloading embed webpage')
1954 jsplayer_url_json = self._search_regex(
1955 ASSETS_RE, embed_webpage, 'JS player URL')
1957 player_url = json.loads(jsplayer_url_json)
1958 if player_url is None:
1959 player_url_json = self._search_regex(
1960 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1961 video_webpage, 'age gate player URL')
1962 player_url = json.loads(player_url_json)
1964 if 'sig' in url_data:
1965 url += '&signature=' + url_data['sig'][0]
1966 elif 's' in url_data:
1967 encrypted_sig = url_data['s'][0]
1969 if self._downloader.params.get('verbose'):
1970 if player_url is None:
1971 player_version = 'unknown'
1972 player_desc = 'unknown'
1974 if player_url.endswith('swf'):
1975 player_version = self._search_regex(
1976 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1977 'flash player', fatal=False)
1978 player_desc = 'flash player %s' % player_version
1980 player_version = self._search_regex(
1981 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js',
1982 r'(?:www|player(?:_ias)?)-([^/]+)(?:/[a-z]{2,3}_[A-Z]{2})?/base\.js'],
1984 'html5 player', fatal=False)
1985 player_desc = 'html5 player %s' % player_version
1987 parts_sizes = self._signature_cache_id(encrypted_sig)
1988 self.to_screen('{%s} signature length %s, %s' %
1989 (format_id, parts_sizes, player_desc))
1991 signature = self._decrypt_signature(
1992 encrypted_sig, video_id, player_url, age_gate)
1993 sp = try_get(url_data, lambda x: x['sp'][0], compat_str) or 'signature'
1994 url += '&%s=%s' % (sp, signature)
1995 if 'ratebypass' not in url:
1996 url += '&ratebypass=yes'
1999 'format_id': format_id,
2001 'player_url': player_url,
2003 if format_id in self._formats:
2004 dct.update(self._formats[format_id])
2005 if format_id in formats_spec:
2006 dct.update(formats_spec[format_id])
2008 # Some itags are not included in DASH manifest thus corresponding formats will
2009 # lack metadata (see https://github.com/ytdl-org/youtube-dl/pull/5993).
2010 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
2011 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
2012 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
2014 filesize = int_or_none(url_data.get(
2015 'clen', [None])[0]) or _extract_filesize(url)
2017 quality = url_data.get('quality', [None])[0]
2020 'filesize': filesize,
2021 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
2024 'fps': int_or_none(url_data.get('fps', [None])[0]),
2025 'format_note': url_data.get('quality_label', [None])[0] or quality,
2026 'quality': q(quality),
2028 for key, value in more_fields.items():
2031 type_ = url_data.get('type', [None])[0]
2033 type_split = type_.split(';')
2034 kind_ext = type_split[0].split('/')
2035 if len(kind_ext) == 2:
2037 dct['ext'] = mimetype2ext(type_split[0])
2038 if kind in ('audio', 'video'):
2040 for mobj in re.finditer(
2041 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
2042 if mobj.group('key') == 'codecs':
2043 codecs = mobj.group('val')
2046 dct.update(parse_codecs(codecs))
2047 if dct.get('acodec') == 'none' or dct.get('vcodec') == 'none':
2048 dct['downloader_options'] = {
2049 # Youtube throttles chunks >~10M
2050 'http_chunk_size': 10485760,
2055 url_or_none(try_get(
2057 lambda x: x['streamingData']['hlsManifestUrl'],
2059 or url_or_none(try_get(
2060 video_info, lambda x: x['hlsvp'][0], compat_str)))
2063 m3u8_formats = self._extract_m3u8_formats(
2064 manifest_url, video_id, 'mp4', fatal=False)
2065 for a_format in m3u8_formats:
2066 itag = self._search_regex(
2067 r'/itag/(\d+)/', a_format['url'], 'itag', default=None)
2069 a_format['format_id'] = itag
2070 if itag in self._formats:
2071 dct = self._formats[itag].copy()
2072 dct.update(a_format)
2074 a_format['player_url'] = player_url
2075 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
2076 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
2077 formats.append(a_format)
2079 error_message = clean_html(video_info.get('reason', [None])[0])
2080 if not error_message:
2081 error_message = extract_unavailable_message()
2083 raise ExtractorError(error_message, expected=True)
2084 raise ExtractorError('no conn, hlsvp, hlsManifestUrl or url_encoded_fmt_stream_map information found in video info')
2087 video_uploader = try_get(
2088 video_info, lambda x: x['author'][0],
2089 compat_str) or str_or_none(video_details.get('author'))
2091 video_uploader = compat_urllib_parse_unquote_plus(video_uploader)
2093 self._downloader.report_warning('unable to extract uploader name')
2096 video_uploader_id = None
2097 video_uploader_url = None
2099 r'<link itemprop="url" href="(?P<uploader_url>https?://www\.youtube\.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
2101 if mobj is not None:
2102 video_uploader_id = mobj.group('uploader_id')
2103 video_uploader_url = mobj.group('uploader_url')
2105 self._downloader.report_warning('unable to extract uploader nickname')
2108 str_or_none(video_details.get('channelId'))
2109 or self._html_search_meta(
2110 'channelId', video_webpage, 'channel id', default=None)
2111 or self._search_regex(
2112 r'data-channel-external-id=(["\'])(?P<id>(?:(?!\1).)+)\1',
2113 video_webpage, 'channel id', default=None, group='id'))
2114 channel_url = 'http://www.youtube.com/channel/%s' % channel_id if channel_id else None
2117 # We try first to get a high quality image:
2118 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
2119 video_webpage, re.DOTALL)
2120 if m_thumb is not None:
2121 video_thumbnail = m_thumb.group(1)
2122 elif 'thumbnail_url' not in video_info:
2123 self._downloader.report_warning('unable to extract video thumbnail')
2124 video_thumbnail = None
2125 else: # don't panic if we can't find it
2126 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
2129 upload_date = self._html_search_meta(
2130 'datePublished', video_webpage, 'upload date', default=None)
2132 upload_date = self._search_regex(
2133 [r'(?s)id="eow-date.*?>(.*?)</span>',
2134 r'(?:id="watch-uploader-info".*?>.*?|["\']simpleText["\']\s*:\s*["\'])(?:Published|Uploaded|Streamed live|Started) on (.+?)[<"\']'],
2135 video_webpage, 'upload date', default=None)
2136 upload_date = unified_strdate(upload_date)
2138 video_license = self._html_search_regex(
2139 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
2140 video_webpage, 'license', default=None)
2142 m_music = re.search(
2144 <h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*
2152 \bhref=["\']/red[^>]*>| # drop possible
2153 >\s*Listen ad-free with YouTube Red # YouTube Red ad
2160 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
2161 video_creator = clean_html(m_music.group('creator'))
2163 video_alt_title = video_creator = None
2165 def extract_meta(field):
2166 return self._html_search_regex(
2167 r'<h4[^>]+class="title"[^>]*>\s*%s\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li>\s*' % field,
2168 video_webpage, field, default=None)
2170 track = extract_meta('Song')
2171 artist = extract_meta('Artist')
2172 album = extract_meta('Album')
2174 # Youtube Music Auto-generated description
2175 release_date = release_year = None
2176 if video_description:
2177 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)
2180 track = mobj.group('track').strip()
2182 artist = mobj.group('clean_artist') or ', '.join(a.strip() for a in mobj.group('artist').split('·'))
2184 album = mobj.group('album'.strip())
2185 release_year = mobj.group('release_year')
2186 release_date = mobj.group('release_date')
2188 release_date = release_date.replace('-', '')
2189 if not release_year:
2190 release_year = int(release_date[:4])
2192 release_year = int(release_year)
2194 m_episode = re.search(
2195 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
2198 series = unescapeHTML(m_episode.group('series'))
2199 season_number = int(m_episode.group('season'))
2200 episode_number = int(m_episode.group('episode'))
2202 series = season_number = episode_number = None
2204 m_cat_container = self._search_regex(
2205 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
2206 video_webpage, 'categories', default=None)
2208 category = self._html_search_regex(
2209 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
2211 video_categories = None if category is None else [category]
2213 video_categories = None
2216 unescapeHTML(m.group('content'))
2217 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
2219 def _extract_count(count_name):
2220 return str_to_int(self._search_regex(
2221 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
2222 % re.escape(count_name),
2223 video_webpage, count_name, default=None))
2225 like_count = _extract_count('like')
2226 dislike_count = _extract_count('dislike')
2228 if view_count is None:
2229 view_count = str_to_int(self._search_regex(
2230 r'<[^>]+class=["\']watch-view-count[^>]+>\s*([\d,\s]+)', video_webpage,
2231 'view count', default=None))
2234 float_or_none(video_details.get('averageRating'))
2235 or try_get(video_info, lambda x: float_or_none(x['avg_rating'][0])))
2238 video_subtitles = self.extract_subtitles(video_id, video_webpage)
2239 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
2241 video_duration = try_get(
2242 video_info, lambda x: int_or_none(x['length_seconds'][0]))
2243 if not video_duration:
2244 video_duration = int_or_none(video_details.get('lengthSeconds'))
2245 if not video_duration:
2246 video_duration = parse_duration(self._html_search_meta(
2247 'duration', video_webpage, 'video duration'))
2250 video_annotations = None
2251 if self._downloader.params.get('writeannotations', False):
2252 video_annotations = self._extract_annotations(video_id)
2254 chapters = self._extract_chapters(description_original, video_duration)
2256 # Look for the DASH manifest
2257 if self._downloader.params.get('youtube_include_dash_manifest', True):
2258 dash_mpd_fatal = True
2259 for mpd_url in dash_mpds:
2262 def decrypt_sig(mobj):
2264 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
2265 return '/signature/%s' % dec_s
2267 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
2269 for df in self._extract_mpd_formats(
2270 mpd_url, video_id, fatal=dash_mpd_fatal,
2271 formats_dict=self._formats):
2272 if not df.get('filesize'):
2273 df['filesize'] = _extract_filesize(df['url'])
2274 # Do not overwrite DASH format found in some previous DASH manifest
2275 if df['format_id'] not in dash_formats:
2276 dash_formats[df['format_id']] = df
2277 # Additional DASH manifests may end up in HTTP Error 403 therefore
2278 # allow them to fail without bug report message if we already have
2279 # some DASH manifest succeeded. This is temporary workaround to reduce
2280 # burst of bug reports until we figure out the reason and whether it
2281 # can be fixed at all.
2282 dash_mpd_fatal = False
2283 except (ExtractorError, KeyError) as e:
2284 self.report_warning(
2285 'Skipping DASH manifest: %r' % e, video_id)
2287 # Remove the formats we found through non-DASH, they
2288 # contain less info and it can be wrong, because we use
2289 # fixed values (for example the resolution). See
2290 # https://github.com/ytdl-org/youtube-dl/issues/5774 for an
2292 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
2293 formats.extend(dash_formats.values())
2295 # Check for malformed aspect ratio
2296 stretched_m = re.search(
2297 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
2300 w = float(stretched_m.group('w'))
2301 h = float(stretched_m.group('h'))
2302 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
2303 # We will only process correct ratios.
2307 if f.get('vcodec') != 'none':
2308 f['stretched_ratio'] = ratio
2311 token = extract_token(video_info)
2313 if 'reason' in video_info:
2314 if 'The uploader has not made this video available in your country.' in video_info['reason']:
2315 regions_allowed = self._html_search_meta(
2316 'regionsAllowed', video_webpage, default=None)
2317 countries = regions_allowed.split(',') if regions_allowed else None
2318 self.raise_geo_restricted(
2319 msg=video_info['reason'][0], countries=countries)
2320 reason = video_info['reason'][0]
2321 if 'Invalid parameters' in reason:
2322 unavailable_message = extract_unavailable_message()
2323 if unavailable_message:
2324 reason = unavailable_message
2325 raise ExtractorError(
2326 'YouTube said: %s' % reason,
2327 expected=True, video_id=video_id)
2329 raise ExtractorError(
2330 '"token" parameter not in video info for unknown reason',
2333 if not formats and (video_info.get('license_info') or try_get(player_response, lambda x: x['streamingData']['licenseInfos'])):
2334 raise ExtractorError('This video is DRM protected.', expected=True)
2336 self._sort_formats(formats)
2338 self.mark_watched(video_id, video_info, player_response)
2342 'uploader': video_uploader,
2343 'uploader_id': video_uploader_id,
2344 'uploader_url': video_uploader_url,
2345 'channel_id': channel_id,
2346 'channel_url': channel_url,
2347 'upload_date': upload_date,
2348 'license': video_license,
2349 'creator': video_creator or artist,
2350 'title': video_title,
2351 'alt_title': video_alt_title or track,
2352 'thumbnail': video_thumbnail,
2353 'description': video_description,
2354 'categories': video_categories,
2356 'subtitles': video_subtitles,
2357 'automatic_captions': automatic_captions,
2358 'duration': video_duration,
2359 'age_limit': 18 if age_gate else 0,
2360 'annotations': video_annotations,
2361 'chapters': chapters,
2362 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
2363 'view_count': view_count,
2364 'like_count': like_count,
2365 'dislike_count': dislike_count,
2366 'average_rating': average_rating,
2369 'start_time': start_time,
2370 'end_time': end_time,
2372 'season_number': season_number,
2373 'episode_number': episode_number,
2377 'release_date': release_date,
2378 'release_year': release_year,
2382 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
2383 IE_DESC = 'YouTube.com playlists'
2384 _VALID_URL = r"""(?x)(?:
2394 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/(?:videoseries|[0-9A-Za-z_-]{11}))
2395 \? (?:.*?[&;])*? (?:p|a|list)=
2398 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
2401 (?:PL|LL|EC|UU|FL|RD|UL|TL|OLAK5uy_)?[0-9A-Za-z-_]{10,}
2402 # Top tracks, they can also include dots
2408 )""" % {'playlist_id': YoutubeBaseInfoExtractor._PLAYLIST_ID_RE}
2409 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s'
2410 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
2411 IE_NAME = 'youtube:playlist'
2413 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2415 'title': 'ytdl test PL',
2416 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
2418 'playlist_count': 3,
2420 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2422 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
2423 'title': 'YDL_Empty_List',
2425 'playlist_count': 0,
2426 'skip': 'This playlist is private',
2428 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
2429 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2431 'title': '29C3: Not my department',
2432 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
2434 'playlist_count': 95,
2436 'note': 'issue #673',
2437 'url': 'PLBB231211A4F62143',
2439 'title': '[OLD]Team Fortress 2 (Class-based LP)',
2440 'id': 'PLBB231211A4F62143',
2442 'playlist_mincount': 26,
2444 'note': 'Large playlist',
2445 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
2447 'title': 'Uploads from Cauchemar',
2448 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
2450 'playlist_mincount': 799,
2452 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2454 'title': 'YDL_safe_search',
2455 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
2457 'playlist_count': 2,
2458 'skip': 'This playlist is private',
2461 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2462 'playlist_count': 4,
2465 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
2468 'url': 'http://www.youtube.com/embed/_xDOZElKyNU?list=PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2469 'playlist_mincount': 485,
2471 'title': '2017 華語最新單曲 (2/24更新)',
2472 'id': 'PLsyOSbh5bs16vubvKePAQ1x3PhKavfBIl',
2475 'note': 'Embedded SWF player',
2476 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
2477 'playlist_count': 4,
2480 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
2483 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
2484 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
2486 'title': 'Uploads from Interstellar Movie',
2487 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
2489 'playlist_mincount': 21,
2491 # Playlist URL that does not actually serve a playlist
2492 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
2494 'id': 'FqZTN594JQw',
2496 'title': "Smiley's People 01 detective, Adventure Series, Action",
2497 'uploader': 'STREEM',
2498 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
2499 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
2500 'upload_date': '20150526',
2501 'license': 'Standard YouTube License',
2502 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
2503 'categories': ['People & Blogs'],
2507 'dislike_count': int,
2510 'skip_download': True,
2512 'add_ie': [YoutubeIE.ie_key()],
2514 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
2516 'id': 'yeWKywCrFtk',
2518 'title': 'Small Scale Baler and Braiding Rugs',
2519 'uploader': 'Backus-Page House Museum',
2520 'uploader_id': 'backuspagemuseum',
2521 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
2522 'upload_date': '20161008',
2523 'license': 'Standard YouTube License',
2524 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
2525 'categories': ['Nonprofits & Activism'],
2528 'dislike_count': int,
2532 'skip_download': True,
2535 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
2536 'only_matching': True,
2538 'url': 'TLGGrESM50VT6acwMjAyMjAxNw',
2539 'only_matching': True,
2541 # music album playlist
2542 'url': 'OLAK5uy_m4xAFdmMC5rX3Ji3g93pQe3hqLZw_9LhM',
2543 'only_matching': True,
2545 'url': 'https://invidio.us/playlist?list=PLDIoUOhQQPlXr63I_vwF9GD8sAKh77dWU',
2546 'only_matching': True,
2549 def _real_initialize(self):
2552 def _extract_mix(self, playlist_id):
2553 # The mixes are generated from a single video
2554 # the id of the playlist is just 'RD' + video_id
2556 last_id = playlist_id[-11:]
2557 for n in itertools.count(1):
2558 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
2559 webpage = self._download_webpage(
2560 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
2561 new_ids = orderedSet(re.findall(
2562 r'''(?xs)data-video-username=".*?".*?
2563 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
2565 # Fetch new pages until all the videos are repeated, it seems that
2566 # there are always 51 unique videos.
2567 new_ids = [_id for _id in new_ids if _id not in ids]
2573 url_results = self._ids_to_results(ids)
2575 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
2577 search_title('playlist-title')
2578 or search_title('title long-title')
2579 or search_title('title'))
2580 title = clean_html(title_span)
2582 return self.playlist_result(url_results, playlist_id, title)
2584 def _extract_playlist(self, playlist_id):
2585 url = self._TEMPLATE_URL % playlist_id
2586 page = self._download_webpage(url, playlist_id)
2588 # the yt-alert-message now has tabindex attribute (see https://github.com/ytdl-org/youtube-dl/issues/11604)
2589 for match in re.findall(r'<div class="yt-alert-message"[^>]*>([^<]+)</div>', page):
2590 match = match.strip()
2591 # Check if the playlist exists or is private
2592 mobj = re.match(r'[^<]*(?:The|This) playlist (?P<reason>does not exist|is private)[^<]*', match)
2594 reason = mobj.group('reason')
2595 message = 'This playlist %s' % reason
2596 if 'private' in reason:
2597 message += ', use --username or --netrc to access it'
2599 raise ExtractorError(message, expected=True)
2600 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2601 raise ExtractorError(
2602 'Invalid parameters. Maybe URL is incorrect.',
2604 elif re.match(r'[^<]*Choose your language[^<]*', match):
2607 self.report_warning('Youtube gives an alert message: ' + match)
2609 playlist_title = self._html_search_regex(
2610 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2611 page, 'title', default=None)
2613 _UPLOADER_BASE = r'class=["\']pl-header-details[^>]+>\s*<li>\s*<a[^>]+\bhref='
2614 uploader = self._search_regex(
2615 r'%s["\']/(?:user|channel)/[^>]+>([^<]+)' % _UPLOADER_BASE,
2616 page, 'uploader', default=None)
2618 r'%s(["\'])(?P<path>/(?:user|channel)/(?P<uploader_id>.+?))\1' % _UPLOADER_BASE,
2621 uploader_id = mobj.group('uploader_id')
2622 uploader_url = compat_urlparse.urljoin(url, mobj.group('path'))
2624 uploader_id = uploader_url = None
2628 if not playlist_title:
2630 # Some playlist URLs don't actually serve a playlist (e.g.
2631 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2632 next(self._entries(page, playlist_id))
2633 except StopIteration:
2636 playlist = self.playlist_result(
2637 self._entries(page, playlist_id), playlist_id, playlist_title)
2639 'uploader': uploader,
2640 'uploader_id': uploader_id,
2641 'uploader_url': uploader_url,
2644 return has_videos, playlist
2646 def _check_download_just_video(self, url, playlist_id):
2647 # Check if it's a video-specific URL
2648 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2649 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2650 r'(?:(?:^|//)youtu\.be/|youtube\.com/embed/(?!videoseries))([0-9A-Za-z_-]{11})', url,
2651 'video id', default=None)
2653 if self._downloader.params.get('noplaylist'):
2654 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2655 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2657 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2658 return video_id, None
2661 def _real_extract(self, url):
2662 # Extract playlist id
2663 mobj = re.match(self._VALID_URL, url)
2665 raise ExtractorError('Invalid URL: %s' % url)
2666 playlist_id = mobj.group(1) or mobj.group(2)
2668 video_id, video = self._check_download_just_video(url, playlist_id)
2672 if playlist_id.startswith(('RD', 'UL', 'PU')):
2673 # Mixes require a custom extraction process
2674 return self._extract_mix(playlist_id)
2676 has_videos, playlist = self._extract_playlist(playlist_id)
2677 if has_videos or not video_id:
2680 # Some playlist URLs don't actually serve a playlist (see
2681 # https://github.com/ytdl-org/youtube-dl/issues/10537).
2682 # Fallback to plain video extraction if there is a video id
2683 # along with playlist id.
2684 return self.url_result(video_id, 'Youtube', video_id=video_id)
2687 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2688 IE_DESC = 'YouTube.com channels'
2689 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com|(?:www\.)?invidio\.us)/channel/(?P<id>[0-9A-Za-z_-]+)'
2690 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2691 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2692 IE_NAME = 'youtube:channel'
2694 'note': 'paginated channel',
2695 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2696 'playlist_mincount': 91,
2698 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2699 'title': 'Uploads from lex will',
2702 'note': 'Age restricted channel',
2703 # from https://www.youtube.com/user/DeusExOfficial
2704 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2705 'playlist_mincount': 64,
2707 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2708 'title': 'Uploads from Deus Ex',
2711 'url': 'https://invidio.us/channel/UC23qupoDRn9YOAVzeoxjOQA',
2712 'only_matching': True,
2716 def suitable(cls, url):
2717 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2718 else super(YoutubeChannelIE, cls).suitable(url))
2720 def _build_template_url(self, url, channel_id):
2721 return self._TEMPLATE_URL % channel_id
2723 def _real_extract(self, url):
2724 channel_id = self._match_id(url)
2726 url = self._build_template_url(url, channel_id)
2728 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2729 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2730 # otherwise fallback on channel by page extraction
2731 channel_page = self._download_webpage(
2732 url + '?view=57', channel_id,
2733 'Downloading channel page', fatal=False)
2734 if channel_page is False:
2735 channel_playlist_id = False
2737 channel_playlist_id = self._html_search_meta(
2738 'channelId', channel_page, 'channel id', default=None)
2739 if not channel_playlist_id:
2740 channel_url = self._html_search_meta(
2741 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2742 channel_page, 'channel url', default=None)
2744 channel_playlist_id = self._search_regex(
2745 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2746 channel_url, 'channel id', default=None)
2747 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2748 playlist_id = 'UU' + channel_playlist_id[2:]
2749 return self.url_result(
2750 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2752 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2753 autogenerated = re.search(r'''(?x)
2755 channel-header-autogenerated-label|
2756 yt-channel-title-autogenerated
2757 )[^"]*"''', channel_page) is not None
2760 # The videos are contained in a single page
2761 # the ajax pages can't be used, they are empty
2764 video_id, 'Youtube', video_id=video_id,
2765 video_title=video_title)
2766 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2767 return self.playlist_result(entries, channel_id)
2770 next(self._entries(channel_page, channel_id))
2771 except StopIteration:
2772 alert_message = self._html_search_regex(
2773 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2774 channel_page, 'alert', default=None, group='alert')
2776 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2778 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2781 class YoutubeUserIE(YoutubeChannelIE):
2782 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2783 _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_-]+)'
2784 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2785 IE_NAME = 'youtube:user'
2788 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2789 'playlist_mincount': 320,
2791 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2792 'title': 'Uploads from The Linux Foundation',
2795 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2796 # but not https://www.youtube.com/user/12minuteathlete/videos
2797 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2798 'playlist_mincount': 249,
2800 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2801 'title': 'Uploads from 12 Minute Athlete',
2804 'url': 'ytuser:phihag',
2805 'only_matching': True,
2807 'url': 'https://www.youtube.com/c/gametrailers',
2808 'only_matching': True,
2810 'url': 'https://www.youtube.com/gametrailers',
2811 'only_matching': True,
2813 # This channel is not available, geo restricted to JP
2814 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2815 'only_matching': True,
2819 def suitable(cls, url):
2820 # Don't return True if the url can be extracted with other youtube
2821 # extractor, the regex would is too permissive and it would match.
2822 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2823 if any(ie.suitable(url) for ie in other_yt_ies):
2826 return super(YoutubeUserIE, cls).suitable(url)
2828 def _build_template_url(self, url, channel_id):
2829 mobj = re.match(self._VALID_URL, url)
2830 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2833 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2834 IE_DESC = 'YouTube.com live streams'
2835 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2836 IE_NAME = 'youtube:live'
2839 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2841 'id': 'a48o2S1cPoo',
2843 'title': 'The Young Turks - Live Main Show',
2844 'uploader': 'The Young Turks',
2845 'uploader_id': 'TheYoungTurks',
2846 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2847 'upload_date': '20150715',
2848 'license': 'Standard YouTube License',
2849 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2850 'categories': ['News & Politics'],
2851 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2853 'dislike_count': int,
2856 'skip_download': True,
2859 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2860 'only_matching': True,
2862 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2863 'only_matching': True,
2865 'url': 'https://www.youtube.com/TheYoungTurks/live',
2866 'only_matching': True,
2869 def _real_extract(self, url):
2870 mobj = re.match(self._VALID_URL, url)
2871 channel_id = mobj.group('id')
2872 base_url = mobj.group('base_url')
2873 webpage = self._download_webpage(url, channel_id, fatal=False)
2875 page_type = self._og_search_property(
2876 'type', webpage, 'page type', default='')
2877 video_id = self._html_search_meta(
2878 'videoId', webpage, 'video id', default=None)
2879 if page_type.startswith('video') and video_id and re.match(
2880 r'^[0-9A-Za-z_-]{11}$', video_id):
2881 return self.url_result(video_id, YoutubeIE.ie_key())
2882 return self.url_result(base_url)
2885 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2886 IE_DESC = 'YouTube.com user/channel playlists'
2887 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2888 IE_NAME = 'youtube:playlists'
2891 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2892 'playlist_mincount': 4,
2894 'id': 'ThirstForScience',
2895 'title': 'Thirst for Science',
2898 # with "Load more" button
2899 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2900 'playlist_mincount': 70,
2903 'title': 'Игорь Клейнер',
2906 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2907 'playlist_mincount': 17,
2909 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2910 'title': 'Chem Player',
2915 class YoutubeSearchBaseInfoExtractor(YoutubePlaylistBaseInfoExtractor):
2916 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2919 class YoutubeSearchIE(SearchInfoExtractor, YoutubeSearchBaseInfoExtractor):
2920 IE_DESC = 'YouTube.com searches'
2921 # there doesn't appear to be a real limit, for example if you search for
2922 # 'python' you get more than 8.000.000 results
2923 _MAX_RESULTS = float('inf')
2924 IE_NAME = 'youtube:search'
2925 _SEARCH_KEY = 'ytsearch'
2926 _EXTRA_QUERY_ARGS = {}
2929 def _get_n_results(self, query, n):
2930 """Get a specified number of results for a query"""
2936 'search_query': query.encode('utf-8'),
2938 url_query.update(self._EXTRA_QUERY_ARGS)
2939 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2941 for pagenum in itertools.count(1):
2942 data = self._download_json(
2943 result_url, video_id='query "%s"' % query,
2944 note='Downloading page %s' % pagenum,
2945 errnote='Unable to download API page',
2946 query={'spf': 'navigate'})
2947 html_content = data[1]['body']['content']
2949 if 'class="search-message' in html_content:
2950 raise ExtractorError(
2951 '[youtube] No video results', expected=True)
2953 new_videos = list(self._process_page(html_content))
2954 videos += new_videos
2955 if not new_videos or len(videos) > limit:
2957 next_link = self._html_search_regex(
2958 r'href="(/results\?[^"]*\bsp=[^"]+)"[^>]*>\s*<span[^>]+class="[^"]*\byt-uix-button-content\b[^"]*"[^>]*>Next',
2959 html_content, 'next link', default=None)
2960 if next_link is None:
2962 result_url = compat_urlparse.urljoin('https://www.youtube.com/', next_link)
2966 return self.playlist_result(videos, query)
2969 class YoutubeSearchDateIE(YoutubeSearchIE):
2970 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2971 _SEARCH_KEY = 'ytsearchdate'
2972 IE_DESC = 'YouTube.com searches, newest videos first'
2973 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2976 class YoutubeSearchURLIE(YoutubeSearchBaseInfoExtractor):
2977 IE_DESC = 'YouTube.com search URLs'
2978 IE_NAME = 'youtube:search_url'
2979 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2981 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2982 'playlist_mincount': 5,
2984 'title': 'youtube-dl test video',
2987 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2988 'only_matching': True,
2991 def _real_extract(self, url):
2992 mobj = re.match(self._VALID_URL, url)
2993 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2994 webpage = self._download_webpage(url, query)
2995 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2998 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2999 IE_DESC = 'YouTube.com (multi-season) shows'
3000 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
3001 IE_NAME = 'youtube:show'
3003 'url': 'https://www.youtube.com/show/airdisasters',
3004 'playlist_mincount': 5,
3006 'id': 'airdisasters',
3007 'title': 'Air Disasters',
3011 def _real_extract(self, url):
3012 playlist_id = self._match_id(url)
3013 return super(YoutubeShowIE, self)._real_extract(
3014 'https://www.youtube.com/show/%s/playlists' % playlist_id)
3017 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
3019 Base class for feed extractors
3020 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
3022 _LOGIN_REQUIRED = True
3026 return 'youtube:%s' % self._FEED_NAME
3028 def _real_initialize(self):
3031 def _entries(self, page):
3032 # The extraction process is the same as for playlists, but the regex
3033 # for the video ids doesn't contain an index
3035 more_widget_html = content_html = page
3036 for page_num in itertools.count(1):
3037 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
3039 # 'recommended' feed has infinite 'load more' and each new portion spins
3040 # the same videos in (sometimes) slightly different order, so we'll check
3041 # for unicity and break when portion has no new videos
3042 new_ids = list(filter(lambda video_id: video_id not in ids, orderedSet(matches)))
3048 for entry in self._ids_to_results(new_ids):
3051 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
3055 more = self._download_json(
3056 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
3057 'Downloading page #%s' % page_num,
3058 transform_source=uppercase_escape)
3059 content_html = more['content_html']
3060 more_widget_html = more['load_more_widget_html']
3062 def _real_extract(self, url):
3063 page = self._download_webpage(
3064 'https://www.youtube.com/feed/%s' % self._FEED_NAME,
3065 self._PLAYLIST_TITLE)
3066 return self.playlist_result(
3067 self._entries(page), playlist_title=self._PLAYLIST_TITLE)
3070 class YoutubeWatchLaterIE(YoutubePlaylistIE):
3071 IE_NAME = 'youtube:watchlater'
3072 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
3073 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
3076 'url': 'https://www.youtube.com/playlist?list=WL',
3077 'only_matching': True,
3079 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
3080 'only_matching': True,
3083 def _real_extract(self, url):
3084 _, video = self._check_download_just_video(url, 'WL')
3087 _, playlist = self._extract_playlist('WL')
3091 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
3092 IE_NAME = 'youtube:favorites'
3093 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
3094 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
3095 _LOGIN_REQUIRED = True
3097 def _real_extract(self, url):
3098 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
3099 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
3100 return self.url_result(playlist_id, 'YoutubePlaylist')
3103 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
3104 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
3105 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
3106 _FEED_NAME = 'recommended'
3107 _PLAYLIST_TITLE = 'Youtube Recommended videos'
3110 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
3111 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
3112 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
3113 _FEED_NAME = 'subscriptions'
3114 _PLAYLIST_TITLE = 'Youtube Subscriptions'
3117 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
3118 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
3119 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
3120 _FEED_NAME = 'history'
3121 _PLAYLIST_TITLE = 'Youtube History'
3124 class YoutubeTruncatedURLIE(InfoExtractor):
3125 IE_NAME = 'youtube:truncated_url'
3126 IE_DESC = False # Do not list
3127 _VALID_URL = r'''(?x)
3129 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
3132 annotation_id=annotation_[^&]+|
3138 attribution_link\?a=[^&]+
3144 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
3145 'only_matching': True,
3147 'url': 'https://www.youtube.com/watch?',
3148 'only_matching': True,
3150 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
3151 'only_matching': True,
3153 'url': 'https://www.youtube.com/watch?feature=foo',
3154 'only_matching': True,
3156 'url': 'https://www.youtube.com/watch?hl=en-GB',
3157 'only_matching': True,
3159 'url': 'https://www.youtube.com/watch?t=2372',
3160 'only_matching': True,
3163 def _real_extract(self, url):
3164 raise ExtractorError(
3165 'Did you forget to quote the URL? Remember that & is a meta '
3166 'character in most shells, so you want to put the URL in quotes, '
3168 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
3169 ' or simply youtube-dl BaW_jenozKc .',
3173 class YoutubeTruncatedIDIE(InfoExtractor):
3174 IE_NAME = 'youtube:truncated_id'
3175 IE_DESC = False # Do not list
3176 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
3179 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
3180 'only_matching': True,
3183 def _real_extract(self, url):
3184 video_id = self._match_id(url)
3185 raise ExtractorError(
3186 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),